An Improved Pre-classification Method for Offline Handwritten Chinese Character Using Four Corner Feature

Size: px
Start display at page:

Download "An Improved Pre-classification Method for Offline Handwritten Chinese Character Using Four Corner Feature"

Transcription

1 ISBN (Print), (CD-ROM) Proceedings of the International Symposium on Intelligent Information Systems and Applications (IISA 09) Qingdao, P. R. China, Oct , 2009, pp An Improved Pre-classification Method for Offline Handwritten Chinese Character Using Four Corner Feature Xin Zhang 1, 2, XueDong Tian 1, 2, and Fang Yang 1, 2 1 College of Mathematics and Computer Science, Hebei University, Baoding Hebei, China zhangxin5313@yahoo.com.cn 2 Hebei key laboratory of Machine Learning and Computational Intelligence, Hehei University,Baoding Hebei, China zhangxin5313@yahoo.com.cn Abstract Pre-classification can effectively improve the performance of handwritten Chinese character recognition. This paper presents a method that uses four corner feature for pre-classification of handwritten Chinese characters. Considering writing variations, we define a set of basic stroke structures and match them with the structures in four corner regions of character image. The matching result will be four feature codes that can be used for character pre-classification. The experiment on 500 Chinese characters from GB2312 shows that our approach can achieve a satisfied result in pre-classification for handwritten Chinese characters. Index Terms Handwritten Chinese character recognition, Pre-classification, Structural feature I. INTRODUCTION Chinese characters amount to as huge as about 10 million words or so. The number of commonly used characters specified in GB2312 is For such big scale of characters, direct recognizing will greatly reduce the recognition speed. Narrow the scope of Chinese characters to be recognized and reduce the complexity of recognition by adding multi-level pre-classification is an effective way to improve system efficiency. Ref. [1] presents the sub-stroke center model in pre-classification, extracting four typical strokes of Chinese characters, the coordinate of stroke center and the number of every same kind of stroke are used as the features of preclassification. Ref. [2] defines a set of structures that are composed of typical strokes and relationships among strokes, and these structures are used to classify characters. It proves that structural feature is feasible and effective in pre-classification of handwritten Chinese character. Because of the complex structures of Chinese characters, different writing habits or interference in the writing process will lead to deformation of the characters and to form different writing styles, which makes the ways of extraction of overall structural features more complicated in the off-line handwritten Chinese character recognition. The outer structure of Chinese characters not only contains abundant information, but also can be kept relatively stable and integrate even when the overall structure of the Chinese character is changed a lot. Ref. [3] mentioned a method combining structural and statistical 2009 ACADEMY PUBLISHER AP-PROC-CS-09CN features for recognition. Fuzzy set theory is used in features extraction while SEART neural network model is used as a classifier to minish the interference from writing variations of Chinese characters. Ref. [4] proposed a simple pre-classification scheme based on four corner coding: stroke features in four corner regions are extracted in order to create several groups of feature code and the codes are the basis of pre-classification. In case of mis-preclassification, a feedback mechanism will generate a new set of feature codes to adapt writing variations. On the basis of Ref. [4], this paper improves the selection and extraction of feature primitive and presents a pre-classification method for off-line handwritten Chinese character using four corner features. Select several simple structures that are not susceptible to writing variations as feature primitives and each primitive corresponds to a decimal value. Extract the properties of the stroke within four corner regions of character and match the properties with feature primitives. The matching result is a 4-D feature code, and that is the basis of pre-classification. II. FOUR CORNER FEATURE Ref. [4] defines 9 typical stroke primitives and matches them with the strokes within specific regions of Chinese character, using the matching result as the feature of preclassification. These stroke primitives include simple stroke primitives and composite stroke primitives, which are very similar with traditional four corner code. This paper continue the idea of Ref. [4]: taking the feature primitives of the traditional four corner code as a basis, considering the handwritten Chinese character structures and image processing features, so as to further improve the stroke primitives in pre-classification. Extract the stroke primitives mentioned in Ref. [4] and traditional four corner code, problems shows as follow: Figure 1. Length divergence of simple stroke primitive.

2 Figure 2. Separate composite stroke primitive. 1) The difference among simple strokes is susceptible to writing variations, and that would result in misrecognition among the primitives. As shown in Fig. 1, the length divergence between the first strokes on the left of two characters is too large that traditional four corner code method can not distinguish it between left falling stroke and dot. 2) The components in composite strokes are independent with each other and also difficult to be recognized as a unity. When the first component is found, the left components are always lost or found by error. In Fig. 2, the composite stroke on top of the character is one of composite primitive as a whole in traditional four corner code, but the three components are not only separate but also far away from each other. That makes the extraction and recognition fallible. Through the observation and study of a large number of handwritten Chinese character images, it can be found that the kinds of writing variations can not be counted out, but there are three stroke structural features that are much more stable than others: inflexion, crossing and direction. On the basis of primary Chinese character stroke, traditional four corner code and stroke primitive in Ref.[4], abandoning composite stroke primitive and the discrimination of stroke length, taking inflexion, crossing and direction as key basis for criteria, there are 7 stroke primitives defined that are typical and easy to extract, as shown in Table I. Chinese character strokes consist of stroke dots. Define stroke dots in four kinds: 1) Terminal: starting point and end point of the stroke; 2) Intersection point: including forkpoint and crosspoint; 3) Inflexion point; 4) Transition point: the connect point among the three stroke points above. Steps of feature extraction algorithm are shown as follows: 1) Scan the character image by 225,315,135,45 from four corners to the center of the image as shown in Fig. 6. Stop scanning when the first black pixel is found, and the stroke which the black pixel belongs to is the feature stroke of the character in this corner. Figure 3. Character image after pre-processing. Figure 4. Example of crosspoint. TABLE I. NEW FEATURE PRIMITIVES Code Feature primitive Description Figure 5. Example of forkpoint. 0 Horizontal 1 Vertical 2 Left-falling 3 Right-falling 4 Crossing 5 Two crossings Figure 6. Determination of feature stroke. 6 Inflexion III. FOUR CORNER CODE EXTRACTION A. Extraction algorithm of four corner feature Thresholding and thinning should be done firstly as pre-processing to character images before feature extraction. Figure 7. 8-neighborhood template. 395

3 2) Track and record feature stroke with 8-neighborhood template in Fig. 7. When the first black pixel is found and feature stroke is determined, the search of the terminal should begin from the black pixel. P in template is active pixel point, P[0]-P[7] stand for pixel points in correspondence positions of the template, sum is the total number of the black pixel from P[0] to P[7]. Tracking rules are as follows: Sum=1, P is the terminal of feature stroke. If P is the first terminal found, the recording of the stroke dots track begins. If P is the second terminal, it means that the feature stroke is completely found. Sum=2, P is a transitional point of feature stroke. Record this pixel and move the center of template to the other black pixels that have not been recorded. Sum=3, P is a forkpoint of the feature stroke. Choose the next proper point and move the center of template to it. Sum=4, P is a crosspoint of feature stroke. Add 1 to the total number of the crosspoints, and choose the next proper point, moving the center of template to it. 3) When the first terminal of feature stroke is found, repeat step 2 and begin to record stroke tracking. 4) If both of the two terminals of feature stroke are found, the tracking and recording of feature stroke should be finished and the analysis of feature stroke properties begins. In this algorithm, the judgment of the next point in forkpoint and crosspoint determines whether we can correctly capture the strokes orientation. It plays a crucial role in feature stroke extraction. There are four branches for every crosspoint, but only two of them belong to feature stroke. The research on the structure of Chinese characters finds that the angle between two branches that belong to the same feature stroke is probably 180. Steps of the judgment of the next point in crosspoint are shown as follows: 1) Set P as the crosspoint, P 0,P 1,P 2 and P 3 are new points that are all 5 points away from P in each of the four branches (as shown in Fig. 8). P 0 is in the branch that has been recorded. 2) D D D 2DD x 0 x0 P0PPx arccos( ), x 1,2,3 (1) 0 x Where D0 Distance( P, P0), DX Distance( P, PX), D0X Distance( P0, PX). 3) Compare the three angles above and choose the one most proximal to 180 for the direction of next point. Record this point and add 1 to the total number of the crosspoint. Figure 8. The judgement of the next point in forkpoint and crosspoint. Forkpoint exists mainly in the area that two strokes osculate but not intersect (as shown in Fig. 5).One of the two strokes is feature stroke while the other one is useless. There are two situations about forkpoint in our algorithm: First, the forkpoint is a terminal of the feature stroke, and the other two branches belong to another stroke; Second, the forkpoint is a transitional point of the feature stroke, two of the three branches constitute feature stroke. As the character in Fig. 5, when the feature stroke is rightfalling in bottom right corner, the forkpoint is a terminal of feature stroke; when the feature stroke is lefttfalling in bottom left corner, the forkpoint is a transitional point. The judgment of the next point in fork-point is similar with the judgment in crosspoint. While besides P 0 PP 1 and P 0 PP 2, P 1 PP 2 should be taken into account, too, as shown in Fig. 8. Compare the three angles with 180, if P 0 PP 1 or P 0 PP 2 is the nearest one, the correspondence branch will be the direction of next point. But if P 1 PP 2 is the nearest one to 180, it means that the fokepoint is a terminal of feature stroke. The fokepoint should be recorded and the tracking of feature stroke should be terminated. By the feature stroke extraction described above, we can get a point coordinate series of feature stroke and the total number of the crosspoints. The last basis for the matching of feature primitive is inflexion. Because the point coordinate of inflexion is not needed, the existence of inflexion will be measured simply in the process of feature primitive matching. B. Feature primitive matching The matching of feature primitive matching is based on three bases: inflexion, crossing and direction. The total number of crossing is known by feature stroke extraction, inflexion and direction will be as follows: Set the first and the last point of feature stroke as A and B. Distance( AB, ) a (2) LS where L s is the length of the feature stroke. If a is less than a threshold, this stroke is considered to have inflexion. The threshold is given by experience. The direction of the feature stroke is judged by angle. Set the first and the last point from the point coordinate series of feature stroke as A(i,j) and B(i,j). a is the angle of the feature stroke. a arccos( Bj Aj ) 2 2 ( Bj Aj) ( Bi Ai) Thus the property set that consists of inflexion, crossing and direction is completed. Match the feature strokes with stroke primitives by the property set. The process of matching is described below: switch(total number of the crossings) { case 0: if(inflexion) feature code=6; (3) 396

4 } else Judge by angle threshold feature code =0,1,2,3; case 1: feature code =4; default : feature code =5; Stroke primitives The angle threshold TABLE II. THE ANGLE THRESHOLD OF STROKE PRIMITIVES IV. EXPERIMENT A. The Process of the Experiment The experiment is carried out by choosing 500 handwritten Chinese characters from GB2312 randomly. Extract the feature stroke from four corner region of the Chinese characters by using the extraction algorithm, and match them with stroke primitives described in Section II. The threshold of inflexion is 0.85, the angle threshold of four simple stroke primitives are shown in Table II. To every Chinese character, we have a 4-D feature code that represents the matching result of the feature primitive described in Section II, and the feature stroke within four corners regions of Chinese character: top left corner, bottom left corner, top right corner and bottom right corner. The four feature strokes of the character in Fig. 9 are dot, dot, intersection of horizontal and leftfalling, and right-falling, they are matched with the feature primitives of right-falling, left-falling, intersection and right-falling, so the feature code of this character is Based on the feature code, this character can be classified in the class with characters that have the same feature code as shown in Fig. 9. B. Experimental results Experiments were performed on 500 handwritten Chinese characters from GB2312, the result of preclassification is shown in Fig. 10. It can be seen from Fig. 10 that the characters are evenly distributed into every class after pre-classification, which proves that the selection of feature primitives is sensible. Though the characters in one class have the same structure in all of the four corners, the similarity of whole structure is very low, and the internal structures also have big divergence (as shown in Table III), that makes the characters in one class can be distinguished accurately by statistical feature and structural feature. On the other hand, as a result of writing variations, every Chinese character will not correspond to one feature code, in another words, a character may not only exist in one class. In Fig. 11, the left top corner region of character shows two different structural relationships in two samples, which will affect the result of pre-classification. Through the experiment of a large numbers of handwritten Chinese character images, we can found that the changes of structural relationship generally exist, but the types of changes are very limited. So the changes of structural relationships break the uniqueness of classification, but it can fit writing variations better and improve the accuracy of pre-classification. Figure 9. Characters in one class. Figure 10. The result of pre-classification. Figure 11. Structural difference in top left corner. TABLE III. EXAMPLE OF PRE-CLASSIFICATION Feature code Characters in the class 1123 示, 栗, 不 2444 升, 华 2626 勿, 用, 豹 V. CONCLUSION In this paper, we propose a improved pre-classification method. Feature primitives are selected by the rules of being steady and easy-extracted. A simple algorithm is designed to extract the feature stroke in four corner regions of the character and to match it with the selected feature primitives, in order to get a 4-D feature code as the basis of pre-classification. The experiment proves that the selection of feature primitives is sensible. Feature extraction algorithm is simple and the experiment gets good results in pre-classification. That one character corresponds to multi-code also promotes the reorganization flexibility of handwritten Chinese characters inflection. But, because of the absence of feedback mechanism, if there are mistakes in the result of pre-classification, the mistakes can not be corrected in 397

5 process of recognition, which will lead to recognition errors. This will be the focus of our research in the future. ACKNOWLEDGMENT This work is supported by National Natural Science Foundation of China under Grant No The Key Scientific Research Project of Hebei Education Department of China under Grant No. ZH REFERENCES [1] Xia-Bi Liu and Yun-De Jia, Chinese Character Structure Models for Handwritten Chinese Character Recognition, Journal of Beijing Institute of Technology, vol. 23, no.3, pp November [2] Rei-Heng Cheng, Chi-Wei Lee, and Zen Chen, Preclassification of handwritten Chinese character based on basic stroke substructures, Pattern Recognition Letters, pp , [3] Hahn-Ming Lee and Chug-Chieh Sheu. A Handwritten Chinese Characters Recognition Method Based on Primitive and Fuzzy Features via SEART Neural Net Model.Systems, Man and Cybernetics, Intelligent Systems for the 21st Century., IEEE International Conference on, Canada, vol.2, pp , October [4] Yiu-Man Tham and Tong Lee. Four Corner Code Based Pre-classification Scheme For Chinese Character Recognition, International Symposium on Speech, Image Processing and Neural Networks, Hong Kong, vol.1, pp , April [5] Jian-Ping Zhao and Dan Che. Stroke Extraction Algorithm for Handwriting Chinese Characters, Journal of Changchun University of Science and Technology, vol.28, no.4, pp.66-70, [6] You-Bin Chen, Xiao-Qing Ding, and You-Shou Wu. A New Feature Extraction Method for Off-line Handwritten Chinese Character Recognition, Signal Processing, vol.14, no.2, pp , [7] Xin-Qiao Lu et al., A Segment Extraction Algorithm Based on Polygonal Approximation for On-Line Chinese Character Recognition, Frontier of Computer Science and Technology, FCST, 2008 Japan-China Joint Workshop on, Japan, pp ,

result, it is very important to design a simulation system for dynamic laser scanning

result, it is very important to design a simulation system for dynamic laser scanning 3rd International Conference on Multimedia Technology(ICMT 2013) Accurate and Fast Simulation of Laser Scanning Imaging Luyao Zhou 1 and Huimin Ma Abstract. In order to design a more accurate simulation

More information

Hidden Loop Recovery for Handwriting Recognition

Hidden Loop Recovery for Handwriting Recognition Hidden Loop Recovery for Handwriting Recognition David Doermann Institute of Advanced Computer Studies, University of Maryland, College Park, USA E-mail: doermann@cfar.umd.edu Nathan Intrator School of

More information

A QR code identification technology in package auto-sorting system

A QR code identification technology in package auto-sorting system Modern Physics Letters B Vol. 31, Nos. 19 21 (2017) 1740035 (5 pages) c World Scientific Publishing Company DOI: 10.1142/S0217984917400358 A QR code identification technology in package auto-sorting system

More information

Research on QR Code Image Pre-processing Algorithm under Complex Background

Research on QR Code Image Pre-processing Algorithm under Complex Background Scientific Journal of Information Engineering May 207, Volume 7, Issue, PP.-7 Research on QR Code Image Pre-processing Algorithm under Complex Background Lei Liu, Lin-li Zhou, Huifang Bao. Institute of

More information

Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian

Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2016) Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian Hebei Engineering and

More information

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical esearch, 015, 7(3):175-179 esearch Article ISSN : 0975-7384 CODEN(USA) : JCPC5 Thread image processing technology research based on

More information

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes 2009 10th International Conference on Document Analysis and Recognition Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes Alireza Alaei

More information

Qingdao, , China. China. Keywords: Deep sea Ultrahigh pressure, Water sound acquisition, LabVIEW, NI PXle hardware.

Qingdao, , China. China. Keywords: Deep sea Ultrahigh pressure, Water sound acquisition, LabVIEW, NI PXle hardware. 2016 International Conference on Control and Automation (ICCA 2016) ISBN: 978-1-60595-329-8 Research and Design on Water Sound Acquisition System of Deep Sea Ultrahigh Pressure Environment Gang TONG 1,

More information

Character Recognition

Character Recognition Character Recognition 5.1 INTRODUCTION Recognition is one of the important steps in image processing. There are different methods such as Histogram method, Hough transformation, Neural computing approaches

More information

Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques

Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques 1 Lohitha B.J, 2 Y.C Kiran 1 M.Tech. Student Dept. of ISE, Dayananda Sagar College

More information

An Integrated Face Recognition Algorithm Based on Wavelet Subspace

An Integrated Face Recognition Algorithm Based on Wavelet Subspace , pp.20-25 http://dx.doi.org/0.4257/astl.204.48.20 An Integrated Face Recognition Algorithm Based on Wavelet Subspace Wenhui Li, Ning Ma, Zhiyan Wang College of computer science and technology, Jilin University,

More information

A Kind of Fast Image Edge Detection Algorithm Based on Dynamic Threshold Value

A Kind of Fast Image Edge Detection Algorithm Based on Dynamic Threshold Value Sensors & Transducers 13 by IFSA http://www.sensorsportal.com A Kind of Fast Image Edge Detection Algorithm Based on Dynamic Threshold Value Jiaiao He, Liya Hou, Weiyi Zhang School of Mechanical Engineering,

More information

A reversible data hiding based on adaptive prediction technique and histogram shifting

A reversible data hiding based on adaptive prediction technique and histogram shifting A reversible data hiding based on adaptive prediction technique and histogram shifting Rui Liu, Rongrong Ni, Yao Zhao Institute of Information Science Beijing Jiaotong University E-mail: rrni@bjtu.edu.cn

More information

Multi-Step Segmentation Method Based on Adaptive Thresholds for Chinese Calligraphy Characters

Multi-Step Segmentation Method Based on Adaptive Thresholds for Chinese Calligraphy Characters Journal of Information Hiding and Multimedia Signal Processing c 2018 ISSN 2073-4212 Ubiquitous International Volume 9, Number 2, March 2018 Multi-Step Segmentation Method Based on Adaptive Thresholds

More information

An Adaptive Threshold LBP Algorithm for Face Recognition

An Adaptive Threshold LBP Algorithm for Face Recognition An Adaptive Threshold LBP Algorithm for Face Recognition Xiaoping Jiang 1, Chuyu Guo 1,*, Hua Zhang 1, and Chenghua Li 1 1 College of Electronics and Information Engineering, Hubei Key Laboratory of Intelligent

More information

Investigation of Algorithms for Calculating Target Region Area

Investigation of Algorithms for Calculating Target Region Area International Journal of Intelligent Engineering & Systems http://www.inass.org/ Investigation of Algorithms for Calculating Target Region Area Yueqiu Jiang 1, Hongwei Gao 2, Lei Jin 1 1 Communication

More information

A 3D Point Cloud Registration Algorithm based on Feature Points

A 3D Point Cloud Registration Algorithm based on Feature Points International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015) A 3D Point Cloud Registration Algorithm based on Feature Points Yi Ren 1, 2, a, Fucai Zhou 1, b 1 School

More information

STUDYING OF CLASSIFYING CHINESE SMS MESSAGES

STUDYING OF CLASSIFYING CHINESE SMS MESSAGES STUDYING OF CLASSIFYING CHINESE SMS MESSAGES BASED ON BAYESIAN CLASSIFICATION 1 LI FENG, 2 LI JIGANG 1,2 Computer Science Department, DongHua University, Shanghai, China E-mail: 1 Lifeng@dhu.edu.cn, 2

More information

A 3D MODEL RETRIEVAL ALGORITHM BASED ON BP- BAGGING

A 3D MODEL RETRIEVAL ALGORITHM BASED ON BP- BAGGING A 3D MODEL RETRIEVAL ALGORITHM BASED ON BP- BAGGING 1 ZUOJUN LIU, 2 LIHONG LI 1 Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai an, Jiangsu, China 2 Faculty of Foreign Language,

More information

High Capacity Reversible Watermarking Scheme for 2D Vector Maps

High Capacity Reversible Watermarking Scheme for 2D Vector Maps Scheme for 2D Vector Maps 1 Information Management Department, China National Petroleum Corporation, Beijing, 100007, China E-mail: jxw@petrochina.com.cn Mei Feng Research Institute of Petroleum Exploration

More information

A Hand Gesture Recognition Method Based on Multi-Feature Fusion and Template Matching

A Hand Gesture Recognition Method Based on Multi-Feature Fusion and Template Matching Available online at www.sciencedirect.com Procedia Engineering 9 (01) 1678 1684 01 International Workshop on Information and Electronics Engineering (IWIEE) A Hand Gesture Recognition Method Based on Multi-Feature

More information

A Real-time Detection for Traffic Surveillance Video Shaking

A Real-time Detection for Traffic Surveillance Video Shaking International Conference on Mechatronics, Control and Electronic Engineering (MCE 201) A Real-time Detection for Traffic Surveillance Video Shaking Yaoyao Niu Zhenkuan Pan e-mail: 11629830@163.com e-mail:

More information

Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition

Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition 2009 0th International Conference on Document Analysis and Recognition Explicit fuzzy modeling of and positioning for handwritten Chinese character recognition Adrien Delaye - Eric Anquetil - Sébastien

More information

Convolution Neural Networks for Chinese Handwriting Recognition

Convolution Neural Networks for Chinese Handwriting Recognition Convolution Neural Networks for Chinese Handwriting Recognition Xu Chen Stanford University 450 Serra Mall, Stanford, CA 94305 xchen91@stanford.edu Abstract Convolutional neural networks have been proven

More information

An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng 1, WU Wei 2

An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng 1, WU Wei 2 International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 015) An algorithm of lips secondary positioning and feature extraction based on YCbCr color space SHEN Xian-geng

More information

Detecting Printed and Handwritten Partial Copies of Line Drawings Embedded in Complex Backgrounds

Detecting Printed and Handwritten Partial Copies of Line Drawings Embedded in Complex Backgrounds 9 1th International Conference on Document Analysis and Recognition Detecting Printed and Handwritten Partial Copies of Line Drawings Embedded in Complex Backgrounds Weihan Sun, Koichi Kise Graduate School

More information

Threshold Visual Cryptography Scheme for Color Images with No Pixel Expansion

Threshold Visual Cryptography Scheme for Color Images with No Pixel Expansion ISBN 978-952-5726-07-7 (Print), 978-952-5726-08-4 (CD-ROM) Proceedings of the Second Symposium International Computer Science and Computational Technology(ISCSCT 09) Huangshan, P. R. China, 26-28,Dec.

More information

Classification of Printed Chinese Characters by Using Neural Network

Classification of Printed Chinese Characters by Using Neural Network Classification of Printed Chinese Characters by Using Neural Network ATTAULLAH KHAWAJA Ph.D. Student, Department of Electronics engineering, Beijing Institute of Technology, 100081 Beijing, P.R.CHINA ABDUL

More information

HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation

HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation 009 10th International Conference on Document Analysis and Recognition HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation Yaregal Assabie and Josef Bigun School of Information Science,

More information

Handwritten Devanagari Character Recognition Model Using Neural Network

Handwritten Devanagari Character Recognition Model Using Neural Network Handwritten Devanagari Character Recognition Model Using Neural Network Gaurav Jaiswal M.Sc. (Computer Science) Department of Computer Science Banaras Hindu University, Varanasi. India gauravjais88@gmail.com

More information

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 17 (2014), pp. 1839-1845 International Research Publications House http://www. irphouse.com Recognition of

More information

12/12 A Chinese Words Detection Method in Camera Based Images Qingmin Chen, Yi Zhou, Kai Chen, Li Song, Xiaokang Yang Institute of Image Communication

12/12 A Chinese Words Detection Method in Camera Based Images Qingmin Chen, Yi Zhou, Kai Chen, Li Song, Xiaokang Yang Institute of Image Communication A Chinese Words Detection Method in Camera Based Images Qingmin Chen, Yi Zhou, Kai Chen, Li Song, Xiaokang Yang Institute of Image Communication and Information Processing, Shanghai Key Laboratory Shanghai

More information

Robust line segmentation for handwritten documents

Robust line segmentation for handwritten documents Robust line segmentation for handwritten documents Kamal Kuzhinjedathu, Harish Srinivasan and Sargur Srihari Center of Excellence for Document Analysis and Recognition (CEDAR) University at Buffalo, State

More information

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory Computers and Mathematics with Applications 61 (2011) 2101 2106 Contents lists available at ScienceDirect Computers and Mathematics with Applications journal homepage: www.elsevier.com/locate/camwa An

More information

Graph Matching Iris Image Blocks with Local Binary Pattern

Graph Matching Iris Image Blocks with Local Binary Pattern Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of

More information

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation K. Roy, U. Pal and B. B. Chaudhuri CVPR Unit; Indian Statistical Institute, Kolkata-108; India umapada@isical.ac.in

More information

Restricted Nearest Feature Line with Ellipse for Face Recognition

Restricted Nearest Feature Line with Ellipse for Face Recognition Journal of Information Hiding and Multimedia Signal Processing c 2012 ISSN 2073-4212 Ubiquitous International Volume 3, Number 3, July 2012 Restricted Nearest Feature Line with Ellipse for Face Recognition

More information

Facial expression recognition based on two-step feature histogram optimization Ling Gana, Sisi Sib

Facial expression recognition based on two-step feature histogram optimization Ling Gana, Sisi Sib 3rd International Conference on Materials Engineering, Manufacturing Technology and Control (ICMEMTC 201) Facial expression recognition based on two-step feature histogram optimization Ling Gana, Sisi

More information

An Algorithm for Calculating Objects Shape Features in Binary Images

An Algorithm for Calculating Objects Shape Features in Binary Images 2017 2 nd International Conference on Artificial Intelligence and Engineering Applications (AIEA 2017) ISBN: 978-1-60595-485-1 An Algorithm for Calculating Objects Shape Features in Binary Images LIFENG

More information

Time Stamp Detection and Recognition in Video Frames

Time Stamp Detection and Recognition in Video Frames Time Stamp Detection and Recognition in Video Frames Nongluk Covavisaruch and Chetsada Saengpanit Department of Computer Engineering, Chulalongkorn University, Bangkok 10330, Thailand E-mail: nongluk.c@chula.ac.th

More information

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network International Journal of Computer Science & Communication Vol. 1, No. 1, January-June 2010, pp. 91-95 Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network Raghuraj

More information

Design and Implementation of an Anycast Efficient QoS Routing on OSPFv3

Design and Implementation of an Anycast Efficient QoS Routing on OSPFv3 Design and Implementation of an Anycast Efficient QoS Routing on OSPFv3 Han Zhi-nan Yan Wei Zhang Li Wang Yue Computer Network Laboratory Department of Computer Science & Technology, Peking University

More information

Research of Traffic Flow Based on SVM Method. Deng-hong YIN, Jian WANG and Bo LI *

Research of Traffic Flow Based on SVM Method. Deng-hong YIN, Jian WANG and Bo LI * 2017 2nd International onference on Artificial Intelligence: Techniques and Applications (AITA 2017) ISBN: 978-1-60595-491-2 Research of Traffic Flow Based on SVM Method Deng-hong YIN, Jian WANG and Bo

More information

Real-time Aerial Targets Detection Algorithm Based Background Subtraction

Real-time Aerial Targets Detection Algorithm Based Background Subtraction Real-time Aerial Targets Detection Algorithm Based Background Subtraction Mao Zheng, Zhen-Rong Wu, Saidsho Bakhdavlatov, Jing-Song Qu, Hong-Yan Li, Jian -Jian Yuan (College of Electronic and control Engineering,

More information

Performance Degradation Assessment and Fault Diagnosis of Bearing Based on EMD and PCA-SOM

Performance Degradation Assessment and Fault Diagnosis of Bearing Based on EMD and PCA-SOM Performance Degradation Assessment and Fault Diagnosis of Bearing Based on EMD and PCA-SOM Lu Chen and Yuan Hang PERFORMANCE DEGRADATION ASSESSMENT AND FAULT DIAGNOSIS OF BEARING BASED ON EMD AND PCA-SOM.

More information

A Novel Field-source Reverse Transform for Image Structure Representation and Analysis

A Novel Field-source Reverse Transform for Image Structure Representation and Analysis A Novel Field-source Reverse Transform for Image Structure Representation and Analysis X. D. ZHUANG 1,2 and N. E. MASTORAKIS 1,3 1. WSEAS Headquarters, Agiou Ioannou Theologou 17-23, 15773, Zografou, Athens,

More information

The Study of Intelligent Scheduling Algorithm in the Vehicle ECU based on CAN Bus

The Study of Intelligent Scheduling Algorithm in the Vehicle ECU based on CAN Bus Send Orders for Reprints to reprints@benthamscience.ae The Open Cybernetics & Systemics Journal, 2015, 9, 1461-1465 1461 Open Access The Study of Intelligent Scheduling Algorithm in the Vehicle ECU based

More information

A Finite State Mobile Agent Computation Model

A Finite State Mobile Agent Computation Model A Finite State Mobile Agent Computation Model Yong Liu, Congfu Xu, Zhaohui Wu, Weidong Chen, and Yunhe Pan College of Computer Science, Zhejiang University Hangzhou 310027, PR China Abstract In this paper,

More information

SOME stereo image-matching methods require a user-selected

SOME stereo image-matching methods require a user-selected IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 3, NO. 2, APRIL 2006 207 Seed Point Selection Method for Triangle Constrained Image Matching Propagation Qing Zhu, Bo Wu, and Zhi-Xiang Xu Abstract In order

More information

A method of three-dimensional subdivision of arbitrary polyhedron by. using pyramids

A method of three-dimensional subdivision of arbitrary polyhedron by. using pyramids 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016) A method of three-dimensional subdivision of arbitrary polyhedron by using pyramids LIU Ji-bo1,a*, Wang Zhi-hong1,b,

More information

Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations

Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations Signature Recognition by Pixel Variance Analysis Using Multiple Morphological Dilations H B Kekre 1, Department of Computer Engineering, V A Bharadi 2, Department of Electronics and Telecommunication**

More information

Skeleton-based Template Retrieval for Virtual Maize Modeling

Skeleton-based Template Retrieval for Virtual Maize Modeling Journal of Computational Information Systems6:5(2010) 1577-1582 Available at http://www.jofcis.com Skeleton-based Template Retrieval for Virtual Maize Modeling Boxiang XIAO 1,2, Chunjiang ZHAO 1,2,, Xinyu

More information

Mubug: a mobile service for rapid bug tracking

Mubug: a mobile service for rapid bug tracking . MOO PAPER. SCIENCE CHINA Information Sciences January 2016, Vol. 59 013101:1 013101:5 doi: 10.1007/s11432-015-5506-4 Mubug: a mobile service for rapid bug tracking Yang FENG, Qin LIU *,MengyuDOU,JiaLIU&ZhenyuCHEN

More information

Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks

Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks Ritika Luthra Research Scholar Chandigarh University Gulshan Goyal Associate Professor Chandigarh University ABSTRACT Image Skeletonization

More information

Fabric Defect Detection Based on Computer Vision

Fabric Defect Detection Based on Computer Vision Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.

More information

The Research of Delay Characteristics in CAN Bus Networked Control System

The Research of Delay Characteristics in CAN Bus Networked Control System Journal of Computational Information Systems 9: 18 (2013) 7517 7523 Available at http://www.jofcis.com The Research of Delay Characteristics in CAN Bus Networked Control System Yi WANG 1, Liren HE 2, Ming

More information

Face Recognition Based on LDA and Improved Pairwise-Constrained Multiple Metric Learning Method

Face Recognition Based on LDA and Improved Pairwise-Constrained Multiple Metric Learning Method Journal of Information Hiding and Multimedia Signal Processing c 2016 ISSN 2073-4212 Ubiquitous International Volume 7, Number 5, September 2016 Face Recognition ased on LDA and Improved Pairwise-Constrained

More information

An Efficient Character Segmentation Algorithm for Printed Chinese Documents

An Efficient Character Segmentation Algorithm for Printed Chinese Documents An Efficient Character Segmentation Algorithm for Printed Chinese Documents Yuan Mei 1,2, Xinhui Wang 1,2, Jin Wang 1,2 1 Jiangsu Engineering Center of Network Monitoring, Nanjing University of Information

More information

Research and Design of Key Technology of Vertical Search Engine for Educational Resources

Research and Design of Key Technology of Vertical Search Engine for Educational Resources 2017 International Conference on Arts and Design, Education and Social Sciences (ADESS 2017) ISBN: 978-1-60595-511-7 Research and Design of Key Technology of Vertical Search Engine for Educational Resources

More information

A Feature based on Encoding the Relative Position of a Point in the Character for Online Handwritten Character Recognition

A Feature based on Encoding the Relative Position of a Point in the Character for Online Handwritten Character Recognition A Feature based on Encoding the Relative Position of a Point in the Character for Online Handwritten Character Recognition Dinesh Mandalapu, Sridhar Murali Krishna HP Laboratories India HPL-2007-109 July

More information

Implementation and Advanced Results on the Non-Interrupted Skeletonization Algorithm

Implementation and Advanced Results on the Non-Interrupted Skeletonization Algorithm Implementation and Advanced Results on the n-interrupted Skeletonization Algorithm Khalid Saeed, Mariusz Rybnik, Marek Tabedzki Computer Engineering Department Faculty of Computer Science Bialystok University

More information

Robust color segmentation algorithms in illumination variation conditions

Robust color segmentation algorithms in illumination variation conditions 286 CHINESE OPTICS LETTERS / Vol. 8, No. / March 10, 2010 Robust color segmentation algorithms in illumination variation conditions Jinhui Lan ( ) and Kai Shen ( Department of Measurement and Control Technologies,

More information

A Fast Caption Detection Method for Low Quality Video Images

A Fast Caption Detection Method for Low Quality Video Images 2012 10th IAPR International Workshop on Document Analysis Systems A Fast Caption Detection Method for Low Quality Video Images Tianyi Gui, Jun Sun, Satoshi Naoi Fujitsu Research & Development Center CO.,

More information

Analysis Range-Free Node Location Algorithm in WSN

Analysis Range-Free Node Location Algorithm in WSN International Conference on Education, Management and Computer Science (ICEMC 2016) Analysis Range-Free Node Location Algorithm in WSN Xiaojun Liu1, a and Jianyu Wang1 1 School of Transportation Huanggang

More information

The Design of Electronic Color Screen Based on Proteus Visual Designer Ting-Yu HOU 1,a, Hao LIU 2,b,*

The Design of Electronic Color Screen Based on Proteus Visual Designer Ting-Yu HOU 1,a, Hao LIU 2,b,* 2016 Joint International Conference on Service Science, Management and Engineering (SSME 2016) and International Conference on Information Science and Technology (IST 2016) ISBN: 978-1-60595-379-3 The

More information

Research on the Knowledge Representation Method of Instance Based on Functional Surface

Research on the Knowledge Representation Method of Instance Based on Functional Surface 5th International Conference on Advanced Engineering Materials and Technology (AEMT 2015) Research on the Knowledge Representation Method of Instance Based on Functional Surface Pengjie Zhai a, Changqing

More information

Recognition of Unconstrained Malayalam Handwritten Numeral

Recognition of Unconstrained Malayalam Handwritten Numeral Recognition of Unconstrained Malayalam Handwritten Numeral U. Pal, S. Kundu, Y. Ali, H. Islam and N. Tripathy C VPR Unit, Indian Statistical Institute, Kolkata-108, India Email: umapada@isical.ac.in Abstract

More information

Hole repair algorithm in hybrid sensor networks

Hole repair algorithm in hybrid sensor networks Advances in Engineering Research (AER), volume 116 International Conference on Communication and Electronic Information Engineering (CEIE 2016) Hole repair algorithm in hybrid sensor networks Jian Liu1,

More information

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Utkarsh Dwivedi 1, Pranjal Rajput 2, Manish Kumar Sharma 3 1UG Scholar, Dept. of CSE, GCET, Greater Noida,

More information

An Efficient Character Segmentation Based on VNP Algorithm

An Efficient Character Segmentation Based on VNP Algorithm Research Journal of Applied Sciences, Engineering and Technology 4(24): 5438-5442, 2012 ISSN: 2040-7467 Maxwell Scientific organization, 2012 Submitted: March 18, 2012 Accepted: April 14, 2012 Published:

More information

Qiqihar University, China *Corresponding author. Keywords: Highway tunnel, Variant monitoring, Circle fit, Digital speckle.

Qiqihar University, China *Corresponding author. Keywords: Highway tunnel, Variant monitoring, Circle fit, Digital speckle. 2017 2nd International Conference on Applied Mechanics and Mechatronics Engineering (AMME 2017) ISBN: 978-1-60595-521-6 Research on Tunnel Support Deformation Based on Camera and Digital Speckle Improvement

More information

5th International Conference on Information Engineering for Mechanics and Materials (ICIMM 2015)

5th International Conference on Information Engineering for Mechanics and Materials (ICIMM 2015) 5th International Conference on Information Engineering for Mechanics and Materials (ICIMM 2015) An Improved Watershed Segmentation Algorithm for Adhesive Particles in Sugar Cane Crystallization Yanmei

More information

Fault Diagnosis of Wind Turbine Based on ELMD and FCM

Fault Diagnosis of Wind Turbine Based on ELMD and FCM Send Orders for Reprints to reprints@benthamscience.ae 76 The Open Mechanical Engineering Journal, 24, 8, 76-72 Fault Diagnosis of Wind Turbine Based on ELMD and FCM Open Access Xianjin Luo * and Xiumei

More information

An embedded system of Face Recognition based on ARM and HMM

An embedded system of Face Recognition based on ARM and HMM An embedded system of Face Recognition based on ARM and HMM Yanbin Sun 1,2, Lun Xie 1, Zhiliang Wang 1,Yi An 2 1 Department of Electronic Information Engineering, School of Information Engineering, University

More information

Hierarchical Shape Primitive Features for Online Text-independent Writer Identification

Hierarchical Shape Primitive Features for Online Text-independent Writer Identification 2009 10th International Conference on Document Analysis and Recognition Hierarchical Shape Primitive Features for Online Text-independent Writer Identification Bangy Li, Zhenan Sun and Tieniu Tan Center

More information

An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques

An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques K. Ntirogiannis, B. Gatos and I. Pratikakis Computational Intelligence Laboratory, Institute of Informatics and

More information

HCR Using K-Means Clustering Algorithm

HCR Using K-Means Clustering Algorithm HCR Using K-Means Clustering Algorithm Meha Mathur 1, Anil Saroliya 2 Amity School of Engineering & Technology Amity University Rajasthan, India Abstract: Hindi is a national language of India, there are

More information

Minimal Test Cost Feature Selection with Positive Region Constraint

Minimal Test Cost Feature Selection with Positive Region Constraint Minimal Test Cost Feature Selection with Positive Region Constraint Jiabin Liu 1,2,FanMin 2,, Shujiao Liao 2, and William Zhu 2 1 Department of Computer Science, Sichuan University for Nationalities, Kangding

More information

Restoring Chinese Documents Images Based on Text Boundary Lines

Restoring Chinese Documents Images Based on Text Boundary Lines Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Restoring Chinese Documents Images Based on Text Boundary Lines Hong Liu Key Laboratory

More information

A Novel Image Transform Based on Potential field Source Reverse for Image Analysis

A Novel Image Transform Based on Potential field Source Reverse for Image Analysis A Novel Image Transform Based on Potential field Source Reverse for Image Analysis X. D. ZHUANG 1,2 and N. E. MASTORAKIS 1,3 1. WSEAS Headquarters, Agiou Ioannou Theologou 17-23, 15773, Zografou, Athens,

More information

The Study and Implementation of Text-to-Speech System for Agricultural Information

The Study and Implementation of Text-to-Speech System for Agricultural Information The Study and Implementation of Text-to-Speech System for Agricultural Information Huoguo Zheng 1,2,*, Haiyan Hu 1,2, Shihong Liu 1,2, and Hong Meng 1,2 1 Agricultural Information Institute, Chinese Academy

More information

The Implementation of Speaker Recognition on VoIP Auditing in Gigabit High-speed Environment

The Implementation of Speaker Recognition on VoIP Auditing in Gigabit High-speed Environment ISBN 978-952-5726-06-0 Proceedings of the 2009 International Workshop on Information Security and Application (IWISA 2009) Qingdao, China, November 21-22, 2009 The Implementation of Speaker Recognition

More information

4th Annual International Conference on Material Science and Engineering (ICMSE 2016)

4th Annual International Conference on Material Science and Engineering (ICMSE 2016) A Bidirectional Walk Method of Random Polygon for Two-dimensional Concrete Model Zheng CHEN 1,2,a,*, Yu-Liu WEI 1,b, Wei-Ying LIANG 1,c and Wo-Cheng HUANG 1,d 1 Key Laboratory of Disaster Prevention and

More information

Research on Design and Application of Computer Database Quality Evaluation Model

Research on Design and Application of Computer Database Quality Evaluation Model Research on Design and Application of Computer Database Quality Evaluation Model Abstract Hong Li, Hui Ge Shihezi Radio and TV University, Shihezi 832000, China Computer data quality evaluation is the

More information

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article

Journal of Chemical and Pharmaceutical Research, 2015, 7(3): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2015, 7(3):2413-2417 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Research on humanoid robot vision system based

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

ISSN: [Mukund* et al., 6(4): April, 2017] Impact Factor: 4.116

ISSN: [Mukund* et al., 6(4): April, 2017] Impact Factor: 4.116 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY ENGLISH CURSIVE SCRIPT RECOGNITION Miss.Yewale Poonam Mukund*, Dr. M.S.Deshpande * Electronics and Telecommunication, TSSM's Bhivarabai

More information

Number Plate Extraction using Template Matching Technique

Number Plate Extraction using Template Matching Technique Number Plate Extraction using Template Matching Technique Pratishtha Gupta Assistant Professor G N Purohit Professor Manisha Rathore M.Tech Scholar ABSTRACT As an application of CCTV Traffic surveillance,

More information

LECTURE 6 TEXT PROCESSING

LECTURE 6 TEXT PROCESSING SCIENTIFIC DATA COMPUTING 1 MTAT.08.042 LECTURE 6 TEXT PROCESSING Prepared by: Amnir Hadachi Institute of Computer Science, University of Tartu amnir.hadachi@ut.ee OUTLINE Aims Character Typology OCR systems

More information

Application of Geometry Rectification to Deformed Characters Recognition Liqun Wang1, a * and Honghui Fan2

Application of Geometry Rectification to Deformed Characters Recognition Liqun Wang1, a * and Honghui Fan2 6th International Conference on Electronic, Mechanical, Information and Management (EMIM 2016) Application of Geometry Rectification to Deformed Characters Liqun Wang1, a * and Honghui Fan2 1 School of

More information

A Template-Matching-Based Fast Algorithm for PCB Components Detection Haiming Yin

A Template-Matching-Based Fast Algorithm for PCB Components Detection Haiming Yin Advanced Materials Research Online: 2013-05-14 ISSN: 1662-8985, Vols. 690-693, pp 3205-3208 doi:10.4028/www.scientific.net/amr.690-693.3205 2013 Trans Tech Publications, Switzerland A Template-Matching-Based

More information

TEVI: Text Extraction for Video Indexing

TEVI: Text Extraction for Video Indexing TEVI: Text Extraction for Video Indexing Hichem KARRAY, Mohamed SALAH, Adel M. ALIMI REGIM: Research Group on Intelligent Machines, EIS, University of Sfax, Tunisia hichem.karray@ieee.org mohamed_salah@laposte.net

More information

MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION

MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION The Fourth Symposium on Natural Language Processing 2000 MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION A. KAWTRAKUL and P. WAEWSAWANGWONG Natural Language Processing and Intelligent Information

More information

Three-dimensional reconstruction of binocular stereo vision based on improved SURF algorithm and KD-Tree matching algorithm

Three-dimensional reconstruction of binocular stereo vision based on improved SURF algorithm and KD-Tree matching algorithm Three-dimensional reconstruction of binocular stereo vision based on improved SURF algorithm and KD-Tree matching algorithm Jie Cheng Informatization Center Tianjin Polytechnic University Tianjin, China

More information

Character Segmentation and Recognition Algorithm of Text Region in Steel Images

Character Segmentation and Recognition Algorithm of Text Region in Steel Images Character Segmentation and Recognition Algorithm of Text Region in Steel Images Keunhwi Koo, Jong Pil Yun, SungHoo Choi, JongHyun Choi, Doo Chul Choi, Sang Woo Kim Division of Electrical and Computer Engineering

More information

Temperature Calculation of Pellet Rotary Kiln Based on Texture

Temperature Calculation of Pellet Rotary Kiln Based on Texture Intelligent Control and Automation, 2017, 8, 67-74 http://www.scirp.org/journal/ica ISSN Online: 2153-0661 ISSN Print: 2153-0653 Temperature Calculation of Pellet Rotary Kiln Based on Texture Chunli Lin,

More information

A Novel Identification Approach to Encryption Mode of Block Cipher Cheng Tan1, a, Yifu Li 2,b and Shan Yao*2,c

A Novel Identification Approach to Encryption Mode of Block Cipher Cheng Tan1, a, Yifu Li 2,b and Shan Yao*2,c th International Conference on Sensors, Mechatronics and Automation (ICSMA 16) A Novel Approach to Encryption Mode of Block Cheng Tan1, a, Yifu Li 2,b and Shan Yao*2,c 1 Science and Technology on Communication

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(6): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(6): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 204, 6(6):2298-2302 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 TCP-like congestion control algorithm for stream

More information

Distribution Network Reconfiguration Based on Relevance Vector Machine

Distribution Network Reconfiguration Based on Relevance Vector Machine 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Distribution Network Reconfiguration Based on Relevance Vector Machine Sheng ZHOU

More information

Data Hiding on Text Using Big-5 Code

Data Hiding on Text Using Big-5 Code Data Hiding on Text Using Big-5 Code Jun-Chou Chuang 1 and Yu-Chen Hu 2 1 Department of Computer Science and Communication Engineering Providence University 200 Chung-Chi Rd., Shalu, Taichung 43301, Republic

More information