Title :
A fault tolerant Chinese bank check recognition system
Author :
Song, Wang ; Bin, Zhao ; Feng, Ma ; Tao, Zhang ; Gengjian, MA ; Shaowei, Xia
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
In this paper, a practical fault-tolerant Chinese bank check recognition system is presented and analyzed in detail. The first part discusses some preprocessing technologies including software-location of the scanned check skew correction of each sub-image containing various numeral strings and segmentation of these strings. Then, a high performance SOM classifier is adopted as the classifier to the segmented numerals. After that, a new idea of fault-tolerant recognition is proposed and the post-processing method is introduced. This system reaches high accuracy and high reliability simultaneously
Keywords :
bank data processing; fault tolerant computing; image segmentation; optical character recognition; fault tolerant Chinese bank check recognition system; image segmentation; preprocessing technologies; reliability; Automation; Color; Fault tolerance; Fault tolerant systems; Forgery; Handwriting recognition; Image recognition; Optical character recognition software; Paper technology; Seals;
Conference_Titel :
Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4253-4
DOI :
10.1109/ICIPS.1997.669171