Fusion of Explicit Segmentation Based System and Segmentation-Free Based System for On-Line Arabic Handwritten Word Recognition

Hanen Khlif (1) , Sophea Prum (2) , Yousri Kessentini (1) , Slim Kanoun (3) , Jean-Marc Ogier (4)

1 Université de Sfax - University of Sfax
2 IDDC
3 MIRACL - Multimedia, InfoRmation systems and Advanced Computing Laboratory
4 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

The complexity and viariability of the Arabic handwriting makes difficult the implementation of an efficient recognition system through the use of a unique recognition engine. In this paper, two handwriting word recognition systems are combined in order to take advantage of their complementarities. The first one is a segmentation free based system that uses the generative classifier HMM. The second system is discriminative based. Relying on analytical approach, it proceeds with explicit segmentation of words into graphemes. Different combination strategies are compared including sum, product, Borda count and Dempster-Shafer rules. The experimental results conducted on ADAB database demonstrate a significant improvement of recognition accuracy of 5% compared to the segmentation free based system and 9% compared to the analytical based system.

Mots clés: on-line handwriting Arabic word recognition segmentation free; analytical approach; HMM; SVM; information fusion

Domaines: Traitement du texte et du document; Traitement des images [eess.IV]; Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Hanen Khlif, Sophea Prum, Yousri Kessentini, Slim Kanoun, Jean-Marc Ogier. Fusion of Explicit Segmentation Based System and Segmentation-Free Based System for On-Line Arabic Handwritten Word Recognition. 5th International Conference on Frontiers in Handwriting Recognition (ICFHR 2016), Oct 2016, Shenzhen, China. pp.399-404, ⟨10.1109/ICFHR.2016.0081⟩. ⟨hal-03030186⟩