Automatic prediction of saliency on JPEG distorted images

Anish Mittal, Anush K. Moorthy, Alan C. Bovik, Lawrence K. CormackQoMEX 2011 · OpenReview

Abstract

We propose an algorithm to detect salient regions for JPEG distorted images for two tasks: quality assessment and free viewing. The algorithm extracts low-level features such as contrast, luminance, quality and so on and uses a machine-learning framework to predict salient regions in JPEG distorted images. We demonstrate that the automatically predicted regions-of-interest highly correlate with those from (human) ground truth saliency maps. Further, we evaluate the relevance of extracted low-level features for saliency prediction and analyze how incorporation of quality as a feature improves prediction performance as a function of the distortion severity. Applications of such a saliency prediction framework include developing novel pooling strategies for image quality assessment.
BibTeX
@inproceedings{mittal2011automatic,
  author = {Anish Mittal and Anush K. Moorthy and Alan C. Bovik and Lawrence K. Cormack},
  title = {{Automatic prediction of saliency on JPEG distorted images}},
  booktitle = {QoMEX},
  year = {2011},
  url = {https://openreview.net/forum?id=g3Wafq8L8zA},
}

Loading related content...

Figure