In this paper, we propose a practical scheme for multi-lingual) multi-font, and multi-size large-set character recognition using self-organizing neural network. In order to improve the performance of the proposed scheme, a nonlinear shape normalization based on dot density and three kinds of hierarchical features are introduced. For coarse classification, two kinds of classifiers are proposed. One is a hierarchical tree classifier, and the other is a SOFM/LVQ based classifier which is composed of an adaptive SOFM coarseclassifier and LVQ4 language-classifiers. For fine classification, an LVQ4 classifier has been adopted. In order to evaluate the performance of the proposed scheme, recognition experiments with 3,367,200 characters having 7,320 diflerent classes have been carried out on a 486 DX-2 66MHz PC. Experimental results reveal that the proposed scheme using an adaptive SOFM coarse-classifier, LVQ4 languageclassifiers, and LVQ4 fine-classifiers has high recognition rate of over 98.27% and fast execution time of more than 40 characters per second.
|Title of host publication||Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995|
|Publisher||IEEE Computer Society|
|Number of pages||6|
|Publication status||Published - 1995|
|Event||3rd International Conference on Document Analysis and Recognition, ICDAR 1995 - Montreal, Canada|
Duration: 1995 Aug 14 → 1995 Aug 16
|Name||Proceedings of the International Conference on Document Analysis and Recognition, ICDAR|
|Conference||3rd International Conference on Document Analysis and Recognition, ICDAR 1995|
|Period||95/8/14 → 95/8/16|
Bibliographical noteFunding Information:
Classification Method 2 Method 1 This research was supported by the POSDATA Co.
© 1995 IEEE.
Copyright 2019 Elsevier B.V., All rights reserved.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition