Non-linear weight adjustment in adaptive gamma correction for image contrast enhancement

Image enhancement remains an intricate problem, crucial for image analysis. Several algorithms exist for the same. A few among these algorithms categorize images into different classes based on their statistical parameters and apply separate enhancement functions for each class. One such algorithm is the well-known adaptive gamma correction (AGC) algorithm. It works well for each class of images, but fails when the statistical parameters lie on the boundary of separation of two classes. We have developed an enhancement algorithm which can enhance images which lie on the boundary of separation equally well, as images which lie deep inside the boundary. The basic idea behind the algorithm is to combine the different enhancement functions of AGC using non-linear weight adjustments. Both contrast and brightness have been modified using these weight adjustments. We have conducted experiments on a data-set consisting of 9979 images. Results show that by using the proposed algorithm, average entropy of the enhanced images increases by 3.97%and average root mean square (rms) increases by 14.29%over AGC. Visual improvement is also perceivable.

Automated summary

This study introduces an image enhancement algorithm that can handle images at classification boundaries, showing promising results in experiments with increased entropy and root mean square values, as well as noticeable visual improvement over the AGC algorithm.