Image enhancement based on contrast limited adaptive histogram equalization for 3D images of stereoscopic endoscopy

Abstract

Image enhancement is an important function of stereoscopic endoscopy. 3D images of stereoscopic endoscopy usually suffer from various kinds of degradation because of undesired noise, inhomogeneous brightness and poor contrast. In addition, it often contains color mismatch and different luminance between two stereo views. It will lead to many problems applying traditional image enhancement methods for 3D images of stereoscopic endoscopy. In order to solve those problems, we proposed a novel image enhancement algorithm which consists of three steps: adjusting image by contrast limited adaptive histogram equalization method, choosing the reference image and color matching. The experimental results show that the proposed algorithm produces high quality 3D images by improving image contrast, enhancing the details of the image obviously, removing the color cast and improving consistency of two stereo views. Therefore, the proposed method can obtain high quality 3D images under stressful conditions and be easily applied to stereoscopic endoscopy.