Adaptive clip limit for contrast limited adaptive histogram equalization (CLAHE) of medical images using least mean square algorithm

Automated detection of abnormalities in human body is a critical application medical image computing. Preprocessing of medical image is of great need as the image quality of the captured images is highly attenuated due to several factors. In this work, we propose a novel idea of using the concepts of adaptive processing (LMS algorithm) for the estimation of clip limit for CLAHE. Statistical metrics like AMBE and PSNR are used for optimum window size selection for CLAHE. The algorithm proposed in this paper has been implemented on TMS320C6713T DSP for real time application and 60 images from STARE, DDSM and OASIS databases have been tested and analyzed. All the tested images show a better result in terms of SSIM index.