Robust Visual Content Representation Using Compression Modes Driven Low-level Visual Descriptors

  • Authors:

  • Charith Abhayaratne;Farooq Muzammil

  • Affiliations:

  • Department of Electronic and Electrical Engineering, University of Sheffield, Sheffield, United Kingdom S1 3JD;Department of Electronic and Electrical Engineering, University of Sheffield, Sheffield, United Kingdom S1 3JD

  • Venue:
  • MMM '09 Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia Modeling
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In conventional visual content representation, low-level visual features are usually extracted from the highest quality and resolutions of visual contents. When visual content is scalable coded and utilised, their bit streams can be adapted at various nodes in multimedia usage chains to cater the variations in network bandwidths, display device resolutions and resources and usage preferences by just discarding insignificant resolution-quality layers. This can result in the existence of different version of the same content with dissimilar low-level visual features. Therefore, mapping of low level visual descriptors into content resolution-quality spaces is important in order to obtain low-level visual features that are robust to such content adaptations. A new scalable domain feature extraction using the compression modes and decisions is presented and its content based image retrieval performance is evaluated. The proposed scheme outperforms MPEG-7 visual descriptors in both the original image and scaled resolution-quality space domains.