To see the other types of publications on this topic, follow the link: Defects detection and classification.
Dissertations / Theses on the topic 'Defects detection and classification'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Defects detection and classification.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Allanqawi, Khaled Kh S. Kh. "A framework for the classification and detection of design defects and software quality assurance." Thesis, Kingston University, 2015. http://eprints.kingston.ac.uk/34534/.
Full textAbstract:
In current software development lifecyeles of heterogeneous environments, the pitfalls businesses have to face are that software defect tracking, measurements and quality assurance do not start early enough in the development process. In fact the cost of fixing a defect in a production environment is much higher than in the initial phases of the Software Development Life Cycle (SDLC) which is particularly true for Service Oriented Architecture (SOA). Thus the aim of this study is to develop a new framework for defect tracking and detection and quality estimation for early stages particularly for the design stage of the SDLC. Part of the objectives of this work is to conceptualize, borrow and customize from known frameworks, such as object-oriented programming to build a solid framework using automated rule based intelligent mechanisms to detect and classify defects in software design of SOA. The framework on design defects and software quality assurance (DESQA) will blend various design defect metrics and quality measurement approaches and will provide measurements for both defect and quality factors. Unlike existing frameworks, mechanisms are incorporated for the conversion of defect metrics into software quality measurements. The framework is evaluated using a research tool supported by sample used to complete the Design Defects Measuring Matrix, and data collection process. In addition, the evaluation using a case study aims to demonstrate the use of the framework on a number of designs and produces an overall picture regarding defects and quality. The implementation part demonstrated how the framework can predict the quality level of the designed software. The results showed a good level of quality estimation can be achieved based on the number of design attributes, the number of quality attributes and the number of SOA Design Defects. Assessment shows that metrics provide guidelines to indicate the progress that a software system has made and the quality of design. Using these guidelines, we can develop more usable and maintainable software systems to fulfil the demand of efficient systems for software applications. Another valuable result coming from this study is that developers are trying to keep backwards compatibility when they introduce new functionality. Sometimes, in the same newly-introduced elements developers perform necessary breaking changes in future versions. In that way they give time to their clients to adapt their systems. This is a very valuable practice for the developers because they have more time to assess the quality of their software before releasing it. Other improvements in this research include investigation of other design attributes and SOA Design Defects which can be computed in extending the tests we performed.
2
Nouri, Arash. "Correlation-Based Detection and Classification of Rail Wheel Defects using Air-coupled Ultrasonic Acoustic Emissions." Thesis, Virginia Tech, 2016. http://hdl.handle.net/10919/78139.
Full textAbstract:
Defected wheel are one the major reasons endangered state of railroad vehicles safety statue, due to vehicle derailment and worsen the quality of freight and passenger transportation. Therefore, timely defect detection for monitoring and detecting the state of defects is highly critical.
This thesis presents a passive non-contact acoustic structural health monitoring approach using ultrasonic acoustic emissions (UAE) to detect certain defects on different structures, as well as, classifying the type of the defect on them. The acoustic emission signals used in this study are in the ultrasonic range (18-120 kHz), which is significantly higher than the majority of the research in this area thus far. For the proposed method, an impulse excitation, such as a hammer strike, is applied to the structure. In addition, ultrasound techniques have higher sensitivity to both surface and subsurface defects, which make the defect detection more accurate. Three structures considered for this study are: 1) a longitudinal beam, 2) a lifting weight, 3) an actual rail-wheel. A longitudinal beam was used at the first step for a better understanding of physics of the ultrasound propagation from the defect, as well, develop a method for extracting the signature response of the defect. Besides, the inherent directionality of the ultrasound microphone increases the signal to noise ratio (SNR) and could be useful in the noisy areas. Next, by considering the ultimate goal of the project, lifting weight was chosen, due to its similarity to the ultimate goal of this project that is a rail-wheel. A detection method and metric were developed by using the lifting weight and two type of synthetic defects were classified on this structure. Also, by using same extracted features, the same types of defects were detected and classified on an actual rail-wheel.Master of Science
3
Ngendangenzwa, Blaise. "Defect detection and classification on painted specular surfaces." Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-146063.
Full textAbstract:
The Volvo Trucks cab plant in Umea is one of the northern Sweden’s largestengineering industries. The plant manufactures only cabs for trucks and is one of the most modern production plants in the world. Despite a highly automated and computerized system among many processes, the paint quality inspection process is still mainly performed manually. A real-time automated and intelligent quality inspection for painted cabs is highly desired to decrease the costs and at the same time to increase both the production efficiency and the product quality. This project is one step forward to the automation of paint quality control. Two different issues were treated during this project, namely defect detection and defect classification. These problems were solved by feeding four statistical approaches such as support vector machine, random forests, k-nearest neighbors and neural networks with extracted histogram of oriented gradients features from the captured images. The results revealed that support vector machine and random forests outperformed their contenders in terms of accuracy to both detect and to classify the defects.Volvokoncernens hyttfabrik i Umeå är en av Norrlands största verkstadsindustrier.Hyttfabriken tillverkar bara hytter för lastbilar och tillhör en av världens modernaste produktionsanläggningar. Trots ett hög automatiserat och datoriserat system bland många processer så är kvalitetsinspektionen av målade hytter fortfarande utförd manuellt. En smart och automatiserad kvalitetskontroll kan leda till lägre kostnader, högre kvalitet samt högre produktions effektivitet. Den här studien är ett steg framåt mot en automatiserad kvalitetskontroll. Två slagsproblem undersöktes närmare i den här studien nämligen defekt inspektion och defekt klassificering. Dessa problem åtgärdades genom att förse fyra statistiskametoder, support vector machine, random forests, k-nearest neighbors och neuralnetworks, med extraherade HOG egenskaper från tagna bilder. Resultaten visade att support vector machine och random forests presterade bättre än dess konkurrenter i förhållande till förmågan att både inspektera och klassificera defekter.
4
Yang, Xuezhi, and 楊學志. "Discriminative fabric defect detection and classification using adaptive wavelet." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2003. http://hub.hku.hk/bib/B29913408.
Full text
5
Rönnqvist, Johannes, and Johannes Sjölund. "A Deep Learning Approach to Detection and Classification of Small Defects on Painted Surfaces : A Study Made on Volvo GTO, Umeå." Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-160194.
Full textAbstract:
In this thesis we conclude that convolutional neural networks, together with phase-measuring deflectometry techniques, can be used to create models which can detect and classify defects on painted surfaces very well, even compared to experienced humans. Further, we show which preprocessing measures enhances the performance of the models. We see that standardisation does increase the classification accuracy of the models. We demonstrate that cleaning the data through relabelling and removing faulty images improves classification accuracy and especially the models' ability to distinguish between different types of defects. We show that oversampling might be a feasible method to improve accuracy through increasing and balancing the data set by augmenting existing observations. Lastly, we find that combining many images with different patterns heavily increases the classification accuracy of the models. Our proposed approach is demonstrated to work well in a real-time factory environment. An automated quality control of the painted surfaces of Volvo Truck cabins could give great benefits in cost and quality. The automated quality control could provide data for a root-cause analysis and a quick and efficient alarm system. This could significantly streamline production and at the same time reduce costs and errors in production. Corrections and optimisation of the processes could be made in earlier stages in time and with higher precision than today.I den här rapporten visar vi att modeller av typen convolutional neural networks, tillsammans med phase-measuring deflektometri, kan hitta och klassificera defekter på målade ytor med hög precision, även jämfört med erfarna operatörer. Vidare visar vi vilka databehandlingsåtgärder som ökar modellernas prestanda. Vi ser att standardisering ökar modellernas klassificeringsförmåga. Vi visar att städning av data genom ommärkning och borttagning av felaktiga bilder förbättrar klassificeringsförmågan och särskilt modellernas förmåga att särskilja mellan olika typer av defekter. Vi visar att översampling kan vara en metod för att förbättra precisionen genom att öka och balansera datamängden genom att förändra och duplicera befintliga observationer. Slutligen finner vi att kombinera flera bilder med olika mönster ökar modellernas klassificeringsförmåga väsentligt. Vårt föreslagna tillvägagångssätt har visat sig fungera bra i realtid inom en produktionsmiljö. En automatiserad kvalitetskontroll av de målade ytorna på Volvos lastbilshytter kan ge stora fördelar med avseende på kostnad och kvalitet. Den automatiska kvalitetskontrollen kan ge data för en rotorsaksanalys och ett snabbt och effektivt alarmsystem. Detta kan väsentligt effektivisera produktionen och samtidigt minska kostnader och fel i produktionen. Korrigeringar och optimering av processerna kan göras i tidigare skeden och med högre precision än idag.
6
Carroll, L. Blair. "Investigation into the detection and classification of defect colonies using ACFM technolgy." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape11/PQDD_0007/MQ42360.pdf.
Full text
7
Wu, Michael. "Transfer Learning Approach to Powder Bed Fusion Additive Manufacturing Defect Detection." DigitalCommons@CalPoly, 2021. https://digitalcommons.calpoly.edu/theses/2324.
Full textAbstract:
Laser powder bed fusion (LPBF) remains a predominately open-loop additive manufacturing process with minimal in-situ quality and process control. Some machines feature optical monitoring systems but lack automated analytical capabilities for real-time defect detection. Recent advances in machine learning (ML) and convolutional neural networks (CNN) present compelling solutions to analyze images in real-time and to develop in-situ monitoring.
Approximately 30,000 selective laser melting (SLM) build images from 31 previous builds are gathered and labeled as either “okay” or “defect”. Then, 14 open-sourced CNN were trained using transfer learning to classify the SLM build images. These models were evaluated by F1 score and down selected to the top 3 models. The top 3 models were then retrained and evaluated using Dietterich’s 5x2 cross-validation and compared with pairwise student t-tests. The pairwise t-test results show no statistically significant difference in performance between VGG- 19, Xception, and InceptionResNet. All models are strong candidates for future development and refinement.
Additional work addresses the entire model development process and establishes a foundation for future work. Collaborations with computer science students has produced an image pre-processing program to enhance as-taken SLM images. Other outcomes include initial work to overlay CAD layer images and preliminary hardware integration plan for the SLM machine. The results from this work have demonstrated the potential of an optical layer-wise image defect detection system when paired with a CNN.
8
Mahendra, Adhiguna. "Methodology of surface defect detection using machine vision with magnetic particle inspection on tubular material." Thesis, Dijon, 2012. http://www.theses.fr/2012DIJOS051.
Full textAbstract:
[...]L’inspection des surfaces considérées est basée sur la technique d’Inspection par Particules Magnétiques (Magnetic Particle Inspection (MPI)) qui révèle les défauts de surfaces après les traitements suivants : la surface est enduite d’une solution contenant les particules, puis magnétisées et soumise à un éclairage Ultra-Violet. La technique de contrôle non destructif MPI est une méthode bien connue qui permet de révéler la présence de fissures en surface d’un matériau métallique. Cependant, une fois le défaut révélé par le procédé, ladétection automatique sans intervention de l’opérateur en toujours problématique et à ce jour l'inspection basée sur le procédé MPI des matériaux tubulaires sur les sites de production deVallourec est toujours effectuée sur le jugement d’un opérateur humain. Dans cette thèse, nous proposons une approche par vision artificielle pour détecter automatiquement les défauts à partir des images de la surface de tubes après traitement MPI. Nous avons développé étape par étape une méthodologie de vision artificielle de l'acquisition d'images à la classification.[...] La première étape est la mise au point d’un prototype d'acquisition d’images de la surface des tubes. Une série d’images a tout d’abord été stockée afin de produire une base de données. La version actuelle du logiciel permet soit d’enrichir la base de donnée soit d’effectuer le traitement direct d’une nouvelle image : segmentation et saisie de la géométrie (caractéristiques de courbure) des défauts. Mis à part les caractéristiques géométriques et d’intensité, une analyse multi résolution a été réalisée sur les images pour extraire des caractéristiques texturales. Enfin la classification est effectuée selon deux classes : défauts et de non-défauts. Celle ci est réalisée avec le classificateur des forêts aléatoires (Random Forest) dont les résultats sontcomparés avec les méthodes Support Vector Machine et les arbres de décision.La principale contribution de cette thèse est l'optimisation des paramètres utilisées dans les étapes de segmentations dont ceux des filtres de morphologie mathématique, du filtrage linéaire utilisé et de la classification avec la méthode robuste des plans d’expériences (Taguchi), très utilisée dans le secteur de la fabrication. Cette étape d’optimisation a été complétée par les algorithmes génétiques. Cette méthodologie d’optimisation des paramètres des algorithmes a permis un gain de temps et d’efficacité significatif. La seconde contribution concerne la méthode d’extraction et de sélection des caractéristiques des défauts. Au cours de cette thèse, nous avons travaillé sur deux bases de données d’images correspondant à deux types de tubes : « Tool Joints » et « Tubes Coupling ». Dans chaque cas un tiers des images est utilisé pour l’apprentissage. Nous concluons que le classifieur du type« Random Forest » combiné avec les caractéristiques géométriques et les caractéristiques detexture extraites à partir d’une décomposition en ondelettes donne le meilleur taux declassification pour les défauts sur des pièces de « Tool Joints »(95,5%) (Figure 1). Dans le cas des « coupling tubes », le meilleur taux de classification a été obtenu par les SVM avec l’analyse multirésolution (89.2%) (figure.2) mais l’approche Random Forest donne un bon compromis à 82.4%. En conclusion la principale contrainte industrielle d’obtenir un taux de détection de défaut de 100% est ici approchée mais avec un taux de l’ordre de 90%. Les taux de mauvaises détections (Faux positifs ou Faux Négatifs) peuvent être améliorés, leur origine étant dans l’aspect de l’usinage du tube dans certaines parties, « Hard Bending ».De plus, la méthodologie développée peut être appliquée à l’inspection, par MPI ou non, de différentes lignes de produits métalliquesIndustrial surface inspection of tubular material based on Magnetic Particle Inspection (MPI) is a challenging task. Magnetic Particle Inspection is a well known method for Non Destructive Testing with the goal to detect the presence of crack in the tubular surface. Currently Magnetic Particle Inspection for tubular material in Vallourec production site is stillbased on the human inspector judgment. It is time consuming and tedious job. In addition, itis prone to error due to human eye fatigue. In this thesis we propose a machine vision approach in order to detect the defect in the tubular surface MPI images automatically without human supervision with the best detection rate. We focused on crack like defects since they represent the major ones. In order to fulfill the objective, a methodology of machine vision techniques is developed step by step from image acquisition to defect classification. The proposed framework was developed according to industrial constraint and standard hence accuracy, computational speed and simplicity were very important. Based on Magnetic Particle Inspection principles, an acquisition system is developed and optimized, in order to acquire tubular material images for storage or processing. The characteristics of the crack-like defects with respect to its geometric model and curvature characteristics are used as priory knowledge for mathematical morphology and linear filtering. After the segmentation and binarization of the image, vast amount of defect candidates exist. Aside from geometrical and intensity features, Multi resolution Analysis wasperformed on the images to extract textural features. Finally classification is performed with Random Forest classifier due to its robustness and speed and compared with other classifiers such as with Support Vector Machine Classifier. The parameters for mathematical morphology, linear filtering and classification are analyzed and optimized with Design Of Experiments based on Taguchi approach and Genetic Algorithm. The most significant parameters obtained may be analyzed and tuned further. Experiments are performed ontubular materials and evaluated by its accuracy and robustness by comparing ground truth and processed images. This methodology can be replicated for different surface inspection application especially related with surface crack detection
9
Janošík, Zdeněk. "Klasifikace detekovaných vad." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-221300.
Full textAbstract:
In this master thesis is described how to design and implement classifier of defects detected during the final stage of production nonwovens. The beginning of the thesis is devoted to the analysis of options for image processing and classification. Followed by the part, where is described process of image segmentation and extraction of feature vector. Description of classifier implementation and table of achieved results of classification on real images of detected defects.
10
Mahmood, Waqas, and Muhammad Faheem Akhtar. "Validation of Machine Learning and Visualization based Static Code Analysis Technique." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4347.
Full textAbstract:
Software security has always been an afterthought in software development which results into insecure software. Companies rely on penetration testing for detecting security vulnerabilities in their software. However, incorporating security at early stage of development reduces cost and overhead. Static code analysis can be applied at implementation phase of software development life cycle. Applying machine learning and visualization for static code analysis is a novel idea. Technique can learn patterns by normalized compression distance NCD and classify source code into correct or faulty usage on the basis of training instances. Visualization also helps to classify code fragments according to their associated colors. A prototype was developed to implement this technique called Code Distance Visualizer CDV. In order test the efficiency of this technique empirical validation is required. In this research we conduct series of experiments to test its efficiency. We use real life open source software as our test subjects. We also collected bugs from their corresponding bug reporting repositories as well as faulty and correct version of source code. We train CDV by marking correct and faulty version of code fragments. On the basis of these trainings CDV classifies other code fragments as correct or faulty. We measured its fault detection ratio, false negative and false positive ratio. The outcome shows that this technique is efficient in defect detection and has low number of false alarms.Software trygghet har alltid varit en i efterhand inom mjukvaruutveckling som leder till osäker mjukvara. Företagen är beroende av penetrationstester för att upptäcka säkerhetsproblem i deras programvara. Att införliva säkerheten vid tidigt utvecklingsskede minskar kostnaderna och overhead. Statisk kod analys kan tillämpas vid genomförandet av mjukvaruutveckling livscykel. Tillämpa maskininlärning och visualisering för statisk kod är en ny idé. Teknik kan lära mönster av normaliserade kompressionständning avstånd NCD och klassificera källkoden till rätta eller felaktig användning på grundval av utbildning fall. Visualisering bidrar också till att klassificera code fragment utifrån deras associerade färger. En prototyp har utvecklats för att genomföra denna teknik som kallas Code Avstånd VISUALISERARE CDV. För att testa effektiviteten hos denna teknik empirisk validering krävs. I denna forskning vi bedriver serie experiment för att testa dess effektivitet. Vi använder verkliga livet öppen källkod som vår test ämnen. Vi har också samlats in fel från deras motsvarande felrapportering förråd samt fel och rätt version av källkoden. Vi utbildar CDV genom att markera rätt och fel version av koden fragment. På grundval av dessa träningar CDV klassificerar andra nummer fragment som korrekta eller felaktiga. Vi mätt sina fel upptäckt förhållandet falska negativa och falska positiva förhållandet. Resultatet visar att den här tekniken är effektiv i fel upptäckt och har låga antalet falsklarm.
waqasmah@gmail.com +46762316108
11
Sorosac, Nicole. "Etude d'un système d'inspection optique d'état de surface de bobines d'acier inoxydable laminées à froid." Grenoble 1, 1988. http://www.theses.fr/1988GRE10164.
Full text
12
Bengali, Umme Salma Yusuf. "Pixel classification of iris transillumination defects." Thesis, University of Iowa, 2012. https://ir.uiowa.edu/etd/3260.
Full text
13
Auger, Marc. "Detection of laser-welding defects using neural networks." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2002. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp05/MQ65599.pdf.
Full text
14
Kehoe, A. "Detection and evaluation of defects in industrial images." Thesis, University of Surrey, 1990. http://epubs.surrey.ac.uk/804357/.
Full text
15
Priyosulistyo, Henricus. "Detection of defects in concrete structures using vibration technique." Thesis, University of Strathclyde, 1992. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=21555.
Full textAbstract:
This thesis investigates the dynamic behaviour of reinforced concrete beams as they are loaded to failure. Four beams have been investigated. Two types of crack pattern and two types or reinforcement pattern were the main variable parameters. Partially bonded reinforcement as artificially created (by greasing the bars) and positioned at the center third span in two of the four beams investigated. The remaining two beams had conventional bonded reinforcement. Flexural and diagonal splitting patterns were created by loading mechanisms individually applied on two beams of each type of reinforcement. Stage by stage application of static loadings was used. Steady state vibration tests were applied at prior to loadings the beams and at several load stages as gradually increasing defects occurred. There are four parts to this investigation and these are presented in this thesis. The first part investigates the accuracy of several techniques dealing with signal parameters from a digital response spectrum in the signal processing. A logic geometry was developed and was applied on the line spectra of the response spectrum. Numerical evaluation found that the error induced in the proposed technique decreased exponentially with increasing numbers of cycles. A maximum of 0.17% errors may exist when examining 100 cycles of the frequency of interest. A regression analysis was used to achieve further accuracy of the results. The second part investigates the jump phenomenon of mechanical exciters and the sharp drop phenomenon of magnetic exciters. Both of which may confuse the analysis of structural dynamic behaviour. By accounting for the stiffness of the magnetic field of the magnetic exciter in a mathematical model, the jump phenomena was shown to be due to the effect of the reflected force in the excited structure. Practical equations were also proposed to relate absolute to relative parameters. The third part of the thesis concerns the algorithms required in filter processing and includes the development of a computer solution. Two algorithms were developed to obtain coefficients of a polynomial equation which was set up from elementary equations and from a rational function respectively. The algorithms were simple and easy to program. The last part of the thesis discusses the detection of flexural and diagonal splitting defects and non-linear behaviour of the beams during the vibration tests. Static and dynamic comparisons are also discussed. Based on the characteristics of the polar diagrams it was found that several possible types of non-linear damping were demonstrated in the experiments. The typical viscous and non-linear higher polynomial damping existed mostly in the models although the crack pattern and intensity of cracks contributed to changes in the type of damping. In addition the beam models in almost all conditions showed non-linear soft spring behaviour. Diagonal splitting crack patterns can be idenuried from a small decrease of resonant frequency and from the sharp drop of resonant amplitude. The presence of single deep cracks greatly reduced the stiffness. The experiments show that a sharp decrease of resonant frequency indicates that a large amount of residual strain exists. It is concluded that defects of the reinforced concrete beams can be identified from the changes of the dynamic parameters using the proper digital signal analyses. The jump phenomenon is shown to be due to the effect of the reflected force on the moving exciter mass rather than due to the presence of the non-linear soft spring system.
16
Wang, Hui. "Software Defects Classification Prediction Based On Mining Software Repository." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-216554.
Full textAbstract:
An important goal during the cycle of software development is to find and fix existing defects as early as possible. This has much to do with software defects prediction and management. Nowadays,many big software development companies have their own development repository, which typically includes a version control system and a bug tracking system. This has no doubt proved useful for software defects prediction. Since the 1990s researchers have been mining software repository to get a deeper understanding of the data. As a result they have come up with some software defects prediction models the past few years. There are basically two categories among these prediction models. One category is to predict how many defects still exist according to the already captured defects data in the earlier stage of the software life-cycle. The other category is to predict how many defects there will be in the newer version software according to the earlier version of the software defects data. The complexities of software development bring a lot of issues which are related with software defects. We have to consider these issues as much as possible to get precise prediction results, which makes the modeling more complex. This thesis presents the current research status on software defects classification prediction and the key techniques in this area, including: software metrics, classifiers, data pre-processing and the evaluation of the prediction results. We then propose a way to predict software defects classification based on mining software repository. A way to collect all the defects during the development of software from the Eclipse version control systems and map these defects with the defects information containing in software defects tracking system to get the statistical information of software defects, is described. Then the Eclipse metrics plug-in is used to get the software metrics of files and packages which contain defects. After analyzing and preprocessing the dataset, the tool(R) is used to build a prediction models on the training dataset, in order to predict software defects classification on different levels on the testing dataset, evaluate the performance of the model and comparedifferent models’ performance.
17
Wilson, Duncan John. "Classification of defects using uncertainty in industrial web inspection." Thesis, University of London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.286894.
Full text
18
Rogers, Stuart Craig. "Defect Detection Microscopy." BYU ScholarsArchive, 2010. https://scholarsarchive.byu.edu/etd/2256.
Full textAbstract:
The automotive industry's search for stronger lighter materials has been hampered in its desire to make greater use of Magnesium alloys by their poor formability below 150°C. One current challenge is to identify the complex structure and deformation mechanisms at work and determine which of these are primary contributors to the nucleation of defects. Orientation Imaging Microscopy has been the most accessible tool for microstructural analysis over the past 15 years. However, using OIM to analyze defect nucleation sites requires prior knowledge of where the defects will occur because once the defects nucleate the majority of microstructural information is destroyed. This thesis seeks to contribute to the early detection of nucleation sites via three mechanisms: 1. Detection of cracks that have already nucleated, 2. Detection of surface topography changes that may indicate imminent nucleation and 3. Beam control strategies for efficiently finding areas of interest in a scan. Successive in-situ OIM scans of a consistent sample region while strain is increased, while using the three techniques developed in this thesis, will be employed in future work to provide a powerful defect analysis tool. By analyzing retrieved EBSD patterns we are able to locate defect / crack sites via shadowing on the EBSD patterns. Furthermore, topographical features (and potentially regions of surface roughening) can be detected via changes in intensity metrics and image quality. Topographical gradients are currently only detectable in line with the beam incidence. It is therefore suggested that the tensile specimens to be examined are orientated such that the resulting shear bands occur preferentially to this direction. The ability to refine the scan around these areas of interest has been demonstrated via an off-line adaptive scan routine that is implemented via the custom scan tool. A first attempt at a defect detection framework has been outlined and coded into MATLAB. These tools offer a first step to accessing the information about defect nucleation that researchers are currently seeking.
19
Moshiri, Farzad, Bahareh Mobasher, and Issa Osama Talib. "Detection of defects in timber using dynamic excitation and vibration analysis." Thesis, Växjö University, School of Technology and Design, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:vxu:diva-5444.
Full textAbstract:
This thesis evaluates the possibility to detect natural defects, such as knots, in timber boards using dynamic excitation test and ABAQUS software. In the study the edgewise bending direction were compared with axial direction. Dynamic excitation and modal analysis were used to extract the natural frequencies of several sound and artificially defected boards with the help of Signalcalc. Mobylizer software. By using the first edgewise natural frequency, modulus of elasticity (MOE) was calculated. An ABAQUS 2D Finite Element model was utilized to model the board and to extract the frequencies for the six first mode shapes in both axial and edgewise directions. The extracted frequencies from the model were compared with the frequencies from the tests. The analytical and experimental results, from the homogeneous boards, in edgewise direction has similar frequency variations. The defects in the timber boards decreased the natural frequencies. The bending modes with more curvature at the location of the artificial defect displayed more frequency deviation in that mode. The variation in response frequencies for uniform and defected boards was more noticeable in edgewise bending modes than in longitudinal modes.
20
Chaiworawitkul, Sakda 1977. "Detection of surface defects in infrastructure using wavelets and neural networks." Thesis, Massachusetts Institute of Technology, 2002. http://hdl.handle.net/1721.1/84310.
Full textAbstract:
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2002.Includes bibliographical references (p. [225]-[228]).
by Sakda Chaiworawitkul.
M.Eng.
21
Wang, Xiaoting. "Transient thermography for detection of micro-defects in multilayer thin films." Thesis, Loughborough University, 2017. https://dspace.lboro.ac.uk/2134/25174.
Full textAbstract:
Delamination and cracks within the multilayer structure are typical failure modes observed in microelectronic and micro electro mechanical system (MEMS) devices and packages. As destructive detection methods consume large numbers of devices during reliability tests, non-destructive techniques (NDT) are critical for measuring the size and position of internal defects throughout such tests. There are several established NDT methods; however, some of them have significant disadvantages for detecting defects within multilayer structures such as those found in MEMS devices. This thesis presents research into the application of transient infrared thermography as a non-destructive method for detecting and measuring internal defects, such as delamination and cracks, in the multilayer structure of MEMS devices. This technique works through the use of an infrared imaging system to map the changing temperature distribution over the surface of a target object following a sudden change in the boundary conditions, such as the application of a heat source to an external surface. It has previously been utilised in various applications, such as damage assessment in aerospace composites and verification of printed circuit board solder joint manufacture, but little research of its applicability to MEMS structures has previously been reported. In this work, the thermal behaviour of a multilayer structure containing defects was first numerically analysed. A multilayer structure was then successfully modelled using COMSOL finite element analysis (FEA) software with pulse heating on the bottom surface and observing the resulting time varying temperature distribution on the top. The optimum detecting conditions such as the pulse heating energy, pulse duration and heating method were determined and applied in the simulation. The influences of thermal properties of materials, physical dimensions of film, substrate and defect and other factors that will influence the surface temperature gradients were analytically evaluated. Furthermore, a functional relationship between the defect size and the resulting surface temperature was obtained to improve the accuracy of estimating the physical dimensions and location of the internal defect in detection. Corresponding experiments on specimens containing artificially created defects in macro-scale revealed the ability of the thermographic method to detect the internal defect. The precision of the established model was confirmed by contrasting the experimental results and numerical simulations.
22
Hu, Yazhe. "Degenerate Near-planar Road Surface 3D Reconstruction and Automatic Defects Detection." Diss., Virginia Tech, 2020. http://hdl.handle.net/10919/98671.
Full textAbstract:
This dissertation presents an approach to reconstruct degenerate near-planar road surface in three-dimensional (3D) while automatically detect road defects. Three techniques are developed in this dissertation to establish the proposed approach. The first technique is proposed to reconstruct the degenerate near-planar road surface into 3D from one camera. Unlike the traditional Structure from Motion (SfM) technique which has the degeneracy issue for near-planar object 3D reconstruction, the uniqueness of the proposed technique lies in the use of near-planar characteristics of surfaces in the 3D reconstruction process, which solves the degenerate road surface reconstruction problem using only two images. Following the accuracy-enhanced 3D reconstructed road surface, the second technique automatically detects and estimates road surface defects. As the 3D surface is inversely solved from 2D road images, the detection is achieved by jointly identifying irregularities from the 3D road surfaces and the corresponding image information, while clustering road defects and obstacles using a mean-shift algorithm with flat kernel to estimate the depth, size, and location of the defects. To enhance the physics-driven automatic detection reliability, the third technique proposes and incorporates a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from supervised learning approaches which need labeled training images, the road anomaly detection network is trained by road surface images that are automatically labeled based on the reconstructed 3D surface information. In order to collect clear road surface images on the public road, a road surface monitoring system is designed and integrated for the road surface image capturing and visualization. The proposed approach is evaluated in both simulated environment and through real-world experiments. The parametric study of the proposed approach shows the small error of the 3D road surface reconstruction influenced by different variables such as the image noise, camera orientation, and the vertical movement of the camera in a controlled simulation environment. The comparison with traditional SfM technique and the numerical results of the proposed reconstruction using real-world road surface images then indicate that the proposed approach effectively reconstructs high quality near-planar road surface while automatically detects road defects with high precision, accuracy, and recall rates without the degenerate issue.Doctor of Philosophy
Road is one of the key infrastructures for ground transportation. A good road surface condition can benefit mainly on three aspects: 1. Avoiding the potential traffic accident caused by road surface defects, such as potholes. 2. Reducing the damage to the vehicle initiated by the bad road surface condition. 3. Improving the driving and riding comfort on a healthy road surface. With all the benefits mentioned above, it is important to examine and check the road surface quality frequently and efficiently to make sure that the road surface is in a healthy condition. In order to detect any road surface defects on public road in time, this dissertation proposes three techniques to tackle the road surface defects detection problem: First, a near-planar road surface three-dimensional (3D) reconstruction technique is proposed. Unlike traditional 3D reconstruction technique, the proposed technique solves the degenerate issue for road surface 3D reconstruction from two images. The degenerate issue appears when the object reconstructed has near-planar surfaces. Second, after getting the accuracy-enhanced 3D road surface reconstruction, this dissertation proposes an automatic defects detection technique using both the 3D reconstructed road surface and the road surface image information. Although physics-based detection using 3D reconstruction and 2D images are reliable and explainable, it needs more time to process these data. To speed up the road surface defects detection task, the third contribution is a technique that proposes a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from traditional neural network-based detection techniques, the proposed combines the 3D road information with the CNN output to jointly determine the road surface defects region. All the proposed techniques are evaluated using both the simulation and real-world experiments. Results show the efficacy and efficiency of the proposed techniques in this dissertation.
23
Oaker, Bradley. "The detection of defects in tubes and plates using guided waves." Master's thesis, University of Cape Town, 2011. http://hdl.handle.net/11427/11182.
Full textAbstract:
Eddy current testing is the non-destructive test method of choice for the inspection of condenser tubes. However, unplanned shutdowns of power stations, due to unexpected condenser tube failures, still occur despite rigorous eddy current inspection programs. In addition to the improvement required in the reliability of inspections, there is also a need to shorten the duration of inspections.
24
Ngan, Yuk-tung Henry, and 顏旭東. "Patterned Jacquard fabric defect detection." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2004. http://hub.hku.hk/bib/B30070880.
Full text
25
Temko, Andriy. "Acoustic event detection and classification." Doctoral thesis, Universitat Politècnica de Catalunya, 2007. http://hdl.handle.net/10803/6880.
Full textAbstract:
L'activitat humana que té lloc en sales de reunions o aules d'ensenyament es veu reflectida en una rica varietat d'events acústics, ja siguin produïts pel cos humà o per objectes que les persones manegen. Per això, la determinació de la identitat dels sons i de la seva posició temporal pot ajudar a detectar i a descriure l'activitat humana que té lloc en la sala. A més a més, la detecció de sons diferents de la veu pot ajudar a millorar la robustes de tecnologies de la parla com el reconeixement automàtica a condicions de treball adverses. L'objectiu d'aquesta tesi és la detecció i classificació automàtica d'events acústics. Es tracta de processar els senyals acústics recollits per micròfons distants en sales de reunions o aules per tal de convertir-los en descripcions simbòliques que es corresponguin amb la percepció que un oient tindria dels diversos events sonors continguts en els senyals i de les seves fonts. En primer lloc, s'encara la tasca de classificació automàtica d'events acústics amb classificadors de màquines de vectors suport (Support Vector Machines (SVM)), elecció motivada per l'escassetat de dades d'entrenament. Per al problema de reconeixement multiclasse es desenvolupa un esquema d'agrupament automàtic amb conjunt de característiques variable i basat en matrius de confusió. Realitzant proves amb la base de dades recollida, aquest classificador obté uns millors resultats que la tècnica basada en models de barreges de Gaussianes (Gaussian Mixture Models (GMM)), i aconsegueix una reducció relativa de l'error mitjà elevada en comparació amb el millor resultat obtingut amb l'esquema convencional basat en arbre binari. Continuant amb el problema de classificació, es comparen unes quantes maneres alternatives d'estendre els SVM al processament de seqüències, en un intent d'evitar l'inconvenient de treballar amb vectors de longitud fixa que presenten els SVM quan han de tractar dades d'àudio. En aquestes proves s'observa que els nuclis de deformació temporal dinàmica funcionen bé amb sons que presenten una estructura temporal. A més a més, s'usen conceptes i eines manllevats de la teoria de lògica difusa per investigar, d'una banda, la importància de cada una de les característiques i el grau d'interacció entre elles, i d'altra banda, tot cercant l'augment de la taxa de classificació, s'investiga la fusió de lessortides de diversos sistemes de classificació. Els sistemes de classificació d'events acústics
desenvolupats s'han testejat també mitjançant la participació en unes quantes avaluacions d'àmbit
internacional, entre els anys 2004 i 2006. La segona principal contribució d'aquest treball de tesi consisteix en el desenvolupament de sistemes de detecció d'events acústics. El problema de la detecció és més complex, ja que inclou tant la classificació dels sons com la determinació dels intervals temporals on tenen lloc. Es desenvolupen dues versions del sistema i es proven amb els conjunts de dades de les dues campanyes d'avaluació internacional CLEAR que van tenir lloc els anys 2006 i 2007, fent-se servir dos tipus de bases de dades: dues bases d'events acústics aïllats, i una base d'enregistraments de seminaris interactius, les quals contenen un nombre relativament elevat d'ocurrències dels events acústics especificats. Els sistemes desenvolupats, que consisteixen en l'ús de classificadors basats en SVM que operen dins
d'una finestra lliscant més un post-processament, van ser els únics presentats a les avaluacions
esmentades que no es basaven en models de Markov ocults (Hidden Markov Models) i cada un d'ells
va obtenir resultats competitius en la corresponent avaluació. La detecció d'activitat oral és un altre dels objectius d'aquest treball de tesi, pel fet de ser un cas particular de detecció d'events acústics especialment important. Es desenvolupa una tècnica de millora de l'entrenament dels SVM per fer front a la necessitat de reducció de l'enorme conjunt de dades existents. El sistema resultant, basat en SVM, és testejat amb uns quants conjunts de dades de l'avaluació NIST RT (Rich Transcription), on mostra puntuacions millors que les del sistema basat en GMM, malgrat que aquest darrer va quedar entre els primers en l'avaluació NIST RT de 2006.
Per acabar, val la pena esmentar alguns resultats col·laterals d'aquest treball de tesi. Com que s'ha dut a terme en l'entorn del projecte europeu CHIL, l'autor ha estat responsable de l'organització de les avaluacions internacionals de classificació i detecció d'events acústics abans esmentades, liderant l'especificació de les classes d'events, les bases de dades, els protocols d'avaluació i, especialment, proposant i implementant les diverses mètriques utilitzades. A més a més, els sistemes de detecció
s'han implementat en la sala intel·ligent de la UPC, on funcionen en temps real a efectes de test i demostració.
The human activity that takes place in meeting-rooms or class-rooms is reflected in a rich variety of acoustic events, either produced by the human body or by objects handled by humans, so the determination of both the identity of sounds and their position in time may help to detect and describe that human activity.
Additionally, detection of sounds other than speech may be useful to enhance the robustness of speech technologies like automatic speech recognition. Automatic detection and classification of acoustic events is the objective of this thesis work. It aims at processing the acoustic signals collected by distant microphones in meeting-room or classroom environments to convert them into symbolic descriptions corresponding to a listener's perception of the different sound events that are present in the signals and their sources. First of all, the task of acoustic event classification is faced using Support Vector Machine (SVM) classifiers, which are motivated by the scarcity of training data. A confusion-matrix-based variable-feature-set clustering scheme is developed for the multiclass recognition problem, and tested on the gathered database. With it, a higher classification rate than the GMM-based technique is obtained, arriving to a large relative average error reduction with respect to the best result from the conventional binary tree scheme. Moreover, several ways to extend SVMs to sequence processing are compared, in an attempt to avoid the drawback of SVMs when dealing with audio data, i.e. their restriction to work with fixed-length vectors, observing that the dynamic time warping kernels work well for sounds that show a temporal structure. Furthermore, concepts and tools from the fuzzy theory are used to investigate, first, the importance of and degree of interaction among features, and second, ways to fuse the outputs of several classification systems. The developed AEC systems are tested also by participating in several international evaluations from 2004 to 2006, and the results
are reported. The second main contribution of this thesis work is the development of systems for detection of acoustic events. The detection problem is more complex since it includes both classification and determination of the time intervals where the sound takes place. Two system versions are developed and tested on the datasets of the two CLEAR international evaluation campaigns in 2006 and 2007. Two kinds of databases are used: two databases of isolated acoustic events, and a database of interactive seminars containing a significant number of acoustic events of interest. Our developed systems, which consist of SVM-based classification within a sliding window plus post-processing, were the only submissions not using HMMs, and each of them obtained competitive results in the corresponding evaluation. Speech activity detection was also pursued in this thesis since, in fact, it is a -especially important - particular case of acoustic event detection. An enhanced SVM training approach for the speech activity detection task is developed, mainly to cope with the problem of dataset reduction. The resulting SVM-based system is tested with several NIST Rich Transcription (RT) evaluation datasets, and it shows better scores than our GMM-based system, which ranked among the best systems in the RT06 evaluation. Finally, it is worth mentioning a few side outcomes from this thesis work. As it has been carried out in the framework of the CHIL EU project, the author has been responsible for the organization of the above mentioned international evaluations in acoustic event classification and detection, taking a leading role in the specification of acoustic event classes, databases, and evaluation protocols, and, especially, in the proposal and implementation of the various metrics that have been used. Moreover, the detection systems have been implemented in the UPC's smart-room and work in real time for purposes of testing and demonstration.
26
Garcia, Luís Paulo Faina. "Noise detection in classification problems." Universidade de São Paulo, 2016. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-29112016-155215/.
Full textAbstract:
In many areas of knowledge, considerable amounts of time have been spent to comprehend and to treat noisy data, one of the most common problems regarding information collection, transmission and storage. These noisy data, when used for training Machine Learning techniques, lead to increased complexity in the induced classification models, higher processing time and reduced predictive power. Treating them in a preprocessing step may improve the data quality and the comprehension of the problem. This Thesis aims to investigate the use of data complexity measures capable to characterize the presence of noise in datasets, to develop new efficient noise ltering techniques in such subsamples of problems of noise identification compared to the state of art and to recommend the most properly suited techniques or ensembles for a specific dataset by meta-learning. Both artificial and real problem datasets were used in the experimental part of this work. They were obtained from public data repositories and a cooperation project. The evaluation was made through the analysis of the effect of artificially generated noise and also by the feedback of a domain expert. The reported experimental results show that the investigated proposals are promising.Em diversas áreas do conhecimento, um tempo considerável tem sido gasto na compreensão e tratamento de dados ruidosos. Trata-se de uma ocorrência comum quando nos referimos a coleta, a transmissão e ao armazenamento de informações. Esses dados ruidosos, quando utilizados na indução de classificadores por técnicas de Aprendizado de Maquina, aumentam a complexidade da hipótese obtida, bem como o aumento do seu tempo de indução, além de prejudicar sua acurácia preditiva. Trata-los na etapa de pré-processamento pode significar uma melhora da qualidade dos dados e um aumento na compreensão do problema estudado. Esta Tese investiga medidas de complexidade capazes de caracterizar a presença de ruídos em um conjunto de dados, desenvolve novos filtros que sejam mais eficientes em determinados nichos do problema de detecção e remoção de ruídos que as técnicas consideradas estado da arte e recomenda as mais apropriadas técnicas ou comitês de técnicas para um determinado conjunto de dados por meio de meta-aprendizado. As bases de dados utilizadas nos experimentos realizados neste trabalho são tanto artificiais quanto reais, coletadas de repositórios públicos e fornecidas por projetos de cooperação. A avaliação consiste tanto da adição de ruídos artificiais quanto da validação de um especialista. Experimentos realizados mostraram o potencial das propostas investigadas.
27
Gatti, Stefano. "Object Detection for Cell Classification." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/22034/.
Full textAbstract:
The human body is an incredibly complex system with deeply interconnected functions. To understand this behaviour requires the knowledge of the genes expressed by every cell in a region of the tissue. As a direct consequence of the complexity of biological tissues the analysis of such images is extremely complex.
The objective of this work is to use techniques of object detection and instance segmentation to help with the analysis of the image, by identifying both the location and shapes of the cells and their content.
In addition to the work’s original objective, a methodology is outlined for dividing the cells in the image, rather than just identifying their positions, based on the application of Voronoi diagrams.
28
Hunt, Kevin. "Modelling the origin of defects in injection moulded ceramics." Thesis, Brunel University, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.280892.
Full text
29
Lonkar, Gajanan M. "Computer aided detection of defects in FRP bridge decks using infrared thermography." Morgantown, W. Va. : [West Virginia University Libraries], 2005. https://eidr.wvu.edu/etd/documentdata.eTD?documentid=4368.
Full textAbstract:
Thesis (M.S.)--West Virginia University, 2005.Title from document title page. Document formatted into pages; contains xii, 129 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 120-123).
30
Gilday, R. T. "Inexpensive equipment for the detection of acquired and congenital colour-vision defects." Thesis, University of Sussex, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.318605.
Full text
31
Asani, Furaha Florence. "Detection of subtle immune defects in individuals at risk of pneumococcal disease." Thesis, University of Sheffield, 2017. http://etheses.whiterose.ac.uk/19508/.
Full textAbstract:
Immunocompromised individuals are at increased risk of developing invasive pneumococcal disease (IPD). We have previously shown that IPD sufferers have defective in vitro B-cell responses to a T-independent antigen mimic (αδdex), relative to healthy controls. We hypothesized that similar defects will be found in HIV-infected individuals, who continue to be at greater risk of IPD despite antiretroviral therapy, and in Monoclonal Gammopathy of Undetermined Significance (MGUS) patients. Lymphocytes enriched from whole blood were cultured with addex alone and combined with anti-CD3, to assess both direct T- and B-cell effects, and T-cell help to B-cells. T- and B-cell activation and proliferation were assessed using standardised flow cytometry. B-cell subsets were stratified by CD19, CD10, CD20, CD21 and CD27 into plasmablasts, activated memory cells, resting memory cells, naive, and tissue-like memory cells. Results from 16 HIV-infected individuals [mean CD4 count 677.63/mm3, undetectable viral loads] showed no change in overall CD19+ B-cell activation but increased proliferation upon T-cell-helped pneumococcal-stimulation, compared to age-, sex- and ethnicity-matched controls. However, addex elicited significantly higher (p = 0.05) activation in plasmablasts in HIV-infected individuals compared to healthy controls. Furthermore, MGUS patients expressed significantly lower CD25 on CD8+ T-cells compared to healthy controls, following stimulation with anti-CD3 and anti-CD28 (p = 0.01). Age, sex and ethnicity were also found to influence T- and B-cell responses to polyclonal-stimulation in healthy individuals. Although activation of CD19+ B-cells was similar between HIV-infected adults and healthy controls, polyclonal B-cell stimulation reveals a persisting hyperactivation defect in the plasmablast B-cell compartment in HIV infection despite virological suppression. The findings in this study may indicate impaired immune control of pathogens such as S. pneumoniae in immunocompromised individuals.
32
Pratiwada, Chaitanya. "High Fidelity Detection of Defects in Polymer Films Using Surface-Modified Nanoparticles." University of Akron / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=akron1345586565.
Full text
33
Honec, Peter. "Spolehlivé systémy zpracování obrazu." Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-233467.
Full textAbstract:
The Doctoral thesis demonstrates the design of reliable industrial visual systems. The special emphasis is dedicated to the detection of defects on webs in industrial applications based on line-scan cameras. This system makes possible detection and classification of defects originating during the real production conditions. This work covers a theoretical study of a visual system for the defect detection on endless bands as well as of appropriate lighting and the scene arrangement. Further to that have been selected, adjusted and designed key components of hardware. Following the design and optimization of algorithms a system prototype had been installed on non-woven textiles production line. Eight visual systems implemented into real-life industrial conditions based on this prototype
34
Malady, Amy Colleen. "Cyclostationarity Feature-Based Detection and Classification." Thesis, Virginia Tech, 2011. http://hdl.handle.net/10919/32280.
Full textAbstract:
Cyclostationarity feature-based (C-FB) detection and classification is a large field of research that has promising applications to intelligent receiver design. Cyclostationarity FB classification and detection algorithms have been applied to a breadth of wireless communication signals â analog and digital alike. This thesis reports on an investigation of existing methods of extracting cyclostationarity features and then presents a novel robust solution that reduces SNR requirements, removes the pre-processing task of estimating occupied signal bandwidth, and can achieve classification rates comparable to those achieved by the traditional method while based on only 1/10 of the observation time. Additionally, this thesis documents the development of a novel low order consideration of the cyclostationarity present in Continuous Phase Modulation (CPM) signals, which is more practical than using higher order cyclostationarity.
Results are presented â through MATLAB simulation â that demonstrate the improvements enjoyed by FB classifiers and detectors when using robust methods of estimating cyclostationarity. Additionally, a MATLAB simulation of a CPM C-FB detector confirms that low order C-FB detection of CPM signals is possible. Finally, suggestions for further research and contribution are made at the conclusion of the thesis.Master of Science
35
Wu, Tsung-Lin, and 吳昌林. "A Computer Vision System for Detection and Classification of Defects." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/66308090046378263068.
Full text
36
Chuang, Fuji, and 莊富傑. "The Detection and Classification of Lead Frame Defects Using Neural Networks." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/44883327211863894990.
Full textAbstract:
碩士中華大學
機械與航太工程研究所
87
As the pitch getting finer and the lead number getting higher, the inspection of IC lead frame using bare eyes becomes more difficult. To lessen the workload of human inspectors, an effective method for the detection and classification of defects is presented. First, the proposed method uses image-processing techniques such as image enhancement, image segmentation, edge detection, morphological operation, and labeling to locate defects. Next, feature extraction techniques are applied to measure such features as perimeter, moments, area, eccentricity, compactness, roughness, and standard deviation of gray level. Finally, by inputting the extracted features of each defect to a pre-trained feedforward backpropagation network, the defect can be classified into pinhole, scratch, or contamination. To automate the inspection process, image processing, feature extraction, artificial neural network, as well as stage and light source control techniques have been integrated into an effective defect detection and classification system. The experimental results show that on an average, the system can finish inspecting an image in 0.4 second and the recognition rate is 99.22%. In summary, the developed system not only can replace the convention inspection method, but also increase the accuracy and efficiency of lead frame inspection.
37
Fernandes, Pedro Miguel Pinto da Cunha. "Detection of production defects using Machine Learning based Image Classification Algorithms." Dissertação, 2020. https://hdl.handle.net/10216/129867.
Full text
38
Fernandes, Pedro Miguel Pinto da Cunha. "Detection of production defects using Machine Learning based Image Classification Algorithms." Master's thesis, 2020. https://hdl.handle.net/10216/129867.
Full text
39
Shehab-Eldeen, Tariq. "An automated system for detection, classification and rehabilitation of defects in sewer pipes." Thesis, 2001. http://spectrum.library.concordia.ca/1624/1/NQ68210.pdf.
Full textAbstract:
The poor status of sewer pipes in North America has been reported by many researchers, revealing the presence of many defects that impact their performance. Inadequate inspection is considered as one of the main causes behind the declining condition of this class of pipes. This could be attributed to high cost of inspection and inadequate funds allocated to this purpose. The high cost is due to the current manual and high labor intensive inspection practice. Sewer rehabilitation methods are numerous and are constantly being developed. One of the rapidly expanding fields in the sewer rehabilitation industry is trenchless technology. Due to the large number of methods associated with this field, selecting the most suitable method manually can be a challenging task. Selection in this environment may also suffer from the limited knowledge and/or experience of the decision-maker. This research presents two developed automated systems: AUTO-DETECT and AUTO-SELECT. AUTO-DETECT detects and classifies defects in sewer pipes automatically. The system utilizes image analysis techniques, artificial intelligence (AI) and Visual Basic programming language for performing its task. A multiple classifier module encompassing a total of fifteen classifiers was developed to counter-check the results generated by the system. A solution strategy was also developed for efficient utilization of the developed specialized classifiers in an effort to improve the system's performance. The automated system was validated using actual data from randomly selected sections of the sewer network of a major Canadian municipality. The system's accuracy was found to range from 80% to 100%. AUTO-SELECT is essentially a multi-attribute decision support system designed to select and rank the most suitable trenchless rehabilitation methods for sewer pipes. The system utilizes two modules: (1) database management system (DBMS) and (2) decision support system (DSS). The developed relational database assists in identifying suitable trenchless rehabilitation techniques that satisfy a total of sixteen factors which account for technical, contractual and cost requirements of projects as well as user specified preferences. In case of having more than one suitable rehabilitation method, a DSS was developed to evaluate and rank them and, accordingly, suggest the most suitable one. A case example has been worked out to demonstrate the use and capabilities of the developed system.
40
Phong-PhuLe and 黎楓富. "Ball-Grid-Array Chip Defects Detection and Classification Using Patch-based Modified YOLOv3." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/vyywa9.
Full text
41
Tseng, Yung-Chin, and 曾永進. "Defect detection and classification of printed art tiles." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/48281639136842937484.
Full textAbstract:
碩士逢甲大學
資訊電機工程碩士在職專班
100
In the printing procedure in art tiles manufacturing process, the defects such as: the scratches, pattern missing, dirt, fly ink will influence the printing quality. The traditional manual inspection methods, because there are a variety of subjective and objective factors, can not complete the task of on-line detection. In this study, a machine vision technology for print defect detection is presented to discuss its feasibility in industrial role. The study was applied in the printed art tiles process. By using a digital image processing technology in the manufacturing process, the defect detection and classification can be successfully achieved. The methods include feature extraction, feature analysis, neural network classification, and grayscale co-occurrence matrix. Then the system can make a judgment as to whether each print pattern is good or bad. The accuracy of the system can reach 90%, and the detection speed is 2-3 sec for a 15x15cm print tile.
42
Silva, Afonso Luís Costa Barbosa da. "Detection of dish manufacturing defects using a deep learning-based approach." Master's thesis, 2020. http://hdl.handle.net/10071/21798.
Full textAbstract:
Quality control is essential to ensure the smooth running of an industrial process. This work
proposes to use and adapt a deep learning-based algorithm that will integrate an automatic
quality control system at a porcelain dish factory. This system will receive images acquired in
real time by high resolution cameras directly placed on production line. The algorithm proposed
in this research work will classify the dishes presented in the images as "defective" or "without
defect". Therefore, the objective of the system will be the detection of defective dishes, causing
fewer defective dishes to reach the market, thus contributing to a better reputation of the factory.
This system is based on the application of an algorithm called Convolutional Neural
Network. This algorithm requires a large amount of data to be trained and to perform the image
classification. Since the COVID-19 pandemic was felt on a larger scale in Portugal at the time
of the development of this research work, it was impossible to obtain data directly from the
factory. Due to this setback, the data used in this work was artificially generated. By providing
the complete images of dishes to the algorithm, it achieved a defect detection accuracy of 92.7%
with the first dataset and 91.9%. with the second. When providing the algorithm 100x100 pixel
segments of the original images, using the second created dataset, it reached 91.6% accuracy in
the classification of these segments, which translated into a 52.0% accuracy rate in the
classification of the complete dish images.O controlo de qualidade é fundamental para assegurar o bom funcionamento de um processo industrial. Este trabalho propõe a utilização e adaptação de um algoritmo, baseado em aprendizagem profunda, como parte integrante de um sistema automático de controlo de qualidade numa fábrica de pratos de porcelana. Este sistema receberá imagens adquiridas em tempo real por câmaras fotográficas colocadas diretamente sobre a linha de produção. O algoritmo utilizado classificará os pratos presentes nas imagens como "defeituoso" ou "sem defeito". O objetivo do sistema será, portanto, a deteção de pratos defeituosos, fazendo com que menos pratos com defeito cheguem ao mercado, contribuindo assim para uma melhor reputação da fábrica. Este sistema é baseado na aplicação de uma rede neuronal convolucional. Este tipo de redes requer um elevado número de dados para ser treinado de modo a conseguir realizar a classificação de imagens. Uma vez que a pandemia de COVID-19 se fez sentir em maior escala em Portugal na altura do desenvolvimento deste trabalho, foi impossível a obtenção de imagens provenientes da fábrica. Devido a este contratempo, os dados utilizados neste trabalho foram gerados artificialmente. Ao fornecer imagens completas de pratos ao algoritmo, o mesmo atingiu uma taxa de acerto da deteção de defeitos de 92,7% com o primeiro conjunto de dados e 91,9% com o segundo. Ao fornecer ao algoritmo segmentos de 100x100 pixéis da imagem original, o mesmo atingiu 91,6% de taxa de acerto, o que se traduziu numa taxa de acerto de 52,0% na classificação das imagens completas de pratos.
43
Ze, Zhuang lang, and 莊揚擇. "Defect Detection and Classification for TFT-LCD Array Process." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/54194990244159495610.
Full textAbstract:
碩士國立勤益科技大學
資訊工程系
102
The thesis integrates the Way of Quick Grabbing Defect and High-accuracy Defect Classification to examine TFT-LCD Array Manufacturing Process Defect Classification. First, we get defects through Crossing Comparative Method Of Neighborhood Blocks Image, and then divide the defects into five characters which finally are substituted into SVM to be trained and later get three categories such as Flock, Particle, and Manufacturing Process Defect etc. With the repeated feature of TFT-LCD Array Manufacturing Process, using Crossing Comparative Method Of Neighborhood Blocks Image can get defects quickly , and using SVM can get accurate classifying results. The experiment shows that the accuracy examined can be up to 97.8%.
44
Chang, Wei-Lun, and 張維倫. "Similarity Based ART 1 Model for Automatic Defect Detection and Classification." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/25670869861506264644.
Full textAbstract:
碩士國立交通大學
電控工程研究所
102
In general, a reliable and automatic semiconductor fabrication processes is of great importance to product yield and cost reduction. In the past, we made use of human vision to do die defect detection and classification, which is hindered by the easy fatigue and fuzziness of human eyes and the decision difference between inspectors. In this thesis, we develop a vision-based automatic defect classification system. In our defect detection component, we apply the MAD method to align the test image with the reference image. To acquire the binary defect images, we subtract the test image from the reference image, then we convert the difference image into the binary image by setting a threshold. Moreover, we removed the scattering noises by setting a minimum number of connected noisy pixels required. Finally, we extract all defects in the test image in order to perform the defect classification. For defect classification, we revise the ART 1 model, which still can retain the stability and the plasticity dilemma. We have found that ART 1 exists an intolerable shortcoming: output is dependent on the ordering of input sequence applied. To remedy this disadvantage, we derive the similarity based ART 1 model which can obtain high classification accuracy and independent on the ordering of input patterns.
45
Tsai, Cia-Yang, and 蔡家揚. "Distance Based Vector Quantization Algorithm for Automatic Defect Detection and Classification." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/09298426281506536411.
Full textAbstract:
碩士國立交通大學
電控工程研究所
103
In general, a reliable and automatic semiconductor fabrication processes is of great importance to product yield and cost reduction. In the past, we made use of human vision to do die defect detection and classification, which is hindered by the easy fatigue and fuzziness of human eyes and the decision difference between inspectors. In this thesis, we implement a vision-based automatic defect classification system. In our defect detection component, we have used the MAD method to align the test image to the reference image. To acquire the binary defect images, we subtract the test image from the reference image, and then we convert the difference image into the binary image by setting a threshold. Moreover, we removed the scattering noises by setting a minimum number of connected noisy pixels required. Finally, we extract all defects in the test image in order to perform the defect classification. For defect classification, we revise the Vector Quantization Algorithm with Kohonen learning rule. Because of the initial seeds have been selected randomly, it will lead to various clustering outcomes. We derive distance based vector quantization with first seed selection measure and it can obtain high classification accuracy and consistent classification result.
46
"Noise Resilient Image Segmentation and Classification Methods with Applications in Biomedical and Semiconductor Images." Doctoral diss., 2010. http://hdl.handle.net/2286/R.I.8607.
Full textAbstract:
abstract: Thousands of high-resolution images are generated each day. Segmenting, classifying, and analyzing the contents of these images are the key steps in image understanding. This thesis focuses on image segmentation and classification and its applications in synthetic, texture, natural, biomedical, and industrial images. A robust level-set-based multi-region and texture image segmentation approach is proposed in this thesis to tackle most of the challenges in the existing multi-region segmentation methods, including computational complexity and sensitivity to initialization. Medical image analysis helps in understanding biological processes and disease pathologies. In this thesis, two cell evolution analysis schemes are proposed for cell cluster extraction in order to analyze cell migration, cell proliferation, and cell dispersion in different cancer cell images. The proposed schemes accurately segment both the cell cluster area and the individual cells inside and outside the cell cluster area. The method is currently used by different cell biology labs to study the behavior of cancer cells, which helps in drug discovery. Defects can cause failure to motherboards, processors, and semiconductor units. An automatic defect detection and classification methodology is very desirable in many industrial applications. This helps in producing consistent results, facilitating the processing, speeding up the processing time, and reducing the cost. In this thesis, three defect detection and classification schemes are proposed to automatically detect and classify different defects related to semiconductor unit images. The first proposed defect detection scheme is used to detect and classify the solder balls in the processor sockets as either defective (Non-Wet) or non-defective. The method produces a 96% classification rate and saves 89% of the time used by the operator. The second proposed defect detection scheme is used for detecting and measuring voids inside solder balls of different boards and products. The third proposed defect detection scheme is used to detect different defects in the die area of semiconductor unit images such as cracks, scratches, foreign materials, fingerprints, and stains. The three proposed defect detection schemes give high accuracy and are inexpensive to implement compared to the existing high cost state-of-the-art machines.Dissertation/Thesis
Ph.D. Electrical Engineering 2010
47
Lin, Pei-Yao, and 林培堯. "Automatic morphological defect detection and classification in Li-ion battery radiographic images." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/95818160785479290762.
Full textAbstract:
碩士國立陽明大學
生物醫學影像暨放射科學系暨研究所
100
In the industry, using non-destructive testing (NDT) by X-ray inspection is very common, which can be divided into off-line and in-line testing. The aim of this thesis is to implement automatic machine learning methods to do in-line testing mainly for lithium battery X-ray images in order to detect defects for classification. About lithium battery X-ray images, we focus eight areas to detect defect. There are two main steps in the study: feature extraction and classification. The aim on feature extraction is to find the position of defects and to outline the features of defects. Feature extraction method includes image processing, morphological analysis, edge detection, labeling, and projection curve observation. Two existing classification methods, support vector machine (SVM) and back-propagation neural network (BPN), were utilized as the classifier of our system. We also asked the experts to determine whether there is any defect in the objects. Finally, we verified the accuracy of feature extraction and classification. We use 200 lithium battery X-ray images to extract their characteristic features, randomly selected 70% of them as training data set and 30% as test data set. The results appear that our proposed system can detect the locations of the defects quickly and accurately. About classification, SVM and BPN obtained classification accuracy around 80% and 70%, respectively. Furthermore, we suggest that using SVM method to classify lithium battery defect detect.
48
Carroll, L. Blair. "Investigation into the detection and classification of defect colonies using ACFM Technology /." 1998.
Find full text
49
Cheng, Che-Fu, and 鄭喆夫. "Automatic Defect Detection and Classification System on Printed Circuit Board Inner Layer." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/twdr26.
Full textAbstract:
碩士國立交通大學
電控工程研究所
101
In this thesis, we implement an automatic defect classification system that combines the detection and classification of the defect on a PCB inner layer. In defect detection part, at first, we have to use the MAD method to align the test images to the reference image which contains no defects. MAD method computes the mean absolute distortion of the two images overlapping area to find the displacement between these two images. Then we subtract the aligned test image from aligned reference images to obtain defects. Finally, there are some noises with small size in the subtracted image. Therefore, we remove these noises by setting a threshold. In defect classification part, we have to find the outer boundary of each defect and then we extract two features, “number of state transition,” and “boundary state,” from the outer boundary. Moreover, we also extract the “defect state” feature in the image subtraction process. By using these three different features, we can classify defects into the following eight types: “open,” “mouse bite,” “pinhole,” “missing conductor,” “short,” “spur,” “missing hole,” and “excess copper.”
50
Hsu, Ming-Chou, and 許名宙. "A Study of Defect Detection and Classification Technique for Compact Camera Lens Images." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/2k52dt.
Full textAbstract:
碩士國立中興大學
資訊科學與工程學系
103
In the majority of optical related industry, the visual inspection process of the wafer surface depends on human experts. However, the inefficiencies of human visual inspection is has led to the development of image process to perform inspection tasks. Compact camera lenses consist of multiple lenses and manufacturing may create defects. The compact camera lenses module structure was multi-layer. When light passed through the compact camera lens module, it will cause a halo because of reflection and refraction. It led defect is difficult to be found. We propose a based inspection approach to defect in Compact Camera Lens Images. The first component mainly used Hough transform to detect circle and to segment region of interes. The polar transform process is used to mapping image into polar coordinate system. So that the image of the lens edge profile becomes horizontal cyclic feature edge. We use the Horizontal Sobel edge detection to solve the problem for the Camera Lens edge. Simple threshold method and morphology operations are used to detect candidate defect which contains defect The combination of the object mask and the result of watershed Alogorithms is able to segment the objects exactly. Then, support vector machine is used to classified defect.