Title :
Confidence computation improvement in an optical field reading system
Author :
Benedetti, Arrigo ; Kovács-V, Zsolt M.
Author_Institution :
Dipt. di Sci. dell´´Ingegneria, Modena Univ., Italy
Abstract :
An expression in closed form is derived for the recognition error vs. rejection rate of optical character or word recognition systems. This expression allows to define a lower bound for the error rate of any recognition system employing a rejection process based on the definition of a confidence threshold. This relation has also proved to be useful to make a quantitative comparison between two confidence computation methods implemented in a system for reading USA Census ´90 hand-written forms. The newly proposed method is based upon a confidence model integrating single-character confidence levels, digram statistics and other information from the dictionary matching phase. At a 50% rejection rate, the field error rate calculated using the new confidence computation algorithm decreased from 47.7% to 44.6%, which represents a considerable improvement, given a theoretical lower bound of 40.8% on the error rate
Keywords :
document image processing; handwriting recognition; optical character recognition; statistics; string matching; US Census hand-written forms; closed form expression; confidence computation algorithm; confidence threshold; dictionary matching phase; digram statistics; error rate lower bound; field error rate; optical character recognition systems; optical field reading system; recognition error; rejection rate; single-character confidence levels; word recognition systems; Character recognition; Dictionaries; Error analysis; Gratings; Handwriting recognition; Image generation; Image recognition; Optical computing; Robustness; Statistics;
Conference_Titel :
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on
Conference_Location :
Ulm
Print_ISBN :
0-8186-7898-4
DOI :
10.1109/ICDAR.1997.620629