Thèses sur le sujet « Automatic Aircraft Recognition System »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Automatic Aircraft Recognition System ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
Kim, Jijoong. « Automatic aircraft recognition and identification ». Access electronically, 2005. http://www.library.uow.edu.au/adt-NWU/public/adt-NWU20060808.161115/index.html.
Texte intégralWei, Yi. « Statistical methods on automatic aircraft recognition in aerial images ». Thesis, University of Strathclyde, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.248947.
Texte intégralCampbell, Larry W. « An intelligent tutor system for visual aircraft recognition ». Thesis, Monterey, California : Naval Postgraduate School, 1990. http://hdl.handle.net/10945/27723.
Texte intégralVisual aircraft recognition (VACR) is a critical skill for U.S. Army Short Range Air Defense (SHORAD) soldiers. It is the most reliable means of identifying aircraft, however VACR skills are not easy to teach or learn, and once learned they are highly degradable. The numerous training aids that exist to help units train soldiers require qualified instructors who are not always available. Also, the varying degrees of proficiency among soldiers make group training less than ideal. In an attempt to alleviate the problems in most VASC training programs, an intelligent tutor system has been developed to teach VACR in accordance with the Wings, Engine, Fuselage, Tail (WEFT) cognitive model. The Aircraft Recognition Tutor is a graphics based, object oriented instructional program that teaches, reviews and tests VACR skills at a level appropriate to the student. The tutor adaptively coaches the student from the novice level, through the intermediate level, to the expert level. The tutor was provided to two U.S. Army Air Defense Battalions for testing and evaluation. The six month implementation, testing, and evaluation process demonstrated that, using existing technology in Computer Science and Artificial Intelligence, useful training tools could be developed quickly and inexpensively for deployment on existing computers in field.
Higgins, C. A. « Automatic recognition of handwritten script ». Thesis, University of Brighton, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.372081.
Texte intégralSherrah, Jamie. « Automatic feature extraction for pattern recognition / ». Title page, contents and abstract only, 1998. http://web4.library.adelaide.edu.au/theses/09PH/09phs553.pdf.
Texte intégralCD-ROM in back pocket comprises experimental results and executables. Includes bibliographical references (p. 251-261).
Benkhedda, Hassen. « Design of a transport aircraft automatic flight control system with analytical redundancy ». Thesis, University of Southampton, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.241599.
Texte intégralBennamoun, Mohammed. « An adaptive vision system for automatic object recognition ». Thesis, Queensland University of Technology, 1996. https://eprints.qut.edu.au/107120/1/T%28BE%26E%29%201022%20An%20adaptive%20vision%20system%20for%20automatic%20object%20recognition.pdf.
Texte intégralTran, Michael. « An approach to a robust speaker recognition system ». Diss., This resource online, 1994. http://scholar.lib.vt.edu/theses/available/etd-06062008-164814/.
Texte intégralBengio, Yoshua. « Connectionist models applied to automatic speech recognition ». Thesis, McGill University, 1987. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=63920.
Texte intégralZaludin, Zairil A. « Flight dynamics and automatic flight control system of an hypersonic transport aircraft ». Thesis, University of Southampton, 1999. https://eprints.soton.ac.uk/47120/.
Texte intégralEhrman, Lisa M. « An Algorithm for Automatic Target Recognition Using Passive Radar and an EKF for Estimating Aircraft Orientation ». Diss., Georgia Institute of Technology, 2005. http://hdl.handle.net/1853/7510.
Texte intégralJonsson, Fredrik. « On the Construction of an Automatic Traffic Sign Recognition System ». Thesis, Linköpings universitet, Statistik och maskininlärning, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-143593.
Texte intégralAndersstuen, Runar, et Christoffer Jun Marcussen. « TaleTUC : Automatic Speech Recognition for a Bus Route Information System ». Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap, 2012. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-20102.
Texte intégralRamirez, Jose Luis. « Effects of clipping distortion on an Automatic Speaker Recognition system ». Thesis, University of Colorado at Denver, 2016. http://pqdtopen.proquest.com/#viewpdf?dispub=10112619.
Texte intégralClipping distortion is a common problem faced in the audio recording world in which an audio signal is recorded at higher amplitude than the recording system’s limitations, resulting in a portion of the acoustic event not being recorded. Several government agencies employ the use of Automatic Speaker Recognition (ASR) systems in order to identify the speaker of an acquired recording. This is done automatically using a nonbiased approach by running a questioned recording through an ASR system and comparing it to a pre-existing database of voice samples of whom the speakers are known. A matched speaker is indicated by a high correlation of likelihood between the questioned recording and the ones from the known database. It is possible that during the process of making the questioned recording the speaker was speaking too loudly into the recording device, a gain setting was set too high, or there was post-processing done to the point that clipping distortion is introduced into the recording. Clipping distortion results from the amplitude of an audio signal surpassing the maximum sampling value of the recording system. This affects the quantized audio signal by truncating peaks at the max value rather than the actual amplitude of the input signal. In theory clipping distortion will affect likelihood ratios in a negative way between two compared recordings of the same speaker. This thesis will test this hypothesis. Currently there is no research that has helped as a guideline for knowing the limitations when using clipped recordings. This thesis will investigate to what degree of effect will clipped material have on the system performance of a Forensic Automatic Speaker Recognition system.
Persson, Martin. « Automatic Gait Recognition : using deep metric learning ». Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167074.
Texte intégralLim, Bock-Aeng. « Design and rapid prototyping of flight control and navigation system for an unmanned aerial vehicle ». Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2002. http://sirsi.nps.navy.mil/uhtbin/hyperion-image/02Mar%5FLimBA.pdf.
Texte intégralKocour, Martin. « Automatic Speech Recognition System Continually Improving Based on Subtitled Speech Data ». Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2019. http://www.nusl.cz/ntk/nusl-399164.
Texte intégralJu, Quan. « A high performance automatic face recognition system using 3D shape information ». Thesis, University of York, 2010. http://etheses.whiterose.ac.uk/1200/.
Texte intégralGibson, Marcia Rose. « A feasibility study on the use of a voice recognition system for training delivery ». Diss., This resource online, 1990. http://scholar.lib.vt.edu/theses/available/etd-08252008-162853/.
Texte intégralCastro, Ceron Ivan Francisco, et Badillo Andrea Graciela Garcia. « A Keyword Based Interactive Speech Recognition System for Embedded Applications ». Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-12479.
Texte intégralKarlsson, Joakim. « The integration of automatic speech recognition into the air traffic control system ». Thesis, Massachusetts Institute of Technology, 1990. http://hdl.handle.net/1721.1/42184.
Texte intégralDong, Junda. « Designing a Visual Front End in Audio-Visual Automatic Speech Recognition System ». DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1382.
Texte intégralMesser, Kieron. « Automatic image database retrieval system using adaptive colour and texture descriptors ». Thesis, University of Surrey, 1999. http://epubs.surrey.ac.uk/614/.
Texte intégral吳建雄 et Jianxiong Wu. « A parallel distributed processing system for machine recognition of speech signals ». Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1991. http://hub.hku.hk/bib/B31232887.
Texte intégralWu, Jianxiong. « A parallel distributed processing system for machine recognition of speech signals / ». [Hong Kong : University of Hong Kong], 1991. http://sunzi.lib.hku.hk/hkuto/record.jsp?B13068568.
Texte intégralNoori, Asaad F. « An investigation of the feasabiltiy of neurophysiologically and psycholinguistically automatic speech recognition system ». Thesis, King's College London (University of London), 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.321736.
Texte intégralCollingham, Russell James. « Towards an automatic speech recognition system for use by deaf students in lectures ». Thesis, Durham University, 1994. http://etheses.dur.ac.uk/5840/.
Texte intégralKUMAR, ASHWINI. « IMPROVED APPROACH FOR INVARIANT AIRCRAFT TYPE RECOGNITION ». Thesis, 2015. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14317.
Texte intégralMrs. MRIDULA VERMA
Chen, You-Cheng, et 陳侑成. « Automatic Face Recognition System ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/07112650942486817095.
Texte intégral立德管理學院
應用資訊研究所
93
The face recognition systems can be roughly divided into two categories. One is the analysis of face expression, which first extracts facial feature points and then uses their relative relation to analyze the face expression. The other is the identification of a to-be-recognized face, which extracts the unique character of face and then identifies the face. This research, belonging to the latter, is to build an automatic face recognition system that accepts a color image with a complete face and identifies the face. The system consists of four modules: face detection module, facial features location module, facial features extraction module and face recognition module. The face detection module adopts the YCbCr color model to separate the face and the background. The facial features location module uses the pupils to locate the relative positions of eyebrows, eyes, nose and mouth roughly. After that, the facial features extraction module exactly locates the positions the facial features, extracts the pre-defined feature points and calculates the moments of the shapes of the eyebrows in order to obtain four local feature vectors and one global feature vector. Finally, the face recognition module uses a hybrid structure, consisting of a RBF and a multilayer neural network, to identify the to-be-recognized face. The experiments are tested by two sets of image database. One database, including 28 persons and 20 images per person, is photoed by us and the other is the well-known partial CMU PIE image database, including 68 persons and 50 images per person. The average recognition accuracy of our images is 95% and that of PIE is 83%. If we put the first two candidates of recognized result into consideration, the accuracies achieve 100% and 91.2% respectively. From the experimental results, the proposed automatic face recognition system is of effective recognition rate and of high reliability.
« An automatic speaker recognition system ». Chinese University of Hong Kong, 1989. http://library.cuhk.edu.hk/record=b5886206.
Texte intégralZeng, Shi-Hao, et 曾士豪. « Automatic Car Plate Recognition System ». Thesis, 2016. http://ndltd.ncl.edu.tw/handle/qafkj5.
Texte intégral國立交通大學
電控工程研究所
105
Car plate recognition system is widely used in all aspects of life, such as parking lot management system and highway toll collection. However, existing recognition systems are limited by image processing. To recognize car plates instantly, extra sensors are installed on most of systems, or a region of interest is defined on single lane. Our aims of research are to process surveillance video directly without additional devices, and to achieve multi-lane recognition in real time. By principal component analysis, we can separate the cars from the background, therefore plenty of processing time has been saved. We also develop the robust recognition module based on different samples, which are influenced by environmental factors such as reflection, dirt and shadow. The module implements plate segmentation by Sobel edge detector and Gaussian filter, analyzes connected component in plate to segment characters and uses support vector machine to recognize characters. In the last chapter, we examine the system with a high-definition video. The result show that our system can recognize the simulation video in real time, and the overall rate of success is 91.35%.
Tsai, Chien-Tsai, et 蔡建材. « Automatic License Plate Recognition system ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/48475416792944540060.
Texte intégral中華大學
資訊工程學系碩士班
93
A real-time automatic license plate recognition system is proposed in this paper to identify the license plate quickly and accurately in the unrestricted environment, e.g. different lighting conditions and various vehicles. The proposed system mainly includes two procedures: license plate locating and character recognition. In license plates locating procedure, we convert the color image into grey level data first. Then apply the morphology technique to find out the location of license plate. The objective of the research is to increase the recognition rate of license plates and to improve the success rate of license plate locating. We demonstrate the feasibility of this system of this system through extensive experiments. The correct plate location rate and characters recognition achieves 96.63% and 93.20%, respectively.
Feng, Kai-Lin, et 馮凱琳. « Benthic Organisms Automatic Recognition System ». Thesis, 2019. http://ndltd.ncl.edu.tw/handle/bpzr7t.
Texte intégral國立中山大學
資訊工程學系研究所
107
Benthic organisms play a very important role both in scientific research and in aquaculture. However, it often takes a long time to observe or take the target organism out of its living environment to observe its status. The massive cost of labor is its main drawback. And in order to achieve automatic identification, it is also necessary to match the technology with flexibility to cope with various benthic organisms. In recent years, image processing technology has become more and more developed. In particular, the recently-popular deep learning technology can identify some of the objects that are less features. In a neural network model, after analyzing multiple neural layers, a set of predictive answers are obtained. Finally, minimize the error rate by training and continually correcting identified parameters. The neural network model must go through a lot of learning processes to achieve this effect, not all items have a large amount of training samples to make the model learn to the extent available. The data of benthic organisms is even more difficult to obtain. Therefore, this paper proposes Benthic Organisms Automatic Recognition System. The system provides the collection method of automatic labeling function, the deep network model with strong and fast computing speed, and finally the system also provides the final recognition result according to the user interface.
D'Souza, Aaron, et Saprem Dalal. « Automatic License plate Recognition System ». Thesis, 2011. http://ethesis.nitrkl.ac.in/2482/1/Automatic_License_plate_Recognition_System(107cs040%2C107cs030).pdf.
Texte intégralHuang, Hsun-Ying, et 黃薰瑩. « An Automatic Recognition System of Leaves ». Thesis, 2008. http://ndltd.ncl.edu.tw/handle/73164125976634594993.
Texte intégral國立交通大學
多媒體工程研究所
96
When wandering around the field, we can touch many plants. It is useful knowing them through image recognition technique. Since leaf is one of the important features for characterizing various plants, it is often taken for plant recognition. The thesis proposes a hierarchical automatic region-based method for leaf recognition. First, delete impossible species to which the input leaf belongs according to the leaf shape represented by five extracted features. Next, based on these candidates, the system finds out the most similar images in our database and allows each user to choose the correct one. The precision rate is 95.14% for top 5. In addition, the proposed method is rotation invariant and solves the noises caused by light reflection in preprocessing.
Yang, Wen Tzong, et 楊文宗. « Automatic Vehicle Identification Number Recognition System ». Thesis, 1996. http://ndltd.ncl.edu.tw/handle/16636917567719883726.
Texte intégralCheng, Chia-Hsuan, et 鄭珈炫. « Automatic Recognition System for Poker Games ». Thesis, 2007. http://ndltd.ncl.edu.tw/handle/75025836689306651265.
Texte intégral元智大學
資訊工程學系
96
Since technology are developed quickly and fetch image equipment (digit camera, webcam ,etc.) are cost reduced, the application of digital image are more extensive. In the computer image field, image recognition has been developed for years, and it applies to many situation such as characters recognition, palm line recognition, cards recognition, license plate recognition, face recognition ,etc. They created a lot of research results. The method utilizing vision of the computer without artificial operation offers diversified services. This paper is mainly to design a real time poker recognition system. Put poker on the tabletop arbitrarily, fetch the image on the tabletop with the webcam, and deliver it to computer for real-time recognition. No matter the angle that card put, the system can recognize the produce design of poker. It mainly includes cutting, calculating the quantity of design, designing recognition, JQK recognition etc. Based on detection, the algorithm of performing recognition the design is mainly to describe the characteristic of the object. The characteristic wave form of the design won can be subsequently obtained. We cut the unsmooth area in the characteristic wave form out and utilize unsmooth difference recognition design. The proposed method can deal with each objects edge outline characteristic value without considering the object angle. It shows good results in resistance to the displacement, rotation and distance of the image. And the value does not change. Moreover, there are good result of recognition of the object with different size. Although JQK image is very complicated, it is the characteristic of utilizing the image head area to recognition the card of these three kinds after analysis. We can recognize the image of this area clearly and can reduce the complexity and computational speed.
Wu, Meng-Tsung, et 吳孟璁. « Automatic Vehicle License Plate Recognition System ». Thesis, 1998. http://ndltd.ncl.edu.tw/handle/96706197081543255915.
Texte intégral淡江大學
資訊工程學系
86
In this thesis, we develop an effective and fast automatic vehicle license plate recognition system. From a digital vehicle image without presetting the location and size of the license plate, the proposed system can automatically find the location of the plate, isolate the letters and digits occurring in the plate, and then recognize the characters. The system includes three parts: license plate location, character isolation, and character recognition. Images with 256 gray levels are used in this system. Firstly, vertical edges appearing in an image are detected by the techniques of digital image processing. Since the difference between the gray-levels of plate''s characters and those of plate''s background are significantly, it is easy to detect the edges of characters. By horizontal scanning, the lines with enough gray-level changes are preserved. Then possible locations of the plate could be identified from the larger areas based on the intervals in the vertical and horizontal projections. After locating the plate, the image of the plate area is converted into binary for accelerating recognition. Then the characters on the plate are isolated according to the vertical projection of the above binary image. Finally, the isolated characters are recognized by the moment method, which compares each character with standard character models by using the Euclidean distance. A postprocessing step is executed if errors exist. The experiment was performed on a Pentium personal computer. The experimental results show that 95 images whose license plates can be located correctly in 100 test car images, and each image needs approximately 0.3 seconds for locating the license plate.
Chen, Hsiang-Chieh, et 陳翔傑. « Automatic vehicle license plate recognition system design ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/26720851603323695840.
Texte intégral國立中央大學
電機工程研究所
93
Recently, vehicle license plate recognition system plays an important role in intelligent transportation system. This paper will propose an algorithm with low computation and high recognition rate algorithm to realize a real time license plate recognition system. We divide our system into three stages, including license plate locating, characters segmentation and characters recognition. A novel method for extracting license plate in complex background is proposed. Due to the influence of lighting effects, tilt or dirty of the license plate, we also create a method to compensate these cases. In characters recognition, template matching and similarity measure are used such that our algorithm is more robust in different inclination and lighting conditions.
Ji, Chang-An, et 紀長安. « Automatic Recognition System of Speed Limit Signs ». Thesis, 2011. http://ndltd.ncl.edu.tw/handle/10052271684091337627.
Texte intégral國立彰化師範大學
電機工程學系
99
The traffic signs are used to provide the traffic information for all drivers and pedestrians. Drivers often pay most attention on the road but ignore the traffic signs on both sides of the road. A driver assistance system is to remind driver of traffic sign contents while driving a car. This paper presents a detection and recognition system of speed limit signs. The traffic signs are detected in the RGB color space. The extracted red circle frame is selected by size, height and width to obtain the appropriate circle frame. The number inside the red circle frame was extracted and normalized. After normalization, the number is compared with the sample to obtain the recognition result. The method we proposed is tested at static state and real time state. The image recognition rate of traffic signs is 91.5% with detecting 109 signs out of 119 signs. The real time recognition rate of traffic signs is 87% with detecting 128 signs out of 147 signs. The results demonstrate the feasibility of this method.
LI, CHENG-XUAN, et 李成軒. « Automatic Multi-feature Facial Expression Recognition System ». Thesis, 2019. http://ndltd.ncl.edu.tw/handle/t9jvz5.
Texte intégral國立中正大學
資訊管理系研究所
107
With the development of science and technology, and the change of human structure, people begin to pursue higher quality of life and the requirements in social welfare, medical care, home care, education and other services are also increasing. Facial expression recognition plays an important role in a variety of applications, such as human-computer interaction (HCI), robot control, and driver state surveillance. Hence, how to extract emotional features accurately is critical for facial expression recognition. This paper mainly combines three kinds of methods to extract facial features. The first one is based on the facial action coding system (FACS), and we capture distance features after the combination of action units (AU). Second, to extract histograms of block-based local binary pattern (B-LBP) features. Third, feature extraction of histogram of oriented gradient (HOG) on each face image. Among them, B-LBP and HOG features will use principal component analysis (PCA) to reduce dimensionality. Finally, we input the three features into support vector machine (SVM) for expression recognition. The experimental results demonstrate high correct recognition rate, and effectively reduce the negative impact on the overall performance.
Hou, Shun-Cheng, et 侯舜程. « An Automatic Recognition System for Credit Card Number ». Thesis, 2014. http://ndltd.ncl.edu.tw/handle/93769698685274548818.
Texte intégral玄奘大學
資訊管理學系碩士班
102
Development of technology more widely and popular, and more recognition system extends from simple digital identification to text recognition more diversity, not only to extend the use of the license plate is also applied to the identification card or credit card numbers. The theory proposes a simple and convenient credit card identification system, the main part of the capture credit card numbers, you need to first color images into grayscale images. Before then use the binary character segmentation way to remove the background and do normalization cutting characters. And we use the template matching method to do character recognition, will do a similar alphanumeric histogram matching, more accurately identify the alphanumeric serial number on the credit card.
Yuan, Shang-Yuan, et 袁上元. « Automatic Iris Recognition System based on Fractal Dimension ». Thesis, 2000. http://ndltd.ncl.edu.tw/handle/14758345036153131568.
Texte intégral逢甲大學
電機工程學系
88
Biometrics and biometric recognition system become very important and valuable in the applications such as identification and security. Fingerprint identification has been the most widespread of application of biometric technology. Recently, iris identification is emerging as the most foolproof method of automated personal identification in demand by an ever more automated world. There are only two such iris recognition systems developed. In this thesis, a prototype system, called Automatic Iris Recognition System (AIRS), which is based on fractal dimension as feature description will be developed. Fractal dimension is a fascinating feature highly correlated with the human perception of surface roughness and has been successfully applied to texture analysis, segmentation, and classification, In addition to theoretical Hausdorff dimension, box dimension and correlation dimension are two significant alternative definitions of fractal dimension, which are computationally manageable. The box-counting (BC) method and the differential box-counting (DBC) method are two popular methods in computing the fractal dimension for digital textured image. They, however, inhere in some drawbacks. In this thesis, three algorithms that can obtain more accurate estimate of the fractal dimension are proposed and investigated. First, a modified algorithm of the DBC method, is called the shifting DBC (SDBC) algorithm is proposed to improve the DBC method. We will theoretically prove that the SDBC algorithm approaches the estimated value closer to the exact fractal dimension than the DBC method. Second, a novel approach, called the scanning BC (SBC) algorithm, is introduced. Third, a novel approach to estimate the correlation dimension for 2-D natural image will be proposed and discussed. These algorithms used for 1-D case will also be investigated. Simulations on 2-D natural textural images and 1-D biomedical waveform sequences, such as ECG and pulse waves, will be performed and discussed. Based on the fractal dimension obtained by the three algorithms as the feature description of iris image, an iris identification technique will be introduced and investigated. Finally, the prototype system (AIRS) of the automatic iris recognition system will developed. The simulation results are also given.
Hsieh, Yi-Jwu, et 謝怡竹. « An Optical-Flow-Based Automatic Expression Recognition System ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/16624477040703413012.
Texte intégral國立中央大學
資訊工程研究所
93
Recently, researchers have put a lot of efforts on the recognition of facial expressions. The goal of the thesis is to develop an automatic facial expression recognition system to automatically perform human face detection, feature extraction and facial expression recognition after the images are faded. Via the use of the automatic human face detection, the region of facial features and the optical flow tracking algorithm, we can construct an automatic facial expression recognition system to achieve our goal. Most of the traditional facial expression systems are first to look for a way to automatically track some facial feature points (ex: canthus, eyebrows, and mouth) and then recognize expressions based on these extracted facial features. But experimental results exhibited that the facial features cannot always be obtained reliably because of the quality of images, illumination, and some other disturbing factors. Some properties of images contribute a lot of errors or bias and cost a lot of process time to overcome them if possible. Although the clear features can make a lot of contribution on the performance, we can also feel the changes of facial expression according to some slight muscle variations of facial area. So the way to utilize some specified feature regions and the uniform-distributed feature points is used to for the facial expression from the motion of these feature points. After a series of images are derived, according to the proposed idea, the first frame is used to perform human face detection, and get the three feature regions (eyes and mouth) by their geometrical ratio relationships. To increase the accuracy of locating feature regions, the Sobel edge detection incorporated with the horizontal projection is used. After three feature regions have been located 84 feature points are uniformly distributed in the specified feature regions. Then we use the optical flow algorithm to track these 84 feature points on the following image series. Therefore, 84 facial motion vectors can be derived from the tracking procedure. Then the facial expression recognition is based on these 84 facial motion vectors. The facial recognition procedures involves in two stages. At the first stage, three multi-layer perceptrons are trained to recognize the action units in the eyebrow, the eye and the mouth regions. Then another five single-layer perceptrons are used to recognize the facial expressions based on the outputs computed from the aforementioned three MLPs. Experiments were conducted to test the performance of the proposed facial recognition system.
Yang, Chih-Chiang, et 楊志強. « Automatic License Plate Recognition System for Patrolling Vehicles ». Thesis, 2014. http://ndltd.ncl.edu.tw/handle/05839643474555607012.
Texte intégral中原大學
資訊工程研究所
102
License plates are considered the first important information for vehicle-related crime investigation (e.g., vehicle theft, etc.). Conventional investigation requires the investigator (policeman) to manually enter the license plate number for suspicious vehicles which remains tedious and labor-intensive. The objective of this study was to develop an Automatic license plate recognition system for patrolling vehicles. We explored the idea to provide an automatic system by installing a surveillance camera (e.g., a vehicle video recorder) on a patrolling vehicle (e.g., police car). The system can be described in two phases, namely hardware configuration and software development. Technical approaches included: License Plate Localization, License Plate Correction, Character Segmentation, and Character Recognition. Overall, our system could achieve the license plate localization and character recognition of over 90%. In summary, our system could be incorporated in an integrated system with wireless communication for querying the vehicles’ information to assist the vehicle-related crime investigation.
Liao, Heng-Yi, et 廖恒毅. « Automatic Facial Skin Defect Detection and Recognition System ». Thesis, 2011. http://ndltd.ncl.edu.tw/handle/96258997271341530730.
Texte intégral國立雲林科技大學
資訊工程研究所
99
Recently medical cosmetic has attracted significant business opportunity. Micro cosmetic surgery usually involves the minimally invasive cosmetic procedures such as non-ablative laser procedure for skin rejuvenation. However, an appropriate treatment selection for skin relies on accurate preoperative evaluation. In this paper, an automatic facial skin defects detection and recognition approach is proposed. The system firstly locates the facial region from the input image. A contour descriptor is adopted to describe the shape of faces. The views were recognized using a support vector machine. The facial features are extracted to define region of interest and an image segment method is used to extracted potential defect. A support-vector-machine-based classifier is then used to classify the potential defects into spot, acne and normal skin. Experimental results demonstrate effectiveness of the proposed approach.
Chen, Ya-Ling, et 陳雅伶. « An Automatic Web Data Table Structure Recognition System ». Thesis, 2011. http://ndltd.ncl.edu.tw/handle/61367533796405320651.
Texte intégral淡江大學
資訊管理學系碩士班
99
Many techniques have been proposed to extract important information in web tables. Many of these information extraction techniques are successful for simple tables. However, their applications to complex tables usually obtain unsatisfactory accuracy, due to inadequate similarity comparison among table cells and insufficient table information collection. We design and implement an automatic web data table structure recognition system to tackle this problem. This system would first classify web data tables into nine table categories by analyzing TSF (Table Structure Feature) and CT (Cell Type) through heuristics. After the classification phase, each cell is identified as table attributes or table values by analyzing table structures in each category. For complex tables, we use heuristics and common attribute name recognition in 2x2 tables to recognize table structures. Furthermore, table attributes and table values are presented as relational tables to save memory space and to identify each record clearly. We not only test the effectiveness of our system, but also analyze why some table structures are wrongly recognized. The reasons are identified and future developments to handle these cases are suggested.
Ma, Jia Hong, et 馬嘉宏. « Automatic Extraction and Recognition System for Craniofacial Features ». Thesis, 2010. http://ndltd.ncl.edu.tw/handle/89569204126270581238.
Texte intégral長庚大學
資訊工程學系
98
Facial recognition has been an important topic and has many applications in the field of image processing. The distinctive examples include entrance guard management, criminal image management, etc. Conventional facial recognition methods usually compared the reference and target images pixel-wise. The robustness of those methods is, however, challenged by the shading and the brightness, etc., of the background. The exhausted approach leads to expensive computation, and too much detail exhibits more than needed sensitivity to the minute difference between the images of concern. In this thesis, we offer a more robust method based on feature points of the face. It reduces computation time and present more reliable extraction and recognition results. The underlying rationale of feature base is that humans identify one people mostly by means of significant or invariant features; people getting fatter, thinner has little effect in recognition. Occlusion is usually a challenge for recognition of two-dimensional (2D) images. In this study, we incorporate three-dimensional (3D) models, as well as their 2D counterparts. A facial model can be affine transformed for both visualization and alignment purposes. We also develop a Mass Distribution Tensor (MDT) algorithm to determine the orientation of the facial model in 3D perspective. An integrated software system is developed to help the user walk through the whole process of facial feature extraction and recognition. The user may also interactively adjust the parameters of individual algorithm gain desired output.
彭裕航. « Automatic Recognition System of the Vehicle License Plate ». Thesis, 2008. http://ndltd.ncl.edu.tw/handle/30879426620739533634.
Texte intégral中華大學
機械工程學系碩士班
96
In this dissertation, we construct the License Plate Recognition system by using PC as a platform and image process techniques. A new character structure hierarchy is proposed and the correlated character characteristic value and character coding are defined. Also, character thinning processing is applied in the system to identify the English characters and digits on the car license plate. The experiments of this system include two parts. The first part is to locate the license plate in images and divide characters on the plate. By using the following technique, such as Sobel edge detection, noise filters, threshold, and projection, to the captured images; characters and dash on license plate are divided. The second part is character recognition. Characters are recognized by determining the character end-point position, direction of end-point, four corner location, and vertical as well as horizontal characteristic categorization. The experiment results demonstrate that the system attains satisfied performance for recognition speed and correctness rate.
Yi, Hsiang-Chen, et 伊象楨. « Automatic license plate recognition system using neural networks ». Thesis, 2007. http://ndltd.ncl.edu.tw/handle/23180934976831793562.
Texte intégral國立中興大學
電機工程學系所
95
This thesis discusses the locating, segmentation, and recognition of the license plates of cars.In the procedure of locating license plates, the input image is first transformed into an image with a pre-specified resolution. Then the Sobel edge detector is adopted to find the edge map of the image. After that, the edge map is scanned to locate the regions with frequent variations in black and white. The threshold in the Sobel edge detector is dynamically adjusted so that the number of characters in the license plate is correct. Spatial transformation is utilized to rectify the detected license plate image to a rectangular image block. As to license plate character segmentation, connected components are extracted for each character. Then the segmented character image is input to the neural network for recognition.In the thesis, 100 images of license plates are used in the experiment. The success rate of the license plate detection is 100%; and success rate of character segmentation and recognition is 96%.