Segmentation of Touching Component in Arabic Manuscripts

Touching components are connection zones occurring between text-lines or words of the same line and are one of the problems that make unconstrained handwritten text segmentation greatly hard. In this paper, we propose a recognition based method to separate these components once localized in Arabic manuscript images. It first identifies, for a given touching component, a similar model stored in a dictionary with its correct segmentation, using shape context descriptor and an interpolation function. Then, it segment the touching component based on the distance from the midpoints of the identified model's parts. Tests are performed using a database of touching components and two metrics: Manhattan and Euclidean distances. Experimental results show the effectiveness of the proposed segmentation method.