Contrast enhancement based on discriminative co-occurrence statistics
- PDF / 12,412,621 Bytes
- 30 Pages / 439.642 x 666.49 pts Page_size
- 100 Downloads / 181 Views
Contrast enhancement based on discriminative co-occurrence statistics X. Wu1
· Y. Sun2 · T. Kawanishi1 · K. Kashino1
Received: 25 June 2020 / Revised: 9 September 2020 / Accepted: 17 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract 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.
X. Wu
[email protected] Y. Sun [email protected] T. Kawanishi [email protected] K. Kashino [email protected] 1
Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi-shi, Kanagawa, 243-0198, Japan
2
Media Intelligence Laboratories, NTT Corporation, 1-1 Hikarinooka, Yokosuka-shi, Kanagawa, 239-0847, Japan
Multimedia Tools and Applications
Keywords 2D Histogram · Contrast enhancement · Histogram equalization · Image enhancement · Reflectance · Retinex model
1 Introduction The aim of contrast enhancement is to enhance the contrast in images with a low dynamic range and reveal hidden image details. The rapid development of emerging digital imaging devices has significantly increased the number of digital images and the demand for contrast enhancement. However, images with a low dynamic range due to low lighting and underexposure not only prevent users from easily understanding the image content, but also increase the difficulty of basic computer vision tasks such as object detection, segmentation, and tracking. Commercial raster graphic editors allow users to interactively adjust images, but it is difficult for nonprofessionals to manipulate color and contrast simultaneously and efficiently. Modern mobile p
Data Loading...
