To see the other types of publications on this topic, follow the link: Automatic Aircraft Recognition System.
Dissertations / Theses on the topic 'Automatic Aircraft Recognition System'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Automatic Aircraft Recognition System.'
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
Kim, Jijoong. "Automatic aircraft recognition and identification." Access electronically, 2005. http://www.library.uow.edu.au/adt-NWU/public/adt-NWU20060808.161115/index.html.
Full text
2
Wei, 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.
Full text
3
Campbell, Larry W. "An intelligent tutor system for visual aircraft recognition." Thesis, Monterey, California: Naval Postgraduate School, 1990. http://hdl.handle.net/10945/27723.
Full textAbstract:
Approved for public release; distribution is unlimited.Visual 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.
4
Higgins, C. A. "Automatic recognition of handwritten script." Thesis, University of Brighton, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.372081.
Full text
5
Sherrah, Jamie. "Automatic feature extraction for pattern recognition /." Title page, contents and abstract only, 1998. http://web4.library.adelaide.edu.au/theses/09PH/09phs553.pdf.
Full textAbstract:
Thesis (Ph. D.)--University of Adelaide, Dept. of Electrical and Electronic Engineering, 1999.CD-ROM in back pocket comprises experimental results and executables. Includes bibliographical references (p. 251-261).
6
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.
Full text
7
Bennamoun, 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.
Full textAbstract:
The aim of this thesis is to propose a modular vision system for automatic 2D object recognition, to determine its performance (with respect to accuracy, robustness, and efficiency), and to compare its performance to the performance of the neocognitron. Most of the existing vision systems assume that a preprocessed and clean image is provided, and that the parameters of the used algorithms are chosen by the user, depending on the scene under consideration. On this basis it is desired from the proposed system to be: 1)accurate, 2) robust, 3) efficient, and 4) adaptive. The system works under the following assumptions: 1) a single object is present in the field of view,
2) a single grey level image of the scene is provided, 3) the contrast in intensity between the object and the background is enough to be able to separate them. Note that we also extended this system to assume multiple moving
objects in the scene.
8
Tran, Michael. "An approach to a robust speaker recognition system." Diss., This resource online, 1994. http://scholar.lib.vt.edu/theses/available/etd-06062008-164814/.
Full text
9
Bengio, 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.
Full text
10
Zaludin, 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/.
Full text
11
Ehrman, 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.
Full textAbstract:
Rather than emitting pulses, passive radar systems rely on illuminators of opportunity, such as TV and FM radio, to illuminate potential targets. These systems are attractive since they allow receivers to operate without emitting energy, rendering them covert. Until recently, most of the research regarding passive radar has focused on detecting and tracking targets. This dissertation focuses on extending the capabilities of passive radar systems to include automatic target recognition.
The target recognition algorithm described in this dissertation uses the radar cross section (RCS) of potential targets, collected over a short period of time, as the key information for target recognition. To make the simulated RCS as accurate as possible, the received signal model accounts for aircraft position and orientation, propagation losses, and antenna gain patterns. An extended Kalman filter (EKF) estimates the target's orientation (and uncertainty in the estimate) from velocity measurements obtained from the passive radar tracker. Coupling the aircraft orientation and state with the known antenna locations permits computation of the incident and observed azimuth and elevation angles. The Fast Illinois Solver Code (FISC) simulates the RCS of potential target classes as a function of these angles. Thus, the approximated incident and observed angles allow the appropriate RCS to be extracted from a database of FISC results. Using this process, the RCS of each aircraft in the target class is simulated as though each is executing the same maneuver as the target detected by the system. Two additional scaling processes are required to transform the RCS into a power profile (magnitude only) simulating the signal in the receiver. First, the RCS is scaled by the Advanced Refractive Effects Prediction System (AREPS) code to account for propagation losses that occur as functions of altitude and range. Then, the Numerical Electromagnetic Code (NEC2) computes the antenna gain pattern, further scaling the RCS. A Rician likelihood model compares the scaled RCS of the illuminated aircraft with those of the potential targets. To improve the robustness of the result, the algorithm jointly optimizes over feasible orientation profiles and target types via dynamic programming.
12
Jonsson, 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.
Full textAbstract:
This thesis proposes an automatic road sign recognition system, including all steps from the initial detection of road signs from a digital image to the final recognition step that determines the class of the sign. We develop a Bayesian approach for image segmentation in the detection step using colour information in the HSV (Hue, Saturation and Value) colour space. The image segmentation uses a probability model which is constructed based on manually extracted data on colours of road signs collected from real images. We show how the colour data is fitted using mixture multivariate normal distributions, where for the case of parameter estimation Gibbs sampling is used. The fitted models are then used to find the (posterior) probability of a pixel colour to belong to a road sign using the Bayesian approach. Following the image segmentation, regions of interest (ROIs) are detected by using the Maximally Stable Extremal Region (MSER) algorithm, followed by classification of the ROIs using a cascade of classifiers. Synthetic images are used in training of the classifiers, by applying various random distortions to a set of template images constituting most road signs in Sweden, and we demonstrate that the construction of such synthetic images provides satisfactory recognition rates. We focus on a large set of the signs on the Swedish road network, including almost 200 road signs. We use classification models such as the Support Vector Machine (SVM), and Random Forest (RF), where for features we use Histogram of Oriented Gradients (HOG).
13
Andersstuen, Runar, and 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.
Full textAbstract:
With the constant increase in smartphone sales, integrated sensors have becomeavailable to the average user. This allows for mobile applications to utilise theuser’s context to provide more accurate information. The popularity of smartphones also attract developers to create audio functionalities that have earlier been restricted to calling interfaces. There is an increasing interest for Automatic Speech Recognition (ASR) services aimed at everyday tasks, where Apple’s release of SIRI is a good example of a system that has contributed to the gained popularity. This report describes TaleTUC, a proof of concept system for the domain of bus route information. TaleTUC uses ASR combined with context-awareness through Case-based Reasoning (CBR), to recognise spoken bus stop names. It is built on a client-server architecture, where theTABuss (Marcussen and Eliassen, 2011) Android application has been extendedto operate as a client. As a TaleTUC client, TABuss uses speech as input to itsmain query functionality, which provides bus route suggestions through BusTUC and AtB’s real-time system. Three modules have been developed server-side, where one is used for ASR, and the two others are used for context-awareness. Testing of the three modulescombined showed improved results compared to the ASR module alone, which indicates that context-awareness is a suitable technology to combine with ASR.
14
Ramirez, 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.
Full textAbstract:
Clipping 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.
15
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.
Full textAbstract:
Recent improvements in pose estimation has opened up the possibility of new areas of application. One of them is gait recognition, the task of identifying persons based on their unique style of walking, which is increasingly being recognized as an important method of biometric indentification. This thesis has explored the possibilities of using a pose estimation system, OpenPose, together with deep Recurrent Neural Networks (RNNs) in order to see if there is sufficient information in sequences of 2D poses to use for gait recognition. For this to be possible, a new multi-camera dataset consisting of persons walking on a treadmill was gathered, dubbed the FOI dataset. The results show that this approach has some promise. It achieved an overall classification accuracy of 95,5 % on classes it had seen during training and 83,8 % for classes it had not seen during training. It was unable to recognize sequences from angles it had not seen during training, however. For that to be possible, more data pre-processing will likely be required.
16
Lim, 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.
Full text
17
Kocour, 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.
Full textAbstract:
V dnešnej dobe systémy rozpoznávania reči s veľkým slovníkom dosahujú pomerne vysoké presnosti. Za ich výsledkami však často stoja desiatky ba až stovky hodín manuálne oanotovaných trénovacích dát. Takéto dáta sú často bežne nedostupné alebo pre požadovaný jazyk vôbec neexistujú. Možným riešením je použitie bežne dostupných no menej kvalitných audiovizuálnych dát. Táto práca sa zaoberá technikou zpracovania práve takýchto dát a ich použitím pre trénovanie akustických modelov. Ďalej táto práca pojednáva o možnom využití týchto dát pre kontinuálne vylepšovanie modelov, kedže tieto dáta sú prakticky nevyčerpateľné. Pre tieto účely bol v rámci práce navrhnutý nový prístup pre výber dát.
18
Ju, Quan. "A high performance automatic face recognition system using 3D shape information." Thesis, University of York, 2010. http://etheses.whiterose.ac.uk/1200/.
Full textAbstract:
Face recognition is one of the most important applications to receive attention in the areas of Computer Vision and Pattern Recognition. However, face recognition has many challenges and difficulties, such as the requirement for high speed search in large datasets and the requirement for high match accuracy under various noise conditions. Currently, as numerous 3D face datasets become available, more and more researchers start to move their concentration to 3D face recognition. Compared with 2D face image, 3D face images contain more explicit information which is very useful for dealing with the head orientation and the facial expression problem. In this thesis, a framework to implement automatic 3D face recognition is proposed and implemented. In the first stage, a key facial feature - the nose has to be extracted for the subsequent face recognition process. In order to exploit the local feature information, we present a face feature extraction methods based on a 3D shape descriptor. Two different 3D shape descriptor Multi Contour Surface Angle Moments Descriptor(MCSAMD) and Multi Shell Surface Angle Moments Descriptor(MSSAMD) are designed and implemented. The nose tip is identified using a binary neural network technique called k-Nearest Neighbour Correlation Matrix Memories(CMM) algorithm. The main face area is localized and cropped based on the nose tip localization with an identification rate of almost 100% on FRGC 3D face database. Secondly, a face aligned approach is implemented by applying a combination of methods including Principal Component Analysis(PCA) face correction, Iterative Closest Point algorithms(ICP) and the alignment using the symmetry of human face. All faces are aligned to a unified coordinate system from the original pose position even under expression variations. The position of the nose tip is also further corrected. After the face alignment, the main face area is divided into several regions with different weights according to the face expression variability. Similarity measurement algorithms based on the pose-invariant 3D shape descriptor MSSAMD are used to match the corresponding regions for different faces. The expression variability weights are applied in the final consideration of face identification and verification. Experiments are performed on the FRGC database which is the largest 3D face database of 4950 faces with different expressions. In the experiments dealing with 4007 faces with different expressions, a 91.96% verification at a false acceptance rate(FAR) of 0.1% and a 97.63% rank-one identification rate are achieved.
19
Gibson, 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/.
Full text
20
Castro, Ceron Ivan Francisco, and 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.
Full textAbstract:
Speech recognition has been an important area of research during the past decades. The usage of automatic speech recognition systems is rapidly increasing among different areas, such as mobile telephony, automotive, healthcare, robotics and more. However, despite the existence of many speech recognition systems, most of them use platform specific and non-publicly available software. Nevertheless, it is possible to develop speech recognition systems using already existing open source technology. The aim of this master's thesis is to develop an interactive and speaker independent speech recognition system. The system shall be able to identify predetermined keywords from incoming live speech and in response, play audio files with related information. Moreover, the system shall be able to provide a response even if no keyword was identified. For this project, the system was implemented using PocketSphinx, a speech recognition library, part of the open source Sphinx technology by the Carnegie Mellon University. During the implementation of this project, the automation of different steps of the process, was a key factor for a successful completion. This automation consisted on the development of different tools for the creation of the language model and the dictionary, two important components of the system. Similarly, the audio files to be played after identifying a keyword, as well as the evaluation of the system's performance, were fully automated. The tests run show encouraging results and demonstrate that the system is a feasible solution that could be implemented and tested in a real embedded application. Despite the good results, possible improvements can be implemented, such as the creation of a different phonetic dictionary to support different languages.
21
Karlsson, 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.
Full text
22
Dong, Junda. "Designing a Visual Front End in Audio-Visual Automatic Speech Recognition System." DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1382.
Full textAbstract:
Audio-visual automatic speech recognition (AVASR) is a speech recognition technique integrating audio and video signals as input. Traditional audio-only speech recognition system only uses acoustic information from an audio source. However the recognition performance degrades significantly in acoustically noisy environments. It has been shown that visual information also can be used to identify speech. To improve the speech recognition performance, audio-visual automatic speech recognition has been studied. In this paper, we focus on the design of the visual front end of an AVASR system, which mainly consists of face detection and lip localization. The front end is built upon the AVICAR database that was recorded in moving vehicles. Therefore, diverse lighting conditions and poor quality of imagery are the problems we must overcome.
We first propose the use of the Viola-Jones face detection algorithm that can process images rapidly with high detection accuracy. When the algorithm is applied to the AVICAR database, we reach an accuracy of 89% face detection rate. By separately detecting and integrating the detection results from all different color channels, we further improve the detection accuracy to 95%. To reliably localize the lips, three algorithms are studied and compared: the Gabor filter algorithm, the lip enhancement algorithm, and the modified Viola-Jones algorithm for lip features. Finally, to increase detection rate, a modified Viola-Jones algorithm and lip enhancement algorithms are cascaded based on the results of three lip localization methods. Overall, the front end achieves an accuracy of 90% for lip localization.
23
Messer, Kieron. "Automatic image database retrieval system using adaptive colour and texture descriptors." Thesis, University of Surrey, 1999. http://epubs.surrey.ac.uk/614/.
Full text
24
吳建雄 and 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.
Full text
25
Wu, 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.
Full text
26
Noori, 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.
Full text
27
Collingham, 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/.
Full textAbstract:
According to the Royal National Institute for Deaf people there are nearly 7.5 million hearing-impaired people in Great Britain. Human-operated machine transcription systems, such as Palantype, achieve low word error rates in real-time. The disadvantage is that they are very expensive to use because of the difficulty in training operators, making them impractical for everyday use in higher education. Existing automatic speech recognition systems also achieve low word error rates, the disadvantages being that they work for read speech in a restricted domain. Moving a system to a new domain requires a large amount of relevant data, for training acoustic and language models. The adopted solution makes use of an existing continuous speech phoneme recognition system as a front-end to a word recognition sub-system. The subsystem generates a lattice of word hypotheses using dynamic programming with robust parameter estimation obtained using evolutionary programming. Sentence hypotheses are obtained by parsing the word lattice using a beam search and contributing knowledge consisting of anti-grammar rules, that check the syntactic incorrectness’ of word sequences, and word frequency information. On an unseen spontaneous lecture taken from the Lund Corpus and using a dictionary containing "2637 words, the system achieved 815% words correct with 15% simulated phoneme error, and 73.1% words correct with 25% simulated phoneme error. The system was also evaluated on 113 Wall Street Journal sentences. The achievements of the work are a domain independent method, using the anti- grammar, to reduce the word lattice search space whilst allowing normal spontaneous English to be spoken; a system designed to allow integration with new sources of knowledge, such as semantics or prosody, providing a test-bench for determining the impact of different knowledge upon word lattice parsing without the need for the underlying speech recognition hardware; the robustness of the word lattice generation using parameters that withstand changes in vocabulary and domain.
28
KUMAR, ASHWINI. "IMPROVED APPROACH FOR INVARIANT AIRCRAFT TYPE RECOGNITION." Thesis, 2015. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14317.
Full textAbstract:
Despite a great deal of efforts to automate the aircraft recognition process aircraft recognition remains a challenging problem. The majority of the aircraft recognition methods assume the successful isolation of the aircraft portrait from the background, and only a few have actually addressed real world concerns, such as clutter and shadows. In this thesis, I present an automatic aircraft recognition system, which shows improved performance because of ring projection and dual tree complex wavelet. This system assumes from the start that the image could possibly be degraded, contain clutter, shadows and blurring.
Feature extraction is a crucial step in invariant pattern recognition. Among all existing feature extraction techniques, ring-projection has been selected for invariant pattern recognition in [28]. This is because it is invariant to translation and scale of the patterns. In addition, the ring-projection transforms the feature space from 2-D to 1-D, which reduces the processing time substantially. This makes it suitable practical approach in real-time applications.
The dual-tree complex wavelet transform is applied to the ring-projection signal in order to extract shift invariant features at different resolution scales. The reason why we choose the dual-tree complex wavelet transform is because it has the approximate shift-invariant property, which is very important for pattern recognition.
Figures 4-7 show the correct recognition rates of the descriptor and the Fourier transform for different rotation angles at SNR=10, 5, 3, 1, respectively. From these figures, it can be seen that this descriptor is much better than the Fourier transform especially for high noise levels. If more representative templates (not only 4 templates) are used to represent an aircraft type, the three failure cases will be tackled well.Mrs. MRIDULA VERMA
29
Chen, You-Cheng, and 陳侑成. "Automatic Face Recognition System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/07112650942486817095.
Full textAbstract:
碩士立德管理學院
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.
30
"An automatic speaker recognition system." Chinese University of Hong Kong, 1989. http://library.cuhk.edu.hk/record=b5886206.
Full text
31
Zeng, Shi-Hao, and 曾士豪. "Automatic Car Plate Recognition System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/qafkj5.
Full textAbstract:
碩士國立交通大學
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%.
32
Tsai, Chien-Tsai, and 蔡建材. "Automatic License Plate Recognition system." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/48475416792944540060.
Full textAbstract:
碩士中華大學
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.
33
Feng, Kai-Lin, and 馮凱琳. "Benthic Organisms Automatic Recognition System." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/bpzr7t.
Full textAbstract:
碩士國立中山大學
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.
34
D'Souza, Aaron, and Saprem Dalal. "Automatic License plate Recognition System." Thesis, 2011. http://ethesis.nitrkl.ac.in/2482/1/Automatic_License_plate_Recognition_System(107cs040%2C107cs030).pdf.
Full textAbstract:
Intelligence surveillance is an important commodity in traffic-based systems. Automatic License Plate Recognition (ALPR) is a challenging area of research. This work deals with problems related to artificial intelligence, neural networks and machine vision in the construction of an automatic license plate recognition (ALPR) system. This is done using mathematical principles and algorithms. These intelligent systems help in traffic monitoring during rush hours, road safety, commercial applications like in car parking lots and law enforcement. In this paper, a license plate recognition system is proposed which uses captured digital images of the rear or front of a vehicle and can be easily applied to commercial car park systems for access to parking spaces and also to prevent car theft issues.
35
Huang, Hsun-Ying, and 黃薰瑩. "An Automatic Recognition System of Leaves." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/73164125976634594993.
Full textAbstract:
碩士國立交通大學
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.
36
Yang, Wen Tzong, and 楊文宗. "Automatic Vehicle Identification Number Recognition System." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/16636917567719883726.
Full text
37
Cheng, Chia-Hsuan, and 鄭珈炫. "Automatic Recognition System for Poker Games." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/75025836689306651265.
Full textAbstract:
碩士元智大學
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.
38
Wu, Meng-Tsung, and 吳孟璁. "Automatic Vehicle License Plate Recognition System." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/96706197081543255915.
Full textAbstract:
碩士淡江大學
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.
39
Chen, Hsiang-Chieh, and 陳翔傑. "Automatic vehicle license plate recognition system design." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/26720851603323695840.
Full textAbstract:
碩士國立中央大學
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.
40
Ji, Chang-An, and 紀長安. "Automatic Recognition System of Speed Limit Signs." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/10052271684091337627.
Full textAbstract:
碩士國立彰化師範大學
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.
41
LI, CHENG-XUAN, and 李成軒. "Automatic Multi-feature Facial Expression Recognition System." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/t9jvz5.
Full textAbstract:
碩士國立中正大學
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.
42
Hou, Shun-Cheng, and 侯舜程. "An Automatic Recognition System for Credit Card Number." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/93769698685274548818.
Full textAbstract:
碩士玄奘大學
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.
43
Yuan, Shang-Yuan, and 袁上元. "Automatic Iris Recognition System based on Fractal Dimension." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/14758345036153131568.
Full textAbstract:
碩士逢甲大學
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.
44
Hsieh, Yi-Jwu, and 謝怡竹. "An Optical-Flow-Based Automatic Expression Recognition System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/16624477040703413012.
Full textAbstract:
碩士國立中央大學
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.
45
Yang, Chih-Chiang, and 楊志強. "Automatic License Plate Recognition System for Patrolling Vehicles." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/05839643474555607012.
Full textAbstract:
碩士中原大學
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.
46
Liao, Heng-Yi, and 廖恒毅. "Automatic Facial Skin Defect Detection and Recognition System." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/96258997271341530730.
Full textAbstract:
碩士國立雲林科技大學
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.
47
Chen, Ya-Ling, and 陳雅伶. "An Automatic Web Data Table Structure Recognition System." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/61367533796405320651.
Full textAbstract:
碩士淡江大學
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.
48
Ma, Jia Hong, and 馬嘉宏. "Automatic Extraction and Recognition System for Craniofacial Features." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/89569204126270581238.
Full textAbstract:
碩士長庚大學
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.
49
彭裕航. "Automatic Recognition System of the Vehicle License Plate." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/30879426620739533634.
Full textAbstract:
碩士中華大學
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.
50
Yi, Hsiang-Chen, and 伊象楨. "Automatic license plate recognition system using neural networks." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/23180934976831793562.
Full textAbstract:
碩士國立中興大學
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%.