Integrated segmentation and recognition of handwritten numerals with cascade neural network
- 1 May 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)
- Vol. 29 (2), 285-290
- https://doi.org/10.1109/5326.760572
Abstract
In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.Keywords
This publication has 10 references indexed in Scilit:
- Reliable online human signature verification systemsIeee Transactions On Pattern Analysis and Machine Intelligence, 1996
- Nonlinear shape normalization methods for the recognition of large-set handwritten charactersPattern Recognition, 1994
- INTEGRATED SEGMENTATION AND RECOGNITION THROUGH EXHAUSTIVE SCANS OR LEARNED SACCADIC JUMPSInternational Journal of Pattern Recognition and Artificial Intelligence, 1993
- Segmentation methods for character recognition: from segmentation to document structure analysisProceedings of the IEEE, 1992
- Reading handwritten digits: a ZIP code recognition systemComputer, 1992
- Recognition of letters in lateral printed strings using a three‐layered BP model with feedback connectionsSystems and Computers in Japan, 1992
- Recognizing Hand-Printed Letters and Digits Using Backpropagation LearningNeural Computation, 1991
- A time-delay neural network architecture for isolated word recognitionNeural Networks, 1990
- Off-line cursive script word recognitionIeee Transactions On Pattern Analysis and Machine Intelligence, 1989
- Classification of handprinted Kanji characters by the structured segment matching methodPattern Recognition Letters, 1983