Skeletonization of binary images with nonuniform width via block decomposition and contour vector matching

Thinning is a very important preprocessing step for many image analysis operations, such as optical character recognition and fingerprint recognition. The main drawbacks of traditional thinning algorithms are low speed and serious deformation. To remedy these problems, a novel approach which generates the skeletons of binary patterns via block decomposition and contour vector matching is proposed in this paper. The proposed skeletonization mechanism not only skeletonizes binary patterns but also vectorizes the generated skeletons simultaneously. In our approach, the considered binary image is first decomposed into several smaller blocks. Then, the block skeleton is generated for each decomposed block. The generated block skeletons are gathered to form the skeleton of the considered image. Last, the gaps inside or between block skeletons are filled based on the block connectivity information to form the final intact skeleton. The performance of the proposed algorithm is compared with existing algorithms. Experimental results confirm the superiority of our proposed approach.