HANDWRITTEN CHARACTER RECOGNITION USING MODIFIED GRADIENT DESCENT TECHNIQUE OF NEURAL NETWORKS AND REPRESENTATION OF CONJUGATE DESCENT FOR TRAINING PATTERNS

The purpose of this study is to analyze the performance of Back propagation algorithm with changing training patterns and the second momentum term in feed forward neural networks. This analysis is conducted on 250 different words of three small letters from the English alphabet. These words are presented to two vertical segmentation programs which are designed in MATLAB and based on portions (1/2 and 2/3) of average height of words, for segmentation into characters. These characters are clubbed together after binarization to form training patterns for neural network. Network was trained by adjusting the connection strengths on each iteration by introducing the second momentum term. This term alters the process of connection strength fast and efficiently. The conjugate gradient descent of each presented training pattern was found to identify the error minima for each training pattern. The network was trained to learn its behavior by presenting each one of the 5 samples (final input samples having 26 × 5 = 130 letters) 100 times to it, thus achieved 500 trials indicate the significant difference between the two momentum variables in the data sets presented to the neural network. The results indicate that the segmentation based on 2/3 portion of height yields better segmentation and the performance of the neural network was more convergent and accurate for the learning with newly introduced momentum term.

[1]  Federico Girosi,et al.  Reducing the run-time complexity of Support Vector Machines , 1999 .

[2]  Sargur N. Srihari,et al.  Recognition of handwritten and machine-printed text for postal address interpretation , 1993, Pattern Recognit. Lett..

[3]  Hamid Lesani,et al.  DISTRIBUTION SYSTEMS RECONFIGURATION USING PATTERN RECOGNIZER NEURAL NETWORKS , 2002 .

[4]  Bernhard Schölkopf,et al.  Support Vector methods in learning and feature extraction , 1998 .

[5]  Bernhard Schölkopf,et al.  Improving the Accuracy and Speed of Support Vector Machines , 1996, NIPS.

[6]  Sung-Bae Cho,et al.  Neural-network classifiers for recognizing totally unconstrained handwritten numerals , 1997, IEEE Trans. Neural Networks.

[7]  Farzin Mokhtarian,et al.  Cursive handwriting recognition using hidden Markov models and a lexicon-driven level building algorithm , 2000 .

[8]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Brijesh Verma,et al.  A new segmentation algorithm for handwritten word recognition , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[10]  Csaba Rekeczky,et al.  Analogic Preprocessing And Segmentation Algorithms For Offline Handwriting Recognition , 2003, J. Circuits Syst. Comput..

[11]  Paul D. Gader,et al.  Fusion of handwritten word classifiers , 1996, Pattern Recognit. Lett..

[12]  Himanshu Joshi,et al.  OFFLINE HANDWRITING RECOGNITION USING GENETIC ALGORITHM , 2008 .

[13]  Ching Y. Suen,et al.  Building a new generation of handwriting recognition systems , 1993, Pattern Recognit. Lett..

[14]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Eric Lecolinet,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Jian Zhou,et al.  Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Patrick Shen-Pei Wang,et al.  Feedback-based architecture for reading courtesy amounts on checks , 2003, J. Electronic Imaging.

[18]  Seong-Whan Lee,et al.  Multilayer cluster neural network for totally unconstrained handwritten numeral recognition , 1995, Neural Networks.

[19]  Xiaoqing Ding,et al.  Handwritten character recognition using gradient feature and quadratic classifier with multiple discrimination schemes , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[20]  Alexander H. Waibel,et al.  Online handwriting recognition: the NPen++ recognizer , 2001, International Journal on Document Analysis and Recognition.

[21]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[22]  Elisa Ricci,et al.  Reduced complexity RBF classifiers with support vector centres and dynamic decay adjustment , 2006, Neurocomputing.

[23]  Amar Gupta,et al.  A system for processing handwritten bank checks automatically , 2008, Image Vis. Comput..

[24]  P. Cunningham,et al.  Using Neural Nets for Decision Support in Prescription and Outcome Prediction in Anticoagulation Drug Therapy , 2000 .

[25]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[26]  Jung-Hsien Chiang,et al.  Recognition of handprinted numerals in VISA® card application forms , 1997, Machine Vision and Applications.

[27]  Gyeonghwan Kim,et al.  A Lexicon Driven Approach to Handwritten Word Recognition for Real-Time Applications , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Alexander S. Dmitriev,et al.  Information processing using dynamical chaos: neural networks implementation , 1996, IEEE Trans. Neural Networks.

[29]  Michael S. Schmidt,et al.  Identifying Speakers With Support Vector Networks , 1996 .