WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 14, 2017
PAWs Segmentation by Intrinsic/discriminant Dual Modeling Based on a Hierarchical Organization of Arab Grapheme and the Curves Bezier
Authors: ,
Abstract: We propose in this work an approach to segmentation of Arabic texts printed offline open vocabulary. The method is based on human perception using their natural power for segmentation. The novelty of our work is in the analysis of this type of approach on complex fonts and calligraphy has strong ligatures; we propose an artificial segmentation feature extraction based on the use of structural primitives for a robust description of the different morphological variability font considered. The proposed algorithm yielded results quite satisfactory with an extension for the resolution of a particular case of the sub-segmentation. This model has enabled us to increase significantly the recognition performance and develop a recognition system open vocabulary.
Search Articles
Pages: 201-212
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 14, 2017, Art. #22