Color image contrast enhancement using a local equalization and weighted sum approach

摘要

Image contrast enhancement is a fundamental step taken to ensure the effectiveness of subsequent image-related processes. In additional to subjective quality evaluation, objective user viewing is also a common performance requirement. However, canonical global histogram equalization methods which though produce a higher information content may give rise to viewing un-comfort due to over-fitting the two ends of the intensity range. A strategy of local sector enhancement by histogram equalization is proposed in this research to mitigate that drawback. The image is first divided into sectors and they are independently enhanced by histogram equalization. Intermediate images are then generated recursively using this method and a resultant image is obtained by a weighted-sum aggregation on the basis of an intensity gradient measure. Local sectors with higher contrast dominate the others thus achieving overall global contrast enhancement. Experimental results from tests conducted on a variety of samples such as indoor, outdoor, and imperfect illumination images have shown the effectiveness of the proposed method.