Contrast Enhancement of Dark Images using Weighted Blending of Bright Channel Prior and Robust Retinex Method

The image took in the dark light has low contrast, which affects the clarity of details in it. This results in the loss of information and details in poorly illuminated images. Such images are not suitable for computer vision analysis and observations. In many places, images taken in the dark light like CCTV images at night, military, satellite images, medical images, etc. Several methods proposed for contrast enhancement of low light (darker) images like histogram equalization, bright channel prior, camera response model, and robust retinex model. The contrast enhancement gone using existing methods have some limitations like getting blurring effect, getting over the brightening of details. To overcome these disadvantages, the paper proposes the contrast enhancement of darker images with the weighted blending of bright channel prior (BCR) and robust retinex model (RRM) with different assigned weights. For the performance evaluation of the variations of the proposed method, the image entropy value is computed. From the experimentation done on images from the ExDark dataset, it observed that the proposed weighted blending based contrast enhancement method gives better performance over existing BCR and RRM.