Fuzzy rule-based image exposure level estimation and adaptive gamma correction for contrast enhancement in dark images
Ajay Khunteta, Debashis Ghosh, Ribhu · 2012
Image enhancement of badly illuminated dark images is always a challenging as well as an important task in image processing. A technique which is often used to increase the contrast of dark images is gamma correction. However, the value of gamma suitable for appropriate enhancement of a given image remains a question. In this paper, we propose to first estimate the level of exposure in the input image using fuzzy reasoning that is based on a set of fuzzy rules. Following this, we derive the gamma value as a function of the exposure level. Also, we propose to apply the gamma correction on the negative of the input image since it produces a better contrast compared to the conventional gamma correction. The proposed method was applied to several badly illuminated images, both gray and color, and the results obtained were compared to that obtained using histogram equalization.