Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
537056 | Signal Processing: Image Communication | 2011 | 11 Pages |
Abstract
No-reference (NR) image quality assessment (QA) presumes no prior knowledge of reference (distortion-free) images and seeks to quantitatively predict visual quality solely from the distorted images. We develop kurtosis-based NR quality measures for JPEG2000 compressed images in this paper. The proposed measures are based on either 1-D or 2-D kurtosis in the discrete cosine transform (DCT) domain of general image blocks. Comprehensive testing demonstrates their good consistency with subjective quality scores as well as satisfactory performance in comparison with both the representative full-reference (FR) and state-of-the-art NR image quality measures.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Jing Zhang, S.H. Ong, Thinh M. Le,