Dissertations / Theses on the topic 'Handwritten Character Recognition (HCR)'
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 'Handwritten Character Recognition (HCR).'
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.
Chai, Sin-Kuo. "Multiclassifier neural networks for handwritten character recognition." Ohio : Ohio University, 1995. http://www.ohiolink.edu/etd/view.cgi?ohiou1174331633.
Full textClarke, Eddie. "A novel approach to handwritten character recognition." Thesis, University of Nottingham, 1995. http://eprints.nottingham.ac.uk/14035/.
Full textXu, Zhengyan, and Yibing Zhou. "Specific Handwritten Chinese Character Recognition Based on Artificial Intelligence." Thesis, Högskolan i Gävle, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-14599.
Full textSawhney, Sumeet S. "Distance measurements and their combination in handwritten character recognition." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/MQ59339.pdf.
Full textAnsari, Nasser. "Handwritten character recognition by using neural network based methods." Ohio : Ohio University, 1992. http://www.ohiolink.edu/etd/view.cgi?ohiou1172080742.
Full text陳國評 and Kwok-ping Chan. "Fuzzy set theoretic approach to handwritten Chinese character recognition." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1989. http://hub.hku.hk/bib/B30425876.
Full textSahai, Anant. "Handwritten character recognition using the minimum description length principle." Thesis, Massachusetts Institute of Technology, 1996. http://hdl.handle.net/1721.1/11015.
Full textShi, Daming. "An active radical approach to handwritten Chinese character recognition." Thesis, University of Southampton, 2002. https://eprints.soton.ac.uk/257379/.
Full textManley-Cooke, Peter. "Handwritten character recognition using a multi-classifier neuro-fuzzy framework." Thesis, University of East Anglia, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.433914.
Full textKassel, Robert H. "A comparison of approaches to on-line handwritten character recognition." Thesis, Massachusetts Institute of Technology, 1995. http://hdl.handle.net/1721.1/11407.
Full textIncludes bibliographical references (p. 155-163).
by Robert Howard Kassel.
Ph.D.
He, Tingting, and 何婷婷. "A study on several problems in online handwritten Chinese character recognition." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2008. http://hub.hku.hk/bib/B42182086.
Full textHe, Tingting. "A study on several problems in online handwritten Chinese character recognition." Click to view the E-thesis via HKUTO, 2008. http://sunzi.lib.hku.hk/hkuto/record/B42182086.
Full textChen, Wen-Tsong. "Word level training of handwritten word recognition systems /." free to MU campus, to others for purchase, 2000. http://wwwlib.umi.com/cr/mo/fullcit?p9974612.
Full textZhao, Mengqiao. "Handwritten digit recognition based on segmentation-free method." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-20685.
Full textMorns, Ian Philip. "The novel dynamic supervised forward propagation neural network for handwritten character recognition." Thesis, University of Newcastle Upon Tyne, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.285741.
Full textKabir, Ehsanollah. "Application of domain knowledge to recognition of hand-printed and handwritten postal addresses." Thesis, University of Essex, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.236248.
Full textJunaidi, Akmal [Verfasser], Gernot A. [Akademischer Betreuer] Fink, and Heinrich [Gutachter] Müller. "Lampung handwritten character recognition / Akmal Junaidi ; Gutachter: Heinrich Müller ; Betreuer: Gernot A. Fink." Dortmund : Universitätsbibliothek Dortmund, 2016. http://d-nb.info/1131355199/34.
Full textRahman, Ahmad Fuad Rezaur. "Study of multiple expert decision combination strategies for handwritten and printed character recognition." Thesis, University of Kent, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.245624.
Full textJunaidi, Akmal [Verfasser], Gernot A. Akademischer Betreuer] Fink, and Heinrich [Gutachter] [Müller. "Lampung handwritten character recognition / Akmal Junaidi ; Gutachter: Heinrich Müller ; Betreuer: Gernot A. Fink." Dortmund : Universitätsbibliothek Dortmund, 2016. http://nbn-resolving.de/urn:nbn:de:101:1-201705052915.
Full textMohan, Sumod K. "Accuracy and multi-core performance of machine learning algorithms for handwritten character recognition." Connect to this title online, 2009. http://etd.lib.clemson.edu/documents/1252424826/.
Full textMonger, David M. "The human factors aspects of interactive document image description for OCR of handwritten forms." Thesis, University of Essex, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.238747.
Full textBonnici, Elias, and Per Arn. "The impact of Data Augmentation on classification accuracy and training time in Handwritten Character Recognition." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-302538.
Full textDetta kandidatexamensarbete har utförts på Kungliga Tekniska Högskolan med syftet att undersöka ett antal kombinationer av dataaugmenteringar för att ta reda på dess effekt på träffsäkerheten hos en klassificeringsmodell, i denna studie ett Convolutional Neural Network (CNN). Vidare ämnar rapporten att undersöka den tid det tar att träna modellen med de olika dataaugmenteringarna i syfte att identifiera vilka av dem som ger bäst resultat i relation till dess resurskostnad. Resultatet tyder på att när alla augmenteringsmetoder tillämpas samtidigt uppnås den högsta träffsäkerheten hos modellen på ny okänd data. Samtidigt kräver dock den senare tillämpningen allra flest resurser vid träning av modellen, därav längre körningstid. Studien visar på att ett rimligt alternativ till detta är att använda sig utav en kombination augmenteringsmetoder som inkluderar Geometriska och Morfologiska transformationer samt injektioner/extraktioner av Gaussiskt brus då de i denna studie visar sig ge högst träffsäkerhet hos modellen i förhållande till den tid det tar att träna modellen med augmenteringsmetoden.
Prum, Sophea. "On the use of a discriminant approach for handwritten word recognition based on bi-character models." Thesis, La Rochelle, 2013. http://www.theses.fr/2013LAROS418/document.
Full textWith the advent of mobile devices such as tablets and smartphones over the last decades, on-line handwriting recognition has become a very highly demanded service for daily life activities and professional applications. This thesis presents a new approach for on-line handwriting recognition. This approach is based on explicit segmentation/recognition integrated in a two level analysis system: character and bi-character. More specifically, our system segments a handwritten word in a sequence of graphemes to be then used to create a L-levels lattice of graphemes. Each node of the lattice is considered as a character to be submitted to a SVM based Isolated Character Recognizer (ICR). The ICR returns a list of potential character candidates, each of which is associated with an estimated recognition probability. However, each node of the lattice is a combination of various segmented graphemes. As a consequence, a node may contain some ambiguous information that cannot be handled by the ICR at character level analysis. We propose to solve this problem using "bi-character" models based on Logistic Regression, in order to verify the consistency of the information at a higher level of analysis. Finally, the recognition results provided by the ICR and the bi-character models are used in the word decoding stage, whose role is to find the optimal path in the lattice associated to each word in the lexicon. Two methods are presented for word decoding (heuristic search and dynamic programming), and dynamic programming is found to be the most effective
Nederhof, Mark-Jan. "OCR of hand-written transcriptions of hieroglyphic text." Universitätsbibliothek Leipzig, 2016. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-201704.
Full textNoghe, Petr. "Vyhodnocení testových formulářů pomocí OCR." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2013. http://www.nusl.cz/ntk/nusl-219986.
Full textHříbek, David. "Active Learning pro zpracování archivních pramenů." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445535.
Full textChen, Ching-Yi, and 陳慶逸. "Off-line Handwritten Character Recognition." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/78087161407572953101.
Full text淡江大學
電機工程學系研究所
86
In this thesis , we propose a new scheme for off-line recognition of totallyun constrained handwritten characters using SOM/LVQ neural networks and extractio ngfeature vectors by kirsch masks method. In the learning phase, the SOM neura l networks is used to cluster the feature vectors into several classes. In the recognitionstage, the learning results of the neural networks are utilized to identify the inputdata. In order to seek the optium cluster set, the resultin g clusters from the SOMneural networks need to be refined such that the hetero geneity among different targetscan be increased. This is done by introducing a supervised refining algorithm. We have chosen the supervied version of Kohone n''s model known as the Learning vector Quantization to refine selected feature s.The proposed scheme consists of two stages: a feature extraction stage for e xtractingfour-directional local feature vectors with Kirsch masks and one glob al feature vectorform compution the density over small regions of the image, a nd a classification stagefor recognizing characters with SOM neural networks. We first use the Kohonen clusteringnetworks (SOM) to represent the training da ta with minimum quantization error whilemaximizes the within-target homogeneit y. We then use the LVQ to learn the between-targetheterogeneity. It is done by collecting those selected neurons as the inital cluster centers for the LVQ t o learn their class boundaries. This is maximize the probability of correct cl assification. In order to verify the performance of the proposed approach, 630 0 handwritten characters written by 70 persons were collected as the database, 2000characters are used as the training set and the other 4300 characters as the testing set.Some experimental results are conducted to show the feasibilit y of our proposed method.
Ghabrial, Melad Y. "Parallel algorithms for handwritten character recognition." Thesis, 1990. http://spectrum.library.concordia.ca/3859/1/MM97702.pdf.
Full text"Video-based handwritten Chinese character recognition." 2003. http://library.cuhk.edu.hk/record=b6073522.
Full text"June 2003."
Thesis (Ph.D.)--Chinese University of Hong Kong, 2003.
Includes bibliographical references (p. [114]-130).
Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web.
Mode of access: World Wide Web.
Abstracts in English and Chinese.
CAI, YU-SHENG, and 蔡玉生. "Handwritten character recognition by graph matching." Thesis, 1988. http://ndltd.ncl.edu.tw/handle/98437928794972396263.
Full textLI, HUEY JIUAN, and 李惠娟. "Part orientation for handwritten character recognition." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/89931911197348736715.
Full text國立中山大學
應用數學研究所
84
A regional decomposition method and a hierarchical model without consideration of orientation have been proposed to investigate the recognition rates of patterns in [1-4]. In this thesis, new models with orientations at various positions have been proposed to produce a more complete character recognizer, based on the probability of occurrence of the patterns.New formulas are developed to evaluate the recognition rates of non- fix orientation from those of fix orientation. Also, mathematical analysis is made to discover some important properties of character recognition versus the sample shapes, rectangle and square, which may facilitate their recognition and analysis. Moverover, the recognition rates have been analyzed and compared to those obtained from the previous studies in [1-4]. Numerical experiments have also been conducted for 89 patterns of the most frequently used alphanumeric handprints. This study displays a deeper, inherent similarity and distinctness among different patterns and characters, which include part symmetry and part resemblance in possibly different positions. Hence, the results of this thesis should be useful to pattern analysis and recognition, character understanding while missing in writing, gambling, poor scanning, noise or various kinds of distortion.
Hoi, Chu-Chong, and 許主聰. "A Study on Handwritten Character Recognition." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/04065851585956727358.
Full text臺灣大學
資訊工程學研究所
98
There are many applications for handwritten character recognition, such as signature verification, handwritten address recognition, pen-based input method used in PDA etc. In this thesis, we just consider offline character recognition because it is the basic building block of many complicate handwriting recognition system. We compare four techniques for handwritten recognition. They are PCA, LDA, NMF and ICA. The result shows that PCA has the highest accuracy. LDA has the lowest accuracy due to small training data set. The difference of performance between ICA and PCA is small. NMF only need smaller number of basis images within each class when considering class information.
"Perspectives of pattern recognition in handwritten character recognition." Tulane University, 1995.
Find full textacase@tulane.edu
Shu-Ling, Chao, and 趙素玲. "Neural Networks on Handwritten Alphanumeric Character Recognition." Thesis, 1994. http://ndltd.ncl.edu.tw/handle/68960372869420102061.
Full text靜宜大學
管理科學研究所
82
Handwritten Character recognition is a well-know complicated but intersting problem. Although numerous efforts have been made based on traditional computers, they are still suffered by eith- er time-consumed procedure or imperfect recognition rate. In th- esis, a new approach based on neural networks for recognition of unconstrained handwritten alphanumeric characters is proposed and implemented.The hybrid system consists of a kernel subsystem which is based on back- propagation networks for learning and re- cognition, and thinning. Good experimental results show the fea- sibility of the proposed approach. Since the proposed system is powerful and efficient for rec- ognition of handwritten alphanumeric characters, it has very hi- gh potential for real-time systems. In other words, it can be used to automatically read handwritten data in many forms such as tax forms, bills,and so on. On the information management po- int of view, the proposed system has achieved a significant con- tribution on man-power and time saving.
GUO, SHI-CHONG, and 郭世崇. "Handwritten Chinese character recognition via neural network." Thesis, 1992. http://ndltd.ncl.edu.tw/handle/18937680590489760523.
Full textChan, Tung Jung, and 詹東融. "Statistical off line handwritten Chinese character recognition." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/07969728621521247131.
Full text王仁裕. "Handwritten Chinese Character Recognition by Neural Networks." Thesis, 1990. http://ndltd.ncl.edu.tw/handle/56580673553701061169.
Full textWu, Shin-Hao, and 吳欣澔. "Handwritten Alphanumeric Character Recognition with Low Ambiguity." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/98421832847713254465.
Full text國立交通大學
多媒體工程研究所
103
The goal of this thesis is to recognize handwritten character with low ambiguity. In order to solve the problem that handwritten characters has too much stroke order, we use computer to analysis the skeleton of character image and get unify stroke order. So, character similar in shape will have same stroke order. This system is composed of into three steps. In the first steps, we find the major skeleton of the character image based on Morphology, and get thinned character image. In the second step, we trace the thinned character image to get stroke order of the character. In the third step, the Universal hashing is used to establish the index of stroke orders.
Hong-De, Chang, and 張鴻德. "A Study on Handwritten Chinese Character Recognition." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/65194069833122183642.
Full text國立成功大學
電機工程研究所
82
Handwritten Chinese character recognition was once considered to be a very difficult problem and regarded as one of the goals of character recognition research. The proposed system contains four main steps: preprocessing, feature extraction, preclassification, and recognition. First of all, the some operations are performed to obtain a suitable data formate. the number of Chinese characters is very large, preclassification stage is usually needed for this work to reduce the number of candidates in matching process. A new preclassification techniqueal shape coding is introduced in this dissertation. Then in feature extraction step, the Logarithmic Coordinate Transform and two stroke extraction methods, GSSE and KBSE are presented to extract global features and local features respectively. Finally, three neural networks are proposed to resolve individual identification within a group. To show the feasibility of the proposed techniques, some experiments are conducted foron, stroke extraction, and recognition. Experimental results show all them are suitable for constructing an OCR system to recognize vocabulary sets of handwritten Chinese characters.
Hua, Chen Bo, and 陳柏樺. "Handwritten Character Recognition using GA-based CNN." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/69041942101896744315.
Full text國立高雄應用科技大學
電機工程系
99
In this paper, the static simulation method is used for handwritten characters recognition. Since a lot of noise and some non-character traces would occur while scanning image of writting characters, it evoked an inevitable noise-elimination problems in character recognition. This paper simulates the image preprocessing by adding several types of noise, and then filter it out by using conventional and gene-based CNN methods. The results demonstrate the superiority of CNN optimization method. In dealing with salt-pepper noise and Gaussian noise, CNN algorithm results with a better image clearness. Even for the shaking blurred image, its restoration effect is better than that of least square filter. After preprocessing and normalized to the same size, the features of handwritten characters are extracted and put into back-propagate neural network for parameter training. In this stage, an innovative horizontal feature extraction method is adoped besides the traditional ones. It is easier to distinct those mixed-strokes. Meanwhile, the amount of data is much less than that in literatures of other researchers. The main contributions of this thesis are: the simplicity of system algorithm, the effectiveness of noise elimination, and a high recognition rate up to 98%.
ZENG, LING-QI, and 曾令祺. "Handwritten Character Recognition Loading in Hopfield Model." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/9wyjk4.
Full text國立臺灣大學
資訊網路與多媒體研究所
106
Nowadays, handwriting recognition systems has been applied to all aspects of industries and social life. Each feature of a radical or a pattern is represented by a five dimensional vector called Bended-ellipse feature which including the coordinates the direction, the angle, and the lengths information. Once the features are generated, they will find the topological relations between those features. We simply obtain a feature-to-feature (FTF) order by define the “neighbor” of the features. After obtaining bended-ellipse features and FTF order information, we can begin the classification. It is achieved by measuring the compatibility of every radical with the handwriting pattern and standard pattern. The standard pattern which minimizes the dis-similarity is the classification result. The original feature-to-feature adhesion method uses only two similarities for classification. There are some other relations of features can be included for more accurate match. In this paper, we improve the method by making some changes to original rules and adding new similarities among features. We also give some other applications of this method by reuse the calculated similarities.
Dai, Cuang-Liang, and 戴光良. "Handwritten Chinese Character Recognition: A Computational Intelligence Approach." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/68043562794816693045.
Full text國立交通大學
資訊科學學系
83
Generally speaking, the process of pattern recognition can be roughly divided into three stages, preprocessing, feature extraction, pattern matching. In this study, we try to accomplish the goal of hand-written Chinese character recognition. In each processing stage, we proposed new methods to cope with various problems. First, we propose an algorithm to cut characters out of a hand-written or printed document and separate them. It performs very well and has been transferred to manufacturers. Next, in the feature extraction stage, we propose a concept of reference vector. We apply reference vector(s) to transform the feature space from high dimension to low dimension. When the dimensionality is reduced, the time complexity of pattern matching will be decreased. Finally, we apply reference vectors together with other techniques for pattern matching.
Wang, An-Bang, and 王安邦. "Radical-based Handwritten Chinese Character Recognition by tching." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/49275709980791176615.
Full text國立中央大學
資訊及電子工程研究所
84
In this dissertation, intrinsic characteristics of off- line handwritten Chinese characters, such as the manner of writing and representation, the location of radicals embedded in Chinese characters, etc., are investigated and used to solve this difficult problem. At first, a novel stroke extraction method is proposed to represent handwritten Chinese characters as the combination of straight-line strokes. After stroke extraction and size normalization, the features of all strokes embedded in the input character are extracted to perform the matching. Second, two relaxation matching methods (based on Rosenfeld''s average scheme and Peleg'' s product scheme, respectively) are proposed to recognize an unknown input Chinese character which is represented by a set of straight-line strokes. After relaxation matching, validation check and feedback relaxation matching are pursued. At last, two radical-based approaches are proposed to recognize handwritten Chinese characters by identifying radicals embedded in Chinese characters. The first approach is hierarchical partial matching scheme which is based on our proposed relaxation method to accomplish the recognition task of Chinese characters by identifying firstly its constituting radicals and associated appearing types. Another approach is hierarchical radical matching method which includes three modules. They are recursive hierarchical radical extraction, feature extraction, and hierarchical radical matching modules. Experiments are conducted to verify the validity, feasibility, and effectiveness of our proposed stroke extraction, relaxation matching, and radical-based recognition methods.
Wang, Hao-Yu, and 王浩宇. "Handwritten English Character and Digit Recognition Using Kinect." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/48647254928685891611.
Full text國立臺灣大學
電機工程學研究所
102
Human-computer interaction (HCI) has been a popular research field recently. Hand gesture recognition is an important part of HCI that provides a natural way of communication. Handwritten recognition is a part of hand gesture recognition that provides an alternative method to input characters. In this thesis, we propose a handwritten recognition system to input English characters and digits without using traditional input devices such as keyboards and mice. Accuracy and real time processing are highly desired in the handwritten digit and character recognition of HCI. In order to improve the accuracy, we suggest a new feature extracting algorithm which contains the temporal and spatial information of hand writing paths. Furthermore, we use support vector machines and random forests to carry out feature classification. Experimental results show that the proposed method has a very high accuracy in the handwritten digit and character recognition in real time.
Cho, Cheng-Ming, and 卓正民. "Fuzzy Rule-Based Handwritten Chinese Character Recognition System." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/15293821733202088575.
Full text大同大學
電機工程研究所
85
The goal of this thesis is to develop a handwritten Chinese character recognition system based on the fuzzy logic theory. Because of the fact that fuzzy theory is found to be naturally effective for any human-like cognition systems and can deal with noisy and imprecise information effectively, it can be applied to pattern or handwritten character systems with vagueness and uncertainty. The architecture of the developed system is simpler than traditional methods and is robust against vagueness. At first, we introduce how to describe the characteristics of characters using fuzzy variables and how to extract the useful fuzzy features. Then we build the fuzzy rules and finally the handwritten Chinese character recognition system is constructed completely. Simulations demonstrate that the proposed system is effective, robust and has high recogniton rate.
Chen, Young-Sheng, and 陳永聖. "Handwritten Chinese Character Recognition by Hierarchical Neural Networks." Thesis, 1994. http://ndltd.ncl.edu.tw/handle/92567855975129997251.
Full text國立交通大學
資訊科學學系
82
A hierarchical neural network system for recognition of handwritten Chinese characters is proposed. The system is composed of two subsystems: the preclassification subsystem and the detailed matching subsystem.The pre- classification subsystem includes multiple Kohonen networks which perform a modified winner-take-all learning algorithm. At first, a character image is normalized. A thinning module converts the normalized image into a skeleton. The probability with which each image point of the skeleton belongs to a directional stroke plane is computed for preclassification. The detailed matching subsystem is composed of several modules ,namely, the line separation module, the stroke prematching module, the iterative matching module, and the similarity measuring module. A voting approach to decision making using five reference character sets is employed. A method for automatic selection of reference character sets is also proposed. 1,000 character classes and 12 characters randomly chosen from each class were used as training samples. The totally 12,000 characters are classified into 130 clusters. The preclassification subsystem was tested by 10,000 other characters to yield a 94% average rate of correct classifications. Detailed matching subsystems for testing three clusters of 143 characters were built and a 92.2% average recognition rate has been achieved.
Yang, Chung-Hsien, and 楊宗憲. "Recognition of Handwritten Character with Any Rotation Angle." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/93542530511725798862.
Full text國立成功大學
資訊工程研究所
87
This thesis proposes a feature extraction approach to solve the problem of handwritten character recognition with any rotation angle. The feature vectors which are extracted by the method are rotation invariant. With this approach, two systems of handwritten character recognition have been implemented. One is based on hidden Markov models (HMMs). The other is based on neural networks (NNs). Three kinds of experiments for each system have been done. These experiments are recognition of handwritten Chinese characters, digit and English alphabet. The recognition rates of HMMs are 54%, 68% and 61% and recognition rates of NNs are 59%, 74% and 67% respectively.
Cheng, Rei-Heng, and 鄭瑞��. "Handwritten Chinese character recognition based on structural relations of character strokes." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/10443923778682920845.
Full text國立交通大學
資訊工程研究所
83
This dissertation is concerned with handwritten Chinese character recognition problem. In the first part, we propose a problem reduction technique to reduce the radical recognition problem to a subproblem of recognizing stable stroke substructure(s) in the radical. Furthermore, the stroke substructure recognition problem can be further reduced to a subproblem of identifying a salient stroke in each stroke substructure. The actual recognition process will work in the reversed order, i.e., from salient stroke toward radical. In this problem reduction formulation, each subproblem deals with a simpler but stabler stroke substructure than its original problem, so we can find an easier and more reliable solution to the subproblem. In the second part, we proposed a preclassification technique for handprinted Chinese characters. By using the stable stroke substructures contained in a character as features, we can get a good classification result. According to the radical recognition strategy mentioned above, the stroke substructures can be expanded to a radical under the guidance of knowledge base. There would be no overhead caused by this proposed preclassification stage. Since there may be some incorrect stroke features, including missing or incorrect stroke intersection and connection relationships caused by handwriting variance. These incorrect features will cause the stroke substructures and radicals to be incorrectly recognized. In the third part, we propose a graph-based approach to deal with these variation problems. By matching subgraphs of a character with graphs of predefined stroke substructures and radicals, we can find all possible stroke substructures and radicals in a character. Examples are included to illustrate the ideas presented above. The performance of the algorithms is also evaluated, and comparisons with some other existing methods are made.
CHEN, YUAN-ZHONG, and 陳元中. "Performance analysis of character recognition systems via handwritten chinese character generator." Thesis, 1992. http://ndltd.ncl.edu.tw/handle/25970235394443528978.
Full textZENG, MING-SHENG, and 曾明聖. "An efficient hardware approach for handwritten alphanumerical character recognition." Thesis, 1988. http://ndltd.ncl.edu.tw/handle/13015000680741927476.
Full text