An Algorithm for Image Binarization Based on Adaptive Threshold

In this paper it discusses the existing algorithm of image binarization, and then proposes a new approach for image binarization based on adaptive threshold. The image binarization is treated as an optimization problem where the best threshold could be found out by partitioning binarization of Ostu threshold, meanwhile the algorithm of eliminating boundary effects is proposed to perfect the purpose of binarization optimization. The new approach is compared with a classic binarization method. Finally the experimental result shows that the new method is better in keeping the original edge feature and available to more applications, especially in obtaining better effects of binarization optimization on images with rich edge information.