To see the other types of publications on this topic, follow the link: Computer vision recognition.
Dissertations / Theses on the topic 'Computer vision recognition'
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 'Computer vision recognition.'
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
PAOLANTI, MARINA. "Pattern Recognition for challenging Computer Vision Applications." Doctoral thesis, Università Politecnica delle Marche, 2018. http://hdl.handle.net/11566/252904.
Full textAbstract:
La Pattern Recognition è lo studio di come le macchine osservano l'ambiente, imparano a distinguere i pattern di interesse dal loro background e prendono decisioni valide e ragionevoli sulle categorie di modelli. Oggi l'applicazione degli algoritmi e delle tecniche di Pattern Recognition è trasversale. Con i recenti progressi nella computer vision, abbiamo la capacità di estrarre dati multimediali per ottenere informazioni preziose su ciò che sta accadendo nel mondo. Partendo da questa premessa, questa tesi affronta il tema dello sviluppo di sistemi di Pattern Recognition per applicazioni reali come la biologia, il retail, la sorveglianza, social media intelligence e i beni culturali. L'obiettivo principale è sviluppare applicazioni di computer vision in cui la Pattern Recognition è il nucleo centrale della loro
progettazione, a partire dai metodi generali, che possono essere sfruttati in più campi di ricerca, per poi passare a metodi e tecniche che affrontano problemi specifici. Di fronte a molti tipi di dati, come immagini, dati biologici e traiettorie, una difficoltà fondamentale è trovare rappresentazioni vettoriali rilevanti. Per la progettazione del sistema di riconoscimento dei modelli vengono eseguiti i seguenti passaggi: raccolta dati, estrazione delle caratteristiche, approccio di apprendimento personalizzato e analisi e valutazione comparativa. Per una valutazione completa delle prestazioni, è di grande importanza collezionare un dataset specifico perché i metodi di progettazione che sono adattati a un
problema non funzionano correttamente su altri tipi di problemi. I metodi su misura, adottati per lo sviluppo delle applicazioni proposte, hanno dimostrato di essere in grado di estrarre caratteristiche statistiche complesse e di imparare in modo efficiente le loro rappresentazioni, permettendogli di generalizzare bene attraverso una vasta gamma di compiti di visione computerizzata.<br>Pattern Recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the patterns categories. Nowadays, the application of Pattern Recognition algorithms and techniques is ubiquitous and transversal. With the recent advances in computer vision, we now have the ability to mine such massive visual data to obtain valuable insight about what is happening in the world. The availability of affordable and high resolution sensors (e.g., RGB-D cameras, microphones and scanners) and data sharing have resulted in huge repositories of digitized documents (text, speech, image and video). Starting from such a premise, this thesis addresses the topic of developing next generation Pattern Recognition systems for real applications such as Biology, Retail, Surveillance, Social Media Intelligence and Digital Cultural Heritage. The main goal is to develop computer vision applications in which Pattern Recognition is the key core in their design, starting from general methods, that can be exploited in more fields, and then passing to methods and techniques addressing specific problems. The privileged focus is on up-to-date applications of Pattern Recognition techniques to real-world problems, and on interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance Pattern Recognition methods. The final ambition is to spur new research lines, especially within interdisciplinary research scenarios. Faced with many types of data, such as images, biological data and trajectories, a key difficulty was to nd relevant vectorial representations. While this problem had been often handled in an ad-hoc way by domain experts, it has proved useful to learn these representations directly from data, and Machine Learning algorithms, statistical methods and Deep Learning techniques have been particularly successful. The representations are then based on compositions of simple parameterized processing units, the depth coming from the large number of such compositions. It was desirable to develop new, efficient data representation or feature learning/indexing techniques, which can achieve promising performance in the related tasks. The overarching goal of this work consists of presenting a pipeline to select the model that best explains the given observations; nevertheless, it does not prioritize in memory and time complexity when matching models to observations. For the Pattern Recognition system design, the following steps are performed: data collection, features extraction, tailored learning approach and comparative analysis and assessment. The proposed applications open up a wealth of novel and important opportunities for the machine vision community. The newly dataset collected as well as the complex areas taken into exam, make the research challenging. In fact, it is crucial to evaluate the performance of state of the art methods to demonstrate their strength and weakness and help identify future research for designing more robust algorithms. For comprehensive performance evaluation, it is of great importance developing a library and benchmark to gauge the state of the art because the methods design that are tuned to a specic problem do not work properly on other problems. Furthermore, the dataset selection is needed from different application domains in order to offer the user the opportunity to prove the broad validity of methods. Intensive attention has been drawn to the exploration of tailored learning models and algorithms, and their extension to more application areas. The tailored methods, adopted for the development of the proposed applications, have shown to be capable of extracting complex statistical features and efficiently learning their representations, allowing it to generalize well across a wide variety of computer vision tasks, including image classication, text recognition and so on.
2
Crossley, Simon. "Robust temporal stereo computer vision." Thesis, University of Sheffield, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.327614.
Full text
3
Fletcher, Gordon James. "Geometrical problems in computer vision." Thesis, University of Liverpool, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.337166.
Full text
4
Matilainen, M. (Matti). "Embedded computer vision methods for human activity recognition." Doctoral thesis, Oulun yliopisto, 2017. http://urn.fi/urn:isbn:9789526216256.
Full textAbstract:
Abstract The way how people interact with machines will change in the future. Long have been the traditional ways – mouse and keyboard – the primary interface between man and computer. Recently, the voice and gesture controlled interfaces have been introduced in many devices but they have not yet become very popular. One possible direction where human-computer interfaces can go is to be able to completely hide the interface from the user and allow him or her to interact with the machines in a way that is more natural to human. This thesis introduces a smart living space concept that is a small step towards that direction. The interfacing is assumed to be done unnoticeably to the user via a wireless sensor network that is monitoring the user and analysing his or her behaviour and also using a hand held mobile device which can be used to control the system. A system for human body part segmentation is presented. The system is applied in various applications related to person identification from one’s gait and unusual activity detection. The system is designed to work robustly when the data streams provided by the sensor network are noisy. This increases the usefulness of the system in home environments where the person using the interface is either occluded by the static objects in the room or is interacting with any movable objects. The second part of the proposed smart living space concept is the mobile device carried by the user. Two methods that can be used in a hand gesture-based UI are proposed. A database for training such methods is proposed<br>Tiivistelmä Tapa jolla ihmiset käyttävät tietokonetta on muuttumassa. Hiiri ja näppäimistö ovat olleet jo pitkään yleisimmät tavat, joilla tietokoneita on ohjattu. Uusia tapoja ohjata tietokonetta on kehitetty, mutta ne eivät ole vielä syrjäyttäneet perinteisiä menetelmiä täysin. Yksi todennäköinen muutos tulevaisuudessa on se, että käyttöliittymät sulautetaan ympäristöön ja sen myötä tehdään käyttökokemuksesta luonnollisempi ihmiselle. Tässä väitöskirjassa esitellään järjestelmä, joka muuttaa ihmisen elinympäristön älykkääksi. Langaton kameraverkko analysoi automaattisesti huoneen tapahtumia ja käyttäjä kontrolloi järjestelmää eleohjatulla mobiililaitteella. Väitöskirjassa esitellään menetelmä ihmisen ruumiinosien tunnistukseen, jota sovelletaan myös ihmisen tunnistukseen kävelytyylistä ja epänormaalien aktiviteettien tunnistukseen. Menetelmää suunnitellessa on painotettu sitä, että se toimisi myös silloin, kun käytettävissä on vain huonolaatuista ja kohinaista videodataa. Kohinaa aiheuttaa kotiympäristöissä erityisesti huonekalut, jotka osittain peittävät näkymää ja tavarat, joita huoneessa oleskeleva ihminen saattaa siirrellä. Toinen osa väitöskirjaa käsittelee mobiililaitteen ohjausta käsielein ja esittelee kaksi menetelmää, joilla tällainen käyttöliittymä on mahdollista toteuttaa. Toisen menetelmän opetuksessa käytetty käsitietokanta ja tietokannan vertailutulokset julkaistaan
5
Ali, Abdulamer T. "Computer vision aided road traffic analysis." Thesis, University of Bristol, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.333953.
Full text
6
Millman, Michael Peter. "Computer vision for yarn quality inspection." Thesis, Loughborough University, 2000. https://dspace.lboro.ac.uk/2134/34196.
Full textAbstract:
Structural parameters that determine yarn quality include evenness, hairiness and twist. This thesis applies machine vision techniques to yarn inspection, to determine these parameters in a non-contact manner. Due to the increased costs of such a solution over conventional sensors, the thesis takes a wide look at, and where necessary develops, the potential uses of machine vision for several key aspects of yarn inspection at both low and high speed configurations. Initially, the optimum optical / imaging conditions for yarn imaging are determined by investigating the various factors which degrade a yarn image. The depth of field requirement for imaging yarns is analysed, and various solutions are discussed critically including apodisation, wave front encoding and mechanical guidance. A solution using glass plate guides is proposed, and tested in prototype. The plates enable the correct hair lengths to be seen in the image for long hairs, and also prevent damaging effects on the hairiness definition due to yarn vibration and yarn rotation. The optical system parameters and resolution limits of the yarn image when using guide plates are derived and optimised. The thesis then looks at methods of enhancing the yarn image, using various illumination methods, and incoherent and coherent dark-field imaging.
7
Steigerwald, Richard. "Computer Sketch Recognition." DigitalCommons@CalPoly, 2013. https://digitalcommons.calpoly.edu/theses/1009.
Full textAbstract:
Tens of thousands of years ago, humans drew sketches that we can see and identify even today. Sketches are the oldest recorded form of human communication and are still widely used. The universality of sketches supersedes that of culture and language. Despite the universal accessibility of sketches by humans, computers are unable to interpret or even correctly identify the contents of sketches drawn by humans with a practical level of accuracy.
In my thesis, I demonstrate that the accuracy of existing sketch recognition techniques can be improved by optimizing the classification criteria. Current techniques classify a 20,000 sketch crowd-sourced dataset with 56% accuracy. I classify the same dataset with 52% accuracy, but identify factors that have the greatest effect on the accuracy.
The ability for computers to identify human sketches would be useful particularly in pictionary-like games and other kinds of human-computer interaction; the concepts from sketch recognition could be extended to other kinds of object recognition.
8
Tordoff, Ben. "Active control of zoom for computer vision." Thesis, University of Oxford, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.270752.
Full text
9
Hunt, Neil. "Tools for image processing and computer vision." Thesis, University of Aberdeen, 1990. http://digitool.abdn.ac.uk/R?func=search-advanced-go&find_code1=WSN&request1=AAIU025003.
Full textAbstract:
The thesis describes progress towards the construction of a seeing machine. Currently, we do not understand enough about the task to build more than the simplest computer vision systems; what is understood, however, is that tremendous processing power will surely be involved. I explore the pipelined architecture for vision computers, and I discuss how it can offer both powerful processing and flexibility. I describe a proposed family of VLSI chips based upon such an architecture, each chip performing a specific image processing task. The specialisation of each chip allows high performance to be achieved, and a common pixel interconnect interface on each chip allows them to be connected in arbitrary configurations in order to solve different kinds of computational problems. While such a family of processing components can be assembled in many different ways, a programmable computer offers certain advantages, in that it is possible to change the operation of such a machine very quickly, simply by substituting a different program. I describe a software design tool which attempts to secure the same kind of programmability advantage for exploring applications of the pipelined processors. This design tool simulates complete systems consisting of several of the proposed processing components, in a configuration described by a graphical schematic diagram. A novel time skew simulation technique developed for this application allows coarse grain simulation for efficiency, while preserving the fine grain timing details. Finally, I describe some experiments which have been performed using the tools discussed earlier, showing how the tools can be put to use to handle real problems.
10
Moore, Darnell Janssen. "Vision-based recognition of actions using context." Diss., Georgia Institute of Technology, 2000. http://hdl.handle.net/1853/16346.
Full text
11
Burns, Anne-Marie. "Computer vision methods for guitarist left-hand fingering recognition." Thesis, McGill University, 2006. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=99578.
Full textAbstract:
This thesis presents a method to visually detect and recognize fingering gestures of the left hand of a guitarist. The choice of computer vision to perform that task is motivated by the absence of a satisfying method for realtime guitarist fingering detection. The development of this computer vision method follows preliminary manual and automated analyses of video recordings of a guitarist. These first analyses led to some important findings about the design methodology of such a system, namely the focus on the effective gesture, the consideration of the action of each individual finger, and a recognition system not relying on comparison against a knowledge-base of previously learned fingering positions. Motivated by these results, studies on three important aspects of a complete fingering system were conducted. One study was on realtime finger-localization, another on string and fret detection, and the last on movement segmentation. Finally, these concepts were integrated into a prototype and a system for left-hand fingering detection was developed. Such a data acquisition system for fingering retrieval has uses in music theory, music education, automatic music and accompaniment generation and physical modeling.
12
Grashei, Ole Kristian Braut. "Use of Clustering to Assist Recognition in Computer Vision." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap, 2013. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-23403.
Full textAbstract:
In computer vision many problems are of non-deterministic polynomial time complexity. One of these problems is graph matching. Suboptimal solutions have been proposed to efficiently do graph matching. This thesis investigates the use of unsupervised learning to cluster structured graph data in polynomial time. Clustering was done on attributed graph nodes and attributed graph node-arc-node triplets, and meaningful results were demonstrated. Self-organizing maps and the minimum message length program Snob were used. These clustering results may help a suboptimal graph matcher arrive at an acceptable solution at an acceptable time. The thesis proposes some methods to do so, but implementation is future work.
13
Tsai, Ming-Jong. "A new technique for 3-D computer vision." Thesis, University of Liverpool, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.240784.
Full text
14
Christmas, W. J. "Structural matching in computer vision using probabilistic reasoning." Thesis, University of Surrey, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.308472.
Full text
15
Setchell, Christopher John. "Applications of computer vision to road-traffic monitoring." Thesis, University of Bristol, 1998. http://hdl.handle.net/1983/a79e87e2-8020-45ce-be27-dd9e382d18c7.
Full text
16
Priestnall, Gary. "Machine recognition of engineering drawings." Thesis, University of Nottingham, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283606.
Full text
17
Bristow, Hilton K. "Registration and representation in computer vision." Thesis, Queensland University of Technology, 2016. https://eprints.qut.edu.au/99587/1/Hilton_Bristow_Thesis.pdf.
Full textAbstract:
Given two animals of the same species, could you recognise common anatomical features between them, even if they appeared in different poses? This thesis studies the representation of photometric and geometric uncertainty in such fine-grained object recognition tasks. The problem is difficult, in part, because image appearance can vary wildly with even small changes in object pose. To constrain this inherently ill-posed problem, we develop methods for aligning novel images based on their semantic content, by efficiently leveraging priors over the statistics of natural images.
18
Gao, Hui. "Extracting key features for analysis and recognition in computer vision." Columbus, Ohio : Ohio State University, 2006. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1141770523.
Full text
19
White, D. J. "The CatchMeter : application of computer vision for fish species recognition." Thesis, University of Aberdeen, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.445154.
Full textAbstract:
This thesis describes trials of a computer vision machine (The CatchMeter) for identifying and measuring different species of fish. The fish are transported along a conveyor underneath a digital camera. Image processing algorithms determine the orientation of the fish utilising a moment-invariant method, identify whether the fish is a flatfish or roundfish with 100% accuracy, and measure the length with a standard deviation of 1.2mm and species with up to 99.8% sorting reliability for sixteen species of fish. The machine can theoretically process up to 30 000 fish per hour using a single conveyor based system. The length measurement algorithms are then further developed so that fish may move along an opaque conveyor belt, through the system and be presented in any position or orientation, against a relatively complex background. By this method the minimum length of fish that can be measured is 50mm and since images can be stitched together the upper limit is >1.5m. The length of fish is measured with an average error of ± 3%. Two methods of object recognition by colour are compared and are applied to fish species identification. The colour histogram method and generates variables for subsequent analysis. The grid method generates a grid on the object and uses the average RGB values in the grid elements as a set of variables for the object. It was found that increasing the number of grid elements and the number of colour cubes (bins) increased sorting accuracy. A classification accuracy of 82.9% for nine species of fish was achieved using colour histograms and 98% using average colours. Furthermore, simple shape descriptors were added to the analysis and this improved the sorting accuracy to 98.5% for the colour histogram method and 99.8% for the grid with average colours method for seven species of fish. Fish species determination using black and white images and by feature extraction using edge detection methods are described with sorting accuracies of up to 95.3% and 97.7% respectively. A machine that was constructed based on the methods in this thesis is currently installed on one of the most advanced marine research vessels in the world, the Norwegian G.O. Sars.
20
Liu, X. (Xin). "Human motion detection and gesture recognition using computer vision methods." Doctoral thesis, Oulun yliopisto, 2019. http://urn.fi/urn:isbn:9789526222011.
Full textAbstract:
Abstract Gestures are present in most daily human activities and automatic gestures analysis is a significant topic with the goal of enabling the interaction between humans and computers as natural as the communication between humans. From a computer vision perspective, a gesture analysis system is typically composed of two stages, the low-level stage for human motion detection and the high-level stage for understanding human gestures. Therefore, this thesis contributes to the research on gesture analysis from two aspects, 1) Detection: human motion segmentation from video sequences, and 2) Understanding: gesture cues extraction and recognition. In the first part of this thesis, two sparse signal recovery based human motion detection methods are presented. In real videos the foreground (human motions) pixels are often not randomly distributed but have the group properties in both spatial and temporal domains. Based on this observation, a spatio-temporal group sparsity recovery model is proposed, which explicitly consider the foreground pixels' group clustering priors of spatial coherence and temporal contiguity. Moreover, a pixel should be considered as a multi-channel signal. Namely, if a pixel is equal to the adjacent ones that means all the three RGB coefficients should be equal. Motivated by this observation, a multi-channel fused Lasso regularizer is developed to explore the smoothness of multi-channels signals. In the second part of this thesis, two human gesture recognition methods are presented to resolve the issue of temporal dynamics, which is crucial to the interpretation of the observed gestures. In the first study, a gesture skeletal sequence is characterized by a trajectory on a Riemannian manifold. Then, a time-warping invariant metric on the Riemannian manifold is proposed. Furthermore, a sparse coding for skeletal trajectories is presented by explicitly considering the labelling information, with the aim to enforcing the discriminant validity of the dictionary. In the second work, based on the observation that a gesture is a time series with distinctly defined phases, a low-rank matrix decomposition model is proposed to build temporal compositions of gestures. In this way, a more appropriate alignment of hidden states for a hidden Markov model can be achieved<br>Tiivistelmä Eleet ovat läsnä useimmissa päivittäisissä ihmisen toiminnoissa. Automaattista eleiden analyysia tarvitaan laitteiden ja ihmisten välisestä vuorovaikutuksesta parantamiseksi ja tavoitteena on yhtä luonnollinen vuorovaikutus kuin ihmisten välinen vuorovaikutus. Konenäön näkökulmasta eleiden analyysijärjestelmä koostuu ihmisen liikkeiden havainnoinnista ja eleiden tunnistamisesta. Tämä väitöskirjatyö edistää eleanalyysin-tutkimusta erityisesti kahdesta näkökulmasta: 1) Havainnointi - ihmisen liikkeiden segmentointi videosekvenssistä. 2) Ymmärtäminen - elemarkkerien erottaminen ja tunnistaminen. Väitöskirjan ensimmäinen osa esittelee kaksi liikkeen havainnointi menetelmää, jotka perustuvat harvan signaalin rekonstruktioon. Videokuvan etualan (ihmisen liikkeet) pikselit eivät yleensä ole satunnaisesti jakautuneita vaan niillä toisistaan riippuvia ominaisuuksia spatiaali- ja aikatasolla tarkasteltuna. Tähän havaintoon perustuen esitellään spatiaalis-ajallinen harva rekonstruktiomalli, joka käsittää etualan pikseleiden klusteroinnin spatiaalisen koherenssin ja ajallisen jatkuvuuden perusteella. Lisäksi tehdään oletus, että pikseli on monikanavainen signaali (RGB-väriarvot). Pikselin ollessa samankaltainen vieruspikseliensä kanssa myös niiden värikanava-arvot ovat samankaltaisia. Havaintoon nojautuen kehitettiin kanavat yhdistävä lasso-regularisointi, joka mahdollistaa monikanavaisen signaalin tasaisuuden tutkimisen. Väitöskirjan toisessa osassa esitellään kaksi menetelmää ihmisen eleiden tunnistamiseksi. Menetelmiä voidaan käyttää eleiden ajallisen dynamiikan ongelmien (eleiden nopeuden vaihtelu) ratkaisemiseksi, mikä on ensiarvoisen tärkeää havainnoitujen eleiden oikein tulkitsemiseksi. Ensimmäisessä menetelmässä ele kuvataan luurankomallin liikeratana Riemannin monistossa (Riemannian manifold), joka hyödyntää aikavääristymille sietoista metriikkaa. Lisäksi esitellään harvakoodaus (sparse coding) luurankomallien liikeradoille. Harvakoodaus perustuu nimiöintitietoon, jonka tavoitteena on varmistua koodisanaston keskinäisestä riippumattomuudesta. Toisen menetelmän lähtökohtana on havainto, että ele on ajallinen sarja selkeästi määriteltäviä vaiheita. Vaiheiden yhdistämiseen ehdotetaan matala-asteista matriisihajotelmamallia, jotta piilotilat voidaan sovittaa paremmin Markovin piilomalliin (Hidden Markov Model)
21
Fakhir, Mahammad Majed. "Biometric fusion methods for adaptive face recognition in computer vision." Thesis, University of Newcastle upon Tyne, 2017. http://hdl.handle.net/10443/4001.
Full textAbstract:
Face recognition is a biometric method that uses different techniques to identify the individuals based on the facial information received from digital image data. The system of face recognition is widely used for security purposes, which has challenging problems. The solutions to some of the most important challenges are proposed in this study. The aim of this thesis is to investigate face recognition across pose problem based on the image parameters of camera calibration. In this thesis, three novel methods have been derived to address the challenges of face recognition and offer solutions to infer the camera parameters from images using a geomtric approach based on perspective projection. The following techniques were used: camera calibration CMT and Face Quadtree Decomposition (FQD), in order to develop the face camera measurement technique (FCMT) for human facial recognition. Facial information from a feature extraction and identity-matching algorithm has been created. The success and efficacy of the proposed algorithm are analysed in terms of robustness to noise, the accuracy of distance measurement, and face recognition. To overcome the intrinsic and extrinsic parameters of camera calibration parameters, a novel technique has been developed based on perspective projection, which uses different geometrical shapes to calibrate the camera. The parameters used in novel measurement technique CMT that enables the system to infer the real distance for regular and irregular objects from the 2-D images. The proposed system of CMT feeds into FQD to measure the distance between the facial points. Quadtree decomposition enhances the representation of edges and other singularities along curves of the face, and thus improves directional features from face detection across face pose. The proposed FCMT system is the new combination of CMT and FQD to recognise the faces in the various pose. The theoretical foundation of the proposed solutions has been thoroughly developed and discussed in detail. The results show that the proposed algorithms outperform existing algorithms in face recognition, with a 2.5% improvement in main error recognition rate compared with recent studies.
22
Linsley, Drew. "A revised framework for human scene recognition." Thesis, Boston College, 2016. http://hdl.handle.net/2345/bc-ir:106986.
Full textAbstract:
Thesis advisor: Sean P. MacEvoy<br>For humans, healthy and productive living depends on navigating through the world and behaving appropriately along the way. But in order to do this, humans must first recognize their visual surroundings. The technical difficulty of this task is hard to comprehend: the number of possible scenes that can fall on the retina approaches infinity, and yet humans often effortlessly and rapidly recognize their surroundings. Understanding how humans accomplish this task has long been a goal of psychology and neuroscience, and more recently, has proven useful in inspiring and constraining the development of new algorithms for artificial intelligence (AI). In this thesis I begin by reviewing the current state of scene recognition research, drawing upon evidence from each of these areas, and discussing an unchallenged assumption in the literature: that scene recognition emerges from independently processing information about scenes’ local visual features (i.e. the kinds of objects they contain) and global visual features (i.e., spatial parameters. ). Over the course of several projects, I challenge this assumption with a new framework for scene recognition that indicates a crucial role for information sharing between these resources. Development and validation of this framework will expand our understanding of scene recognition in humans and provide new avenues for research by expanding these concepts to other domains spanning psychology, neuroscience, and AI<br>Thesis (PhD) — Boston College, 2016<br>Submitted to: Boston College. Graduate School of Arts and Sciences<br>Discipline: Psychology
23
Tu, Peter Henry. "Extracting and analysing seismic events using computer vision techniques." Thesis, University of Oxford, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.282329.
Full text
24
Khendek, Hamid. "Computer optical-vision system for glass measurement and inspection." Thesis, University of Nottingham, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283378.
Full text
25
Andreadis, Ioannis. "Colour processing for image segmentation and recognition." Thesis, University of Manchester, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.284238.
Full text
26
Berry, David T. "A knowledge-based framework for machine vision." Thesis, Heriot-Watt University, 1987. http://hdl.handle.net/10399/1022.
Full text
27
Pan, Wendy. "A simulated shape recognition system using feature extraction /." Online version of thesis, 1989. http://hdl.handle.net/1850/10496.
Full text
28
Billings, Rachel Mae. "On Efficient Computer Vision Applications for Neural Networks." Thesis, Virginia Tech, 2021. http://hdl.handle.net/10919/102957.
Full textAbstract:
Since approximately the dawn of the new millennium, neural networks and other machine learning algorithms have become increasingly capable of adeptly performing difficult, dull, and dangerous work conventionally carried out by humans in times of old. As these algorithms become steadily more commonplace in everyday consumer and industry applications, the consideration of how they may be implemented on constrained hardware systems such as smartphones and Internet-of-Things (IoT) peripheral devices in a time- and power- efficient manner while also understanding the scenarios in which they fail is of increasing importance. This work investigates implementations of convolutional neural networks specifically in the context of image inference tasks. Three areas are analyzed: (1) a time- and power-efficient face recognition framework, (2) the development of a COVID-19-related mask classification system suitable for deployment on low-cost, low-power devices, and (3) an investigation into the implementation of spiking neural networks on mobile hardware and their conversion from traditional neural network architectures.<br>Master of Science<br>The subject of machine learning and its associated jargon have become ubiquitous in the past decade as industries seek to develop automated tools and applications and researchers continue to develop new methods for artificial intelligence and improve upon existing ones. Neural networks are a type of machine learning algorithm that can make predictions in complex situations based on input data with human-like (or better) accuracy. Real-time, low-power, and low-cost systems using these algorithms are increasingly used in consumer and industry applications, often improving the efficiency of completing mundane and hazardous tasks traditionally performed by humans. The focus of this work is (1) to explore when and why neural networks may make incorrect decisions in the domain of image-based prediction tasks, (2) the demonstration of a low-power, low-cost machine learning use case using a mask recognition system intended to be suitable for deployment in support of COVID-19-related mask regulations, and (3) the investigation of how neural networks may be implemented on resource-limited technology in an efficient manner using an emerging form of computing.
29
Hoad, Paul. "Active robot vision and its use in object recognition." Thesis, University of Surrey, 1994. http://epubs.surrey.ac.uk/844223/.
Full textAbstract:
Object recognition has been one of the main areas of research into computer vision in the last 20-30 years. Until recently most of this research has been performed on scenes taken using static monocular, binocular or even trinocular cameras. It is believed, however, that by adding the ability to move the look point and concentrate on a region of interest a more robust and efficient method of vision can be achieved. Recent studies into the ability to provide human-like vision systems for a more active approach to vision have lead to the development of a number of robot controlled vision systems. In this thesis the development of one such system at the University of Surrey, the stereo robot head "Getafix" is described. The design, construction and development of the head and its control system have been undertaken as part of this project with the aim of improving current vision tasks, in particular, that of object recognition. In this thesis the design of the control systems, kinematics and control software of the stereo robot head will be discussed. A number of simple commissioning experiments are also shown, using the concepts of the robot control developed herein. Camera lens control and calibration is also described. A review of classical primitive based object recognition systems is given and the development of a novel generic cylindrical object recognition strategy is shown. The use of this knowledge source is demonstrated with other vision processes of colour and stereo. The work on the cylinder recognition strategy and the stereo robot head are finally combined within an active vision framework. A purposive active vision strategy is used to detect cylindrical structures, that would otherwise be undetectable by the cylindrical object detection algorithm alone.
30
Bernier, Thomas. "An adaptable recognition system for biological and other irregular objects /." Thesis, McGill University, 2001. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=38150.
Full textAbstract:
Automated visual recognition and detection processes are becoming increasingly prevalent in almost all scientific fields and being currently implemented in many fields of industry. In most cases, systems are painstakingly designed and developed in order to detect only a single and specific object or property of an object. The objective of this project was to create a framework of development in which any object distinguishable in a two-dimensional digital image could be analyzed and subsequently detected in other images. Furthermore, as new methods are developed, they could be easily incorporated into this framework to ultimately improve the performance of the system.<br>This thesis describes a highly adaptable, general-application visual detection system as well as several innovative methods for the description of objects without which such adaptivity would be impossible. Two-dimensional, still images are analyzed and objects of interest can be introduced to the system. Objects are then described by a variety of properties through derived attributes and stored in a database. Occurrences of these objects can then be detected in future images through comparisons to selected models. The system is fully expandable in that new properties and comparison techniques or criteria can be added as they are developed and as their need becomes apparent. The system is presented with a basic set of attribute representations and methods of comparison, and their development and origin are described in detail. The database structure is outlined and the process by which new properties and comparative methods can be added is described. Seventeen different images containing nearly two thousand separate objects were searched for various model objects and the average classification accuracy was 98.3%. In most images, more than 100 object classifications could be performed per second at an accuracy higher than 95% when no higher order analyses were required.
31
Liu, Gang. "Automatic target recognition using location uncertainty /." Thesis, Connect to this title online; UW restricted, 2000. http://hdl.handle.net/1773/5826.
Full text
32
Kannala, J. (Juho). "Models and methods for geometric computer vision." Doctoral thesis, University of Oulu, 2010. http://urn.fi/urn:isbn:9789514261510.
Full textAbstract:
Abstract
Automatic three-dimensional scene reconstruction from multiple images is a central problem in geometric computer vision. This thesis considers topics that are related to this problem area. New models and methods are presented for various tasks in such specific domains as camera calibration, image-based modeling and image matching. In particular, the main themes of the thesis are geometric camera calibration and quasi-dense image matching. In addition, a topic related to the estimation of two-view geometric relations is studied, namely, the computation of a planar homography from corresponding conics. Further, as an example of a reconstruction system, a structure-from-motion approach is presented for modeling sewer pipes from video sequences.
In geometric camera calibration, the thesis concentrates on central cameras. A generic camera model and a plane-based camera calibration method are presented. The experiments with various real cameras show that the proposed calibration approach is applicable for conventional perspective cameras as well as for many omnidirectional cameras, such as fish-eye lens cameras. In addition, a method is presented for the self-calibration of radially symmetric central cameras from two-view point correspondences.
In image matching, the thesis proposes a method for obtaining quasi-dense pixel matches between two wide baseline images. The method extends the match propagation algorithm to the wide baseline setting by using an affine model for the local geometric transformations between the images. Further, two adaptive propagation strategies are presented, where local texture properties are used for adjusting the local transformation estimates during the propagation. These extensions make the quasi-dense approach applicable for both rigid and non-rigid wide baseline matching.
In this thesis, quasi-dense matching is additionally applied for piecewise image registration problems which are encountered in specific object recognition and motion segmentation. The proposed object recognition approach is based on grouping the quasi-dense matches between the model and test images into geometrically consistent groups, which are supposed to represent individual objects, whereafter the number and quality of grouped matches are used as recognition criteria. Finally, the proposed approach for dense two-view motion segmentation is built on a layer-based segmentation framework which utilizes grouped quasi-dense matches for initializing the motion layers, and is applicable under wide baseline conditions.
33
Griffin, A. C. "Computer vision techniques for the automatic interpretation of thermochromic paint." Thesis, University of Surrey, 2001. http://epubs.surrey.ac.uk/844526/.
Full textAbstract:
The aim of this study is to provide an automatic method for the interpretation of images of objects that are coated with thermal paint. Thermal paint changes colour permanently according to the temperature to which it is heated and can be employed as a temperature gauge where more cumbersome measurement apparatus may not be suitable. Such a gauge requires a means to convert the manifestation of the measurement to the corresponding numerical values. In our case this involves the grouping of ranges of colour together into temperature bands and the extraction of the temperature contours between these bands, a task currently performed by a human operator. This study will demonstrate some success in the automatic interpretation of thermal paints through computer vision approaches. In summary the main contributions of this work are: The demonstration that edge detection is not a useful step. Human operators tend to interpret thermochromic paint not simply by colour matching, but by locating prominent colour change points. We demonstrate why in our opinion this in not necessarily the best step through an exploration of colour edge detection. The development of a feature space model of the paint colour formation based on B-splines and the employment of this within a maximum likelihood estimation scheme [GKWG96],[CSGW97] The development of a paint interpretation method based on a Markov Random Field and Simulated Annealing [GSW+98] Our methods axe applicable to cases of ideal data. We highlight some troublesome paint artefacts that occur in real cases and that hinder interpretation. We discuss possible solutions. Finally we draw conclusions and point to directions for possible future work. Key words: thermochromic paint, maximum likelihood estimate, simulated annealing.
34
Evans, Alun C. "Geometric feature distributions for shape representation and recognition." Thesis, University of Sheffield, 1994. http://etheses.whiterose.ac.uk/1890/.
Full textAbstract:
One of the fundamental problems in computer vision is the identification of objects from their shape. The research reported in this thesis is directed toward the development of a scheme for representing the shape of an object which allows it to be recognised both quickly and robustly across a wide range of viewing conditions. Given a shape described by a set of primitive elements, eg. straight line segments, the proposed scheme involves using a histogram to record the distribution of geometric features, eg. angle and distance, measured between pairs of primitives. This form of shape representation has a number advantages over previously proposed schemes. Foremost among these is the fact that it is able to produce local representations of shape, based on individual line segments. Recognition based on such representation is robust to the problems arising in cluttered scenes. Representations produced by the scheme are also invariant to certain object transformations, they degrade gracefully as the shape is fragmented and are strong enough to support discrimination between dissimilar objects. By treating the histogram recording a geometric feature distribution as a feature vector it is possible to match shapes using techniques from statistical pattern classification. This has the advantage that optimal matching accuracy can be achieved using processing which is both simple and uniform. The approach is therefore ideally suited to implementation in dedicated hardware. A detailed analysis is undertaken of the effect on recognition of changes in the description of a shape caused by fragmentation noise, scene clutter and sensor error. It is found that the properties of both the representation and matching components of the system combine to ensure that recognition is, in theory, unaffected by fragmentation noise, while it is maintained to very high levels of scene clutter. The factors which determine the effect of sensor error on the performance of the recognition system are fully analysed. The ability of the representational scheme to support object recognition is demonstrated in a number of different domains. The recognition of both 2D and 3D objects from a fixed viewpoint is demonstrated in conditions of severe fragmentation noise, occlusion and clutter. The scheme is then shown to extend straightforwardly to the representation of 3D shape. This is exploited to perform recognition and localisation of 3D objects from an arbitrary viewpoint, based on the matching of 3D scene and ,model shape descriptions. Finally, the use of the scheme within a multiple view-based approach to 3D object recognition is demonstrated.
35
Moustafa, Moustafa Abdel-Azim. "Feature recognition using a fast radon transform-based computer vision system." Thesis, Cranfield University, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.305610.
Full text
36
CARCANGIU, ALESSANDRO. "Combining declarative models and computer vision recognition algorithms for stroke gestures." Doctoral thesis, Università degli Studi di Cagliari, 2019. http://hdl.handle.net/11584/260670.
Full textAbstract:
The consumer-level devices that track the user’s gestures eased the design and
the implementation of interactive applications relying on body movements as
input. Gesture recognition based on computer vision and machine-learning
focuses mainly on accuracy and robustness. The resulting classifiers label precisely gestures after their performance, but they do not provide intermediate
information during the execution. Human-Computer Interaction research focused instead on providing an easy and effective guidance for performing and
discovering interactive gestures. The compositional approaches developed for
solving such problem provide information on both the whole gesture and on
its sub-parts, but they exploit heuristic techniques that have a low recognition
accuracy. In this thesis, we introduce two methods, DEICTIC and G-Gene,
designed for establishing a compromise between the accuracy and the provided
information. DEICTIC exploits a compositional and declarative description
for stroke gestures. It uses basic Hidden Markov Models (HMMs) to recognise
meaningful predefined primitives (gesture sub-parts) and it composes them
to recognise complex gestures. It provides information for supporting gesture
guidance and it reaches an accuracy comparable with state-of-the-art approaches
on two datasets from the literature. The normalization of the gesture samples
limits the online recognition in the general case. Instead, G-Gene is a method
for transforming compositional stroke gesture definitions into profile Hidden
Markov Models (HMMs), able to provide both a good accuracy and information
on gesture sub-parts. It supports online recognition without using any global
feature, and it updates the information while receiving the input stream, with an
accuracy useful for prototyping the interaction. We evaluated both approaches
in a simplified development task with real developers, showing that they require
less time and an effort comparable to compositional approaches, while the
definition procedure and the perceived recognition accuracy is comparable to
machine learning.
37
Aljarrah, Inad A. "Color face recognition by auto-regressive moving averaging." Ohio : Ohio University, 2002. http://www.ohiolink.edu/etd/view.cgi?ohiou1174410880.
Full text
38
Redfield, Signe Anne. "Efficient object recognition using color quantization." [Gainesville, Fla.] : University of Florida, 2001. http://purl.fcla.edu/fcla/etd/UFE0000347.
Full textAbstract:
Thesis (Ph. D.)--University of Florida, 2001.<br>Title from title page of source document. Document formatted into pages; contains xiv, 150 p.; also contains graphics. Includes vita. Includes bibliographical references.
39
Wallenberg, Marcus. "Embodied Visual Object Recognition." Doctoral thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-132762.
Full textAbstract:
Object recognition is a skill we as humans often take for granted. Due to our formidable object learning, recognition and generalisation skills, it is sometimes hard to see the multitude of obstacles that need to be overcome in order to replicate this skill in an artificial system. Object recognition is also one of the classical areas of computer vision, and many ways of approaching the problem have been proposed. Recently, visually capable robots and autonomous vehicles have increased the focus on embodied recognition systems and active visual search. These applications demand that systems can learn and adapt to their surroundings, and arrive at decisions in a reasonable amount of time, while maintaining high object recognition performance. This is especially challenging due to the high dimensionality of image data. In cases where end-to-end learning from pixels to output is needed, mechanisms designed to make inputs tractable are often necessary for less computationally capable embodied systems.Active visual search also means that mechanisms for attention and gaze control are integral to the object recognition procedure. Therefore, the way in which attention mechanisms should be introduced into feature extraction and estimation algorithms must be carefully considered when constructing a recognition system.This thesis describes work done on the components necessary for creating an embodied recognition system, specifically in the areas of decision uncertainty estimation, object segmentation from multiple cues, adaptation of stereo vision to a specific platform and setting, problem-specific feature selection, efficient estimator training and attentional modulation in convolutional neural networks. Contributions include the evaluation of methods and measures for predicting the potential uncertainty reduction that can be obtained from additional views of an object, allowing for adaptive target observations. Also, in order to separate a specific object from other parts of a scene, it is often necessary to combine multiple cues such as colour and depth in order to obtain satisfactory results. Therefore, a method for combining these using channel coding has been evaluated. In order to make use of three-dimensional spatial structure in recognition, a novel stereo vision algorithm extension along with a framework for automatic stereo tuning have also been investigated. Feature selection and efficient discriminant sampling for decision tree-based estimators have also been implemented. Finally, attentional multi-layer modulation of convolutional neural networks for recognition in cluttered scenes has been evaluated. Several of these components have been tested and evaluated on a purpose-built embodied recognition platform known as Eddie the Embodied.<br>Embodied Visual Object Recognition<br>FaceTrack
40
Ashbrook, Anthony P. "Pairwise geometric histograms for object recognition : developments and analysis." Thesis, University of Sheffield, 1999. http://etheses.whiterose.ac.uk/14675/.
Full textAbstract:
One of the fundamental problems in the field of computer vision is the task of classifying objects, which are present in an image or sequence of images, based on their appearance. This task is commonly referred to as the object recognition problem. A system designed to perform this task must be able to learn visual cues such as shape, colour and texture from examples of objects presented to it. These cues are then later used to identify examples of the known objects in previously unseen scenes. The work presented in this thesis is based on a statistical representation of shape known as a pairwise geometric histogram which has been demonstrated by other researchers in 2-dimensional object recognition tasks. An analysis of the performance of recognition based on this representation has been conducted and a number of contributions to the original recognition algorithm have been made. An important property of an object recognition system is its scalability. This is the. ability of the system to continue performing as the number of known objects is increased. The analysis of the recognition algorithm presented here considers this issue by relating the classification error to the number of stored model objects. An estimate is also made of the number of objects which can be represented uniquely using geometric histograms. One of the main criticisms of the original recognition algorithm based on geometric histograms was the inability to recognise objects at different scales. An algorithm is presented here that is able to recognise objects over a range of scale using the geometric histogram representation. Finally, a novel pairwise geometric histogram representation for arbitrary surfaces has been proposed. This inherits many of the advantages of the 2-dimensional shape descriptor but enables recognition of 3-dimensional object from arbitrary viewpoints.
41
Rangarajan, Vibhav Shyam 1980. "Interfacing speech recognition an vision guided microphone array technologies." Thesis, Massachusetts Institute of Technology, 2003. http://hdl.handle.net/1721.1/29687.
Full textAbstract:
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2003.<br>Includes bibliographical references (p. 57-58).<br>One goal of a pervasive computing environment is to allow the user to interact with the environment in an easy and natural manner. The use of spoken commands, as inputs to a speech recognition system, is one such way to naturally interact with the environment. In challenging acoustic environments, microphone arrays can improve the quality of the input audio signal by beamforming, or steering, to the location of the speaker of interest. The existence of multiple speakers, large interfering signals and/or reverberations or reflections in the audio signal(s) requires the use of advanced beamforming techniques which attempt to separate the target audio from the mixed signal received at the microphone array. In this thesis I present and evaluate a method of modeling reverberations as separate anechoic interfering sources emanating from fixed locations. This acoustic modelling technique allows for tracking of acoustic changes in the environment, such as those caused by speaker motion.<br>by Vibhav Shyam Rangarajan.<br>M.Eng.
42
Subirana-Vilanova, J. Brian. "Mid-level vision and recognition of non-rigid objects." Thesis, Massachusetts Institute of Technology, 1993. http://hdl.handle.net/1721.1/37708.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1994.<br>Includes bibliographical references (p. 215-239).<br>by J. Brian Subirana-Vilanova.<br>Ph.D.
43
Hluchoweckyj, Lydia Theodosia. "Recognising road marking structures for autonomous vehicle navigation using computer vision." Thesis, University of Bristol, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.357691.
Full text
44
Kolesnik, Paul. "Conducting gesture recognition, analysis and performance system." Thesis, McGill University, 2004. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=81499.
Full textAbstract:
A number of conducting gesture analysis and performance systems have been developed over the years. However, most of the previous projects either primarily concentrated on tracking tempo and amplitude indicating gestures, or implemented individual mapping techniques for expressive gestures that varied from research to research. There is a clear need for a uniform process that could be applied toward analysis of both indicative and expressive gestures. The proposed system provides a set of tools that contain extensive functionality for identification, classification and performance with conducting gestures. Gesture recognition procedure is designed on the basis of Hidden Markov Model (HMM) process. A set of HMM tools are developed for Max/MSP software. Training and recognition procedures are applied toward both right-hand beat- and amplitude-indicative gestures, and left-hand expressive gestures. Continuous recognition of right-hand gestures is incorporated into a real-time gesture analysis and performance system in Eyesweb and Max/MSP/Jitter environments.
45
Lennartsson, Mattias. "Object Recognition with Cluster Matching." Thesis, Linköping University, Department of Electrical Engineering, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-51494.
Full textAbstract:
<p>Within this thesis an algorithm for object recognition called Cluster Matching has been developed, implemented and evaluated. The image information is sampled at arbitrary sample points, instead of interest points, and local image features are extracted. These sample points are used as a compact representation of the image data and can quickly be searched for prior known objects. The algorithm is evaluated on a test set of images and the result is surprisingly reliable and time efficient.</p>
46
Ahmadyfard, Alireza. "Object recognition by region matching using relaxation with relational constraints." Thesis, University of Surrey, 2003. http://epubs.surrey.ac.uk/843289/.
Full textAbstract:
Our objective in this thesis is to develop a method for establishing an object recognition system based on the matching of image regions. A region is segmented from image based on colour homogeneity of pixels. The method can be applied to a number of computer vision applications such as object recognition (in general) and image retrieval. The motivation for using regions as image primitives is that they can be represented invariantly to a group of geometric transformations and regions are stable under scaling. We model each object of interest in our database using a single frontal image. The recognition task is to determine the presence of object(s) of interest in scene images. We propose a novel method for afflne invariant representation of image regions in the form of Attributed Relational Graph (ARG). To make image regions comparable for matching, we project each region to an affine invariant space and describe it using a set of unary measurements. The distinctiveness of these features is enhanced by describing the relation between the region and its neighbours. We limit ourselves to the low order relations, binary relations, to minimise the combinatorial complexity of both feature extraction and model matching, and to maximise the probability of the features being observed. We propose two sets of binary measurements: geometric relations between pair of regions, and colour profile on the line connecting the centroids of regions. We demonstrate that the former measurements are very discriminative when the shape of segmented regions is informative. However, they are susceptible to distortion of regions boundaries as a result of severe geometric transformations. In contrast, the colour profile binary measurements are very robust. Using this representation we construct a graph to represent the regions in the scene image and refer to it as the scene graph. Similarly a graph containing the regions of all object models is constructed and referred to as the model graph. We consider the object recognition as the problem of matching the scene graph and model graphs. We adopt the probabilistic relaxation labelling technique for our problem. The method is modified to cope better with image segmentation errors. The implemented algorithm is evaluated under affine transformation, occlusion, illumination change and cluttered scene. Good performance for recognition even under severe scaling and in cluttered scenes is reported. Key words: Region Matching, Object Recognition, Relaxation Labelling, Affine Invariant.
47
Caparrelli, Fabio. "View-based three-dimensional object recognition using pairwise geometric histograms." Thesis, University of Sheffield, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.322876.
Full text
48
Zhu, Yonggen. "Feature extraction and 2D/3D object recognition using geometric invariants." Thesis, King's College London (University of London), 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.362731.
Full text
49
Cowell, J. R. "Character recognition in unconstrained environments." Thesis, Nottingham Trent University, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.277696.
Full text
50
Flitton, Greg. "Extending computer vision techniques to recognition problems in 3D volumetric baggage imagery." Thesis, Cranfield University, 2012. http://dspace.lib.cranfield.ac.uk/handle/1826/7993.
Full textAbstract:
We investigate the application of computer vision techniques to rigid object recognition in Computed Tomography (CT) security scans of baggage items. This imagery is of poor resolution and is complex in nature: items of interest can be imaged in any orientation and copious amounts of clutter, noise and artefacts are prevalent. We begin with a novel 3D extension to the seminal SIFT keypoint descriptor that is evaluated through specific instance recognition in the volumetric data. We subsequently compare the performance of the SIFT descriptor against a selection of alternative descriptor methodologies. We demonstrate that the 3D SIFT descriptor is notably outperformed by simpler descriptors which appear to be more suited for use in noise and artefact-prone CT imagery. Rigid object class recognition in 3D volumetric baggage data has received little attention in prior work. We evaluate contrasting techniques between a traditional approach derived from interest point descriptors and a novel technique based on modelling of the primary components of the primate visual cortex. We initially demonstrate class recognition through the implementation of a codebook approach. A variety of aspects relating to codebook generation are investigated (codebook size, assignment method) using a range of feature descriptors. Recognition of a number of object classes is performed and results from this show that the choice of descriptor is a critical aspect. Finally, we present a unique extension to the established standard model of the visual cortex: a volumetric implementation. The visual cortex model comprises a hierarchical structure of alternating simple and complex operations that has demonstrated excellent class recognition results using 2D imagery. We derive 3D extensions to each layer in the hierarchy resulting in class recognition results that signficantly outperform those achieved using the earlier traditional codebook approach. Overall we present several novel solutions to object recognition within 3D CT security images that are supported by strong statistical results.