Intensity and edge based adaptive unsharp masking filter for color image enhancement

Enhancement of image quality is a fundamental process for a wide range of vision-based applications. Images captured under unfavorable environments are often degraded in information content, sharpness and colorfulness. In the attempts to improve an image, the unsharp masking filter is an attractive candidate for its computational efficiency. However, the filter is vulnerable to the over-range problem where pixel magnitudes are driven beyond permissible ranges. This drawback is particularly noticeable if a non-adaptive procedure is used in the enhancement. Hence, an adaptive gain adjustment method is proposed here aiming at minimizing the number of over-range pixels while maximizing the image sharpness and information content. In this method, colorfulness is improved via color channel stretching and contrast is enhanced by edge augmentation. Specifically, a hyperbolic-tangent function, whose scale is dependent on the original image intensity and detected edges, is constructed to adjust the gain in sharpness enhancement. A collection of natural images captured under poor illumination conditions are used in the test against conventional and mask-based image enhancement approaches. Results have demonstrated that the proposed method outperforms the others with regard to colorfulness, information content, and sharpness.