Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

This is an Open Access publication published under CSC-OpenAccess Policy.
Publications from CSC-OpenAccess Library are being accessed from over 158 countries worldwide.
Faster Training Algorithms in Neural Network Based Approach For Handwritten Text Recognition
Haradhan Chel, Aurpan Majumder, Debashis Nandi
Pages - 358 - 371     |    Revised - 15-08-2013     |    Published - 15-09-2013
Volume - 7   Issue - 4    |    Publication Date - September 2013  Table of Contents
Transition Feature, Sliding Window Amplitude Feature, Contour Feature, Scaled Conjugate Gradient.
Handwritten text and character recognition is a challenging task compared to recognition of handwritten numeral and computer printed text due to its large variety in nature. As practical pattern recognition problems uses bulk data and there is a one step self sufficient deterministic theory to resolve recognition problems by calculating inverse of Hessian Matrix and multiplication the inverse matrix it with first order local gradient vector. But in practical cases when neural network is large the inversing operation of the Hessian Matrix is not manageable and another condition must be satisfied the Hessian Matrix must be positive definite which may not be satishfied. In these cases some repetitive recursive models are taken. In several research work in past decade it was experienced that Neural Network based approach provides most reliable performance in handwritten character and text recognition but recognition performance depends upon some important factors like no of training samples, reliable features and no of features per character, training time, variety of handwriting etc. Important features from different types of handwriting are collected and are fed to the neural network for training. It is true that more no of features increases test efficiency but it takes longer time to converge the error curve. To reduce this training time effectively proper train algorithm should be chosen so that the system provides best train and test efficiency in least possible time that is to provide the system fastest intelligence. We have used several second order conjugate gradient algorithms for training of neural network. We have found that Scaled Conjugate Gradient Algorithm , a second order training algorithm as the fastest for training of neural network for our application. Training using SCG takes minimum time with excellent test efficiency. A scanned handwritten text is taken as input and character level segmentation is done. Some important and reliable features from each character are extracted and used as input to a neural network for training. When the error level reaches into a satisfactory level (10 -12 ) weights are accepted for testing a test script. Finally a lexicon matching algorithm solves the minor misclassification problems.
1 Google Scholar 
2 CiteSeerX 
3 refSeek 
4 Scribd 
5 SlideShare 
6 PdfSR 
1 S-B. Cho,“Neural-Network Classifiers for Recognizing Totally Unconstrained Handwritten Numerals”, IEEE Trans. on Neural Networks, vol.8, 1997, pp. 43-53.
2 Verma, B. “A Contour Code Feature Based Segmentation For Handwriting Recognition”, 7th IAPR International conference on Document Analysis and Recognition, ICDAR’03, 2003,pp. 1203-07.
3 N.W. Strathy, C.Y. Suen and A. Krzyzak, “Segmentation of Handwritten Digits using Contour Features”, ICDAR ‘93,1993, pp. 577-580.2003.
4 R G Casey and E Lecolinet “A Survey of Methods and Strategies in Character Segmentation,”IEEE Trans. Pattern analysis and Machine Intelligence, vol. 18, 1996, pp. 690-706.
5 Fletcher, R., and C.M. Reeves “Function minimization by conjugate gradients” the computer journal, vol-7 149-153, 1964.
6 D. Gorgevik and D. Cakmakov,An Efficient Three-Stage Classifier for Handwritten Digit Recognition, ICPR, vol. 4, 2004, pp. 507-510.
7 Gernot A. Fink, Thomas Plotz, “On Appearance-Based feature Extraction Methods for WriterIndependent Handwritten Text Recognition” Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR’05) 1520-5263/05.
8 C. E. Dunn and P. S. P. Wang, “Character Segmentation Techniques for Handwritten Text A Survey Proceedings of the II n International Conference on Pattern Recognition, The Hague,The Netherlands,1992 pp 577-580.
9 Matthias Zimmermann and Horst Bunke “Optimizing the Integration of a Statistical Language Model in HMM based Offline Handwritten Text Recognition” .Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04) 1051- 4651/04.
10 . Hestenes, M.” conjugate Direction Methods In Optimization”, Springer-verlag, New York,1980.
11 S-W. Lee,“Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network”. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 18,1996, pp. 648-652.
12 P. D. Gader, M. Mohamed and J-H. Chiang, ‘Handwritten Word Recognition with Character and Inter-Character Neural Networks”, IEEE Transactions on Systems, Man, and Cybernetics-Part B:Cybernetics, vol .27, 1997, pp. 158-164.
13 Blumenstein and B. Verma. “Neural–based solutions for the segmentation and recognition of difficult handwritten words from a benchmark database”. In Proc. 5th International Conference on Document Analysis and Recognition, pages 281–284 Bangalore, India,1999.
14 J-H. Chiang, “A Hybrid Neural Model in Handwritten Word Recognition”, Neural Networks,vol. 1I, 1998, pp. 337-346.
15 Simon Haykin ‘Neural Networks A comprehensive Foundation’,second edition.
16 R.O.Duda ,P.E. Hart , D.G.stock ‘Pattern classification’ second edition.
17 William K.Pratt ‘DIGITAL IMAGE PROCESSING’ Third edition.
18 . S.Rajeshkaran and G.A. Vijayalakshmi Pai ‘Neural Networks, Fuzzy Logic, and Genetic Algorithms Synthesis and Applications.’ Eastern Economy Edition.
19 . K.M.Khoda, Y.Liu and C. Storey “Generalized Polak –Ribiere Algorithm” journal of optimization theory and application: vol 75,No 2,November 1992.
20 Verma, B.; Hong Lee;’ A Segmentation based Adaptive Approach for Cursive Hand written Text Recognition Neural Networks, 2007. IJCNN 2007. International Joint Conference on 12-17 Aug. 2007 Page(s):2212 – 2216 Digital Object Identifier 10.1109/IJCNN.2007.4371301.
21 Fletcher, R.(1975). “practical methods of optimization “. New York: John Wiley & Sons.
22 Martin Fodslette Moller. “A Scaled Conjugate Gradient Algorithm For Fast Supervised Learning.” Neural Networks, vol 6:525-533, 1993.
23 M. Blumenstein and B. Verma “Neural-based Solutions for the Segmentation and Recognition of Difficult Handwritten Words from a Benchmark Database” In Proc. 5th International Conference on Document Analysis and recognition, pages 281–284,Bangalore, India, 1999.
24 Y. H. Dai and Y. Yuan, Convergence properties of the Beale-Powell restart algorithm,Sci.China Ser. A, 41 (1998), pp. 1142-1150.
25 U. Pal, N. Sharma, T. Wakabayashi, F. Kimura, "Off-line handwritten character recognition of Devanagari script", Proceedings of 9th international conference on document analysis and recognition , vol. 1, pp. 496-500, 2007.
26 Haradhan Chel, Aurpan Majumder, Debashis nandi, “Scaled Conjugate Gradient Algorithm in Neural NetworkBased Approach for Handwritten Text Recognition” D. Nagamalai, E.Renault, M. Dhanushkodi (Eds.): CCSEIT 2011, CCIS 204, pp. 196–210, 2011.
27 P. Gader, M. Whalen, M. Ganzberger, and D. Hepp. “Handprinted word recognition on a NIST dataset. Machine Vision and Applications, 8:31–41, 1995.
Mr. Haradhan Chel
Dept. of Electronics and Communication CIT Kokrajhar, Assam - India
Mr. Aurpan Majumder
Dept. of Electronics and Communication NIT Durgapur, West Bengal - India
Dr. Debashis Nandi
Dept. of Electronics and Communication NIT Durgapur, West Bengal - India