Feature extraction based on fuzzy set theory for handwriting recognition
Natanael Gomes, Lee Luan Ling · 2002
The paper presents a method based on fuzzy set theory for extracting features from handwritten words. After the feature extraction and word segmentation process, a handwritten word is represented by an ordered sequence of line segments. For each of these segments, membership values for fuzzy sets are calculated, representing different types of curved lines and straight lines. The position of the line segments in a letter or piece of a letter resulting from the word segmentation is also evaluated by means of fuzzy sets. Fuzzy hidden Markov models are employed to classify the handwritten words. A database comprising handwritten words extracted from Brazilian bank checks is used to test the proposed system.