Title :
Robust handwritten word recognition with fuzzy sets
Author :
Gader, Paul ; Chiang, Jung-Hsien
Author_Institution :
Missouri Univ., Columbia, MO, USA
Abstract :
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
Keywords :
character recognition; feedforward neural nets; fuzzy set theory; handwriting recognition; multilayer perceptrons; self-organising feature maps; Choquet fuzzy integrals; Kohonen Self Organizing Feature Map; fuzzy sets; handwritten word recognition; handwritten words; hybrid fuzzy neural system; hybrid neural system; multi-layer feedforward network; word recognition; Assembly; Dictionaries; Dynamic programming; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Handwriting recognition; Image recognition; Image segmentation; Robustness;
Conference_Titel :
Uncertainty Modeling and Analysis, 1995, and Annual Conference of the North American Fuzzy Information Processing Society. Proceedings of ISUMA - NAFIPS '95., Third International Symposium on
Conference_Location :
College Park, MD
Print_ISBN :
0-8186-7126-2
DOI :
10.1109/ISUMA.1995.527693
