An efficient method of image identification by combining image features

ABSTRACT

This paper proposes an efficient image identification method by combining image features and using image clustering. For more efficient image identification, we use global and local features in a hierarchical manner. The combined global feature reflecting general information of image helps faster retrieval of candidate images and the feature point based local feature facilitates more accurate fine matching with the candidate images. We consider the Fuzzy C-Means clustering method since it is effective for the image data which are characteristically alike and have fuzzy boundary in coordinate by their global features. The global feature vector which we use is very effective in clustering and retrieval since it represents general properties of image and its dimension is very low. As a result, the number of fine matching which requires very large computing time and high complexity is considerably decreased since searching original image of query is done by fine matching within partial database of candidate images.

REFERENCES

• 1: Michael J. Swain , Dana H. Ballard, Color indexing, International Journal of Computer Vision, v.7 n.1, p.11-32, Nov. 1991 [doi>10.1007/BF00130487]
• 2: S. O. Shim and T. S. Choi, "Edge Color Histogram For Image Retrieval", IEEE ICIP 2002, Vol. 3, pp. 957--960 (2002)
• 3: B. S. Manjunath, J. R. Ohm, V. V. Vasudevan and A. Yamada, "Color and Texture Descriptors", IEEE Transaction on Circuits and Systems for Video Technology, Vol. 11, No. 6, pp. 703--715 (2001)
• 4: J. S. Seo, J. Haitsma, T. Kalker and C. D. Yoo, "A robust image fingerprinting system using the Radon transform", Signal Processing: Image Communication, Vol. 19, No. 14, pp. 325--339 (2004)
• 5: Alexander Kadyrov , Maria Petrou, The Trace Transform and Its Applications, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.23 n.8, p.811-828, August 2001 [doi>10.1109/34.946986]
• 6: P. Ballester, "Hough transform and astronomical data analysis", Vistas in Astronomy, Vol. 40, No. 4, pp. 479--485
• 7: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 8: J. K. Jeong, H. Y. Jeon, and C. J. Hwang, "An Image Identification Method based on Radon Transform", International Technical Conference on Circuits/Systems, Computers and Communications, July 2007
• 9: http://www.mathworks.com/access/helpdesk/help/techdoc/index.html
• 10: James C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithms, Kluwer Academic Publishers, Norwell, MA, 1981

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
        I.4.10 Image Representation

General Terms:
Algorithms, Performance

Keywords:
clustering, descriptor, feature point, global feature, identifier, image identification, image retrieval, interest point, local feature