New Approach for the Skeletonization of Handwritten Characters in Gray-Level Images

Existing skeletonization methods operate directly on the binary image ignoring the gray-level information. In this paper we propose a new method for the skeletonization of handwritten characters that uses graylevel information and capitalizes on their elongated pattern properties. The method controls the development of the skeleton while iteratively binarizing the gray-level image. Two types of iterations are performed: the iterative skeletonization and deletion of boundary pixels, which is nested within the iterative binarization of the gray-level image. Detailed analysis of the skeletonization process is presented to show its superior performance related to the prevention of \ ooding water" and end point shrinkage and to noise immunity.

• Type: Conference
• Year: 2003
• Where: ICDAR
• Authors: Amer Dawoud, Mohamed Kamel
• Keywords: Document Analysis, Elongated Pattern Properties, Gray-level Image, Gray-level Information, ICDAR 2003