A Rotation Invariant Image Retrieval with Local Features

  • You, Hee-Jun (Department Electrical and Electronic Engineering, Yonsei University) ;
  • Shin, Dae-Kyu (Telecommunication R & D Center, Samsung Electronics Co., LTD.,) ;
  • Kim, Dong-Hoon (Mobile Communication Division, Samsung Electronics Co., LTD.,) ;
  • Kim, Hyun-Sool (Mobile Communication Division, Samsung Electronics Co., LTD.,) ;
  • Park, Sang-Hui (Department Electrical and Electronic Engineering, Yonsei University)
  • Published : 2003.09.01

Abstract

Content-based image retrieval is the research of images from database, that are visually similar to given image examples. Gabor functions and Gabor filters are regarded as excellent methods for feature extraction and texture segmentation. However, they have a disadvantage not to perform well in case of a rotated image because of its direction-oriented filter. This paper proposes a method of extracting local texture features from blocks with central interest points detected in an image and a rotation invariant Gabor wavelet filter. We also propose a method of comparing pattern histograms of features classified by VQ (Vector Quantization) among images.

Keywords

References

  1. JISC Technology Applications Report:39 Content-based image retrieval J. Eakins;M. Graham
  2. JISC Technology Application A review of content-based image retrieval systems C. C. Venters;M. Cooper
  3. IEEE Trans. ASSP v.36 Complete discrete 2d gabor transforms by neural networks for image analysis and compression J. G. Daugman
  4. IEEE International Symposium on Circuits and Systems Gabor filter for rotation invariant texture classification R. Porter;N. Canagarajah
  5. IEEE Trans. Pattern Analysis and Machine Intelligence v.19 no.5 Local grayvalue invariants for image retrieval C. Schmid;R. Mohr
  6. Proc. 4th Alvey Vision Conference A combined corner and edge detector C. Harris;M. Stephens
  7. IEEE Trans. Pattern Analysis and Machine Intelligence v.12 no.1 Multi-channel texture analysis using localized spatial filters A. C. Bovik;M. Clark;W. S Geisler
  8. IEEE Trans. on Communications v.COM-28 no.1 An algorithm for vector quantizer deign Y Linde;A. Buzo;R. M. Gray
  9. International J. Computer Vision v.7 no.1 Color indexing M. J. Swain;D. H. Ballad
  10. IEEE Trans. on Pattern Analysis and Machine Intelligence v.12 no.5 Invariant image recognition by zernike moments A. Khotanzad;Y. H. Hong
  11. Pattern Recongnition v.29 no.8 Image retrieval using color and shape A. K. Jain;A. Vailaya
  12. Electronics Letters v.38 no.11 Image retrieval using VQ-based local Gabor feature D. K. Shin;H. S. Kim;T. Y. Chung;T. S. Kim;S. H. Park