IMAGE CONTRAST ENHANCEMENT USING MODIFIED DCT

Abstract

Image enhancement plays a significant role in image processing. Devices are able to capture and process images from complex surveillance monitoring systems. However, the quality of captured images is degraded during the acquisition process because of poor lighting and incorrect setting of the aperture or the speed of shutter or both. Due to the deficiencies in image acquisition process the acquired image may have low contrast images which contain noisy background. In addition, there are several reasons for images to have poor contrast: due to the poor quality device used to capture the image, inexpertness of the operator or because of the unfavourable environmental condition at the time of acquisition. To overcome the artifacts, noise and unnatural enhancement an effective enhancement method for gray scale images is introduced. The proposed method consists of two parts. First, a global contrast enhancement method is introduced. This method uses sigmoid function and histogram to generate the distribution function for the input images. Then the distribution function is used to obtain the new image with improved global contrast. Second, the DCT coefficients of the previous improved contrast image are scale using entropy. The proposed method generate an enhance image with richer details and better contrast compared to the conventional methods.