Demonstration of image retrieval based on illumination invariant textural MRF features

ABSTRACT

Content-based image retrieval (CBIR) systems target database images using feature similarities with respect to the query. Our CBIR demonstration utilises novel illumination invariant features, which are extracted from Markov random field (MRF) based texture representations. These features allow retrieving images with similar scenes comprising colour-textured objects viewed with different illumination brightness or spectrum. The illumination invariant retrieval is verified on textures from the Outex database.

REFERENCES

• 1: Timo Ojala , Topi Mäenpää , Matti Pietikäinen , Jaakko Viertola , Juha Kyllönen , Sami Huovinen, Outex - New Framework for Empirical Evaluation of Texture Analysis Algorithms, Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1, p.10701, August 11-15, 2002
• 2: Pavel Vacha , Michal Haindl, Image retrieval measures based on illumination invariant textural MRF features, Proceedings of the 6th ACM international conference on Image and video retrieval, p.448-454, July 09-11, 2007, Amsterdam, The Netherlands [doi>10.1145/1282280.1282346]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.7 Feature Measurement
          Subjects: Invariants; Texture

General Terms:
Algorithms, Verification

Keywords:
Markov random fields (MRF), content-based image retrieval (CBIR), demonstration, illumination invariants