Edge Detection of Noisy Medical Images Based Mixed Entropy

Abstract

Edge detection of medical image has used as one of diagnostics techniques largely applied for the doctor's diagnosis determination. Although the edge detection of medical images is existing since years but it is still challenging and scope of research. It has been found that the previous used algorithms were not able to produce optimized or ideal results in different cases. In most applications, medical images contain object boundaries and object shadows and noise. Therefore, they may be difficult to distinguish the exact edge from noise or trivial geometric features. In this paper, we propose a new efficient algorithm for edge detection of noisy medical images based on mixed entropy. Mixed entropy  is defined in order to suppress noise and adapt to different edge in the image. Our target is to get the best edge representation under noise effect. The performance of our algorithm is compared against other methods using images corrupted with various levels of "salt and pepper". It is observed that the proposed algorithm displayed superior noise resilience and decrease the computation time. The results indicate the accuracy of the proposed edge-detection method is superior to that of conventional edge-detection methods for medical image.

Keywords: Edge Detection; Medical Images ; Entropy; Noisy Image.