Integrated segmentation and recognition of handwritten numerals with cascade neural network

Proposes an integrated image segmentation and recognition method using a new type of cascade neural network that has been is developed to train the spatial dependencies in connected handwritten numerals. This network was originally extended from a multilayer feedforward neural network in order to improve its discrimination and generalization power. To verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numerals databases have been performed. The experimental results reveal that the proposed method has a higher discrimination and generalization power than previous integrated segmentation and recognition methods have had. Moreover, the network size of the proposed method is smaller than that of the previous methods.

[1]  Yoshiyuki Yamashita,et al.  Classification of handprinted Kanji characters by the structured segment matching method , 1983, Pattern Recognit. Lett..

[2]  James A. Pittman,et al.  Integrated Segmentation and Recognition Through Exhaustive Scans or Learned Saccadic Jumps , 1993, Int. J. Pattern Recognit. Artif. Intell..

[3]  Seong-Whan Lee,et al.  Nonlinear shape normalization methods for the recognition of large-set handwritten characters , 1994, Pattern Recognit..

[4]  Sargur N. Srihari,et al.  Off-Line Cursive Script Word Recognition , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Toby Berger,et al.  Reliable On-Line Human Signature Verification Systems , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[7]  James D. Keeler,et al.  A Self-Organizing Integrated Segmentation and Recognition Neural Net , 1991, NIPS.

[8]  J.-C. Simon,et al.  Off-line cursive word recognition , 1992, Proc. IEEE.

[9]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning , 1991, Neural Computation.

[10]  Yoshiki Uchikawa,et al.  Recognition of letters in lateral printed strings using a three-layered BP model with feedback connections , 1992, Systems and Computers in Japan.

[11]  David E. Rumelhart,et al.  Self-organizing integrated segmentation and recognition neural network , 1992, Defense, Security, and Sensing.

[12]  Lawrence D. Jackel,et al.  Constrained neural network for unconstrained handwritten digit recognition , 1990 .

[13]  Geoffrey E. Hinton,et al.  A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.

[14]  Isabelle Guyon,et al.  Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[15]  Yasuaki Nakano,et al.  Segmentation methods for character recognition: from segmentation to document structure analysis , 1992, Proc. IEEE.

[16]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits , 1989, NIPS.

[17]  Yann LeCun,et al.  Multi-Digit Recognition Using a Space Displacement Neural Network , 1991, NIPS.

[18]  Lawrence D. Jackel,et al.  Reading handwritten digits: a ZIP code recognition system , 1992, Computer.