To see the other types of publications on this topic, follow the link: Bird recognition.
Dissertations / Theses on the topic 'Bird recognition'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 33 dissertations / theses for your research on the topic 'Bird 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
Van, der Merwe Hugo Jacobus. "Bird song recognition with Hidden Markov Models /." Thesis, Link to the online version, 2008. http://hdl.handle.net/10019/914.
Full text
2
Bastas, Selin A. "Nocturnal Bird Call Recognition System for Wind Farm Applications." University of Toledo / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1325803309.
Full text
3
Reyes, Elsa. "A Comparison of Image Processing Techniques for Bird Detection." DigitalCommons@CalPoly, 2014. https://digitalcommons.calpoly.edu/theses/1239.
Full textAbstract:
Orchard fruits and vegetable crops are vulnerable to wild birds and animals. These wild birds and animals can cause critical damage to the produce. Traditional methods of scaring away birds such as scarecrows are not long-term solutions but short-term solutions. This is a huge problem especially near areas like San Luis Obispo where there are vineyards. Bird damage can be as high as 50% for grapes being grown in vineyards. The total estimated revenue lost annually in the 10 counties in California due to bird and rodent damage to 22 selected crops ranged from $168 million to $504 million (in 2009 dollars). A more effective and permanent system needs to be put into place. Monitoring systems in agricultural settings could potentially provide a lot of data for image processing. Most current monitoring systems however don’t focus on image processing but instead really heavily on sensors. Just having sensors for certain systems work, but for birds, monitoring it is not an option because they are not domesticated like pigs, cows etc. in which most these agricultural monitoring systems work on. Birds can fly in and out of the area whereas domesticated animals can be confined to certain physical regions. The most crucial step in a smart scarecrow system would be how a threat would v be detected. Image processing methods can be effectively applied to detecting items in video footage. This paper will focus on bird detection and will analyze motion detection with image subtraction, bird detection with template matching, and bird detection with the Viola-Jones Algorithm. Of the methods considered, bird detection with the Viola-Jones Algorithm had the highest accuracy (87%) with a somewhat low false positive rate. This image processing step would ideally be incorporated with hardware (such as a microcontroller or FPGA, sensors, a camera etc.) to form a smart scarecrow system.
4
Patton, Tadd B. "Altered features of female pigeons (Columba livia) elicit preference behavior in male pigeons." [Tampa, Fla] : University of South Florida, 2006. http://purl.fcla.edu/usf/dc/et/SFE0001656.
Full text
5
Kahl, Stefan. "Identifying Birds by Sound: Large-scale Acoustic Event Recognition for Avian Activity Monitoring." Universitätsverlag Chemnitz, 2019. https://monarch.qucosa.de/id/qucosa%3A36986.
Full textAbstract:
Automated observation of avian vocal activity and species diversity can be a transformative tool for ornithologists, conservation biologists, and bird watchers to assist in long-term monitoring of critical environmental niches. Deep artificial neural networks have surpassed traditional classifiers in the field of visual recognition and acoustic event classification. Still, deep neural networks require expert knowledge to design, train, and test powerful models. With this constraint and the requirements of future applications in mind, an extensive research platform for automated avian activity monitoring was developed: BirdNET. The resulting benchmark system yields state-of-the-art scores across various acoustic domains and was used to develop expert tools and public demonstrators that can help to advance the democratization of scientific progress and future conservation efforts.Die automatisierte Überwachung der Vogelstimmenaktivität und der Artenvielfalt kann ein revolutionäres Werkzeug für Ornithologen, Naturschützer und Vogelbeobachter sein, um bei der langfristigen Überwachung kritischer Umweltnischen zu helfen. Tiefe künstliche neuronale Netzwerke haben die traditionellen Klassifikatoren im Bereich der visuellen Erkennung und akustische Ereignisklassifizierung übertroffen. Dennoch erfordern tiefe neuronale Netze Expertenwissen, um leistungsstarke Modelle zu entwickeln, trainieren und testen. Mit dieser Einschränkung und unter Berücksichtigung der Anforderungen zukünftiger Anwendungen wurde eine umfangreiche Forschungsplattform zur automatisierten Überwachung der Vogelaktivität entwickelt: BirdNET. Das daraus resultierende Benchmark-System liefert state-of-the-art Ergebnisse in verschiedenen akustischen Bereichen und wurde verwendet, um Expertenwerkzeuge und öffentliche Demonstratoren zu entwickeln, die dazu beitragen können, die Demokratisierung des wissenschaftlichen Fortschritts und zukünftige Naturschutzbemühungen voranzutreiben.
6
Whitwell, Sarah Margaret. "The impact of isolation from mammalian predators on the anti-predator behaviours of the North Island robin (Petroica longipes) : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Conservation Biology at Massey University, Auckland, New Zealand." Massey University, 2009. http://hdl.handle.net/10179/1142.
Full textAbstract:
Conservation in New Zealand has begun to focus heavily on the restoration of degraded mainland ecosystems and the reintroduction of native species that have become locally extinct. In many cases the individuals that are selected for reintroduction are harvested from ‘mammal-free’ offshore islands. This thesis examines the effects of isolation from mammalian predators on the predator avoidance behaviours and predator recognition abilities of New Zealand birds using the North Island robin as a model. It also investigates whether any effects of isolation from mammalian predators has a lasting impact on mainland populations founded by individuals from offshore islands. Nest site selection behaviours were compared across three populations that are exposed to different suites of predators and have differing translocation histories; Benneydale, Tiritiri Matangi and Wenderholm. Point height intercept and point-centred quarter surveys were used to compare habitat availability between the sites and to compare nest sites with the available habitat. Eight nest characteristic variables were also compared across the three sites using a principle component analysis. Benneydale nests were located higher in the trees and were more concealed than nests at the other two sites. Nests on Tiritiri Matangi were supported by large numbers of thin branches and were located toward the periphery of the nest tree. Unfortunately these differences are very difficult to interpret due to a high degree of variation in the habitat types present at the three sites. The anti-predator behaviours initiated in response to a model stoat, model morepork and control were used to test the ability of nesting robins to recognise the threat that each of these treatments might pose to nest success. Behavioural variables were compared between Benneydale, Tiritiri Matangi and Wenderholm using a response intensity scoring system and a principle component analysis. The results indicated that isolation from mammalian predators on Tiritiri Matangi has suppressed the ability of robins on the island to recognise the predatory threat posed by a stoat. They also suggest that the intense mammal control carried out at Wenderholm may have inhibited the ability of local robins to produce strong anti-predator responses when faced with a stoat.
7
Movin, Andreas, and Jonathan Jilg. "Kan datorer höra fåglar?" Thesis, KTH, Skolan för teknikvetenskap (SCI), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254800.
Full textAbstract:
Ljudigenkänning möjliggörs genom spektralanalys, som beräknas av den snabba fouriertransformen (FFT), och har under senare år nått stora genombrott i samband med ökningen av datorprestanda och artificiell intelligens. Tekniken är nu allmänt förekommande, i synnerhet inom bioakustik för identifiering av djurarter, en viktig del av miljöövervakning. Det är fortfarande ett växande vetenskapsområde och särskilt igenkänning av fågelsång som återstår som en svårlöst utmaning. Även de främsta algoritmer i området är långt ifrån felfria. I detta kandidatexamensarbete implementerades och utvärderades enkla algoritmer för att para ihop ljud med en ljuddatabas. En filtreringsmetod utvecklades för att urskilja de karaktäristiska frekvenserna vid fem tidsramar som utgjorde basen för jämförelsen och proceduren för ihopparning. Ljuden som användes var förinspelad fågelsång (koltrast, näktergal, kråka och fiskmås) så väl som egeninspelad mänsklig röst (4 unga svenska män). Våra resultat visar att framgångsgraden normalt är 50–70%, den lägsta var fiskmåsen med 30% för en liten databas och den högsta var koltrasten med 90% för en stor databas. Rösterna var svårare för algoritmen att särskilja, men de hade överlag framgångsgrader mellan 50% och 80%. Dock gav en ökning av databasstorleken generellt inte en ökning av framgångsgraden. Sammanfattningsvis visar detta kandidatexamensarbete konceptbeviset bakom fågelsångigenkänning och illustrerar såväl styrkorna som bristerna av dessa enkla algoritmer som har utvecklats. Algoritmerna gav högre framgångsgrad än slumpen (25%) men det finns ändå utrymme för förbättring eftersom algoritmen vilseleddes av ljud av samma frekvenser. Ytterligare studier behövs för att bedöma den utvecklade algoritmens förmåga att identifiera ännu fler fåglar och röster.Sound recognition is made possible through spectral analysis, computed by the fast Fourier transform (FFT), and has in recent years made major breakthroughs along with the rise of computational power and artificial intelligence. The technology is now used ubiquitously and in particular in the field of bioacoustics for identification of animal species, an important task for wildlife monitoring. It is still a growing field of science and especially the recognition of bird song which remains a hard-solved challenge. Even state-of-the-art algorithms are far from error-free. In this thesis, simple algorithms to match sounds to a sound database were implemented and assessed. A filtering method was developed to pick out characteristic frequencies at five time frames which were the basis for comparison and the matching procedure. The sounds used were pre-recorded bird songs (blackbird, nightingale, crow and seagull) as well as human voices (4 young Swedish males) that we recorded. Our findings show success rates typically at 50–70%, the lowest being the seagull of 30% for a small database and the highest being the blackbird at 90% for a large database. The voices were more difficult for the algorithms to distinguish, but they still had an overall success rate between 50% and 80%. Furthermore, increasing the database size did not improve success rates in general. In conclusion, this thesis shows the proof of concept and illustrates both the strengths as well as short-comings of the simple algorithms developed. The algorithms gave better success rates than pure chance of 25% but there is room for improvement since the algorithms were easily misled by sounds of the same frequencies. Further research will be needed to assess the devised algorithms' ability to identify even more birds and voices.
8
Mann, Richard Philip. "Prediction of homing pigeon flight paths using Gaussian processes." Thesis, University of Oxford, 2010. http://ora.ox.ac.uk/objects/uuid:bf6c3fb5-5208-4dfe-aa0a-6e6da45c0d87.
Full textAbstract:
Studies of avian navigation are making increasing use of miniature Global Positioning Satellite devices, to regularly record the position of birds in flight with high spatial and temporal resolution. I suggest a novel approach to analysing the data sets pro- duced in these experiments, focussing on studies of the domesticated homing pigeon (Columba Livia) in the local, familiar area. Using Gaussian processes and Bayesian inference as a mathematical foundation I develop and apply a statistical model to make quantitative predictions of homing pigeon flight paths. Using this model I show that pigeons, when released repeatedly from the same site, learn and follow a habitual route back to their home loft. The model reveals the rate of route learning and provides a quantitative estimate of the habitual route complete with associated spatio-temporal covariance. Furthermore I show that this habitual route is best described by a sequence of isolated waypoints rather than as a continuous path, and that these waypoints are preferentially found in certain terrain types, being especially rare within urban and forested environments. As a corollary I demonstrate an extension of the flight path model to simulate ex- periments where pigeons are released in pairs, and show that this can account for observed large scale patterns in such experiments based only on the individual birds’ previous behaviour in solo flights, making a successful quantitative prediction of the critical value associated with a non-linear behavioural transition.
9
Fox, Elizabeth J. S. "Call-independent identification in birds." University of Western Australia. School of Animal Biology, 2008. http://theses.library.uwa.edu.au/adt-WU2008.0218.
Full textAbstract:
[Truncated abstract] The identification of individual animals based on acoustic parameters is a non-invasive method of identifying individuals with considerable advantages over physical marking procedures. One requirement for an effective and practical method of acoustic individual identification is that it is call-independent, i.e. determining identity does not require a comparison of the same call or song type. This means that an individuals identity over time can be determined regardless of any changes to its vocal repertoire, and different individuals can be compared regardless of whether they share calls. Although several methods of acoustic identification currently exist, for example discriminant function analysis or spectrographic cross-correlation, none are call-independent. Call-independent identification has been developed for human speaker recognition, and this thesis aimed to: 1) determine if call-independent identification was possible in birds, using similar methods to those used for human speaker recognition, 2) examine the impact of noise in a recording on the identification accuracy and determine methods of removing the noise and increasing accuracy, 3) provide a comparison of features and classifiers to determine the best method of call-independent identification in birds, and 4) determine the practical limitations of call-independent identification in birds, with respect to increasing population size, changing vocal characteristics over time, using different call categories, and using the method in an open population. ... For classification, Gaussian mixture models and probabilistic neural networks resulted in higher accuracy, and were simpler to use, than multilayer perceptrons. Using the best methods of feature extraction and classification resulted in 86-95.5% identification accuracy for two passerine species, with all individuals correctly identified. A study of the limitations of the technique, in terms of population size, the category of call used, accuracy over time, and the effects of having an open population, found that acoustic identification using perceptual linear prediction and probabilistic neural networks can be used to successfully identify individuals in a population of at least 40 individuals, can be used successfully on call categories other than song, and can be used in open populations in which a new recording may belong to a previously unknown individual. However, identity was only able to be determined with accuracy for less than three months, limiting the current technique to short-term field studies. This thesis demonstrates the application of speaker recognition technology to enable call-independent identification in birds. Call-independence is a pre-requisite for the successful application of acoustic individual identification in many species, especially passerines, but has so far received little attention in the scientific literature. This thesis demonstrates that call-independent identification is possible in birds, as well as testing and finding methods to overcome the practical limitations of the methods, enabling their future use in biological studies, particularly for the conservation of threatened species.
10
Weary, Daniel Martin. "Inter- and intra-specific recognition by song in the veery (Catharus fuscescens)." Thesis, McGill University, 1985. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=64479.
Full text
11
wu, yenan [Verfasser], and Stefan [Akademischer Betreuer] Wiemann. "Identification of transcription factors that specifically bind methylated recognition sites / yenan wu ; Betreuer: Stefan Wiemann." Heidelberg : Universitätsbibliothek Heidelberg, 2020. http://d-nb.info/1203446330/34.
Full text
12
Wu, Yenan [Verfasser], and Stefan [Akademischer Betreuer] Wiemann. "Identification of transcription factors that specifically bind methylated recognition sites / yenan wu ; Betreuer: Stefan Wiemann." Heidelberg : Universitätsbibliothek Heidelberg, 2020. http://d-nb.info/1203446330/34.
Full text
13
Vaskevicius, Narunas [Verfasser], Andreas [Akademischer Betreuer] [Gutachter] Birk, Michael [Gutachter] Beetz, and Kaustubh [Gutachter] Pathak. "Surface Patches with Uncertainties for 3D Object Recognition and 3D Mapping with Noisy Sensors / Narunas Vaskevicius ; Gutachter: Andreas Birk, Michael Beetz, Kaustubh Pathak ; Betreuer: Andreas Birk." Bremen : IRC-Library, Information Resource Center der Jacobs University Bremen, 2017. http://d-nb.info/1135778558/34.
Full text
14
Häggqvist, Victor, and Peter Lundberg. "Image Comparing and Recognition : Food Classification." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-177474.
Full textAbstract:
Bildigenkänning och jämförelse är ett ämne som har varit i fokus under en lång tid inom datavetenskap. Många företag har försökt att skapa produkter, som utnyttjar olika lösningar för att känna igen objekt och människor. Dock har ingen lyckats skapa en lösning som kan göra detta felfritt. Lifesum vill ha en lösning till deras kaloriräknarapplikation. Denna ska erbjuda användaren möjligheten att fotografera en maträtt, för att sedan kunna ta fram vilken maträtt som bilden illustrerar. Histogramjämförelse är ett av lösningsalternativen, dock inte den mest optimala bildjämförelsealgoritmen. Att använda en algoritm som utnyttjar nyckelpunktsdetektion är den mest optimala lösningen, om träning av algoritmen är ett alternativ. En av idéerna för att öka precisionen är att låta användaren välja mellan de fem bästa maträtterna som algoritmen rekommenderar. På så sätt ökar man sannolikheten att maträtten som söks är en av de rekommenderade maträtterna. Framtida arbeten inom detta ämne kan involvera forskning i hur träning utav HOG, Histogram of Oriented Gradients, algoritmen skulle fungera. Detta för att få ett bättre resultat som låter FLANN, Fast Approximate Nearest Neighbor Search Library, algoritmen arbeta snabbare.Image recognition and comparison is a topic that has been in focus for a long time within computer science. Many companies have tried to create products that use different solutions to recognize objects and people. However, none of these companies have managed to create a solution that can do this flawlessly. Lifesum want a solution to their calorie counting application. This will offer the user the opportunity to take a picture of a dish and then be able to retrieve which dish the image illustrates. Histogram comparison is one solution to this problem, thought not the most optimal one. Using an algorithm that uses keypoint detection is the most optimal solution, if training of the algorithm is an option. One of the ideas to improve the precision is to allow the user to choose between the five best dishes that the algorithm recommends. In this way one increase the probability of that the wanted dish is one of the recommended dishes. Future work in this topic can involve researching on how training the HOG, Histogram of Oriented Gradients, algorithm would work, to get a better result that could let the FLANN, Fast Approximate Nearest Neighbor Search Library, algorithm work faster.
15
Kahl, Stefan [Verfasser], Maximilian [Akademischer Betreuer] Eibl, Maximilian [Gutachter] Eibl, Marc [Gutachter] Ritter, and Holger [Akademischer Betreuer] Klinck. "Identifying Birds by Sound: Large-scale Acoustic Event Recognition for Avian Activity Monitoring / Stefan Kahl ; Gutachter: Maximilian Eibl, Marc Ritter ; Maximilian Eibl, Holger Klinck." Chemnitz : Universitätsverlag Chemnitz, 2020. http://d-nb.info/1219664502/34.
Full text
16
Nederhof, Mark-Jan. "OCR of hand-written transcriptions of hieroglyphic text." Universitätsbibliothek Leipzig, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-201704.
Full textAbstract:
Encoding hieroglyphic texts is time-consuming. If a text already exists as hand-written transcription, there is an alternative, namely OCR. Off-the-shelf OCR systems seem difficult to adapt to the peculiarities of Ancient Egyptian. Presented is a proof-of-concept tool that was designed to digitize texts of Urkunden IV in the hand-writing of Kurt Sethe. It automatically recognizes signs and produces a normalized encoding, suitable for storage in a database, or for printing on a screen or on paper, requiring little manual correction.
The encoding of hieroglyphic text is RES (Revised Encoding Scheme) rather than (common dialects of) MdC (Manuel de Codage). Earlier papers argued against MdC and in favour of RES for corpus development. Arguments in favour of RES include longevity of the encoding, as its semantics are font-independent. The present study provides evidence that RES is also much preferable to MdC in the context of OCR. With a well-understood parsing technique, relative positioning of scanned signs can be straightforwardly mapped to suitable primitives of the encoding.
17
Santos, Sheila Daniela Medeiros dos. "Filhos da lua : a ausencia de relações sociais de reconhecimento em crianças que vivem em instituições de atendimento a infancia." [s.n.], 2006. http://repositorio.unicamp.br/jspui/handle/REPOSIP/252449.
Full textAbstract:
Orientador: Angel Pino SirgadoTese (doutorado) - Universidade Estadual de Campinas, Faculdade de Educação
Made available in DSpace on 2018-08-07T23:21:30Z (GMT). No. of bitstreams: 1 Santos_SheilaDanielaMedeirosdos_D.pdf: 2523027 bytes, checksum: e99d45425450fc7f9e702122186f27f1 (MD5) Previous issue date: 2006
Resumo: Este trabalho tem como objetivo elucidar a essência de um paradoxo (aparente): crianças que não vivem em família, mas falam continuamente de família, tendo como pontos de ancoragem o referencial teórico de Lefebvre e Vigotski. Após realizar, durante um ano, visitas semanais a uma instituição de atendimento à infância, localizada em um município da região de Campinas, há evidências de que as crianças não estão falando propriamente de família; na realidade, elas estão reclamando da ausência de relações sociais de reconhecimento, já que o Estado/a sociedade ignoram os seus direitos, impondo-lhes como destino a situação em que foram geradas: a pobreza, a realização de tarefas socialmente desvalorizadas e a participação no sistema produtivo como exército de reserva
Abstract: This work has the objective of elucidating the essence of an apparent paradox: children who do not live in family, but talk continuously about family. The work has its anchor points on the theoretical referential of Lefebvre and Vigotski. After carrying out, during one year, weekly visits to an institution of attendance to infancy, located in the Campinas region, there are evidences that the children are not talking exactly about family; in reality, they are complaining about the absence of social relations of recognition, since the State and the society ignore their rights, imposing to them as their destiny the same situation in which they were born: poverty, the accomplishment of tasks socially devaluated and participation in the productive system as reserve army
Doutorado
Educação, Conhecimento, Linguagem e Arte
Doutor em Educação
18
Dufour, Olivier. "Reconnaissance automatique de sons d'oiseaux et d'insectes." Thesis, La Réunion, 2016. http://www.theses.fr/2016LARE0005.
Full textAbstract:
Cette thèse consiste en l'utilisation d'outils d'informatiques pour recueillir des informations concernant l'écologie d'espèces animales. L'objectif de départ était d'assembler des algorithmes capables de traiter des enregistrements acoustiques et de détecter, lister et dénombrer les sons éventuellement présents d'insectes, amphibiens et oiseaux. Pour ce faire nous avons testé de manière non exhaustive différents classifieurs et descripteurs de signal audio9 pour (première partie) organiser et participer à trois concours internationaux de reconnaissance automatique de sons d'animaux et (seconde partie) construire un outil de suivi d'abondance de deux espèces d'oiseaux marins pélagiques sur l'île de la Réunion. La première moitié de la thèse (chapitre 7) a été dédiée à la construction et au test de modèles de reconnaissance multi-classes (92 espèces animales : 82 espèces d'oiseaux (dont 66 passériformes), 9 espèces d'insectes, et 1 espèce d'amphibien, Pelophylax kl. grafi). La seconde moitié de la thèse (chapitre 8) s'est concentrée sur la construction de détecteurs de cris de deux espèces d'oiseaux protégées dont les colonies sont particulièrement difficiles d'accès et menacées par le développement et les éclairages urbains : Le Pétrel de Barau (Pterodroma baraui, endémique de la Réunion et en danger d'extinction depuis 2008 d'après l'UICN) et le Puffin tropical (Puffinus bailloni)The present manuscript deals with computer science applied to ecology. The main objective was to assembly algorithms able to analyse acoustic recordings and automatically detect, list and count sounds of insects, amphibiansand birds. We tested a non exhaustive list of audio features and classifiers to (first part) organize and participate to three international challenges of automatic regnotion of animal's sounds and (second part) build a automatic and passive acoustic monitoring of two species of pelagic seabirds on the Reunion island
19
莊清乾. "Automatic Bird Songs Recognition using Gaussian Mixture Model." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/09774268339453426682.
Full textAbstract:
碩士中華大學
資訊工程學系(所)
96
In this paper, Gaussian mixture models (GMM) were applied to identify bird species from their sounds. First, each syllable corresponding to a piece of vocalization is manually segmented. Two-dimension MFCC (TDMFCC), dynamic two-dimension MFCC (DTDMFCC), and normalized audio spectrum envelope (NASE) modulation coefficients are calculated for each syllable and regarded as the vocalization features of each syllable. Principal component analysis (PCA) is used to reduce the feature space dimension of the original input features vector space. GMM is used to cluster the feature vectors from the same bird species into several groups with each group represented by a Gaussian distribution. The self-splitting Gaussian mixture learning (SGML) algorithm is then employed to find an appropriate number of Gaussian components for each GMM. In addition, a model selection algorithm based on the Bayesian information criterion (BIC) is applied to select the optimal model between GMM and extended VQ (EVQ) according to the amount of training data available. Linear discriminant analysis (LDA) is finally exploited to increase the classification accuracy at a lower dimensional feature vector space. In our experiments, the combination of TDMFCC, DTDMFCC, and NASE modulation coefficients achieve the average classification accuracy of 83.9% for the classification of 28 bird species.
20
Peng, Cheng-Wei, and 彭政偉. "Automatic Recognition of Bird Species from Captured Images." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/z758q6.
Full textAbstract:
碩士國立臺北科技大學
電腦與通訊研究所
102
A majority of people learn to recognize bird species by reading the illustrated Handbooks first and then doing field investigation again and again to become more and more familiar. However, such a learning procedure takes time and energy, which is usually an obstacle for a beginner. To alleviate this obstacle, this study attempts to develop automated methods for recognizing bird species from the captured images. The methods can be applied in mobile smart devices to help beginners learn the bird species efficiently. At first we proposed an algorithm to recognize bird species based on the feature of images’ edge, which uses Principle Component Analysis and Linear Discriminant Analysis to reduce the feature dimensionality and thereby classify the images. Then we proposed an alternative algorithm which captures the images’ features of color and texture and uses k-NN and k-means to classify the images. Experiments conducted using 220 images from 10 different bird species show that the highest recognition accuracy is 70%.
21
Colombick, Illan Samson. "An experimental system for computer aided bird call recognition." Thesis, 2014.
Find full text
22
Huang, Yu-Jen, and 黃佑任. "Using Hilbert Huang Transform Method for Bird Sound Recognition." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/vmydyh.
Full textAbstract:
碩士國立臺灣海洋大學
電機工程學系
107
There are various species of birds and how to recognize them through feature analysis of sounds is the main research objective of this thesis. Hilbert Huang Transform, the most advanced technology in signal’s time-frequency analysis, can be applied to nonlinear and nonstationary signals, such as sound signal. Therefore, the Hilbert Huang Transform is adopted to explore an effective way for automatic identification of bird’s sounds. In the Hilbert-Huang transform, the empirical mode decomposition is replaced by the ensemble empirical mode decomposition (EEMD) in order to overcome the mode mixing problem. The intrinsic mode functions (IMFs) produced from EEMD decomposition represent signals ranging from high frequency to low frequency. Through the Hilbert spectral analysis, the Hilbert amplitude spectra obtained from all IMFs as well as the first three IMFs are quite similar. Thus in order to achieve fast identification purpose, only the first three IMFs are retained for subsequent data comparison. Next, the three features of root-mean-square (RMS), peak value, and peak factor are extracted from the autocorrelation sequences of these three IMFs, and then used to calculate the Pearson product-moment correlation coefficient (PPMCC) for the basis of recognition. Experimental results show that successful recognition can be achieved from the database that contains sound recordings originated from eight different species of birds。
23
Ni, Hui-Wen, and 倪慧雯. "Automatic Bird-species Recognition System Based on Syllable-Type HMM." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/79341307782793399239.
Full textAbstract:
碩士中華大學
資訊工程學系(所)
94
This thesis is related to the development of automatic recognition-system, which is to recognize the bird-species with their sound. The “Basic frequency-sequences” are extracted from birdcall or birdsong, and are used for the training sequences, in order to build syllable-type hidden Markov models (HMMs). In the training phase, three successive stages, respectively named as 1) basic frequency sequence extracting, 2) syllable segmentation and 3) syllable clustering; are proceeded before HMM training. Before those 3 above, FFT is used to compute a sepctrogram form the bird sound recording. The frequency bins, with maximum magnitude in spectrum, constitute the “Basic frequency-sequences”. Isolated syllables are segmented from continuous recording, and then clustered by fuzzy c-mean. One cluster presents one syllable-type and could be characterized as an HMM. Before estimating parameters of an HMM, a specific “observation symbol” is added in the beginning of all syllables. Then “Basic frequency-sequences”, which are belonged to the cluster of syllables, are arranged to form one another bigger one, which is the feature of syllable-type. In testing phase, the same procedure is preceded to get a set of sequences that represents the feature of syllable-type, the observation sequences for HMM evaluation. The test sample will be considered to the specific bird, if the specific bird gets the highest similarity or probability among all the bird species as a whole based on syllable-type HMM.
24
林士棻. "Bird songs recognition using two-dimensional Mel-scale frequency cepstral coefficients." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/38302762655714685237.
Full textAbstract:
碩士中華大學
資訊工程學系(所)
94
We propose a method to automatically identify birds from their sounds in this paper. First, each syllable corresponding to a piece of vocalization is segmented. The average LPCC (ALPCC), average MFCC (AMFCC), Static MFCC (SMFCC), Two-dimensional MFCC (TDMFCC), Dynamic two-dimensional MFCC (DTDMFCC) and TDMFCC+DTDMFCC over all frames in a syllable are calculated as the vocalization features. Linear discriminant analysis (LDA) is exploited to increase the classification accuracy at a lower dimensional feature vector space. A clustering algorithm, called progressive constructive clustering (PCC) algorithm, is used to divide the feature vectors which were computed from the same bird species into several subclasses. In our experiments, TDMFCC+DTDMFCC can achieve average classification accuracy 90% and 89% for 420 bird species and 561 bird species.
25
Lin, Shih-Fen, and 林士棻. "Bird songs recognition using two-dimensional Mel-scale frequency cepstral coefficients." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/94553686394732089037.
Full text
26
Chang, Yung-Fu, and 張勇富. "The Study On Corpus-based Analysis For Bird Sound Recognition System." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/86274419275035157145.
Full textAbstract:
碩士國立東華大學
電機工程學系
91
The purpose of this paper is to develop a bird sound recognition system based on corpus analysis. Corpus analysis usually applied in computational linguistics. We observed that each kind of bird’s sound has a special frequency sequence. The feature segmentations of bird sound are found by utilizing the voiceprint analysis, and the frequency sequence, called corpus of bird sound, is obtained. We have been created a corpus database that collected over 90 kinds of corpus of birds in Taiwan, to provide the knowledge base for bird sound recognizing engine in this paper. Three successive processing stages, named as bird sound preprocessing, corpus analysis, and target bird sound searching, are employed in the bird sound recognition system. In the first instance the sound of under recognizing bird (URB) is preprocessed in the sound preprocessing stage by a fifth-order butter worth filter to eliminate from environment noise. The corpus analysis stage performs automated feature segmentations of bird sound, and partitioned into frequency sequence. The target bird sound is searching through corpus database by a recognizing engine. The result of this system is the rank of position in a candidate target birds list. The advantages of adopting the corpus database by using frequency sequence are reducing the amount of database capacity, more fast for recognition and high correction ratio. Now, we begin to transplant this system to personal digital assistant (PDA) and smart phone etc. In the future, it can also extend to human natural language recognition. Keyword: corpus analysis, corpus database, Fourier transform, voiceprint, bird sound recognition.
27
柯惠裕. "MFCCs based feature extraction for the design of bird species recognition system." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/97439792007864349250.
Full textAbstract:
碩士中華大學
資訊工程學系(所)
96
In this thesis, an automatic birdsong recognition system based on MFCCs was developed. In this system, the basic unit for identification is the birdsong syllable. The training stage is composed of four main modules: syllable segmentation, feature extraction, syllable clustering, and linear discriminant analysis. First, isolated syllables are segmented from continuous recording data. In the frequency domain, three features including mean, QI, QE, are extracted from MFCCs representing the features of syllables. After clustering by fuzzy c-mean algorithm, the linear discriminant analysis (LDA) is applied to extract the principle features and reduce the dimensions of feature vector. In the recognition stage, after the procedures of syllable segmentation and feature extraction as the one in the training stage, the LDA is also applied to reduce the feature dimensions. The species identification is accomplished by finding the template species that has feature vector closest to the test one. In the experiments, part or all of the three features were applied to check the recognition rates. The experimental results shows that combination of all the three features achieved the highest average recognition rates of about 83.3%.
28
Liao, Wei-En, and 廖偉恩. "A Study of Bird Sound Recognition Based on Timbre and Pitch Features." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/ds587t.
Full textAbstract:
碩士國立臺北科技大學
電腦與通訊研究所
99
Wild bird watching has become a popular leisure activities in recent years. However, very often the public can only see birds or hear their sounds, but no idea about what kind of bird species they see. To help the public learn the bird species from their sounds, we propose an automatic system for recognizing birdsongs. Two acoustic features are used for analysis, timbre and pitch. In the timbre-based, Mel-scale cepstrum coefficients are used to characterizes the bird sound. Then, we use Gaussian Mixture Models represent the MFCCs as a set of parameters, so that it is easier to compare one bird species from another. In the pitch-based analysis, we convert bird sounds from their waveform representations into a sequence of MIDI note. Then, Bigram models are used to capture the dynamic change information of the notes. We chose the top ten common bird species in the Taipei urban area. The audio data were collected from commercial CDs and the bird sound-related websites. We divided the data into non-overlaping two subsets, on for training and the other for testing. The results showed that the timbre-based, pitch-based, and the combination thereof system achieved 71.1%, 72.1%, and 75.04% accuracy of bird sound recognition, respectively. Further, if the bird sounds were pre-classified into calls and songs, the timbre-based, pitch-based, and the combination thereof systems achieved 95.02%, 91.06% and 95.76% accuracy of bird sound recognition, respectively.
29
Chiu-YuehChen and 陳秋月. "Interaction between Face and Expert Object Recognition: a Study on Bird Expertise." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/me2wyy.
Full textAbstract:
碩士國立成功大學
心理學系認知科學碩士班
101
Face recognition is the hallmark of human ultimate performance： efficient, parallel, highly accurate, and with seemingly unlimited capacity. To explain this, some have suggested that, through the evolution that endows into our genes (shown in newborn infants), faces enjoy privileged processing mechanisms and resources. On the other hand, proponents of the perceptual expertise hypothesis emphasize the importance of experience：by showing not only some acclaimed face-only effects in domain experts, but also interactions between faces and objects of expertise under tasks (i.e., 2-back face-car interference task). To broaden such interaction beyond car experts and also to explore other aspects of this interaction, the current study recruited 19 bird experts and 19 age-matched novices to do (a) face configuration task of various difficulty; (b) two (visual and auditory) bird expertise measurements, (c) composite face and bird task, and (d) the 2-back face-bird interference task. The results showed that (a) though there was no systematic differences between bird experts’ and novices’ performance, birders as a group correlated in the harder distance discrimination (e.g., between eyes or between nose and lip) tasks, suggesting that birding experience seems to increase their discriminability in face gestalts; (b) bird expertise can, depending on their birding locales, be divided into two related, but separate, visual (shorebirds) and auditory (passerines) expertise; (c) there is no bird or face congruency effects in the standard composite task, consistent with some early study’s results. This may reflect the ceiling effect, or that subjects can flexibly change their attended halves (upper or lower); (d) in accordance and extending the previous 2-back alternative task’s results, we also found that the higher the bird expertise, the larger the face interference in our 2-back face-bird task. Furthermore, the higher the face composite effect (meaning the flexible looking of face parts) in study c, the lower the bird interference in the 2-back task on birders. Lastly, both negative (competing common resources) and positive (higher correlation of internal feature sensitivity, and lower bird interference with higher face composite effect) aspects of the face-bird interactions coexist independently, deepening the claim that faces and expert object categories share highly overlapping processing resources.
30
Ross, Derek J. "Bird call recognition with artificial neural networks, support vector machines, and kernel density estimation." 2006. http://hdl.handle.net/1993/20399.
Full text
31
Huang, Hsiang-En, and 黃祥恩. "The Study on Hidden Markov Models Incorporated with Fuzzy Cluster for Feature Extraction Applied to Bird Sound Recognition System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/28299314742256851785.
Full textAbstract:
碩士國立東華大學
電機工程學系
93
Fuzzy cluster analysis (FCA) is an general data analysis method of feature extraction. The target of FCA is to sort cases (people, things, events, etc.) into several clusters (groups) and further to find out the cluster center. A cluster center of cluster is describing the data characteristic. In general, it is a useful method for static data, but it is not good enough to deal with the relationship of clusters which with dynamic data. This research proposed a new FCA method to deal with feature extraction, and further, involved probability concept from the Hidden Markov Models. The proposed method would describe the relationship of clusters when data are sequentially order. Thus, our FCA method provided not only cluster date but also involved time sequence information for feature extraction. This research took each cluster as a state, and utilize the FCA to calculate the fuzzy partition matrix. And then calculate the state-transition probability and initial state probability distribution by fuzzy partition matrix. Finally, we can record the cluster’s relationship between the two continually data with time sequence information for feature extraction Our proposed method has been applied to the bird song recognition system to extract bird song’s feature and build the database. The advantages of adopting our method for bird recognition system are: reducing the database storage capacity, well recognition speed, and better recognition rate.
32
NÁCAROVÁ, Jana. "Research on cognitive abilities in untrained birds." Doctoral thesis, 2017. http://www.nusl.cz/ntk/nusl-371666.
Full textAbstract:
This study investigates the cues used for predator recognition by wild-living untrained birds great tits (Parus major). The experimental approach is used to test the reaction to the variously modified dummies of sparrowhawk (Accipiter nisus) and pigeon (Columba livia f. domestica) under laboratory conditions. The role of key features (yellow eye, hooked beak and talons), colour and size is tested. The results imply that the presence of raptor-specific features is mostly necessary but not sufficient to recognize predator in the presented dummies. Following research revealed that the part of the variability in response of great tits can be taken on the account of personality.
33
Tai, Kuei-Hsiung, and 戴貴雄. "The Separation and Recognition of Multiple Sound of Birds." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/09025771795175674002.
Full textAbstract:
碩士清雲科技大學
電機工程系所
97
This thesis proposes that the Fast Independent Component Analysis (FastICA) and Dynamic Time Warping (DTW) are applied for bird recognition in an environment with mixture of multiple birds and noise. Three phases are emphasized in this thesis, which are training, separation and recognition. In this first training phase, the sound of birds from the bird sound illustration CD, in which 40 kinds of wild live birds are seen in Taiwan frequently, are collected. As often used as the most of speech recognition processes, the Mel-scale Frequency Cepstral Coefficients (MFCC) is an effective sound features which is used in this thesis as well. In the second phase, the FastICA algorithm is applied to separate specific bird sound from a mixture of birds and ambient noise. In the last phase, the End-Point Detection (EPD) can chop down the silent or unvoiced sound. Therefore, the MFCC of the being recognized bird sound can be compared with the MFCC of original bird sound in the database. In summary of this thesis, the simulation of FastICA and DTW showsthat the FastICA algorithm is worked effectively to separate a mixture of birds and noises.