Fuzzy image enhancement for low contrast and non-uniform illumination images

Abstract

This paper presents the fuzzy image enhancement for low contrast and non-uniform illumination images. A new fuzzy intensity measure is proposed to distinguish between the dark and bright regions. This measure is computed by considering the average intensity and deviation of the intensity distribution of the image. The input image is enhanced using a power-law transformation. Implementation of the proposed algorithm on the non-uniform illumination and low contrast images show that the proposed algorithm outperforms the other enhancement techniques. The proposed algorithm produces more even illumination with improvement in the details and contrasts. In addition, the proposed algorithm is computationally fast to be implemented in real time application.