Learning Optimization in a MLP Neural Network Applied to OCR

Autor:	Rafael Esteban Bello Pérez, Yanetsy Sardiñas Oliva, Adolfo Díaz Sardiñas, Isis Bonet Cruz
Rok vydání:	2002
Předmět:	Imagination Artificial neural network Computer science business.industry media_common.quotation_subject Image processing Optical character recognition computer.software_genre Machine learning Backpropagation Artificial intelligence business Heuristics computer Classifier (UML) media_common
Zdroj:	MICAI 2002: Advances in Artificial Intelligence ISBN: 9783540434757 MICAI
Popis:	This paper focuses on the possibilities of optimization of the training process of an MLP neural net using Backpropagation as a learning algorithm, employed as a classifier in an Optical Character Recognition (OCR) application. Also, the process for determination of a set of optimal parameters describing the characters that conform each class is described. The processing and analysis of the images in BMP, GIF, JPG and TIF format are included. A comparative study of the possibilities of improvement of the learning process of an MLP net employing heuristics for its design and training is made. As a fundamental result a substantial improvement of the net learning process is obtained and an OCR of great reliability is built.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e802653e2accb21b413b819619212808 https://doi.org/10.1007/3-540-46016-0_31 Zobrazit plný text záznamu