| Paper ID | IVMSP-32.5 |
| Paper Title |
CAPTURING BANDING IN IMAGES: DATABASE CONSTRUCTION AND OBJECTIVE ASSESSMENT |
| Authors |
Akshay Kapoor, Jatin Sapra, Zhou Wang, University of Waterloo, Canada |
| Session | IVMSP-32: Applications 4 |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Image, Video, and Multidimensional Signal Processing: [IVSMR] Image & Video Sensing, Modeling, and Representation |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
With the fast technology advancement and the accelerated growth of high-quality image and video production and services, banding or false contour has become a frequently observed artifact in images, creating annoying negative impact on the visual quality-of-experience (QoE) of end users. Nevertheless, thorough investigations on the causes of banding, and effective and efficient methods to detect and reduce banding are largely lacking. This work targets at capturing and quantifying banding artifacts in images. We construct the first of its kind large-scale public database, consisting of 1,200 images with segmented banding regions and 169,501 image patches with class labels. We also develop a deep neural network based no-reference deep banding index (DBI), which not only produces an overall banding assessment of a given image, but also creates a banding map that indicates the variation of banding across the image space. Our experiments show that the proposed method achieves accurate banding prediction with low computational cost. The database and the proposed algorithm will be made publicly available. |
