Image contrast enhancement is an essential process that improves the visibility of many features that may remain hidden due to low-contrast conditions arising from environmental causes, limitations of the device, or the wrong setting of the camera. This paper introduces a new technique of image contrast enhancement that combines insights from social sciences and image processing. In this model, the intensity of each pixel represents the opinion of an individual, and all the neighboring pixels interact by influencing each other. The algorithm operates to first increase the similarity of those pixels in the regions where pixels maintain similar intensities and, second, to amplify the differences in regions where differences exist. This process increases the contrast in regions with significant differences and reduces variation in uniform regions, hence enhancing clarity in the visual information and details of the image. The effectiveness and high performance of the proposed method are evaluated by a variety of experiments conducted on different image datasets using different quality indexes. The results obtained after experimentation highlight the superiority of the approach with respect to the state-of-the-art techniques of contrast enhancement.