Title :
Two simple cooperating neural systems for efficient handwritten digit recognition
Author :
Autret, Y. ; Thépaut, A.
Author_Institution :
Lab. LIMI, Univ. de Bretagne Occidentale, Brest, France
Abstract :
In this paper we focus on “off-line” recognition with unknown scriptor. We only consider isolated digits. We present an approach whose aim is simplicity and performance. Two simple neural solutions are first presented. Their main characteristic is nonneural pretreatment reduced as much as possible. A simple method for integration is then proposed. The method has been evaluated on a database from French postal services (SRTP). This database contains 12000 digits and is kept secret
Keywords :
neural nets; optical character recognition; French postal services; SRTP; cooperating neural systems; database; efficient handwritten digit recognition; isolated digits; off-line recognition; unknown scriptor; Biological neural networks; Brain; Data mining; Databases; Feature extraction; Handwriting recognition; Image recognition; Performance evaluation; Postal services; Sorting;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.489017
