Benchaou, Soukaina University Mohammed 1 - EST - Labo MATSI, Morocco , Nasri, M’barek University Mohammed 1 - EST - Labo MATSI, Morocco , El Melhaoui, Ouafae University Mohammed 1 - EST - Labo MATSI, Morocco , Bouali, Bouchta University Mohammed 1 - FS - Labo AGA, Morocco

New structural approach for numeral recognition based on mathematical morphology and Freeman code

15237

This paper proposes a new structural approach of features extraction for handwritten, printed and isolated numeral recognition based on Freeman code method. The new approach consists first of contour detection and closing it by morphological operators. Then, the Freeman code was applied by widening its directions to 24-connectivity instead of 8-connectivity. Numeral recognition is carried out in this work through k nearest neighbors. The recognition rate obtained by the proposed method is improved indicating that the numeral features extracted contain more details.

159

Structural approach , handwritten and printed numeral recognition , features extraction , Freeman chain code , mathematical morphology , K nearest neighbors

Mediterranean Telecommunications Journal

163