Robust handwritten word recognition with fuzzy sets

Paul Gader, Jung-Hsien Chiang

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

A hybrid fuzzy neural system is used to improve a handwritten word recognition algorithm. The word recognition algorithm matches digital images of handwritten words to strings in a lexicon. This algorithm requires a module to assign character class membership values to images of segments of handwritten words. Many of these images are not characters. It is shown that a hybrid neural system consisting of a cascade of a Kohonen Self-Organizing Feature Map (SOFM) followed by Choquet fuzzy integrals can yield improved performance over a multi-layer feedforward network (MLFN). The hybrid method scored a word recognition rate of 85% compared to 77% for the MLFN method.

原文English
主出版物標題Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc
發行者IEEE
頁面198-203
頁數6
出版狀態Published - 1995
事件Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95) - College Park, MD, USA
持續時間: 1995 九月 171995 九月 20

Other

OtherProceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95)
城市College Park, MD, USA
期間95-09-1795-09-20

    指紋

All Science Journal Classification (ASJC) codes

  • Engineering(all)

引用此

Gader, P., & Chiang, J-H. (1995). Robust handwritten word recognition with fuzzy sets. 於 Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc (頁 198-203). IEEE.