A Neighborhood Dependent Nonlinear Technique for Enhancement of Color Images Captured Under Non-Uniform Lighting Conditions

The aim of image enhancement process is to improve the interpretability of the information in images for human viewers or to provide better input for automated image processing techniques. Many image processing applications begin with a nonlinear enhancement process to improve visual quality of video sequences captured under nonuniform lighting conditions. This improves the visibility of the scene captured from physical sensing devices which have limited dynamic range. This physical limitation causes the saturated region of the image to either shadow out or wash out the rest of the scene. When extremely bright and dark regions are present in an image, the object details in the low intensity areas as well as in the high intensity areas cannot be clearly interpreted. It is therefore desirable to bring back a more uniform scene which eliminates the shadows and overexposed regions to a certain extent. In this thesis, an image enhancement algorithm based on a neighborhood dependent nonlinear model is presented to improve visual quality of digital images captured under extremely non-uniform lighting conditions. This thesis presents techniques for adaptive and simultaneous intensity enhancement of extremely dark and bright images, contrast enhancement, and color restoration. The core idea of the algorithm is the development of a nonlinear sine transfer function with an image dependent parameter. Adaptive computation of the control parameter increases flexibility in enhancing the dark regions and compressing overexposed regions in an image. A neighborhood dependent approach is employed for contrast enhancement. A linear color restoration process is used to obtain color image from the enhanced intensity image by utilizing the chromatic information of the original image. It is observed that the proposed algorithm yields visually optimal results on images captured under extreme lighting conditions. Further, research work is progressing at application of ratio rule for color restoration to produce color constant images.