Title :
A new system for reading handwritten zip codes
Author :
Strathy, N.W. ; Suen, C.Y.
Author_Institution :
Centre for Pattern Recognition & Machine Intelligence, Concordia Univ., Montreal, Que., Canada
Abstract :
A new method of reading the handwritten zip codes in the U.S. Postal Services CD-ROM database is presented. Zip code images are binarized, segmented and recognised. A recognition driven method for splitting multiple connected digits has been developed; for grouping together of broken digits, the system targets components with near-touching stroke tips, 5-hats, and 4-Ls. The digit recogniser is a majority vote combination of 3 neural networks with a zero rejection performance of 96.53% on the 2711 imperfectly segmented digits in the cedarbs test set. With digit splitting capability disabled, the system performance on the 930 whole zip codes of the test set is 61.0% correct with no errors when up to two rejected symbol positions are allowed. With digit splitting enabled the performance rises to 66.3%
Keywords :
image recognition; image segmentation; neural nets; postal services; U.S. Postal Services CD-ROM database; broken digit grouping; cedarbs test set; digit recogniser; handwritten zip code reading; imperfectly segmented digits; majority vote neural network combination; multiple connected digit splitting; near-touching stroke tips; rejected symbol positions; zero rejection performance; zip code image binarization; zip code image recognition; zip code image segmentation; CD-ROMs; Image databases; Image recognition; Image segmentation; Neural networks; Postal services; System performance; Target recognition; Testing; Voting;
Conference_Titel :
Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-8186-7128-9
DOI :
10.1109/ICDAR.1995.598947
