Amharic Character Recognition using a fast signature based algorithm

Size: px
Start display at page:

Download "Amharic Character Recognition using a fast signature based algorithm"

Transcription

1 Amharic Character Recognition using a fast signature based algorithm Dr JOHN COWELL Dept. of Computer Science, De Montfort University, The Gateway, Leicester, LE1 9BH, England. jcowell@dmu.ac.uk Dr FIAZ HUSSAIN Dept. of Computing & Information Systems University of Luton, Park Square, Luton, LU1 3JU, England. fiaz.hussain@luton.ac.uk

2 Abstract The Amharic language is the principal language of over 20 million people mainly in Ethiopia. An extensive literature survey reveals no journal or conference papers on Amharic character recognition. The Amharic script has 33 basic characters each with seven s giving 231 distinct characters, not including numbers and punctuation symbols. The characters are cursive but not connected and unlike other cursive scripts do not use dots. This paper describes the Amharic script and discusses the difficulties of applying conventional structural and syntactic recognition processes. Two statistical algorithms for identifying Amharic characters are described. In both, the characters are normalised for both size and orientation. The first compares the character against a series of templates. The second derives a characteristic signature from the character and compares this against a set of signature templates. The signatures used are fifty times smaller than the original character and the recognition process is corresponding faster but with some loss of accuracy. The statistical techniques described have been fully implemented and the resulting performance outlined. Keywords: optical character recognition, OCR, confusion matrix, Amharic character recognition, structural recognition, syntactic recognition, character signature 1. Introduction Optical character recognition systems for Latin characters have been available for over a decade and perform well on clear typed text. There are still developments in these commercial applications concerned with coping with the widest variety of fonts, and with character recognition in less constrained environments, such as the identification of vehicle licence plates for road pricing schemes. There has been considerable recent research in the development of Arabic OCR systems for off and on-line systems. Off-line systems are where only the final printed characters are available and on-line systems where the characters are written on a graphics tablet and information is therefore available on the speed and direction of movement of the pen. Comprehensive surveys covering off-line techniques for Arabic script recognition are given by Mori et al [1], Tappert et al [2] and Amin [3]. A more up-to date review is provided by Plamondon and Srihari [4]. El-Wakil [5] reviews on-line recognition techniques where the characters are written on a tablet which records the speed and direction of the pen, while both areas are reviewed by Al-Badr et al. [12]. There are roughly two non-latin dozen scripts in wide usage and research has also been directed at other non-latin scripts such as Japanese, Chinese, Hindu, Tibetan. A notable exception to the research effort is the Amharic character set. This is the principle script of over 20 million people mainly in Ethiopia. An extensive review of the literature reveals no journal or conference papers which discuss the problem of recognition of the Amharic script apart from some MSc theses from Addis Ababa University [7-9]. In printed Amharic material very few fonts are available for two reasons. Firstly there is little commercial incentive to develop and distribute fonts in such a relatively small market. Secondly and more importantly there is no standardised mapping between Latin keyboards and the keystrokes required to generate the Amharic characters. This means that a typist trained to use one font and set of mappings cannot type in another font which uses different mappings without retraining. For these reasons multi-font support is not important in an Amharic OCR system. This paper begins with a description of the Amharic character set and then discusses possible approaches to the development of an OCR system. Finally, two statistical approaches are described. Both of these systems have been implemented. 2. The Amharic Character Set The Amharic script has 33 basic characters. There are six s derived from the basic forms. The first five s represent a combination of a consonant and vowel. The sixth may represent either a consonant alone or a consonant followed by a vowel [10,11]. Therefore, there are 231 (7 33 = 231) core characters in Amharic writing system. Besides these, there are over forty others which contain a special feature usually representing labialization. The list of these Amharic characters is shown in Table 1. Table 1. The Amharic character set 1 st 2 nd 3 rd 4 th 5 th 6 th 7 th H hä hù hu hi ha ÿ he H h ç ho L lä lù lu lþ li la l le L l lö lo ¼ hä ¼ù hu ¼þ hi ˆ ha ¼ he Þ h ho M mä Ñ mu mi ma» me M m ä mo sä ù su œþ si œ sa œ se o s ƒ so R rä ru ri ra Ê re R r é ro S sä sù su sþ si ú sa s se S s î so ¹ šä ¹ù šu ¹þ ši š ša ¹ še > š ë šo Q qä qü qu qe qi Ý qa q½ qe Q q ö qo B bä bù bu bþ bi Æ ba b be B b ï bo T tä tü tu te ti ta t½ te T t è to C čä cü ču ce či Ò ča c½ če C č Ó čo ^ hä ^ù hu ^þ hi ` ha ^ he ~ h ho N nä nù nu nþ ni  na n ne N n ñ no ß ňä ßù ňu ßþ ňa ¾ ňa ß ňe Ÿ ň ňo x ä xù u xþ i a x e X å o W wä ý wu êe wi ê wa ê½ we W w ã wo ; ä ;ù u þ i a e : â o K kä kù ku kþ ki µ ka k ke K k ko hä ù hu þ hi á ha he < h ó ho Z zä zù zu zþ zi ² za z ze Z z Ø zo žä Ü žu E ži Ï ža ½ že i ž Î žo

3 Y yä yu yi à ya ü ye Y y yo G gä gù gu gþ gi U ga g ge G g go D dä Ç du Äþ di Ä da Á de D d ì do J jä ju þ ji ja Ë je J j í jo «ţä «ù ţu «þ ţi È ţa «ţe _ ţ õ ţo = ćä Œ ću À ći Å ća će u ć ô ćo şä ù şu þ şi Ú şa şe A ş Û şo { şä {ù şu Éþ şi É şa É şe I ş ò şo ρä ù ρu þ ρi Ô ρa ρe e ρ Õ ρo F fä û fu ð fi Í fa Ø fe F f æ fo P pä pü pu pe pi pa p½ pe P p ± po A notable differences with many other non-latin scripts such as Arabic are that Amharic characters do not use dots and the characters although cursive are not connected. 3. Structural Approaches to OCR A popular approach to character recognition is to employ a structural and syntactic approach where the character is broken into primitives and the spatial relationships between these components is expressed using operators to create sentences in a pattern grammar. One of the best descriptions of structural and syntactic approach to pattern recognition remains the work of the late K.S. Fu [12]. This approach often requires the characters to be thinned in to extract information on stroke intersections [13-16]. Figure 1 shows six stages of thinning an Amharic character, removing a layer of edge pixels at each iteration. Note the development of superfluous tails produced at the stroke ends and the lack of relationship between the original and thinned form. These problems and some solutions are discussed in detail by the authors [22]. Figure 1 Growth of superfluous tails when thinning. Structural and syntactic recognition systems have a number of shortcomings that are resultant of the required thinning process. These include unwanted tails in the thinned and sensitivity to minor variations to the original. For these reasons, a statistical rather than structural approaches were used. In addition to the template and signature based methods described in this paper a neural network approach is an obvious choice as a statistical recogniser and this is forming the next phase of the research. 4. The Recognition Process Prior to submission to the recognition system the input characters must be normalised for size and orientation, both of which are critical in this type of statistical recognition Normalising for Size To normalise for size the character is converted to a representation. The distance between the two most distant pixels in both the x and y directions is altered so that they are both 100 pixels long. This process is discussed in more detail in earlier published work by the authors [17]. Figure 2 shows the effect of normalising two of the 321 characters of the Amharic character sets for both size and orientation. Before After Before After Figure 2 Typical Amharic script templates. 4.2 Normalising for Orientation Since the approach used is intended to be general purpose and could be used for applications where the orientation of the characters is not known, the original character is mapped onto a new axis. This is achieved by creating a list of edge pixels and calculating the longest chord that can be drawn between any pair of pixels forming the character outline. An edge pixel, here, is defined as one that is black but has one or more adjacent white pixels, including diagonally adjacent white pixels (that is 8- connectedness rather than 4-connectedness). The line defined by these two points is used to represent the new vertical axis of the normalised character. The horizontal axis of the new co-ordinate frame is at right angles to this axis and the point of intersection (0,0) of both axes is the lowest edge point. This defines fully the new co-ordinate frame. To normalise the bitmapped character for orientation, it is rotated about the intersection of the axes so it can be mapped onto the new co-ordinate frame. This is achieved by multiplying every pixel of the character by the direction cosines of the new co-ordinate system. Figure 3 shows a typical character before and after normalisation for orientation. new vertical axis new horizontal axis Figure 3 Normalising for orientation. 4.3 Recognising Characters In the recognition phase two alternative set of templates were used and their performance compared 1. The first compared each character against each of the template characters. The degree of closeness is given as a percentage. The highest percentage value returned by a comparison is deemed to indicate (that is, to recognise) the input figure.

4 2. The second technique used is a signature which can be quickly derived from the normalised character. The signature for each character is produced through a process of iteration. We loop to count the number of black pixels in each of the 100 rows and then the number of pixels in each of the 100 columns. This is compared against the corresponding count of black pixels in a set of templates. If a statistical template is used, the value of a pixel is based on the intensity of that pixel rather than simply being 0 (white) or 1 (black). The main disadvantage of the first technique is that for a character, 10,000 pixels have to be compared for each template. In the signature based system only 200 pixels have to be compared, despite the time taken to derive the signature there is an improvement in speed of about 10,000/200 = 50 times, but this is achieved at the loss of some accuracy. This variation can be expressed using a Confusion Matrix as discussed in section 5.0. An important benefit shared by both of these recognition processes is that we do not simply get a recognised output, but also a good reflection of what level of confusion is embedded in the process. This way, we gain knowledge of likely candidates for misinterpretation and can take steps to minimise their effect. 4.4 Extracting the Characters When a page is scanned it is usually done so as 256 grey-scale image. The recognition process is greatly simplified by means of converting to a set of black characters on a while background by the application of a global threshold. All of the pixels with intensity less than the threshold are converted to black, the other are converted to white. It is often sufficient to use the same threshold, however it is straightforward to consider the distribution of intensities on the input image. There will typically be two large peaks corresponding to the background and characters. Choosing a value midway between these two extremes will provide a satisfactory threshold. Amharic characters are not connected which simplifies the process of extracting individual characters. The image is scanned horizontally. When the first 'black' pixel is encountered this is converted to 'grey', that is, some value which is not black or white. Using conventional region growing techniques, all black pixels which touch this grey pixel are converted to grey, until no more pixels can be changed. The grey character can be presented to the character recognition part of the system. Before the next character can be identified the grey pixels are converted to white which erases the character. The process then begins again until no more characters are found. 4.5 Identifying Individual Characters Figure 4 shows the interactive interface of the recognition system prototype which identifies individual characters. The Language menu option is used to select a small textual configuration file which identifies the number and names of the characters in the character set to be recognised and the location of the templates to be used. No changes are required to the system to recognise a new character set. All that is required is the configuration file and a set of representative characters of that character set which can be used to produce the templates. Since the matching process is the same for both the full template and the signature recognition process, the process which is to be used is simply identified in the configuration file. At this stage, we simply input the name of the character or number that requires to be recognised, this corresponds to a file name. The system responds by locating the bitmap for the input, which is shown in the first output window in Figure 4. The recognition process then follows the mentioned phases. A practical problem was found with Amharic text since many Amharic characters are visually so similar and many have pronunciations which are identical to non-native users. To reduce the mistakes and to ensure that there was no confusion about what character was being referred to, we adopted a simple system of naming the character. The first two letters referred to the language, Am, in this case (the authors also use other non Latin character sets, so this part is essential). The next one or two characters in the sequence refer to the number of the basic character and is a value between 1 and 33 for Amharic. An underscore provides a break before a character between 1 and 7 which identifies the. For example ¼ is referred to as Am_1_3. The sample characters used in the experimental phase are further identified by another underscore and a number from 1 to the number of sample characters tested. Figure 4 shows the identification of the fourth sample of the Amharic character we identify as am1_3, that is third of the first character in Amharic character set. Figure 4 The recognition software in action. For each pixel in the character and the corresponding pixel in a template, the difference in intensity is found. This is summed for the whole image to yield a closeness of fit. The smaller the sum of the differences, the closer the match between a character and a template. The template, which gives the closest match, identifies the character. 4.6 The Signature Comparison System The signature for each character is produced through iteration. We loop to count the number of black pixels in each of the 100 rows and then the number of pixels in each of the 100 columns. This is compared against the

5 corresponding count of black pixels in a set of templates[18,19]. For each row, the modulus of the difference in the number of pixels is calculated and the resultant values added. The process is repeated for columns and the two difference (one for row and the other for column) values are added. A complete match would yield a sum of zero, while the other extreme would yield a value of 20,000 when a 100% exclusive-or of input character with a template occurs. This outcome can be more readily appreciated by converting the result to a value between 0 and 100 through dividing the resulting difference value by 200. The recognition process is approximately 40 times faster than comparing every pixel. 5. Experimental Results The recognition algorithm described not only identifies the template character which most closely matches the input character but also other template characters which are similar. Character Am1_1 100 Am1_ Am1_ Am1_ Am1_ Am1_ Am1_ Am2_ Am2_ Am2_ Am2_ Am2_ Am2_ Am2_ Char 1_1 1_2 1_3 1_4 1_5 1_6 1_7 2_1 2_2 2_3 2_4 2_5 2_6 2_7 Figure 5 - The Confusion Matrix for Amharic script using template comparison If every template character is compared against every other template character, a closeness of fit between every pair of characters can be produced and presented as a triangular matrix which shows how closely pairs of characters resemble each other. This is known as the Confusion Matrix [20,21]. Since the entire matrix has 231 columns and rows only a portion of the Confusion Matrix is shown in Figure 5 to illustrate the scenario. The distribution of results is shown in figure 6. The vertical axis is percentage of character pairs having a particular confusion rating. The horizontal axis shows the confusion rating between 0 and % Figure 6 - Distribution when using template comparison. The highest rating of 97 is given by 4 pairs and 37 pairs give a rating of 90 or more. Experimental work shows that character pairs with a rating of 90 or over on clear type are readily confused as the quality of the input character diminishes. The situation with the signature templates is event worse. The number of pairs with a rating of 90 or over is 377, Indeed two pairs give a rating of 99 and 23 pairs a rating of 98. Even on very clear input images characters with a rating of 99 are very likely to be confused. The distribution is shown in figure 7. Experimental work shows that if the quality of the images falls slightly many errors occur. For Amharic characters, the signature templates produce an unacceptable error rate which is not compensated for by greatly increased recognition speed compared to the template comparison approach. These results indicate that the identification of Amharic script is far more demanding than the recognition of Latin script or other cursive scripts such as Arabic text because of the greater number of characters and the greater similarity between pairs of characters. In Arabic script, similar characters can usually be distinguished by an analysis of the number and position of dots, however this is not the case in Amharic which does not use dots, and characters are distinguished by the number and position of small attached embellishments. Experimental work shows that on very clear printed type characters with a confusion rating of 97 can be distinguished every time, however as the quality of the input character diminishes The confusion factor increases % Figure 7 Distribution when using signature comparison

6 6. Conclusions This paper describes a fast recognition system based on creating image signatures which can be used for any character set. The system normalises characters for size and orientation. Two template comparison techniques are presented, one compares the every pixel of the input character to a set of templates, the other uses a set of signatures. The template comparison system achieves nearly perfect recognition rates for very clear text, but the quality of the image is even more important and as it deteriorates, the recognition rate falls significantly. The system has been demonstrated using the Amharic character set but could read any character set with a small amount of work to create the signatures for idealised characters. The system not only identifies a character but also gives a measure of how close other characters are to one recognised. The Confusion Matrix gives the degree of similarity between characters. The use of the Confusion Matrix gives an indication of how likely a character is to be confused with other characters and highlights possible problem areas. Results to date are encouraging and work has already begun to assess the performance of the recognition system using real, everyday, data. Bibliography [1] S. Mori, C.Y. Suen and K. Yamamoto. Historical review of OCR research and development. Proceedings IEEE 80, (1992). [2] C.C. Tappert, C.Y. Suen, and T. Wakahara, On-line handwriting recognition - a survey., Proceedings 9th ICPR International Conference on Pattern Recognition ICPR9, Rome, Italy (1988), IEEE, New York, N.Y., USA, 1988, [3] Amin A, Off-line Arabic character recognition - the state of the art [review], Pattern Recognition, vol. 31, no. 5, , (1998). [4] R. Plamondon and S.N. Srihari, On-line and off-line Handwriting Recognition: A Comprehensive Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, (2000). [5] El-Wakil M.S. and Shoukry A.A., On-line recognition of handwritten isolated Arabic characters, Pattern Recognition, vol. 22, no. 2, , (1989). [6] Al-Badr B. and Mahmoud S.A., Survey and bibliography of Arabic optical text recognition, Signal Processing, vol. 41, no. 1, (1995). [7] Ermias Abebe (1998). Recognition of Formatted Amharic text using optical character recognition; (Masters thesis) School of Information studies for Africa, Addis Ababa University, Addis Ababa. [8] Worku Alemu (1997). The Application of OCR Techniques to the Amharic Script; (Masters thesis) School of Information studies for Africa, Addis Ababa University, Addis Ababa. [9] Yaregal Assabie Lake (2001). Optical character recognition of Amharic text: an integrated approach; (Masters thesis) School of Information studies for Africa, Addis Ababa University, Addis Ababa. [10] Bender, M. et al. (1976). Language in Ethiopia. London: Oxford University Press. [11] Ullendorff, E. (1973). The Ethiopians: An Introduction to the Country and People. 3rd ed., London: Oxford University Press. [12] Fu K. S. Syntactic models in pattern recognition and applications. Pattern recognition in practice. ed. Gelsema E.S [13] Bazzi I, Schwatz R and Makhoul J., An Omnifont Open-Vocabulary OCR System for English and Arabic. IEEE Transactions on pattern Analysis and Machine Intelligence. vol. 21, no 6, , (1999). [14] Romeo-Pakker K., Ameur A., Olivier C., and Lecourtier Y., Structural analysis of Arabic handwriting: segmentation and recognition, Machine Vision and Applications, vol. 8, no 4, (1995). [15] Bushofa and Spann M., Segmentation and recognition of Arabic characters by structural classification, Image and Vision Computing, vol. 15, , (1998). [16] Cowell J., Syntactic pattern recognizer for vehicle identification numbers, Image and Vision Computing, vol. 13, no. 1, (1995). [17] Hussain, F., and Cowell, J., Character recognition of Arabic and Latin Script, Proceedings IV2000 conference, London [18] Hussain, F., and Cowell, J., A fast signature based algorithm for recognition of isolated Arabic characters, IASTED conference on Visualisation, Imaging and Image Processing, VIIP September 2002, Malaga. [19] Kinser Jason. Image signatures: Ontology and classification. CGIM2001 Computer Graphics and Imaging conference. IASTED, Hawaii USA CGIM2001. [20] Cowell, J., and Hussain, F., The Confusion Matrix identifying Conflicts in Arabic and Latin Character Recognition, Proceedings CGIM2000, Las Vegas November [21] Cowell, J., and Hussain, F., Resolving Conflicts in Arabic and Latin Character Recognition, EG2001 UCL London. [22] Cowell, J., and Hussain, F., Extracting Features from Arabic Characters, Proc. CGIM2001, Hawaii Acknowledgements The authors wish to express their thanks to Yaregal Assabie Lake (Computer Science Department, Addis Ababa University) for his valuable assistance for providing the understanding for the Amharic character set.

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

On-line handwriting recognition using Chain Code representation

On-line handwriting recognition using Chain Code representation On-line handwriting recognition using Chain Code representation Final project by Michal Shemesh shemeshm at cs dot bgu dot ac dot il Introduction Background When one preparing a first draft, concentrating

More information

Support for word-by-word, non-cursive handwriting

Support for word-by-word, non-cursive handwriting Decuma Latin 3.0 for SONY CLIÉ / PalmOS 5 Support for word-by-word, non-cursive handwriting developed by Decuma AB Copyright 2003 by Decuma AB. All rights reserved. Decuma is a trademark of Decuma AB in

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

Using non-latin alphabets in Blaise

Using non-latin alphabets in Blaise Using non-latin alphabets in Blaise Rob Groeneveld, Statistics Netherlands 1. Basic techniques with fonts In the Data Entry Program in Blaise, it is possible to use different fonts. Here, we show an example

More information

Structural and Syntactic Techniques for Recognition of Ethiopic Characters

Structural and Syntactic Techniques for Recognition of Ethiopic Characters Structural and Syntactic Techniques for Recognition of Ethiopic Characters Yaregal Assabie and Josef Bigun School of Information Science, Computer and Electrical Engineering Halmstad University, SE-301

More information

Üù àõ [tai 2 l 6] (in older orthography Üù àõ»). Tai Le orthography is simple and straightforward:

Üù àõ [tai 2 l 6] (in older orthography Üù àõ»). Tai Le orthography is simple and straightforward: ISO/IEC JTC1/SC2/WG2 N2372 2001-10-05 Universal Multiple-Octet Coded Character Set International Organization for Standardization Organisation internationale de normalisation еждународная организация по

More information

APPLESHARE PC UPDATE INTERNATIONAL SUPPORT IN APPLESHARE PC

APPLESHARE PC UPDATE INTERNATIONAL SUPPORT IN APPLESHARE PC APPLESHARE PC UPDATE INTERNATIONAL SUPPORT IN APPLESHARE PC This update to the AppleShare PC User's Guide discusses AppleShare PC support for the use of international character sets, paper sizes, and date

More information

Markham J. Geller K The first of the tablets presented here is a bilingual incantation which has one line also found in Utukkū Lemnūtu.

Markham J. Geller K The first of the tablets presented here is a bilingual incantation which has one line also found in Utukkū Lemnūtu. Two Bilingual Incantation Fragments Markham J. Geller It is usually inevitable that while editing a large group of tablets, one comes across fragments which look like they belong to the series with which

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

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

International Journal of Advance Research in Engineering, Science & Technology

International Journal of Advance Research in Engineering, Science & Technology Impact Factor (SJIF): 3.632 International Journal of Advance Research in Engineering, Science & Technology e-issn: 2393-9877, p-issn: 2394-2444 (Special Issue for ITECE 2016) Analysis and Implementation

More information

ASCII Code - The extended ASCII table

ASCII Code - The extended ASCII table ASCII Code - The extended ASCII table ASCII, stands for American Standard Code for Information Interchange. It's a 7-bit character code where every single bit represents a unique character. On this webpage

More information

Handwritten Hindi Character Recognition System Using Edge detection & Neural Network

Handwritten Hindi Character Recognition System Using Edge detection & Neural Network Handwritten Hindi Character Recognition System Using Edge detection & Neural Network Tanuja K *, Usha Kumari V and Sushma T M Acharya Institute of Technology, Bangalore, India Abstract Handwritten recognition

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 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

FREEMAN CODE BASED ONLINE HANDWRITTEN CHARACTER RECOGNITION FOR MALAYALAM USING BACKPROPAGATION NEURAL NETWORKS

FREEMAN CODE BASED ONLINE HANDWRITTEN CHARACTER RECOGNITION FOR MALAYALAM USING BACKPROPAGATION NEURAL NETWORKS FREEMAN CODE BASED ONLINE HANDWRITTEN CHARACTER RECOGNITION FOR MALAYALAM USING BACKPROPAGATION NEURAL NETWORKS Amritha Sampath 1, Tripti C 2 and Govindaru V 3 1 Department of Computer Science and Engineering,

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

Separation of Overlapping Text from Graphics

Separation of Overlapping Text from Graphics Separation of Overlapping Text from Graphics Ruini Cao, Chew Lim Tan School of Computing, National University of Singapore 3 Science Drive 2, Singapore 117543 Email: {caorn, tancl}@comp.nus.edu.sg Abstract

More information

OOstaExcel.ir. J. Abbasi Syooki. HTML Number. Device Control 1 (oft. XON) Device Control 3 (oft. Negative Acknowledgement

OOstaExcel.ir. J. Abbasi Syooki. HTML Number. Device Control 1 (oft. XON) Device Control 3 (oft. Negative Acknowledgement OOstaExcel.ir J. Abbasi Syooki HTML Name HTML Number دهدهی ا کتال هگزاد سیمال باینری نشانه )کاراکتر( توضیح Null char Start of Heading Start of Text End of Text End of Transmission Enquiry Acknowledgment

More information

Pe h-ōe-jī Unicode Correspondence Table

Pe h-ōe-jī Unicode Correspondence Table Pe h-ōe-jī Correspondence Table This document contains the code points and font examples for characters needed to write Pe h-ōe-jī for Taiwanese (Hoklo). Standard latin capital and small letters are not

More information

Online Bangla Handwriting Recognition System

Online Bangla Handwriting Recognition System 1 Online Bangla Handwriting Recognition System K. Roy Dept. of Comp. Sc. West Bengal University of Technology, BF 142, Saltlake, Kolkata-64, India N. Sharma, T. Pal and U. Pal Computer Vision and Pattern

More information

Chinese Handwritten Character Segmentation in Form Documents

Chinese Handwritten Character Segmentation in Form Documents Chinese andwritten Character Segmentation in Form Documents Jiun-Lin Chen, Chi-ong Wu and si-jian Lee Department of Computer Science and Information Engineering National Chiao Tung University, sinchu,

More information

LEKHAK [MAL]: A System for Online Recognition of Handwritten Malayalam Characters

LEKHAK [MAL]: A System for Online Recognition of Handwritten Malayalam Characters LEKHAK [MAL]: A System for Online Recognition of Handwritten Malayalam Characters Gowri Shankar, V. Anoop and V. S. Chakravarthy, Department of Electrical Engineering, Indian Institute of Technology, Madras,

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

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

Artificial Neural Network Approach to the Development of OCR for Real Life Amharic Documents

Artificial Neural Network Approach to the Development of OCR for Real Life Amharic Documents Artificial Neural Network Approach to the Development of OCR for Real Life Amharic Documents Abay Teshager Birhanu, R. Sethuraman Lecturer, College of Engineering & Technology, Department of Computing

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 online captured, handwritten Tamil words on Android

Recognition of online captured, handwritten Tamil words on Android Recognition of online captured, handwritten Tamil words on Android A G Ramakrishnan and Bhargava Urala K Medical Intelligence and Language Engineering (MILE) Laboratory, Dept. of Electrical Engineering,

More information

Cartons (PCCs) Management

Cartons (PCCs) Management Final Report Project code: 2015 EE04 Post-Consumer Tetra Pak Cartons (PCCs) Management Prepared for Tetra Pak India Pvt. Ltd. Post Consumer Tetra Pak Cartons (PCCs) Management! " # $ " $ % & ' ( ) * +,

More information

A Novel Approach for Rotation Free Online Handwritten Chinese Character Recognition +

A Novel Approach for Rotation Free Online Handwritten Chinese Character Recognition + 2009 0th International Conference on Document Analysis and Recognition A Novel Approach for Rotation Free Online andwritten Chinese Character Recognition + Shengming uang, Lianwen Jin* and Jin Lv School

More information

CHAPTER 1 INTRODUCTION

CHAPTER 1 INTRODUCTION CHAPTER 1 INTRODUCTION 1.1 Introduction Pattern recognition is a set of mathematical, statistical and heuristic techniques used in executing `man-like' tasks on computers. Pattern recognition plays an

More information

Slant Correction using Histograms

Slant Correction using Histograms Slant Correction using Histograms Frank de Zeeuw Bachelor s Thesis in Artificial Intelligence Supervised by Axel Brink & Tijn van der Zant July 12, 2006 Abstract Slant is one of the characteristics that

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

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

Appendix C. Numeric and Character Entity Reference

Appendix C. Numeric and Character Entity Reference Appendix C Numeric and Character Entity Reference 2 How to Do Everything with HTML & XHTML As you design Web pages, there may be occasions when you want to insert characters that are not available on your

More information

Template for comments and secretariat observations Date: Document: ISO/IEC 10646:2014 PDAM2

Template for comments and secretariat observations Date: Document: ISO/IEC 10646:2014 PDAM2 Template for s and secretariat observations Date: 014-08-04 Document: ISO/IEC 10646:014 PDAM 1 (3) 4 5 (6) (7) on each submitted GB1 4.3 ed Subclause title incorrectly refers to CJK ideographs. Change

More information

Spotting Words in Latin, Devanagari and Arabic Scripts

Spotting Words in Latin, Devanagari and Arabic Scripts Spotting Words in Latin, Devanagari and Arabic Scripts Sargur N. Srihari, Harish Srinivasan, Chen Huang and Shravya Shetty {srihari,hs32,chuang5,sshetty}@cedar.buffalo.edu Center of Excellence for Document

More information

User Guide for Greek GGT-Fonts Revision date: 23 May, 2011

User Guide for Greek GGT-Fonts Revision date: 23 May, 2011 User Guide for Greek GGT-Fonts Revision date: 23 May, 2011 by Graham G Thomason Copyright Graham G Thomason, 2009. Permission is granted to copy or publish this document, provided this complete notice

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

B. Technical General 1. Choose one of the following: 1a. This proposal is for a new script (set of characters) Yes.

B. Technical General 1. Choose one of the following: 1a. This proposal is for a new script (set of characters) Yes. ISO/IEC JTC1/SC2/WG2 N3024 L2/06-004 2006-01-11 Universal Multiple-Octet Coded Character Set International Organization for Standardization Organisation Internationale de Normalisation Международная организация

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

Adorn. Slab Serif BOLD. v x. user s gu ide

Adorn. Slab Serif BOLD. v x. user s gu ide Adorn f Slab Serif BOLD t 9a0 v2226222x user s gu ide v fon t faq HOW T O I N S TA L L YOU R F ON T H O W T O I N S E R T S WA S H E S, You will receive your files as a zipped folder. For instructions

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

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

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

Review of Automatic Handwritten Kannada Character Recognition Technique Using Neural Network

Review of Automatic Handwritten Kannada Character Recognition Technique Using Neural Network Review of Automatic Handwritten Kannada Character Recognition Technique Using Neural Network 1 Mukesh Kumar, 2 Dr.Jeeetendra Sheethlani 1 Department of Computer Science SSSUTMS, Sehore Abstract Data processing

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

Pointers. CS2023 Winter 2004

Pointers. CS2023 Winter 2004 Pointers CS2023 Winter 2004 Outcomes: Introduction to Pointers C for Java Programmers, Chapter 8, sections 8.1-8.8 Other textbooks on C on reserve After the conclusion of this section you should be able

More information

Extracting Characters From Books Based On The OCR Technology

Extracting Characters From Books Based On The OCR Technology 2016 International Conference on Engineering and Advanced Technology (ICEAT-16) Extracting Characters From Books Based On The OCR Technology Mingkai Zhang1, a, Xiaoyi Bao1, b,xin Wang1, c, Jifeng Ding1,

More information

Adorn. Serif. v x. user s gu ide

Adorn. Serif. v x. user s gu ide Adorn f Serif t 9a0 v2226222x user s gu ide v fon t faq HOW T O I N S TA L L YOU R F ON T H O W T O I N S E R T S WA S H E S, You will receive your files as a zipped folder. For instructions on how to

More information

A semi-incremental recognition method for on-line handwritten Japanese text

A semi-incremental recognition method for on-line handwritten Japanese text 2013 12th International Conference on Document Analysis and Recognition A semi-incremental recognition method for on-line handwritten Japanese text Cuong Tuan Nguyen, Bilan Zhu and Masaki Nakagawa Department

More information

OPTICAL CHARACTER RECOGNITION FOR VIETNAMESE SCANNED TEXT

OPTICAL CHARACTER RECOGNITION FOR VIETNAMESE SCANNED TEXT OPTICAL CHARACTER RECOGNITION FOR VIETNAMESE SCANNED TEXT Authors: Tran Anh Viet, Le Minh Hoang Hac, Le Tuan Bao Ngoc, Le Anh Duy Class: 08ECE, Electronic and Communication Engineering Department, DaNang

More information

Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script

Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script Galaxy Bansal Dharamveer Sharma ABSTRACT Segmentation of handwritten words is a challenging task primarily because of structural features

More information

This file contains an excerpt from the character code tables and list of character names for The Unicode Standard, Version 3.0.

This file contains an excerpt from the character code tables and list of character names for The Unicode Standard, Version 3.0. Range: This file contains an excerpt from the character code tables and list of character names for The Unicode Standard, Version.. isclaimer The shapes of the reference glyphs used in these code charts

More information

State of Connecticut Workers Compensation Commission

State of Connecticut Workers Compensation Commission State of Connecticut Workers Compensation Commission Notice to Employees Workers Compensation Act Chapter 568 of the Connecticut General Statutes (the Workers Compensation Act) requires your employer,

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

ESANN'2001 proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), April 2001, D-Facto public., ISBN ,

ESANN'2001 proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), April 2001, D-Facto public., ISBN , Recognition of Consonant-Vowel Utterances using Support Vector Machines C.Chandra Sekhar, K.Takeda and F.Itakura CIAIR, Itakura Laboratory, Dept. of Information Electronics, Nagoya University, Nagoya-4648603,

More information

Automated Digital Conversion of Hand-Drawn Plots

Automated Digital Conversion of Hand-Drawn Plots Automated Digital Conversion of Hand-Drawn Plots Ruo Yu Gu Department of Electrical Engineering Stanford University Palo Alto, U.S.A. ruoyugu@stanford.edu Abstract An algorithm has been developed using

More information

Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features

Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features Md. Abul Hasnat Center for Research on Bangla Language Processing (CRBLP) Center for Research on Bangla Language Processing

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

Anale. Seria Informatică. Vol. XVII fasc Annals. Computer Science Series. 17 th Tome 1 st Fasc. 2019

Anale. Seria Informatică. Vol. XVII fasc Annals. Computer Science Series. 17 th Tome 1 st Fasc. 2019 EVALUATION OF AN OPTICAL CHARACTER RECOGNITION MODEL FOR YORUBA TEXT 1 Abimbola Akintola, 2 Tunji Ibiyemi, 3 Amos Bajeh 1,3 Department of Computer Science, University of Ilorin, Nigeria 2 Department of

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

BUCKLEY. User s Guide

BUCKLEY. User s Guide BUCKLEY User s Guide O P E N T Y P E FAQ : For information on how to access the swashes and alternates, visit LauraWorthingtonType.com/faqs All operating systems come equipped with a utility that make

More information

2009 International Conference on Emerging Technologies

2009 International Conference on Emerging Technologies 2009 International Conference on Emerging Technologies A Self Organizing Map Based Urdu Nasakh Character Recognition Syed Afaq Hussain *, Safdar Zaman ** and Muhammad Ayub ** afaq.husain@mail.au.edu.pk,

More information

RECOGNITION FOR LARGE SETS OF HANDWRITTEN MATHEMATICAL SYMBOLS. Stephen M. Watt and Xiaofang Xie

RECOGNITION FOR LARGE SETS OF HANDWRITTEN MATHEMATICAL SYMBOLS. Stephen M. Watt and Xiaofang Xie RECOGNITION FOR LARGE SETS OF HANDWRITTEN MATHEMATICAL SYMBOLS Stephen M. Watt and Xiaofang Xie Dept. of Computer Science University of Western Ontario London Ontario, Canada N6A 5B7 {watt,maggie}@csd.uwo.ca

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 New Algorithm for Detecting Text Line in Handwritten Documents

A New Algorithm for Detecting Text Line in Handwritten Documents A New Algorithm for Detecting Text Line in Handwritten Documents Yi Li 1, Yefeng Zheng 2, David Doermann 1, and Stefan Jaeger 1 1 Laboratory for Language and Media Processing Institute for Advanced Computer

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

Hardware withdrawal: ThinkPad and IdeaPad laptop select models and machine types - Replacements available

Hardware withdrawal: ThinkPad and IdeaPad laptop select models and machine types - Replacements available Announcement 909-235, dated October 6, 2009 Hardware withdrawal: ThinkPad and IdeaPad laptop select models and machine types - Replacements available Table of contents 1 Overview 4 Replacement product

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

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

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

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

An Adaptive Approach to Extract Characters from Digital Ink Text in Chinese Based on Extracted Errors

An Adaptive Approach to Extract Characters from Digital Ink Text in Chinese Based on Extracted Errors An Adaptive Approach to Extract Characters from Digital Ink Text in Chinese Based on Extracted Errors Hao Bai ( ) Beijing Language and Culture University, Beijing, China baihao@blcu.edu.cn Abstract. Extracting

More information

USB-ASC232. ASCII RS-232 Controlled USB Keyboard and Mouse Cable. User Manual

USB-ASC232. ASCII RS-232 Controlled USB Keyboard and Mouse Cable. User Manual USB-ASC232 ASCII RS-232 Controlled USB Keyboard and Mouse Cable User Manual Thank you for purchasing the model USB-ASC232 Cable HAGSTROM ELECTRONICS, INC. is pleased that you have selected this product

More information

Optical Character Recognition

Optical Character Recognition Optical Character Recognition Jagruti Chandarana 1, Mayank Kapadia 2 1 Department of Electronics and Communication Engineering, UKA TARSADIA University 2 Assistant Professor, Department of Electronics

More information

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang Extracting Layers and Recognizing Features for Automatic Map Understanding Yao-Yi Chiang 0 Outline Introduction/ Problem Motivation Map Processing Overview Map Decomposition Feature Recognition Discussion

More information

Identifying Layout Classes for Mathematical Symbols Using Layout Context

Identifying Layout Classes for Mathematical Symbols Using Layout Context Rochester Institute of Technology RIT Scholar Works Articles 2009 Identifying Layout Classes for Mathematical Symbols Using Layout Context Ling Ouyang Rochester Institute of Technology Richard Zanibbi

More information

Hangul Recognition Using Support Vector Machine

Hangul Recognition Using Support Vector Machine Hangul Recognition Using Support Vector Machine Rahmatina Hidayati University of Brawijaya Moechammad Sarosa State Polytechnic of Malang Panca Mudjirahardjo University of Brawijaya Abstract: The recognition

More information

A Parameter Study for Differential Evolution

A Parameter Study for Differential Evolution A Parameter Study for Differential Evolution ROGER GÄMPERLE SIBYLLE D MÜLLER PETROS KOUMOUTSAKOS Institute of Computational Sciences Department of Computer Science Swiss Federal Institute of Technology

More information

ADORN. Roman. v x. user s gu ide

ADORN. Roman. v x. user s gu ide ADORN f Roman t 9a0 v2226222x user s gu ide v fon t faq HOW T O I N S TA L L YOU R F ON T H O W T O I N S E R T S WA S H E S, You will receive your files as a zipped folder. For instructions on how to

More information

with Profile's Amplitude Filter

with Profile's Amplitude Filter Arabic Character Segmentation Using Projection-Based Approach with Profile's Amplitude Filter Mahmoud A. A. Mousa Dept. of Computer and Systems Engineering, Zagazig University, Zagazig, Egypt mamosa@zu.edu.eg

More information

PRAGUE EGYPTOLOGICAL STUDIES

PRAGUE EGYPTOLOGICAL STUDIES 1 PRAGUE EGYPTOLOGICAL STUDIES GUIDELINES FOR CONTRIBUTIONS Manuscript Manuscripts must be submitted to prague.egyptological.studies@gmail.com The submitted papers must be original works of the contributors

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

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

Communication and processing of text in the Kildin Sámi, Komi, and Nenets, and Russian languages.

Communication and processing of text in the Kildin Sámi, Komi, and Nenets, and Russian languages. TYPE: 96 Character Graphic Character Set REGISTRATION NUMBER: 200 DATE OF REGISTRATION: 1998-05-01 ESCAPE SEQUENCE G0: -- G1: ESC 02/13 06/00 G2: ESC 02/14 06/00 G3: ESC 02/15 06/00 C0: -- C1: -- NAME:

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

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra Pattern Recall Analysis of the Hopfield Neural Network with a Genetic Algorithm Susmita Mohapatra Department of Computer Science, Utkal University, India Abstract: This paper is focused on the implementation

More information

Structural and Syntactic Pattern Recognition

Structural and Syntactic Pattern Recognition Structural and Syntactic Pattern Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Fall 2017 CS 551, Fall 2017 c 2017, Selim Aksoy (Bilkent

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

Handwritten Marathi Character Recognition on an Android Device

Handwritten Marathi Character Recognition on an Android Device Handwritten Marathi Character Recognition on an Android Device Tanvi Zunjarrao 1, Uday Joshi 2 1MTech Student, Computer Engineering, KJ Somaiya College of Engineering,Vidyavihar,India 2Associate Professor,

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

Pointers & Arrays. CS2023 Winter 2004

Pointers & Arrays. CS2023 Winter 2004 Pointers & Arrays CS2023 Winter 2004 Outcomes: Pointers & Arrays C for Java Programmers, Chapter 8, section 8.12, and Chapter 10, section 10.2 Other textbooks on C on reserve After the conclusion of this

More information

To provide state and district level PARCC assessment data for the administration of Grades 3-8 Math and English Language Arts.

To provide state and district level PARCC assessment data for the administration of Grades 3-8 Math and English Language Arts. 200 West Baltimore Street Baltimore, MD 21201 410-767-0100 410-333-6442 TTY/TDD msde.maryland.gov TO: FROM: Members of the Maryland State Board of Education Jack R. Smith, Ph.D. DATE: December 8, 2015

More information

The Coptic Standard Character Code (CSCC)

The Coptic Standard Character Code (CSCC) The Coptic Standard Character Code (CSCC) Preview This is a project of standardization of the Coptic Fonts that work on windows format: *.ttf so, as to make a unified Character coding. It is done by Remenkimi

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

Khmer OCR for Limon R1 Size 22 Report

Khmer OCR for Limon R1 Size 22 Report PAN Localization Project Project No: Ref. No: PANL10n/KH/Report/phase2/002 Khmer OCR for Limon R1 Size 22 Report 09 July, 2009 Prepared by: Mr. ING LENG IENG Cambodia Country Component PAN Localization

More information

Pixels. Orientation π. θ π/2 φ. x (i) A (i, j) height. (x, y) y(j)

Pixels. Orientation π. θ π/2 φ. x (i) A (i, j) height. (x, y) y(j) 4th International Conf. on Document Analysis and Recognition, pp.142-146, Ulm, Germany, August 18-20, 1997 Skew and Slant Correction for Document Images Using Gradient Direction Changming Sun Λ CSIRO Math.

More information