论文信息 - Handwritten Word Recognit ion for Real-Time Applications

Handwritten Word Recognit ion for Real-Time Applications

A fast handwritten word recognition system for real time applications is presented in this paper. Preprocessing, segmentation and feature extraction are implemented using chain code representation. Dynamic matching between each character of a lexicon entry and segment(s) of input word image is used for ranking words in the lexicon. Speed of the entire recognition process is about 200 msec on a single SPARC-IO platform for lexicon size of 10. A top choice performance of 96% is achieved on a database of postal words captured at 212dpi.

Gyeonghwan Kim | Venu Govindaraju

[1] H. Sakoe,et al. Two-level DP-matching--A dynamic programming-based pattern matching algorithm for connected word recognition , 1979 .

[2] C. Myers,et al. A level building dynamic time warping algorithm for connected word recognition , 1981 .

[3] J.-C. Simon,et al. Off-line cursive word recognition , 1992, Proc. IEEE.

[4] Hermann Ney. A Comparative Study of Two Search Strategies for Connected Word Recognition: Dynamic Programming and Heuristic Search , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[5] Herbert Freeman,et al. Computer Processing of Line-Drawing Images , 1974, CSUR.