MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION

Size: px
Start display at page:

Download "MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION"

Transcription

1 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 System Technology Research Laboratory (NAiST), Department of Computer Engineering, Kasetsart University, Thailand This paper presents a simplified printed Thai character recognition system using multiple feature extraction and character classification. Three relevant information extracted from a set of training character images are the direction of each character s contour, the density of character body and character peripheral information. This set of features is used as reference for classifying unknown input characters. Based on Euclidean space model, the category of the reference vector yielding the minimum distance is assigned to the input character pattern. From the experiments, the recognizing speed is 5 character images per second with 97.44% correctness. The performance of recognition can be improved gradually in strengthening the robustness and lowering the error recognition rate by simply training and maintaining the knowledge by users. Key words : character recognition, feature extraction. INTRODUCTION Research interest both in machine printed Thai character and handwritten recognition has been intense in the past decades. Various recognition techniques were employed such as recognition by comparing the stroke changing sequence information (Choruengwiwat 998), recognition based on the statistical approach (Ding 997), recognition based on neural network (Kijsirikul 998; Lursinsap 995; Phokharatkul 998; Tanprasert 995), recognition by comparing the Hough transform information (Phokharatkul 997), recognition based on the fuzzy similarity relation (Taewit 997), recognition based on the expert system (Thumwarin 998). When developing an OCR system, not only classifier or recognizer but several issues need to be considered, i.e., speed, accuracy, image quality and post processing. Recently, there are some Thai OCR software products in the market, but the accuracy of recognizing the Thai characters is still not as high as that of English OCR software products which indicate that their accuracy is 99.9% or that of the Chinese OCR software product (Ding 997) which has the accuracy of 98.6%. The accuracy of English OCR is comparatively higher than that of Chinese OCR since the English character set has much less characters than those in the Chinese character set. In case of Thai OCR system, the accuracy is also not high. The difficulty in Thai OCR (Cooper 995) is that the Thai alphabet contains many pairs of letters that closely resemble each other, for example 'ข ' is almost the same as 'ฃ ' where only the little notch is different. Additionally, Thai character images are not obviously separated in block as the Chinese characters in the Chinese documents, and there are 4 levels of the character position (middle, upper, lower, above upper). These are the sources of ambiguities of segmentation before classifying. This paper presents a simplified and applicable system development for machine printed Thai character recognition. At the current stage, the performance of the system is improved by the assistance of the end users. A design of the system will be described in 2000 The Fourth Symposium on Natural Language Processing 2000

2 2 SNLP 2000, CHIANG MAI, THAILAND section. Section 2 gives a brief of the main part of the current system. The experimental result will be shown in section 3.. A DESIGN OF THAI SEMI-AUTOMATIC OCR SYSTEM A recognition system is usually composed of three major components : Document Analyzer and Preprocessor for document image alignment, locating text blocks and further segmenting into text lines and characters. This component also includes binarization, and normalization. Character Image Recognizer for classifying the input character pattern and outputting the results into an application. Postprocessor for improving accuracy by lexical processing. However, recognizer and its accuracy is the most important part of the system. Additionally, in practical system, more attention should be paid to the speed and knowledge maintenance of the system. Our system is, then, designed as the semi-automatic OCR system. The basic requirements for using the system are the pre-locating the text blocks by the end user and the image quality should not be too poor. The advantage of this system is that the performance can be improved gradually in strengthening the robustness and lowering the error recognition rate with simply training by the end users. Based on the idea that most documents, usually, are typed with only one font, only that font in training set will be selected as the system knowledge base. Accordingly, the speed and accuracy of recognizing will be enhanced. At the current stage, the recognizing speed is 5 character images per second with 97.44% correctness. 2. THE MAIN PART OF THE SYSTEM The main parts of the current system are multiple feature extraction and character classification. Since our approach based on extracted features, the normalization does affect the recognition result greatly. 2. NORMALIZATION There are two problems needed to be processes before recognizing, i.e., how to standardize the size of each image and how to put the image at the center of the frame. The following steps are, then, designed for image s size and position normalization :.) Start the image frame with xsize0 * ysize0 pixels which fit the isolated character. 2.) Rescale the size of the image to xsize * ysize pixels which is the maximum size according to xsize0 or ysize0, i.e., xsize = max(xsize0, ysize0) ysize = max(xsize0, ysize0)

3 MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION 3 3.) Find the center of gravity coordinate, (Xcg, Ycg), which is given by X xsize ( i ysize i= j= cg = xsize ysize i= j= pt( i, j)) pt( i, j) Y cg ysize ( j j= i= = xsize ysize xsize i= j= pt( i, j)) pt( i, j) where pt(i, j) is the point in the image at the coordinate (i, j), which pt(i, j) = if it is the black pixel, 0 if white pixel. 4.) Put the character image at the center position of the frame by using the following equation : where CentralizedPt(i, j) = pt( i + Xcg - Xmid, j + Ycg - Ymid ) Xmid = xsize / 2 Ymid = ysize / 2 5) Finally, rescale the image to the size of 36 * 36 pixels as the normalize size. 2.2 MULTI FEATURE EXTRACTION Three relevant information are extracted from a set of training character images : the direction of each character s contour, the density of character s body and the character peripheral information Extracting the Direction of the Character s Contour To extract the direction of the character s contour, the normalized image (36*36 pixels) is divided into 6 * 6 cells. The size of each cell is 6 * 6 pixels. (see Fig.)

4 4 SNLP 2000, CHIANG MAI, THAILAND Figure Dividing the normalized image into 6 * 6 cells for extracting the character contour direction. There are 4 feature windows (see Fig.2) in 3 * 3 pixels, consisting of 4 directions in horizontal (A), vertical (B), left diagonal (C), and right diagonal (D) Figure 2 The 4 Feature Windows Each feature window will be slided through each cell of the normalized image row by row. The contour direction feature vectors, X C, in four directions is, then, represented by the number of matched pixels in all possible location of these 4 windows inside each cell. X C = ( x A, x B, x C, x D, x 2A, x 2B, x 2C, x 2D,..., x 36A, x 36B, x 36C, x 36D ) T Computing the Density of the Character s Body Each normalized character image (36*36 pixels) will be divided into 9 * 9 cells. The size of each cell is 4 * 4 pixels. (see Fig. 3) Figure 3 Dividing the normalized image for extracting the density feature vector into 9 * 9 cells The density feature vector, X D, is the representation of the number of the black pixels in 8 cells, i.e., X D = ( x, x 2, x 3,..., x 8 ) T Extracting the Peripheral Information The peripheral information is the measurement of the distance from the normalized image frame to the nearest character contour within that image. (see Fig. 4) Since there are 4 sides, each side has 36 pixels long, the peripheral feature vector, X P, is : X P = ( x, x 2, x 3,..., x 44 ) T

5 MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION 5 Figure 4 The Peripheral Information of the character pattern 2.3 CHARACTER CLASSIFICATION The recognizer of the system is implemented by using the minimum distance classification method (Ding 997). Based on Euclidean space model, the minimum distance will decide the category of the unknown pattern The Reference Feature Vector from the Learning Process To compute the reference feature vector, training set must be collected. At present, 9 normalized characters in 3 fonts are trained as the primary knowledge of the system. The three feature vectors of each character in the same-font sample S will be extracted. Let M be the reference vector of each feature (3 features). M = Avg(X i ), i =..n where X i is the feature vector of each character in S Minimum Distance Classifier At this step, in order to recognize the character, a distance between unknown or input feature vector X and the reference vectors, M k, of category ω k in the training set must be computed. The distance will be computed based on Euclidean model as: d( X, M N k 2 k ) = ( x i m i ) i= where M k = (m k, m k 2,..., m k N ) T, N = 44, 8 and 44 for feature : the direction of each character s contour, feature 2: the density of character body and feature 3: the character peripheral information respectively. To determine the final solution of each input image character, the following steps are needed :

6 6 SNLP 2000, CHIANG MAI, THAILAND.) Compute three sets of the distance between the unknown character and the references based on the three features. The results are as the follows. fset = { d, d 2,..., d P } f2set = { d 2, d 2 2,..., d 2 P } f3set = { d 3, d 3 2,..., d 3 P } where P is the number of the characters in the knowledge base. { d i, d i 2,..., d i P } is the set of distance between the unknown character and the reference based on feature i, i = to 3. 2.) Normalize the three sets mentioned in.) as fset' = { a, a 2,..., a P } f2set' = { a 2, a 2 2,..., a 2 P } f3set' = { a 3, a 3 2,..., a 3 P } where a i j is the normalized value of the distance between the unknown character and the j th reference on feature i. and a i j= d i j / (d i + d i 2 +,...,+ d i P) 3.) Compute the final set of the distance by using the following weight equation : r j = w.a j + w 2.a 2 j + w 3.a 3 j where w, w 2, w 3 are the weight constants based on the statistical information and w + w 2 + w 3 = then the final set is finalset = { r, r 2,..., r P } 4.) The minimum distance, r k, in the final set in 3.) will be selected, where r k r i for all i k Then, the final solution for X is given by ω(x) = ω k

7 MULTI-FEATURE EXTRACTION FOR PRINTED THAI CHARACTER RECOGNITION 7 3. EXPERIMENTAL RESULT The system has been developed by using the MS Visual Basic 5.0 on Windows 98. The computer we used is Cyrix 6X CPU with 80 Mbyte EDO RAM. To enhance speed and accuracy, based on the idea that most documents are usually typed with only one font, only that font in training set will be selected as the system knowledge base. The recognizing speed is, then, about 5 character images per second with 97.44% correctness. The system was trained with the character images of the font AngsanaUPC, BrowalliaUPC and CordiaUPC. The testing set consists of character images of the same fonts as those of the training set. The total number of all testing patterns are 092 character images. These character images are obtained by scanning the practical documents that have a comparable image quality as those of the training set. The scanning resolution is 300 dpi. The experimental result in Table obviously shows that classification based on multiple feature gives more accuracy than using only one feature information. Table The Experimental Result Feature Extraction Percent of the Correct Result direction of contour density peripheral information all features CONCLUSION AND FUTURE WORK This paper presents a simplified and applicable Thai OCR system which based on multiple feature extraction and minimum distance classifier. The character images that can be recognized correctly are the normalized images of which the black pixels are in the same region as that of the learned characters in the knowledge base. Accordingly, the handwritten characters which have the same characteristics as mentioned above, can also be recognized correctly. Figure 5 shows the examples of unseen scribbly Thai handwritten characters that can be recognized by using the knowledge base of the printed character of font Angsana + Browallia + Cordia. For the future work, the system will focus on the extracted feature information from the character image region that can discriminate its category, for example, the image of 'ด' and 'ต' should focus on the upper region. In addition to extracting more feature, the post processor based on [4] will be integrated in order to enhance the performance of the system.

8 8 SNLP 2000, CHIANG MAI, THAILAND Figure 5 The unseen scribbly Thai handwritten characters that were correctly recognized. REFERENCES CHORUENGWIWAT, P., JITAPUNKUL, S., WUTTISITTIKULKIJ, L., and SEEHAPAN, P Distinctive Feature Analysis for Thai Handwritten Character Recognition Based on Modified Stroke Changing Sequence. In Proceedings of the 998 IEEE Asia-Pacific Conference on Circuits and Systems, Thailand, COOPER, D Fuzzy Letters and Thai Optical Character Recognition. In Proceedings SNLP 95 The 2 nd Symposium on Natural Language Processing, Thailand, DING, X. 997., Machine Printed Chinese Character Recognition. Handbook of Character Recognition and Document Image Analysis, WSPC, KAWTRAKUL, A A Computational Model for a Writing Production Assistant. In Proceedings NLPRS 95 Natural Language Processing Pacific Rim Symposium'95, Seoul, KIJSIRIKUL, B., SINTHUPINYO, S., and SUPANWANSA, A Thai Printed Character Recognition by Combining Inductive Logic Programming with Backpropagation Neural Network. In Proceedings of the 998 IEEE Asia-Pacific Conference on Circuits and Systems, Thailand, LURSINSAP, C Speeding Up Handwritten Character Neural Learning by surface Projection. In Proceedings SNLP 95 The 2 nd Symposium on Natural Language Processing, Thailand, PHOKHARATKUL, P., and KIMPAN, C Printed Thai Characters Recognition Using Hough Transform Method. Ladgrabang Engineering Journal, Vol. 3 No. 2, PHOKHARATKUL, P., and KIMPAN, C Recognition of Handprinted Thai Characters Using the Cavity Features of Character Based on Neural Network. In Proceedings of the 998 IEEE Asia-Pacific Conference on Circuits and Systems, Thailand, SUPAPA, S Probability and Statistic for Engineer. Physics Center, Bangkok. TAEWIT, T., and PIN-NGERN, A Pattern Recognition Using Fuzzy Similarity Relations. Ladgrabang Engineering Journal, Vol. 3 No. 2, 0-9. TANPRASERT, C., and TANPRASERT, T Variable Simulated Light Sensitive Model for Handwritten Thai Digit Recognition. In Proceedings SNLP 95 The 2 nd Symposium on Natural Language Processing, Thailand, THUMWARIN, P., and CHITTAYASOTHORN, S An Object-oriented Expert System for Thai Character Recognition. In Proceedings of the 998 IEEE Asia-Pacific Conference on Circuits and Systems, Thailand,

The Clustering Technique for Thai Handwritten Recognition

The Clustering Technique for Thai Handwritten Recognition The Clustering Technique for Thai Handwritten Recognition Ithipan Methasate, Sutat Sae-tang Information Research and Development Division National Electronics and Computer Technology Center National Science

More information

OCR For Handwritten Marathi Script

OCR For Handwritten Marathi Script International Journal of Scientific & Engineering Research Volume 3, Issue 8, August-2012 1 OCR For Handwritten Marathi Script Mrs.Vinaya. S. Tapkir 1, Mrs.Sushma.D.Shelke 2 1 Maharashtra Academy Of Engineering,

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

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

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

HANDWRITTEN GURMUKHI CHARACTER RECOGNITION USING WAVELET TRANSFORMS

HANDWRITTEN GURMUKHI CHARACTER RECOGNITION USING WAVELET TRANSFORMS International Journal of Electronics, Communication & Instrumentation Engineering Research and Development (IJECIERD) ISSN 2249-684X Vol.2, Issue 3 Sep 2012 27-37 TJPRC Pvt. Ltd., HANDWRITTEN GURMUKHI

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

Broken Characters Identification for Thai Character Recognition Systems

Broken Characters Identification for Thai Character Recognition Systems Broken Characters Identification for Thai Character Recognition Systems NUCHAREE PREMCHAISWADI*, WICHIAN PREMCHAISWADI* UBOLRAT PACHIYANUKUL**, SEINOSUKE NARITA*** *Faculty of Information Technology, Dhurakijpundit

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

Handwritten Gurumukhi Character Recognition by using Recurrent Neural Network

Handwritten Gurumukhi Character Recognition by using Recurrent Neural Network 139 Handwritten Gurumukhi Character Recognition by using Recurrent Neural Network Harmit Kaur 1, Simpel Rani 2 1 M. Tech. Research Scholar (Department of Computer Science & Engineering), Yadavindra College

More information

One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition

One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition One Dim~nsional Representation Of Two Dimensional Information For HMM Based Handwritten Recognition Nafiz Arica Dept. of Computer Engineering, Middle East Technical University, Ankara,Turkey nafiz@ceng.metu.edu.

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

A Fast Recognition System for Isolated Printed Characters Using Center of Gravity and Principal Axis

A Fast Recognition System for Isolated Printed Characters Using Center of Gravity and Principal Axis Applied Mathematics, 2013, 4, 1313-1319 http://dx.doi.org/10.4236/am.2013.49177 Published Online September 2013 (http://www.scirp.org/journal/am) A Fast Recognition System for Isolated Printed Characters

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

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

International Journal of Advance Research in Engineering, Science & Technology

International Journal of Advance Research in Engineering, Science & Technology Impact Factor (SJIF): 4.542 International Journal of Advance Research in Engineering, Science & Technology e-issn: 2393-9877, p-issn: 2394-2444 Volume 4, Issue 4, April-2017 A Simple Effective Algorithm

More information

Part-Based Skew Estimation for Mathematical Expressions

Part-Based Skew Estimation for Mathematical Expressions Soma Shiraishi, Yaokai Feng, and Seiichi Uchida shiraishi@human.ait.kyushu-u.ac.jp {fengyk,uchida}@ait.kyushu-u.ac.jp Abstract We propose a novel method for the skew estimation on text images containing

More information

A Technique for Classification of Printed & Handwritten text

A Technique for Classification of Printed & Handwritten text 123 A Technique for Classification of Printed & Handwritten text M.Tech Research Scholar, Computer Engineering Department, Yadavindra College of Engineering, Punjabi University, Guru Kashi Campus, Talwandi

More information

Handwritten Character Recognition with Feedback Neural Network

Handwritten Character Recognition with Feedback Neural Network Apash Roy et al / International Journal of Computer Science & Engineering Technology (IJCSET) Handwritten Character Recognition with Feedback Neural Network Apash Roy* 1, N R Manna* *Department of Computer

More information

Real Time Handwriting Recognition Techniques for Mathematical Notation in Interactive Teaching & Learning Applications

Real Time Handwriting Recognition Techniques for Mathematical Notation in Interactive Teaching & Learning Applications Real Time Handwriting Recognition Teciques for Mathematical Notation in Interactive Teaching & Learning Applications A. Chiou School of Engineering & Tecology, Central Queensland University, Rockhampton

More information

Handwritten Script Recognition at Block Level

Handwritten Script Recognition at Block Level Chapter 4 Handwritten Script Recognition at Block Level -------------------------------------------------------------------------------------------------------------------------- Optical character recognition

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

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

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

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

A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models

A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models A Visualization Tool to Improve the Performance of a Classifier Based on Hidden Markov Models Gleidson Pegoretti da Silva, Masaki Nakagawa Department of Computer and Information Sciences Tokyo University

More information

A Brief Study of Feature Extraction and Classification Methods Used for Character Recognition of Brahmi Northern Indian Scripts

A Brief Study of Feature Extraction and Classification Methods Used for Character Recognition of Brahmi Northern Indian Scripts 25 A Brief Study of Feature Extraction and Classification Methods Used for Character Recognition of Brahmi Northern Indian Scripts Rohit Sachdeva, Asstt. Prof., Computer Science Department, Multani Mal

More information

Extract an Essential Skeleton of a Character as a Graph from a Character Image

Extract an Essential Skeleton of a Character as a Graph from a Character Image Extract an Essential Skeleton of a Character as a Graph from a Character Image Kazuhisa Fujita University of Electro-Communications 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585 Japan k-z@nerve.pc.uec.ac.jp

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

INTERNATIONAL RESEARCH JOURNAL OF MULTIDISCIPLINARY STUDIES

INTERNATIONAL RESEARCH JOURNAL OF MULTIDISCIPLINARY STUDIES STUDIES & SPPP's, Karmayogi Engineering College, Pandharpur Organize National Conference Special Issue March 2016 Neuro-Fuzzy System based Handwritten Marathi System Numerals Recognition 1 Jayashri H Patil(Madane),

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

Neural Network Classifier for Isolated Character Recognition

Neural Network Classifier for Isolated Character Recognition Neural Network Classifier for Isolated Character Recognition 1 Ruby Mehta, 2 Ravneet Kaur 1 M.Tech (CSE), Guru Nanak Dev University, Amritsar (Punjab), India 2 M.Tech Scholar, Computer Science & Engineering

More information

SEVERAL METHODS OF FEATURE EXTRACTION TO HELP IN OPTICAL CHARACTER RECOGNITION

SEVERAL METHODS OF FEATURE EXTRACTION TO HELP IN OPTICAL CHARACTER RECOGNITION SEVERAL METHODS OF FEATURE EXTRACTION TO HELP IN OPTICAL CHARACTER RECOGNITION Binod Kumar Prasad * * Bengal College of Engineering and Technology, Durgapur, W.B., India. Rajdeep Kundu 2 2 Bengal College

More information

Automatic State Machine Induction for String Recognition

Automatic State Machine Induction for String Recognition Automatic State Machine Induction for String Recognition Boontee Kruatrachue, Nattachat Pantrakarn, and Kritawan Siriboon Abstract One problem of generating a model to recognize any string is how to generate

More information

NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL

NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL NEW ALGORITHMS FOR SKEWING CORRECTION AND SLANT REMOVAL ON WORD-LEVEL E.Kavallieratou N.Fakotakis G.Kokkinakis Wire Communication Laboratory, University of Patras, 26500 Patras, ergina@wcl.ee.upatras.gr

More information

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Stefan Müller, Gerhard Rigoll, Andreas Kosmala and Denis Mazurenok Department of Computer Science, Faculty of

More information

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition

Linear Discriminant Analysis in Ottoman Alphabet Character Recognition Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /

More information

RECOGNIZING TYPESET DOCUMENTS USING WALSH TRANSFORMATION. Attila Fazekas and András Hajdu University of Debrecen 4010, Debrecen PO Box 12, Hungary

RECOGNIZING TYPESET DOCUMENTS USING WALSH TRANSFORMATION. Attila Fazekas and András Hajdu University of Debrecen 4010, Debrecen PO Box 12, Hungary RECOGNIZING TYPESET DOCUMENTS USING WALSH TRANSFORMATION Attila Fazekas and András Hajdu University of Debrecen 4010, Debrecen PO Box 12, Hungary Abstract. In this paper we present an effective character

More information

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM Anoop K. Bhattacharjya and Hakan Ancin Epson Palo Alto Laboratory 3145 Porter Drive, Suite 104 Palo Alto, CA 94304 e-mail: {anoop, ancin}@erd.epson.com Abstract

More information

A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script

A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script Arwinder Kaur 1, Ashok Kumar Bathla 2 1 M. Tech. Student, CE Dept., 2 Assistant Professor, CE Dept.,

More information

6. Applications - Text recognition in videos - Semantic video analysis

6. Applications - Text recognition in videos - Semantic video analysis 6. Applications - Text recognition in videos - Semantic video analysis Stephan Kopf 1 Motivation Goal: Segmentation and classification of characters Only few significant features are visible in these simple

More information

Localization, Extraction and Recognition of Text in Telugu Document Images

Localization, Extraction and Recognition of Text in Telugu Document Images Localization, Extraction and Recognition of Text in Telugu Document Images Atul Negi Department of CIS University of Hyderabad Hyderabad 500046, India atulcs@uohyd.ernet.in K. Nikhil Shanker Department

More information

Abstract. Problem Statement. Objective. Benefits

Abstract. Problem Statement. Objective. Benefits Abstract The purpose of this final year project is to create an Android mobile application that can automatically extract relevant information from pictures of receipts. Users can also load their own images

More information

ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM

ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM RAMZI AHMED HARATY and HICHAM EL-ZABADANI Lebanese American University P.O. Box 13-5053 Chouran Beirut, Lebanon 1102 2801 Phone: 961 1 867621 ext.

More information

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm.

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm. Volume 7, Issue 5, May 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Hand Gestures Recognition

More information

DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS

DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS Sushilkumar N. Holambe Dr. Ulhas B. Shinde Shrikant D. Mali Persuing PhD at Principal

More information

Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate

Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate Surekha.R.Gondkar 1, C.S Mala 2, Alina Susan George 3, Beauty Pandey 4, Megha H.V 5 Associate Professor, Department of Telecommunication

More information

Arabic Text Extraction from Video Film

Arabic Text Extraction from Video Film Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 5, May 2015, pg.1117

More information

Indian Multi-Script Full Pin-code String Recognition for Postal Automation

Indian Multi-Script Full Pin-code String Recognition for Postal Automation 2009 10th International Conference on Document Analysis and Recognition Indian Multi-Script Full Pin-code String Recognition for Postal Automation U. Pal 1, R. K. Roy 1, K. Roy 2 and F. Kimura 3 1 Computer

More information

An Improvement Study for Optical Character Recognition by using Inverse SVM in Image Processing Technique

An Improvement Study for Optical Character Recognition by using Inverse SVM in Image Processing Technique An Improvement Study for Optical Character Recognition by using Inverse SVM in Image Processing Technique I Dinesh KumarVerma, II Anjali Khatri I Assistant Professor (ECE) PDM College of Engineering, Bahadurgarh,

More information

Seminar. Topic: Object and character Recognition

Seminar. Topic: Object and character Recognition Seminar Topic: Object and character Recognition Tse Ngang Akumawah Lehrstuhl für Praktische Informatik 3 Table of content What's OCR? Areas covered in OCR Procedure Where does clustering come in Neural

More information

A Segmentation Free Approach to Arabic and Urdu OCR

A Segmentation Free Approach to Arabic and Urdu OCR A Segmentation Free Approach to Arabic and Urdu OCR Nazly Sabbour 1 and Faisal Shafait 2 1 Department of Computer Science, German University in Cairo (GUC), Cairo, Egypt; 2 German Research Center for Artificial

More information

Mobile Application with Optical Character Recognition Using Neural Network

Mobile Application with Optical Character Recognition Using Neural Network Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 1, January 2015,

More information

Segmentation of Characters of Devanagari Script Documents

Segmentation of Characters of Devanagari Script Documents WWJMRD 2017; 3(11): 253-257 www.wwjmrd.com International Journal Peer Reviewed Journal Refereed Journal Indexed Journal UGC Approved Journal Impact Factor MJIF: 4.25 e-issn: 2454-6615 Manpreet Kaur Research

More information

Radial Basis Function Neural Network Classifier

Radial Basis Function Neural Network Classifier Recognition of Unconstrained Handwritten Numerals by a Radial Basis Function Neural Network Classifier Hwang, Young-Sup and Bang, Sung-Yang Department of Computer Science & Engineering Pohang University

More information

Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier

Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier Hetal R. Thaker Atmiya Institute of Technology & science, Kalawad

More information

Keywords Handwritten alphabet recognition, local binary pattern (LBP), feature Descriptor, nearest neighbor classifier.

Keywords Handwritten alphabet recognition, local binary pattern (LBP), feature Descriptor, nearest neighbor classifier. Volume 4, Issue 11, November 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Efficient

More information

Parallel string matching for image matching with prime method

Parallel string matching for image matching with prime method International Journal of Engineering Research and Development e-issn: 2278-067X, p-issn: 2278-800X, www.ijerd.com Volume 10, Issue 6 (June 2014), PP.42-46 Chinta Someswara Rao 1, 1 Assistant Professor,

More information

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS 8.1 Introduction The recognition systems developed so far were for simple characters comprising of consonants and vowels. But there is one

More information

Word-wise Hand-written Script Separation for Indian Postal automation

Word-wise Hand-written Script Separation for Indian Postal automation Word-wise Hand-written Script Separation for Indian Postal automation K. Roy U. Pal Dept. of Comp. Sc. & Engg. West Bengal University of Technology, Sector 1, Saltlake City, Kolkata-64, India Abstract

More information

A two-stage approach for segmentation of handwritten Bangla word images

A two-stage approach for segmentation of handwritten Bangla word images A two-stage approach for segmentation of handwritten Bangla word images Ram Sarkar, Nibaran Das, Subhadip Basu, Mahantapas Kundu, Mita Nasipuri #, Dipak Kumar Basu Computer Science & Engineering Department,

More information

Handwriting Recognition of Diverse Languages

Handwriting Recognition of Diverse Languages Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 6.017 IJCSMC,

More information

A New Technique for Segmentation of Handwritten Numerical Strings of Bangla Language

A New Technique for Segmentation of Handwritten Numerical Strings of Bangla Language I.J. Information Technology and Computer Science, 2013, 05, 38-43 Published Online April 2013 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijitcs.2013.05.05 A New Technique for Segmentation of Handwritten

More information

A new approach to reference point location in fingerprint recognition

A new approach to reference point location in fingerprint recognition A new approach to reference point location in fingerprint recognition Piotr Porwik a) and Lukasz Wieclaw b) Institute of Informatics, Silesian University 41 200 Sosnowiec ul. Bedzinska 39, Poland a) porwik@us.edu.pl

More information

Text Recognition in Videos using a Recurrent Connectionist Approach

Text Recognition in Videos using a Recurrent Connectionist Approach Author manuscript, published in "ICANN - 22th International Conference on Artificial Neural Networks, Lausanne : Switzerland (2012)" DOI : 10.1007/978-3-642-33266-1_22 Text Recognition in Videos using

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

A System to Automatically Index Genealogical Microfilm Titleboards Introduction Preprocessing Method Identification

A System to Automatically Index Genealogical Microfilm Titleboards Introduction Preprocessing Method Identification A System to Automatically Index Genealogical Microfilm Titleboards Samuel James Pinson, Mark Pinson and William Barrett Department of Computer Science Brigham Young University Introduction Millions of

More information

Human pose estimation using Active Shape Models

Human pose estimation using Active Shape Models Human pose estimation using Active Shape Models Changhyuk Jang and Keechul Jung Abstract Human pose estimation can be executed using Active Shape Models. The existing techniques for applying to human-body

More information

Early-Modern Printed Character Recognition using Ensemble Learning

Early-Modern Printed Character Recognition using Ensemble Learning 288 Int'l Conf. Par. and Dist. Proc. Tech. and Appl. PDPTA'17 Early-Modern Printed Character Recognition using Ensemble Learning Kaori Fujimoto, Yu Ishikawa, Masami Takata, Kazuki Joe Department of Advanced

More information

Human Performance on the USPS Database

Human Performance on the USPS Database Human Performance on the USPS Database Ibrahim Chaaban Michael R. Scheessele Abstract We found that the human error rate in recognition of individual handwritten digits is 2.37%. This differs somewhat

More information

Optical Character Recognition Based Speech Synthesis System Using LabVIEW

Optical Character Recognition Based Speech Synthesis System Using LabVIEW Optical Character Recognition Based Speech Synthesis System Using LabVIEW S. K. Singla* 1 and R.K.Yadav 2 1 Electrical and Instrumentation Engineering Department Thapar University, Patiala,Punjab *sunilksingla2001@gmail.com

More information

Available online at ScienceDirect. Procedia Computer Science 45 (2015 )

Available online at  ScienceDirect. Procedia Computer Science 45 (2015 ) Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 45 (2015 ) 205 214 International Conference on Advanced Computing Technologies and Applications (ICACTA- 2015) Automatic

More information

Segmentation Framework for Multi-Oriented Text Detection and Recognition

Segmentation Framework for Multi-Oriented Text Detection and Recognition Segmentation Framework for Multi-Oriented Text Detection and Recognition Shashi Kant, Sini Shibu Department of Computer Science and Engineering, NRI-IIST, Bhopal Abstract - Here in this paper a new and

More information

A Review on Handwritten Character Recognition

A Review on Handwritten Character Recognition IJCST Vo l. 8, Is s u e 1, Ja n - Ma r c h 2017 ISSN : 0976-8491 (Online) ISSN : 2229-4333 (Print) A Review on Handwritten Character Recognition 1 Anisha Sharma, 2 Soumil Khare, 3 Sachin Chavan 1,2,3 Dept.

More information

Input output and memory devices

Input output and memory devices Input output and memory devices One marks 1. What is cache memory The very high speed memory present between CPU and RAM 2. Expand the term OCR Optical Character Recognition (Recognizer) 3. Expand the

More information

A New Approach to Detect and Extract Characters from Off-Line Printed Images and Text

A New Approach to Detect and Extract Characters from Off-Line Printed Images and Text Available online at www.sciencedirect.com Procedia Computer Science 17 (2013 ) 434 440 Information Technology and Quantitative Management (ITQM2013) A New Approach to Detect and Extract Characters from

More information

Probabilistic Artificial Neural Network For Recognizing the Arabic Hand Written Characters

Probabilistic Artificial Neural Network For Recognizing the Arabic Hand Written Characters Journal of Computer Science 2 (12): 879-884, 2006 ISSN 1549-3636 2006 Science Publications Probabilistic Artificial Neural Network For Recognizing the Arabic Hand Written Characters 1 Khalaf khatatneh,

More information

Enhanced Image. Improved Dam point Labelling

Enhanced Image. Improved Dam point Labelling 3rd International Conference on Multimedia Technology(ICMT 2013) Video Text Extraction Based on Stroke Width and Color Xiaodong Huang, 1 Qin Wang, Kehua Liu, Lishang Zhu Abstract. Video text can be used

More information

FUZZY NETWORKS APPLICATION FOR OCR

FUZZY NETWORKS APPLICATION FOR OCR 2 nd Conference MAINTENAN 2012 Zenica, B&H, June 13 16, 2012 FUZZY NETWORKS APPLICATION FOR OCR Josef Kokeš Vysoká škola manažerské informatiky a ekonomiky, a.s. Praha Czech Republic ABSRACT This paper

More information

A Novel Feature Extraction and Classification Methodology for the Recognition of Historical Documents

A Novel Feature Extraction and Classification Methodology for the Recognition of Historical Documents 2009 10th International Conference on Document Analysis and Recognition A Novel Feature Eraction and Classification Methodology for the Recognition of Historical Documents G. Vamvakas, B. Gatos and S.

More information

Sinhala Handwriting Recognition Mechanism Using Zone Based Feature Extraction

Sinhala Handwriting Recognition Mechanism Using Zone Based Feature Extraction Sinhala Handwriting Recognition Mechanism Using Zone Based Feature Extraction 10 K.A.K.N.D. Dharmapala 1, W.P.M.V. Wijesooriya 2, C.P. Chandrasekara 3, U.K.A.U. Rathnapriya 4, L. Ranathunga 5 Department

More information

Word Slant Estimation using Non-Horizontal Character Parts and Core-Region Information

Word Slant Estimation using Non-Horizontal Character Parts and Core-Region Information 2012 10th IAPR International Workshop on Document Analysis Systems Word Slant using Non-Horizontal Character Parts and Core-Region Information A. Papandreou and B. Gatos Computational Intelligence Laboratory,

More information

Keyword Spotting in Document Images through Word Shape Coding

Keyword Spotting in Document Images through Word Shape Coding 2009 10th International Conference on Document Analysis and Recognition Keyword Spotting in Document Images through Word Shape Coding Shuyong Bai, Linlin Li and Chew Lim Tan School of Computing, National

More information

Skeletonization Algorithm for Numeral Patterns

Skeletonization Algorithm for Numeral Patterns International Journal of Signal Processing, Image Processing and Pattern Recognition 63 Skeletonization Algorithm for Numeral Patterns Gupta Rakesh and Kaur Rajpreet Department. of CSE, SDDIET Barwala,

More information

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of

More information

Capability of Thailand on Nuclear Forensics and Regional Collaboration

Capability of Thailand on Nuclear Forensics and Regional Collaboration Capability of Thailand on Nuclear Forensics and Regional Collaboration The International Symposium on Technology Development for Nuclear Security Focus on Nuclear Forensics and Regional Collaboration 5

More information

SKEW DETECTION AND CORRECTION

SKEW DETECTION AND CORRECTION CHAPTER 3 SKEW DETECTION AND CORRECTION When the documents are scanned through high speed scanners, some amount of tilt is unavoidable either due to manual feed or auto feed. The tilt angle induced during

More information

Semi-Automatic Transcription Tool for Ancient Manuscripts

Semi-Automatic Transcription Tool for Ancient Manuscripts The Venice Atlas A Digital Humanities atlas project by DH101 EPFL Students Semi-Automatic Transcription Tool for Ancient Manuscripts In this article, we investigate various techniques from the fields of

More information

FyFont: Find-your-Font in Large Font Databases

FyFont: Find-your-Font in Large Font Databases FyFont: Find-your-Font in Large Font Databases Martin Solli and Reiner Lenz Dept. Sci & Tech., Linköping University, 601 74 Norrköping, Sweden marso@itn.liu.se reile@itn.liu.se Abstract. A search engine

More information

PRINTED ARABIC CHARACTERS CLASSIFICATION USING A STATISTICAL APPROACH

PRINTED ARABIC CHARACTERS CLASSIFICATION USING A STATISTICAL APPROACH PRINTED ARABIC CHARACTERS CLASSIFICATION USING A STATISTICAL APPROACH Ihab Zaqout Dept. of Information Technology Faculty of Engineering & Information Technology Al-Azhar University Gaza ABSTRACT In this

More information

A Document Image Analysis System on Parallel Processors

A Document Image Analysis System on Parallel Processors A Document Image Analysis System on Parallel Processors Shamik Sural, CMC Ltd. 28 Camac Street, Calcutta 700 016, India. P.K.Das, Dept. of CSE. Jadavpur University, Calcutta 700 032, India. Abstract This

More information

Texture recognition of medical images with the ICM method

Texture recognition of medical images with the ICM method Nuclear Instruments and Methods in Physics Research A 525 (2004) 387 391 Texture recognition of medical images with the ICM method Jason M. Kinser*, Guisong Wang George Mason University, Institute for

More information

Journal of Applied Research and Technology ISSN: Centro de Ciencias Aplicadas y Desarrollo Tecnológico.

Journal of Applied Research and Technology ISSN: Centro de Ciencias Aplicadas y Desarrollo Tecnológico. Journal of Applied Research and Technology ISSN: 1665-6423 jart@aleph.cinstrum.unam.mx Centro de Ciencias Aplicadas y Desarrollo Tecnológico México Singla, S. K.; Yadav, R. K. Optical Character Recognition

More information

Multi prototype fuzzy pattern matching for handwritten character recognition

Multi prototype fuzzy pattern matching for handwritten character recognition Multi prototype fuzzy pattern matching for handwritten character recognition MILIND E. RANE, DHABE P. S AND J. B. PATIL Dept. of Electronics and Computer, R.C. Patel Institute of Technology, Shirpur, Dist.

More information

A Technique for Offline Handwritten Character Recognition

A Technique for Offline Handwritten Character Recognition A Technique for Offline Handwritten Character Recognition 1 Shilpy Bansal, 2 Mamta Garg, 3 Munish Kumar 1 Lecturer, Department of Computer Science Engineering, BMSCET, Muktsar, Punjab 2 Assistant Professor,

More information

MOMENT AND DENSITY BASED HADWRITTEN MARATHI NUMERAL RECOGNITION

MOMENT AND DENSITY BASED HADWRITTEN MARATHI NUMERAL RECOGNITION MOMENT AND DENSITY BASED HADWRITTEN MARATHI NUMERAL RECOGNITION S. M. Mali Department of Computer Science, MAEER S Arts, Commerce and Science College, Pune Shankarmali007@gmail.com Abstract In this paper,

More information

Speeding up the Detection of Line Drawings Using a Hash Table

Speeding up the Detection of Line Drawings Using a Hash Table Speeding up the Detection of Line Drawings Using a Hash Table Weihan Sun, Koichi Kise 2 Graduate School of Engineering, Osaka Prefecture University, Japan sunweihan@m.cs.osakafu-u.ac.jp, 2 kise@cs.osakafu-u.ac.jp

More information

An evaluation of HMM-based Techniques for the Recognition of Screen Rendered Text

An evaluation of HMM-based Techniques for the Recognition of Screen Rendered Text An evaluation of HMM-based Techniques for the Recognition of Screen Rendered Text Sheikh Faisal Rashid 1, Faisal Shafait 2, and Thomas M. Breuel 1 1 Technical University of Kaiserslautern, Kaiserslautern,

More information

Mono-font Cursive Arabic Text Recognition Using Speech Recognition System

Mono-font Cursive Arabic Text Recognition Using Speech Recognition System Mono-font Cursive Arabic Text Recognition Using Speech Recognition System M.S. Khorsheed Computer & Electronics Research Institute, King AbdulAziz City for Science and Technology (KACST) PO Box 6086, Riyadh

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information