Toward a generic hybrid neural system for handwriting recognition: an application to arabic words

Title:

Toward a generic hybrid neural system for handwriting recognition: an application to arabic words

Creator:

Souici , L. and Meslati , D.

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:7479dc28-f323-4d8d-9512-85d981c55d14
uuid:7479dc28-f323-4d8d-9512-85d981c55d14

Subject:

Neuro-symbolic combination, handwriting recognition, Arabic word recognition, and knowledge based neural networks

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

In this article, we propose an automated construction of knowledge based artificial neural networks (KBANN) for the recognition of restricted sets of handwritten words or characters. The features that better describe the chosen vocabulary are first selected, according to the characteristics of the used script, language and lexicon. Then, ideal samples of lexicon elements (words or characters) are submitted to a feature extraction module to derive their description using the chosen primitives. The analysis of these descriptions generates a symbolic knowledge base reflecting a hierarchical classification of the words (or characters). The rules are then translated into a multilayer neural network by determining precisely its architecture and initializing its connections with specific values. This construction approach reduces the training stage, which enables the network to reach its final topology and to generalize. The proposed method has been tested on the automated construction of neuro-symbolic classifiers for two Arabic word lexicons.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2006 Volume:16 | Number:4

Harvested from:

CDK

Metadata only:

false