Effects of improved Adaptive Gamma Correction Method on Wireless Capsule Endoscopy images: Illumination compensation and edge detection

Abstract

Several methods for adjusting image contrast have been developed in the field of image processing for image enhancement. Illumination is one of the most significant factors affecting the appearance of an image. Improper illumination causes a variety of problems in practice and thus, it is necessary to compensate for nonuniform illumination. Wireless Capsule Endoscopy (WCE) images suffer from this problem too. We propose an improved Adaptive Gamma Correction Method (AGCM) to compensate for nonuniform illumination in WCE color images.The experiments have shown that the proposed AGCM performs well in improving image quality. The WCE images obtained with AGCM are also better than those obtained with histogram equalization and adaptive histogram equalization in terms of brightness constancy, overall visual rendition and contrast. The Peak Signal to Noise Ratio (PSNR) and Contrast to Noise Ratio (CNR) values are also higher for AGCM than for other correction algorithms. Also, the differences between edge pixels and neighboring pixels in the WCE images are increased. We use a color variant of the canny operator for color edge detection. By using this method, 65% of the borders are detected correctly, while the detection rate is 45% without using this method.