MUSCLE     EC project no. FP6-507752 MUSCLE 
DAR     MSMT grant 1M6798555601 DAR
 

Image Retrieval Measures Based on Illumination Invariant Textural MRF Features

  Pavel Vacha     Michal Haindl

Abstract:
Content-based image retrieval (CBIR) systems, target database images using feature similarities with respect to the query. We introduce fast and robust image retrieval measures that utilise novel illumination invariant features extracted from three different Markov random field (MRF) based texture representations. These measures allow retrieving images with similar scenes comprising colour-textured objects viewed with different illumination brightness or spectrum.
The proposed illumination insensitive measures are compared favourably with the most frequently used features like the Local Binary Patterns, steerable pyramid and Gabor textural features, respectively. The superiority of these new illumination invariant measures and their robustness to added noise are empirically demonstrated in the illumination invariant recognition of textures from the Outex database.

Demonstration

Original textures were acquired from Outex database. Resolution 100dpi, angle 00, all illuminations.


Video of Texture retrieval (65MB, 4:18, XDIV AVI):   part 1 (noise),   part 2,   part 3,   part 4  



Screenshot
Screenshot



Further information can be found in the paper:
Vacha P., Haindl M.,
Image retrieval measures based on illumination invariant textural mrf features,
in: ACM International Conference on Image and Video Retrieval (CIVR’07). ACM, July 9-11 2007
   Back to the demonstration page.