Contrast enhancement based on discriminative co-occurrence statistics

• Published in: Multimedia tools and applications Vol. 80; no. 4; pp. 6413 - 6442
• Main Authors: Wu, X., Sun, Y., Kawanishi, T., Kashino, K.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2021; Springer Nature B.V
• Subjects: Brightness; Cameras; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Deep learning; Equalization; Histograms; Image contrast; Image enhancement; Laboratories; Light; Methods; Multimedia; Multimedia Information Systems; Optimization; Pixels; Reflectance; Special Purpose and Application-Based Systems; 2D Histogram; Retinex model; Contrast enhancement; Image enhancement; Histogram equalization; Reflectance
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-020-09948-6

Despite recent advances in contrast enhancement, it remains difficult for existing methods to simultaneously achieve consistent improvements in image brightness and contrast in both low-light and normal-light images. To address this issue, we revisit 2D histogram equalization methods and extend them to accommodate more diversified and poor lighting conditions. The extension is based on the observation that the contrast needs to be improved by increasing the intensity difference between spatially neighboring pixels, while the degree of increase should be proportional to the difference in their reflectances. On the basis of this observation, we propose to embed the inter-pixel contextual information of image reflectance into the 2D histogram of intensity co-occurrence. An intensity mapping function can thus be derived by solving optimization problems formulated with the 2D histogram, leading to two novel contrast enhancement methods. Qualitative and quantitative evaluations on more than 600 images showed that the proposed methods are superior to state-of-the-art contrast enhancement methods. It was also shown that the reflectance of an image provides important visual information on the significance and objectness of local image areas. Using this reflectance as a clue, the degree of contrast enhancement can be adaptively derived to achieve sufficient brightness improvement in low-light images and to avoid excessive enhancement in normal-light images.