Multi scale top-hat transform based algorithm for image enhancement

To efficiently enhance images, a multi scale top-hat transform based algorithm is proposed in this paper. Firstly, the multi scale white and black regions are extracted by using structuring elements with the same shape and increasing sizes. Then, two types of multi scale image features, which are multi scale white and black image regions at each scale and multi scale detail image regions between neighboring scales, are used to form the final extracted white and black image regions. Finally, the image is enhanced through enlarging the contrast between the extracted white and black image regions. Experimental results on images from different applications verified that the proposed algorithm could efficiently enhance the contrast and image details. And, the proposed algorithm produces very few noise regions. Therefore, the proposed algorithm could be widely used in different applications.