Abstract

This paper presents an automatic detection of handwritten Bengali Broken Characters (BBC) using a feed forward neural network (FFNN). It simulates the Human Visual System (HVS) the way human eye matches the patterns of the broken characters to a meaningful character and identifies it. Here the challenge is to detect and retrieve handwritten character which has been distorted up to 90%. The database consists of fifty bangle characters, each with twenty samples. Each character is presented as an image, which has been preprocessed, segmented and the features are then extracted. A new method has been proposed in this paper. It uses FFNN to calculate the mismatch for the recognition of a character, where it is observed that the distorted characters show very low mismatch with the original characters. For example, characters up to 70% distortions are found to be retrieved effectively.

References

• S. Chattopadhyay "A Prototype Depression Screening Tool for Rural Healthcare: A Step towards e-Health Informatics", Journal of Medical Imaging and Health Informatics Vol. 2, No. 3, pp 244-249, 2012.
• S. Satapathy, S. Chattopadhyay "Observation-Prevention of Cardiac Risk Factors: an Indian Study", Journal of Medical Imaging and Health Informatics Vol. 2, No. 2, pp 102-113, 2012.
• S. Chattopadhyay, R. M. Davis. , D. D. Menezes, G. Singh, U. R. Acharya, T. Tamura "Application of Bayesian Classifier for the Diagnosis of Dental Pain", Journal of Medical Systems Vol. 36, pp. 1425-1439, 2012
• S. Chattopadhyay, F. A. Rabhi, U. R. Acharya, R. Joshi, R. Gajendran "An Approach to Model Right Iliac Fossa Pain using Pain-only-parameters for Screening of Acute Appendicitis", Journal of Medical Systems Vol. 36, pp. 1491-1502, 2012.
• M. Yetirajam, M. R. Nayak, S. Chattopadhyay "Design of Fuzzy Logic Controller to Enhance the Operation of Cricket Bowling Machine", International Journal of Computer Technology and Applications, Vol. 3, No. 5, pp. 1662-1666, 2012.
• T. Dash, S. Chattopadhyay, T. Nayak "Handwritten Signature Verification using Adaptive Resonance Theory Type-2 (ART-2) Net". Journal of Global Research in Computer Science Vol. 3, No. 8, pp. 21-25, 2012.
• S. Chattopadhyay S. , R. Saurabh, L. Land, U. R. Acharya "Studying Infant Mortality Rate: A Data Mining Approach", Health and Technology Vol. 1, No. 1, pp. 25-34, 2011.
• S. Chattopadhyay, F. Daneshgar "A Study on Suicidal Risks in Psychiatric Adults". International Journal of Biomedical Engineering and Technology Vol. 5, No. 4, pp. 390-408, 2011.
• P. Ray, S. Chattopadhyay "Fuzzy Awareness Model for Disaster Situations". Intelligent Decision Technologies: an international journal [Special Issue on Intelligent Decision Making in Dynamic Environments: Methods, Architectures and Applications] Vol. 3, No. 1, pp. 75-82, 2009.
• S. Chattopadhyay 'A Study on Suicidal Risk Analysis'. In proceedings of 9th IEEE Intl. Conf. on e-Health Networking, Applications and Service (HEALTHCOM 2007), pp. 74-79, Taipei, Taiwan, 2007.
• J. Rocha, T. Pravlidis,"A Shape analysis model with application to a character recognition system," IEEE Trans. on Pattern Analysis and Machine Intelligence , vol. 16, pp. 393-404, 1994.
• J. U. Duncombe, "Infrared navigation—Part I: An assessment of feasibility," IEEE Trans. Electron Devices, vol. ED-11, pp. 34-39, Jan. 1959.
• M. K. Shukla, Dr. H. Banka, "A Study of Different Kinds of Degradation in Printed Bengali Script", International Journal of Advanced Computer Engineering and Architecture Vol. 2, pp. 143-151, 2012.
• C. B. Bose and S-S Kuo, "Connected and degraded text recognition using Hidden Markov Model", Pattern Recognition, Vol. 27, No. 10, pp. 1345-1363, 1994.
• S-W Lee, D-J. Lee, and H-S Park, "A New Methodology for Gray-Scale Character Segmentation and Recognition", IEEE Transactions on PAMI, Vol. 18, No. 10, pp. 1045-1050, 1996.
• S. Kahan, T. Pavlidis, and H. S. Baird, "On the recognition of printed characters of any font and size", IEEE Transactions on PAMI, Vol. 9, No. 2, pp. 274 – 288, 1987.
• S. Tsujimoto and H. Asada, "Resolving Ambiguity in Segmenting Touching Characters", Ist Int. Conference on Document Analysis and Recognition, Saint-Malo, France, pp. 701-709, Oct. 1991.
• R. G. Casey and G. Nagy, "Recursive Segmentation and Classification of Composite Character Patterns", Proc. 6th Int. Conf. on Pattern Recognition, Munich, Germany, pp. 1023-1026, 1982.
• T. Hong, "Degraded text recognition using visual and linguistic context", Ph. D. Thesis, Computer Science Department of SUNY at Buffalo, 1995.
• Y. Lu, "Machine printed character segmentation – An overview", Pattern Recognition, Vol. 28, No. 1, pp. 67-80, 1995.
• B. B. Chaudhuri, U. Pal, and M. Mitra, "Automatic Recognition of Printed Oriya Script", ICDAR, pp. 795-799, 2001.
• M. K. Jindal, G. S. Lehal, and R. K. Sharma, "Segmentation problems and solutions in printed Degraded Gurmukhi Script", International Journal of Signal Processing, Vol. 2, No. 4, pp. 258-267, 2005.
• G. S. Lehal and C. Singh, "Text segmentation of machine printed Gurmukhi script", Document Recognition and Retrieval VIII, Proceedings SPIE, USA, Vol. 4307, pp. 223-231, 2001.
• G. S. Lehal and C. Singh, "A technique for segmentation of Gurmukhi script", Computer Analysis of Images and Patterns, Proceedings CAIP 2001, Warsaw, Poland, Lecture Notes in Computer Science, Springer-Verlag, Vol. 2127, pp. 191-200, 2001.
• V. Bansal and R. M. K. Sinha, "Segmentation of touching and fused Devanagari characters", Pattern Recognition, Vol. 35, No. 4, pp. 875-893, 2002.
• Yetirajam M. , Nayak M. R. , Chattopadhyay S. "Recognition and Classification of Broken Characters using Feed Forward Neural Network to Enhance an OCR Solution", International Journal of Advanced Research in Computer Engineering & Technology, Vol. 1, No. 8, pp. 11-15, 2012.
• Sahu S. K, Sahani S. , Jena P. K,, Chattopadhyay S. "Fingerprint Identification System using Tree based Matching", International Journal of Computer Applications Vol. 53, No. 10, pp. 11-16.
• C. Sumetphong , S. Tangwongsan , " Recognizing Broken Thai Characters Based on Set-Partitions and N-grams Graphs," Journal Of Pattern Recognition Research, vol. 7 , pp. 26-41,2012.
• R. I. Gandhi, N. F. Abubacker, "An Extended method for recognition of broken typewritten characters special reference to tamil scripts," in Proc. IEEE Conf. , Open Systems (ICOS), pp. 214-219, 2011.
• A. H. Pilevar, M. T. Pilevar, "Broken and Touching Characters Recognition in Persian Text Documents", world Applied Sciences Journal Vol. 13, No. 6, pp. 1459-1464, 2011.
• L. L. Sulem, M. Sigelle, "Recognition of degraded characters using dynamic Bayesian networks," Journal of pattern Recognition, vol. 41, pp. 3092-3103, 2008.
• D. Yu, H. Yan, "Reconstruction of broken handwritten digits based on structural morphological features," The Journal of Pattern Recognition Society, vol. 34, pp. 235-254, 2001.
• S. Chattopadhyay "Neurofuzzy Models to Automate the Grading of Old-age Depression". Expert Systems: the Journal of Knowledge Engineering (2012); DOI: 10. 1111/exsy. 12000.
• T. Dash, T. Nayak, S. Chattopadhyay "Offline Handwritten Signature Verification using Associative Memory Net". International Journal of Advanced Research in Computer Engineering & Technology, Vol. 1, No. 4, pp. 370-374, 2012.
• Dash T. , Nayak T. , Chattopadhyay S. "Handwritten Signature Verification (Offline) using Neural Network Approaches: A Comparative Study", International Journal of Computer Applications Vol. 57, No. 7, pp. 33-41.
• Dash T. , Nayak T. , Chattopadhyay S. "Offline Verification of Hand Written Signature Using Adaptive Resonance Theory Net (Type-1)". In the proceedings of the 4th International Conference on Electronic Computer Technology (ICECT-2012 Vol-2) Kanyakumari, India (6-8 April'12). Editor: Yuan Li, pp. 205-210.
• S. S. Behera, S. Bhanja Choudhuri, S. Chattopadhyay "A Comparative Study on Neural Net Classifier Optimizations". International Journal of Advanced Engineering and Technology, Vol. 4, No. 2, pp. 179-187, 2012.
• S. Chattopadhyay, P. Kaur, F. A. Rabhi, U. R. Acharya "Neural Network Approaches to Grade Adult Depression", Journal of Medical Systems, Vol. 36, No. 5, pp. 2803-2815, 2012.
• A. Dasari, N. B. Hui, S. Chattopadhyay "A Neuro-fuzzy System for Modeling the Depression Data", International Journal of Computer Applications, Vol. 53, No. 6, pp. 1-6, 2012.
• S. S. Behera, S. Chattopadhyay "A Comparative Study of Back Propagation and Simulated Annealing Algorithms for Neural Net Classifier Optimization", International Conference on Modelling Optimization and Computing (ICMOC-2012) Nagercoli, Tamilnadu India Vol. 38, pp. 448-455, (10-11 April 2012).
• K. Krishna, A. Goyal, S. Chattopadhyay "Non-correlated Character Recognition using Hopfield Network: A Study". In the proceedings of International Conference on Computer and Computational Intelligence (ICCCI-2011) (Ed. Yi Xie) pp. 385-389 Bangkok, Thailand (2-4th December) 2011.
• S. Chattopadhyay, P. Kaur, F. A. Rabh, U. R. Acharya "An Automated System to Diagnose the Severity of Adult Depression". In the proceedings of 2nd International Conference on Emerging Applications of Information Technology (CSI EAIT-2011), 19-20th February Kolkata India, (Editors - Jana D. , and Pal P. ), pp. 121-124. Publishers: IEEE Computer Society and Conference Publishing Services IEEE Xplore.