Dissertationen zum Thema „Camera recognition“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Dissertationen für die Forschung zum Thema "Camera recognition" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Johansson, Fredrik. „Recognition of Targets in Camera Networks“. Thesis, Linköpings universitet, Institutionen för teknik och naturvetenskap, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-95351.
Der volle Inhalt der QuelleTadesse, Girmaw Abebe. „Human activity recognition using a wearable camera“. Doctoral thesis, Universitat Politècnica de Catalunya, 2018. http://hdl.handle.net/10803/668914.
Der volle Inhalt der QuelleLos avances en tecnologías wearables facilitan la comprensión de actividades humanas utilizando cuando se usan videos grabados en primera persona para una amplia gama de aplicaciones. En esta tesis, proponemos características robustas de movimiento para el reconocimiento de actividades humana a partir de videos en primera persona. Las características propuestas codifican características discriminativas estimadas a partir de optical flow como magnitud, dirección y dinámica de movimiento. Además, diseñamos nuevas características de inercia virtual a partir de video, sin usar sensores inerciales, utilizando el movimiento del centroide de intensidad a través de los fotogramas. Los resultados obtenidos en múltiples bases de datos demuestran que las características inerciales basadas en centroides mejoran el rendimiento de reconocimiento en comparación con grid-based características. Además, proponemos un algoritmo multicapa que codifica las relaciones jerárquicas y temporales entre actividades. La primera capa opera en grupos de características que codifican eficazmente las dinámicas del movimiento y las variaciones temporales de características de apariencia entre múltiples fotogramas utilizando una jerarquía. La segunda capa aprovecha el contexto temporal ponderando las salidas de la jerarquía durante el modelado. Además, diseñamos una técnica de postprocesado para filtrar las decisiones utilizando estimaciones pasadas y la confianza de la estimación actual. Validamos el algoritmo propuesto utilizando varios clasificadores. El modelado temporal muestra una mejora del rendimiento en el reconocimiento de actividades. También investigamos el uso de redes profundas (deep networks) para simplificar el diseño manual de características a partir de videos en primera persona. Proponemos apilar espectrogramas para representar movimientos globales a corto plazo. Estos espectrogramas contienen una representación espaciotemporal de múltiples componentes de movimiento. Esto nos permite aplicar convoluciones bidimensionales para aprender funciones de movimiento. Empleamos long short-term memory recurrent networks para codificar la dependencia temporal a largo plazo entre las actividades. Además, aplicamos transferencia de conocimiento entre diferentes dominios (cross-domain knowledge) entre enfoques inerciales y basados en la visión para el reconocimiento de la actividad en primera persona. Proponemos una combinación ponderada de información de diferentes modalidades de movimiento y/o secuencias. Los resultados muestran que el algoritmo propuesto obtiene resultados competitivos en comparación con existentes algoritmos basados en deep learning, a la vez que se reduce la complejidad.
Erhard, Matthew John. „Visual intent recognition in a multiple camera environment /“. Online version of thesis, 2006. http://hdl.handle.net/1850/3365.
Der volle Inhalt der QuelleSoh, Ling Min. „Recognition using tagged objects“. Thesis, University of Surrey, 2000. http://epubs.surrey.ac.uk/844110/.
Der volle Inhalt der QuelleMudduluru, Sravani. „Indian Sign Language Numbers Recognition using Intel RealSense Camera“. DigitalCommons@CalPoly, 2017. https://digitalcommons.calpoly.edu/theses/1815.
Der volle Inhalt der QuelleBellando, John Louis. „Modeling and Recognition of Gestures Using a Single Camera“. University of Cincinnati / OhioLINK, 2000. http://rave.ohiolink.edu/etdc/view?acc_num=ucin973088031.
Der volle Inhalt der QuelleBrauer, Henrik Siebo Peter. „Camera based human localization and recognition in smart environments“. Thesis, University of the West of Scotland, 2014. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.739946.
Der volle Inhalt der QuelleHannuksela, J. (Jari). „Camera based motion estimation and recognition for human-computer interaction“. Doctoral thesis, University of Oulu, 2008. http://urn.fi/urn:isbn:9789514289781.
Der volle Inhalt der QuelleAkman, Oytun. „Multi-camera Video Surveillance: Detection, Occlusion Handling, Tracking And Event Recognition“. Master's thesis, METU, 2007. http://etd.lib.metu.edu.tr/upload/12608620/index.pdf.
Der volle Inhalt der QuelleKurihata, Hiroyuki, Tomokazu Takahashi, Ichiro Ide, Yoshito Mekada, Hiroshi Murase, Yukimasa Tamatsu und Takayuki Miyahara. „Rainy weather recognition from in-vehicle camera images for driver assistance“. IEEE, 2005. http://hdl.handle.net/2237/6798.
Der volle Inhalt der QuelleTurk, Matthew Robert. „A homography-based multiple-camera person-tracking algorithm /“. Online version of thesis, 2008. http://hdl.handle.net/1850/7853.
Der volle Inhalt der QuelleChen, Quanxin. „Camera calibration and shape recovery from videos of two mirrors“. HKBU Institutional Repository, 2015. https://repository.hkbu.edu.hk/etd_oa/168.
Der volle Inhalt der QuelleLiang, Jian. „Processing camera-captured document images geometric rectification, mosaicing, and layout structure recognition /“. College Park, Md. : University of Maryland, 2006. http://hdl.handle.net/1903/3659.
Der volle Inhalt der QuelleThesis research directed by: Electrical Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
Anwar, Qaiser. „Optical Navigation by recognition of reference labels using 3D calibration of camera“. Thesis, Mittuniversitetet, Institutionen för informationsteknologi och medier, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-18453.
Der volle Inhalt der QuelleKotwal, Thomas (Thomas Prabhakar Pramod) 1978. „The untrusted computer problem and camera based authentication using optical character recognition“. Thesis, Massachusetts Institute of Technology, 2002. http://hdl.handle.net/1721.1/87272.
Der volle Inhalt der QuelleQin, Yinghao. „The Smart Phone as a Mouse“. The University of Waikato, 2006. http://hdl.handle.net/10289/2289.
Der volle Inhalt der QuelleMohammed, Abdulmalik. „Obstacle detection and emergency exit sign recognition for autonomous navigation using camera phone“. Thesis, University of Manchester, 2017. https://www.research.manchester.ac.uk/portal/en/theses/obstacle-detection-and-emergency-exit-sign-recognition-for-autonomous-navigation-using-camera-phone(e0224d89-e743-47a4-8c68-52f718457098).html.
Der volle Inhalt der QuelleSmith, Benjamin Andrew. „Determination of Normal or Abnormal Gait Using a Two-Dimensional Video Camera“. Thesis, Virginia Tech, 2007. http://hdl.handle.net/10919/31795.
Der volle Inhalt der QuelleMaster of Science
Williams, William. „A novel multispectral and 2.5D/3D image fusion camera system for enhanced face recognition“. Thesis, Birkbeck (University of London), 2017. http://bbktheses.da.ulcc.ac.uk/272/.
Der volle Inhalt der QuellePakalapati, Himani Raj. „Programming of Microcontroller and/or FPGA for Wafer-Level Applications - Display Control, Simple Stereo Processing, Simple Image Recognition“. Thesis, Linköpings universitet, Elektroniksystem, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-89795.
Der volle Inhalt der QuelleOzkilic, Sibel. „Performance Improvement Of A 3-d Configuration Reconstruction Algorithm For An Object Using A Single Camera Image“. Master's thesis, METU, 2004. http://etd.lib.metu.edu.tr/upload/1095793/index.pdf.
Der volle Inhalt der QuelleMURASE, Hiroshi, Yoshito MEKADA, Ichiro IDE, Tomokazu TAKAHASHI und Hiroyuki ISHIDA. „Generation of Training Data by Degradation Models for Traffic Sign Symbol Recognition“. Institute of Electronics, Information and Communication Engineers, 2007. http://hdl.handle.net/2237/14958.
Der volle Inhalt der QuelleTang, Zongzhi. „A Novel Road Marking Detection and Recognition Technique Using a Camera-based Advanced Driver Assistance System“. Thesis, Université d'Ottawa / University of Ottawa, 2017. http://hdl.handle.net/10393/35729.
Der volle Inhalt der QuelleAdeeb, Karam, und Adam Alveteg. „SIYA - Slide Into Your Albums : Design and construction of a controllable dolly camera with object recognition“. Thesis, KTH, Skolan för industriell teknik och management (ITM), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-264450.
Der volle Inhalt der QuelleSyftet med detta projekt är att konstruera och bygga en automatiserad kamerarigg med objektigenkänning. Projektet undersöker om det finns några fördelar med en automatiserad kamerarigg gentemot en manuell, hur en extern kameramodul implementeras för att kamerariggen ska kunna följa ett objekt och under vilka förhållanden kameramodulen registrerar objekten bäst. Kamerariggen är byggd för att åka längsmed en räls som består av två järnrör. En filmkamera är monterad på en vagn som rullar ovanpå denna räls och drivs med hjälp av en DC-motor. Ovanpå vagnen ska en extern kameramodul vid namn Pixy2 upptäcka ett förbestämt objekt som användaren vill att filmkameran ska fokusera på. Med hjälp av återkoppling av datan som Pixy2 registrerar styrs två stycken stegmotorer som antingen roterar filmkameran horisontellt i x-led eller vertikalt i y-led tills objektet är placerat i mitten av Pixy2’s synfält. På detta sätt kommer konstruktionen att fokusera på objektet samtidigt som den rör sig i sidled på rälsen.
ULRICH, LUCA. „RGB-D methodologies for Face Expression Recognition“. Doctoral thesis, Politecnico di Torino, 2021. http://hdl.handle.net/11583/2872356.
Der volle Inhalt der QuelleSarella, Kanthi. „An image processing technique for the improvement of Sign2 using a dual camera approach /“. Online version of thesis, 2008. http://hdl.handle.net/1850/5721.
Der volle Inhalt der QuelleColberg, Kathryn. „Investigating the ability of automated license plate recognition camera systems to measure travel times in work zones“. Thesis, Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/49048.
Der volle Inhalt der QuelleMinetto, Rodrigo 1983. „Detecção robusta de movimento de camera em videos por analise de fluxo otico ponderado“. [s.n.], 2007. http://repositorio.unicamp.br/jspui/handle/REPOSIP/276203.
Der volle Inhalt der QuelleDissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação
Made available in DSpace on 2018-08-09T20:36:43Z (GMT). No. of bitstreams: 1 Minetto_Rodrigo_M.pdf: 4634555 bytes, checksum: 6335c719fb04357e47f9dd14b51fbaa9 (MD5) Previous issue date: 2007
Resumo: Nosso objetivo nesta dissertação é a detecção robusta de movimento de câmera (tilt, pan, roll e zoom) em vídeos. Para tanto, desenvolvemos um algoritmo original para esta tarefa, baseado em um ajuste ponderado de mínimos quadrados de um fluxo ótico, onde um procedimento iterativo é utilizado para melhorar o peso de cada vetor. Além da detecção de movimento de câmera, nosso algoritmo fornece uma análise quantitativa precisa e confiável dos movimentos. Este também fornece uma segmentação grosseira de cada quadro em duas regiões, "objeto" e "fundo", correspondentes às partes estacionárias e com movimento na cena, respectivamente. Experimentos com vídeos reais mostram que o algoritmo é rápido e eficaz, mesmo para cenas com movimento substancial de objetos
Abstract: Our goal in this dissertation is the reliable detection of camera motion (tilt, pan, roll and zoom) in videos. We propose an original algorithm for this task based on weighted leastsquare fitting of the optical flow, where an iterative procedure is used to improve the weight of each flow vector. Besides detecting camera motion, our algorithm provides a precise and reliable quantitative analysis of the movements. It also provides a rough segmentation of each frame into two regions, "foreground" and "background", corresponding to the moving and stationary parts of the scene, respectively. Tests with real videos show that the algorithm is fast and effective, even for scenes with substantial object motion
Mestrado
Processamento de Imagens
Mestre em Ciência da Computação
Zagnoli, Andrea. „Human Activity Recognition con telecamere di profondità“. Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/12946/.
Der volle Inhalt der QuelleCarraro, Marco. „Real-time RGB-Depth preception of humans for robots and camera networks“. Doctoral thesis, Università degli studi di Padova, 2018. http://hdl.handle.net/11577/3426800.
Der volle Inhalt der QuelleQuesta tesi tratta di percezione per robot autonomi e per reti di telecamere da dati RGB-Depth. L'obiettivo è quello di fornire algoritmi robusti ed efficienti per l'interazione con le persone. Per questa ragione, una particolare attenzione è stata dedicata allo sviluppo di soluzioni efficienti che possano essere eseguite in tempo reale su computer e schede grafiche consumer. Il contributo principale di questo lavoro riguarda la stima automatica della posa 3D del corpo delle persone presenti in una scena. Vengono proposti due algoritmi che sfruttano lo stream di dati RGB-Depth da una rete di telecamere andando a migliorare lo stato dell'arte sia considerando dati da singola telecamera che usando tutte le telecamere disponibili. Il secondo algoritmo ottiene risultati migliori in quanto riesce a stimare la posa di tutte le persone nella scena con overhead trascurabile e non richiede sincronizzazione tra i vari nodi della rete. Tuttavia, il primo metodo utilizza solamente nuvole di punti che sono disponibili anche in ambiente con poca luce nei quali il secondo algoritmo non raggiungerebbe gli stessi risultati. Il secondo contributo riguarda la re-identificazione di persone a lungo termine in reti di telecamere. Questo problema è particolarmente difficile in quanto non si può contare su feature di colore o che considerino i vestiti di ogni persona, in quanto si vuole che il riconoscimento funzioni anche a distanza di giorni. Viene proposto un framework che sfrutta il riconoscimento facciale utilizzando una Convolutional Neural Network e un sistema di classificazione Bayesiano. In questo modo, ogni qual volta viene generata una nuova traccia dal sistema di people tracking, la faccia della persona viene analizzata e, in caso di match, il vecchio ID viene riassegnato. Il terzo contributo riguarda l'Ambient Assisted Living. Abbiamo proposto e implementato un robot di assistenza che ha il compito di sorvegliare periodicamente un ambiente conosciuto, riportando eventi non usuali come la presenza di persone a terra. A questo fine, abbiamo sviluppato un approccio veloce e robusto che funziona anche in assenza di luce ed è stato validato usando un nuovo dataset RGB-Depth registrato a bordo robot. Con l'obiettivo di avanzare la ricerca in questi campi e per fornire il maggior beneficio possibile alle community di robotica e computer vision, come contributo aggiuntivo di questo lavoro, abbiamo rilasciato, con licenze open-source, la maggior parte delle implementazioni software degli algoritmi descritti in questo lavoro.
Wang, Chong, und 王翀. „Joint color-depth restoration with kinect depth camera and its applications to image-based rendering and hand gesture recognition“. Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2014. http://hdl.handle.net/10722/206343.
Der volle Inhalt der QuelleRönnqvist, Patrik. „Surveillance Applications : Image Recognition on the Internet of Things“. Thesis, Mittuniversitetet, Institutionen för informationsteknologi och medier, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-18557.
Der volle Inhalt der QuelleMediaSense
Graumann, Jean-Marc. „Intelligent optical methods in image analysis for human detection“. Thesis, Brunel University, 2005. http://bura.brunel.ac.uk/handle/2438/7892.
Der volle Inhalt der QuelleBubeník, Martin. „RaspberryPI kamerový checker“. Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2019. http://www.nusl.cz/ntk/nusl-402129.
Der volle Inhalt der QuelleBodén, Rikard, und Jonathan Pernow. „SORTED : Serial manipulator with Object Recognition Trough Edge Detection“. Thesis, KTH, Skolan för industriell teknik och management (ITM), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-264513.
Der volle Inhalt der QuelleIdag ökar efterfrågan på smarta robotar som kan ta egna beslut och samarbeta med människor i föränderliga miljöer. Tillämpningsområdena för robotar med kamerasensorer kommer sannolikt att öka i en framtid av artificiell intelligens med algoritmer som blir mer intelligenta och anpassningsbara än tidigare. Syftet med detta kandidatexamensarbete är att utveckla en robotarm som, med hjälp av en kamerasensor, kan ta upp och sortera godtyckliga objekt när de uppträder på oförutsägbara positioner. Robotarmen har tre frihetsgrader och hela konstruktionen är 3D-printad och modulariserad för att vara underhållsvänlig, men också anpassningsbar för nya tillämpningsområden. Kamerasensorn ¨ar integrerad i ett externt kamerastativ med sitt synfält över robotarmens arbetsyta. Kamerasensorn detekterar objekt med hjälp av en färgfiltreringsalgoritm och returnerar sedan storlek, position och signatur för objekten med hjälp av en kantdetekteringsalgoritm. Objektens storlek används för att kalibrera kameran och kompensera för den radiella förvrängningen hos linsen. Objektens relativa position används sedan till invers kinematik för att räkna ut hur mycket varje stegmotor ska rotera för att erhålla den önskade vinkeln på varje axel som gör att gripdonet kan nå det detekterade objektet. Robotarmen har även tre olika potentiometrar integrerade i varje axel för att reglera rotationen av varje stegmotor. Resultaten i denna rapport visar att robotarmen kan detektera och plocka upp till 90% av objekten när kamerakalibrering används i algoritmen. Slutsatsen från rapporten är att förvrängningen från kameralinsen har störst påverkan på robotarmens precision och därmed resultatet. Det går även att konstatera att metoden som används för att korrigera kameraförvrängningen påverkas av geometrin samt orienteringen av objekten som ska detekteras, men framför allt variationer i belysning och skuggor över arbetsytan. En annan slutsats är att belysningen över arbetsytan är helt avgörande för om kamerasensorn ska kunna särskilja objekt med olika färgmättad och nyans.
Dadej, Vincent. „Raspberry Pi: programování v prostředí Matlab/Simulink“. Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2018. http://www.nusl.cz/ntk/nusl-320104.
Der volle Inhalt der QuelleKannala, J. (Juho). „Models and methods for geometric computer vision“. Doctoral thesis, University of Oulu, 2010. http://urn.fi/urn:isbn:9789514261510.
Der volle Inhalt der QuelleKrutílek, Jan. „Systémy průmyslového vidění s roboty Kuka a jeho aplikace na rozpoznávání volně ložených prvků“. Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2010. http://www.nusl.cz/ntk/nusl-229174.
Der volle Inhalt der QuelleTaha, Abu Snaineh Sami. „AUTOMATIC PERFORMANCE LEVEL ASSESSMENT IN MINIMALLY INVASIVE SURGERY USING COORDINATED SENSORS AND COMPOSITE METRICS“. UKnowledge, 2013. http://uknowledge.uky.edu/cs_etds/12.
Der volle Inhalt der QuelleDarmadi, Steve. „Strobed IR Illumination for Image Quality Improvement in Surveillance Cameras“. Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235632.
Der volle Inhalt der QuelleInfraröd (IR) belysning påträffas ofta i övervakningskameror för att förbättra bildkvalitén vid videoinspelning på natten. Den begränsade tillgängliga effekten från Power over Ethernet-anslutningen (PoE) i nätverksaktiverade kameror sätter dock en övre gräns för hur mycket effekt som kameran tillåts använda till belysningssystemet, och därmed hur pass mycket bildkvalitén kan ökas.I detta examensarbete undersöktes ett alternativt sätt att förbättra bildkvalitén genom att använda blixtrande (eng: ”strobed”) IR-belysning. Olika strobe-metoder undersöktes i relation till rullande slutare, vilket är den slutar-metod som vanligtvis används i CMOS-sensorer. Den metod som gav mest fördelaktiga resultat vid utvärdering implementerades i en prototyp baserad på en kommersiell nätverkskamera av Fixed box-typ från Axis Communications. Denna prototyp visade framgångsrikt ett koncept för hur synkronisering av bildsensorn och belysningssystemet kan uppnås.Registreringsskyltigenkänning (LPR) på en mörk motorväg valdes som utvärderingsscenario och en analys av bilens rörelser gjordes för att skapa en motsvarande testuppställning inomhus. Inomhustesterna gav en kontrollerad miljö medan testerna utomhus utsatte prototypen för verkliga förhållanden. Testresultaten visar att med strobed IR blev bilden från kameran både ljusare och uppvisade mindre artefakter till följd av rullande slutare, jämfört med konstant IR-belysning. Teoretiska beräkningar visade också att dessa förbättringar inte påverkar varken kamerans genomsnittliga effektförbrukning eller ögonsäkerheten för belysningssystemet negativt.
Yang, Shih-Chuan, und 楊世詮. „Human Action Recognition Using Kinect Camera“. Thesis, 2013. http://ndltd.ncl.edu.tw/handle/76928392913615657701.
Der volle Inhalt der Quelle義守大學
資訊工程學系
101
An action is composed of a sequence of postures with a high degree of complexity in time and space, and thus it has become one of important issues to effectively recognize high-level semantic about human action. Along with rapid development of human-machine interface technology, the body sensing device has been gradually changed into video camera to capture the human action. In particular, Microsoft released Kinect sensor with infrared camera in 2010, which is gradually widely used in digital teaching, medical applications, animation and other applications. In the past decade, some researchers devoted themselves to relevant issues on action recognition, but most of them used video camera to capture human action. Since video data are lack of depth values in scene, the subject cannot be stably separated from background image. This study is focused on human action recognition based on Kinect camera. The first is to define user-defined actions in which each action needs recording one or more repetitive actions to extract common action features, and to build an action database. When a sequence of images with unknown high-level semantics is captured in real time, feature extraction is used to generate a series of feature symbols which is belonged to the action database. Then, the string matching algorithm is applied to match action database, and finally high-level action semantics are recognized based on the matching similarity.
Lu, Chen-Che, und 盧清治. „Application Of Web Camera In Dices Recognition“. Thesis, 2006. http://ndltd.ncl.edu.tw/handle/08847007594270303858.
Der volle Inhalt der Quelle南台科技大學
資訊工程系
94
Nowadays, the Web camera has been broadly used and applied to many fields in industry. The purpose of this research is to study real-time pattern recognition using the Web camera, which is a promising solution to some fields in modern computer industry such as keyboard recognition. In this paper, an effective real-time pattern recognition system using the Web camera is proposed and evaluated against real objects - dices. First, the system converted the original image from RGB to HSV color space, followed by polarizing the image. The observed image further went through an iterative morphological process to eliminate noisy data. Following the mathematical morphological approach, Region Filling is to fill up the depressions or holes on the ground of the number of the dices. And erosion gets rid of noisy data such as shadows. Meanwhile, a pixel shrinking technique was employed to speed up the image processing. Finally, the system applied a clustering technique to pixels in order to classify the numbers of dices. There are 500 test patterns that are used in the experiment. The results show that the recognition rate is up to 90% in the application of dices recognition. Based on the experimental results, it is practical to apply the Web Camera to other recognition applications.
Hu, Jhen-Da, und 胡振達. „Hybrid Hand Gesture Recognition Based on Depth Camera“. Thesis, 2014. http://ndltd.ncl.edu.tw/handle/7febjn.
Der volle Inhalt der Quelle國立交通大學
多媒體工程研究所
103
Hand gesture recognition (HRG) becomes one of most popular topics in recent years because that hand gesture is one of the most natural and intuitive way of communication between Human and machines. It is widely used in HCI (Human-Computer-interaction). In this paper, we proposed a method for hand gesture recognition based on depth camera. Firstly, the hand information within depth image is separated from background based on a specific range of depth. And the contour of hand is detected after segmentation. After that, we estimate centroid of hand, and palm size is calculated by using linear regression. Then, fingers’ states of gesture are estimated depending on information of hand contour. And fingertips are estimated by means of smooth hand contours which reduce number of contours by Douglas-Peucker Algorithm. Finally, we propose a gesture type estimation algorithm to determine which gesture is. The extensive experiments demonstrate that the accuracy rate of our method is from 84.35% to 99.55%, and the mean accuracy is 94.29%.
Huang, Tzu-Ta, und 黃自達. „Camera based Preprocessing System for Chinese Document Image Recognition“. Thesis, 2007. http://ndltd.ncl.edu.tw/handle/86838882293892444033.
Der volle Inhalt der Quelle國立中央大學
資訊工程研究所
95
As we know, Chinese documents convey a lot of meaningful and useful information. Due to the popularization of digital cameras, it is convenient to take picture and retrieve important text information from the digitalized Chinese document images. A successful camera-based Chinese document processing system should overcome the problems resulted from various document formats, font sizes, and document skewing to extract correct text block without generating erroneous results. The major difference between Chinese documents and English documents is that Chinese characters are mainly composed of multiple connected components. The most important step in obtaining the message of the existence of Chinese documents is to merge connected components with correct combining and produce complete Chinese character blocks. In this thesis, we propose a method to link Chinese characters into text line and develop a rule to discriminate the merging condition of ordering connected components to hypothesize the existence of skewing documents. Two mechanisms are developed in the thesis. The first mechanism is the detection of inversed text blocks which may be filtered out as oversize noise blocks in the preprocessing. The second mechanism is the detection of document images laid in incorrect direction because sometimes people will rotate camera 90o or 270o to capture document images. A two pass statistical method is proposed to automatically determine the rotating degree of documents images(0o、90o、180o、270o). The first step is devised by using the phenomenon that horizontal strokes appear more frequently than vertical strokes in Chinese characters. The second step is devised by analyzing the vertical projection histogram of each text block and defining keywords that assist in deciding the rotating degree.
Chiang, Cheng-Ming, und 姜政銘. „Single-camera Hand Gesture Recognition for Human-Computer Interface“. Thesis, 2013. http://ndltd.ncl.edu.tw/handle/14566311560453722557.
Der volle Inhalt der Quelle國立交通大學
電子工程學系 電子研究所
102
In this thesis, we propose a novel hand gesture recognition technique for a remote-control human computer interface (HCI) using a single visible-light camera. The system is mainly composed of an image projector and a camera installed on the left side of the panel. We wish to develop a human computer interface that is not limited to finger touching on the board, but allows remotely controlling the system. In this system, we develop our human computer interface in order to find the hand location and to recognize human hand gesture in cluttered backgrounds in real time. In our approach, we first use a simple calibration process to get the initial position of the hand and the relation between image coordinates and the projected board coordinates. After that, we develop a tracking algorithm to get the position of hand, with the help of a hand detection algorithm. Next, we use a gesture recognition technique to recognize the current gesture. We also integrate the detection algorithm with the tracking algorithm to boost the performance. Finally, by projecting the detected hand position onto the projected screen, we can replace the use of mouse and use hand gesture to control the system.
Lin, Li-Wei, und 林立偉. „The Applications of Web Camera on Head Turning Recognition“. Thesis, 2009. http://ndltd.ncl.edu.tw/handle/47177539701971589181.
Der volle Inhalt der Quelle南台科技大學
機械工程系
97
In this paper, a webcam is used to capture images, and combining image processing and neural network technology to develop a head rotation recognition system. First, to identify the face region, then to find out the locations of eyes and lips, and after that according to the head rotating angle, to identify the centers of gravity of the eyes and lips. Furthermore, three sides of the triangle based on the three centers of gravity are obtained, after appropriate calculations to obtain five characteristics. After normalizing these characteristics and the corresponding rotating angles of head, the database is obtained and is used as the training data of the neural network. The experimental results indicate that, in the same light source, the rotating angle of head from -40 degrees to 40 degrees, the proposed head rotation recognition system can identify the head rotation degree direction.
LIN, CHENG-YEN, und 林政諺. „Taiwanese Sign Language Recognition Using an RGB-D Camera“. Thesis, 2016. http://ndltd.ncl.edu.tw/handle/91582000909725784127.
Der volle Inhalt der Quelle國立臺灣科技大學
機械工程系
104
In this thesis hand images were applied to perform sign language recognition through an RGB-D camera in general environments. Unlike many available methods focusing on number (from zero to nine) recognition in sign language, we proposed a method to perform Taiwanese sign language recognition, both for single vocabulary and sentences. For practical use, users first put their hands in front of the RGB-D camera with a distance between 40 cm and 70 cm. The depth information extracted from RGB-D camera was then used to construct the hand images and perform Taiwanese sign language vocabulary recognition using Haar feature-based cascade classifiers. The recognition can be classified into two parts. The first part is static Taiwanese sign language recognition for a sentence. The second part is recognizing dynamic Taiwanese sign language vocabularies as a sentence. Because hands are moving during dynamic sign language vocabulary recognition, we applied the optical flow method to recognize the hand orientation. Using the methods above, we have successfully performed Taiwanese sign language recognition. Finally, we also developed a Taiwanese sign language recognition module, which can be treated as a key technology for Taiwanese sign language translation. The recognition includes static and dynamic Taiwanese sign language vocabularies. These results may be useful for future real-time Taiwanese sign language recognition researches.
Lin, Yi-ta, und 林逸達. „3D Object Tracking and Recognition with RGB-Depth Camera“. Thesis, 2018. http://ndltd.ncl.edu.tw/handle/yn2qzy.
Der volle Inhalt der Quelle國立中山大學
電機工程學系研究所
106
The main purpose of this paper is 3D object tracking by using RGB-D camera. In addition, we would change our object during the tracking phase and our system can identify the new object. This paper is basically composed of three phases. The first phase is off-line training. The second phase is on-line tracking. The third phase is identification of the new object. In the first phase, we create three 3D models of the tracking objects which are box, cylinder and sphere, and we use a method to calculate the point pair features for each 3D model. Then, we store those point pair feature into the database which would be used later. In the second phase, use the RGB-D sensor to obtain the real world scenery, and calculate the point pair feature of the real world scenery as well as the first phase. After that, we compare the scenery ''s point pair features to the database so that we can find out where the 3D model is in the scenery. However, it is just an initial pose for the 3D model, so here we have to use the Iterative Closet Point (ICP) algorithm to obtain a better pose. In the third phase, we would change the tracking object during the tracking phase, and our system can detect the situation from the scenery. Besides, it can identify the new tracking object and keep tracking of it by the method introduced in the second phase.
Harguess, Joshua David. „Face recognition from video“. Thesis, 2011. http://hdl.handle.net/2152/ETD-UT-2011-12-4711.
Der volle Inhalt der Quelletext
Kuo, Wen-Te, und 郭文德. „Auto-Recognition and Performing of Music Score Captured By Camera“. Thesis, 2011. http://ndltd.ncl.edu.tw/handle/399v4q.
Der volle Inhalt der Quelle國立臺北科技大學
電資碩士班
100
As the technology developed for the camera capturing images, people need faster and smarter method for processing. This paper focuses on the image processing of music scores captured from the video camera. There are two main goals. One, because the existing recognition software could not provide a good correction for the distorted image, the paper proposed an improved method. First of all, we cut the images into small pieces. Then, we used the Hough Transform to calculate the slope of each piece. When we obtained slope, we used tangent function to obtain the offset value. Finally, based on the slopes and the connections between the pieces, the correction makes images become better. According to the good results, this process could effectively improve the pattern recognition rate. Two, to effectively identify the music symbols and increase the recognition rate, we decide to use neural networks to enhance the music score recognition. After many experiments were done, proving success rate averaged 96.4%, the results indicate the significant improvements of the music score recognition. Finally, this article will integrate the two approaches into a complete processing method and to verify by the actual reading music score image. Then, we prove the method that distorted image correction and neural network for recognition in this paper is work correctly.