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.
|Number of pages
|IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
|Published - 1999
Bibliographical noteFunding Information:
Manuscript received March 18, 1996; revised September 1, 1998. This work was supported by the Hallym Academy of Science, Hallym University and the Creative Research Initiatives of the Korea Ministry of Science and Technology. A preliminary version of this paper was presented at the Third International Conference on Document Analysis and Recognition, Montreal, P.Q., Canada, August 1995.
ASJC Scopus subject areas
- Control and Systems Engineering
- Information Systems
- Human-Computer Interaction
- Computer Science Applications
- Electrical and Electronic Engineering