A contour character extraction approach in conjunction with a neural confidence fusion technique for the segmentation of handwriting recognition

The purpose of this paper is to present a novel neural network based algorithm to improve the segmentation process of cursive handwriting recognition and a detailed analysis of the performance of the algorithm on a benchmark database. The algorithm is based on a technique to fuse left character, center character and neural validation confidence values. A technique is proposed to extract a character between two segmentation points, which avoids vertical segmentation. Also a fusion technique and a technique to over-segment the words are described in this paper. A large number of experiments were conducted and an extensive analysis of comparative results on a benchmark database is included. The segmentation results obtained are very promising.