A novel technique for the blind assessment of image degradation due to compression

  • Authors:
  • Ankan Bhattacharya;Sarbani Palit;Gourav Roy

  • Affiliations:
  • Indian Statistical Institute, Kolkata, India;Indian Statistical Institute, Kolkata, India;Tata Consultancy Services, Bangalore, India

  • Venue:
  • Proceedings of the 27th Conference on Image and Vision Computing New Zealand
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

A new approach is proposed for the quality assessment of images undergoing JPEG compression. The approach is especially designed to handle degradation due to compression. It is completely blind and requires neither a reference image nor an external watermark. This feature makes the algorithm particularly attractive for situations where quality assessment must be done without having access to the original image. The watermark is constructed from the image itself in such a way that it is not only fragile but also changes smoothly with the distortion of the image brought about by compression. The fragile watermark is embedded as a robust signature in the image. The Discrete Wavelet Transform (DWT) is used to separate the medium and high frequency (detail) from the low frequency (approximation) parts of the image. The watermark is made from the low frequency region and embedded into the medium and high frequency regions. As compression has a far greater impact on the medium and high frequency regions, the quality of the watermark thus embedded, deteriorates when the image is compressed. Simulations on a large number of well-known images have been used to demonstrate the performance of the proposed approach.