Title :
A system for cursive handwritten address recognition
Author :
Mao, Jianchang ; Sinha, Prasun ; Mohiuddin, K.
Author_Institution :
IBM Almaden Res. Center, San Jose, CA, USA
Abstract :
This paper presents a cursive handwritten address recognition system, which consists of four main modules; 1) over-segmentor, 2) dynamic zip locator, 3) zip candidates generator, and 4) city-state-zip verifier. The dynamic zip locator and city-state-zip verifier are based on a flexible matcher for matching a sequence of graphemes with a list of generalized strings. The dynamic zip locator is able to locate zip without knowing exactly where the zip starts. The zip candidates generator uses a hidden Markov model with position-dependent state transition probabilities. A scheme for utilizing prefixes is designed to reduce computation and memory requirement. Finally, the system employs a mechanism for rejection based on rank features extracted from the matching. The overall system achieves an acceptance rate of 83.5% with 3.6% error for 5-digit encoding on 805 USPS cursive address images
Keywords :
feature extraction; handwritten character recognition; hidden Markov models; mailing systems; pattern matching; probability; automatic mail sorting; cursive handwritten character recognition; encoding; graphemes; hidden Markov model; pattern matching; postal address recognition; rank feature extraction; state transition probability; zip code locator; zip verifier; Computer science; Electronic switching systems; Encoding; Handwriting recognition; Hidden Markov models; Infrared detectors; Optical character recognition software; Postal services; Read only memory; Sorting;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711936
