Combining Wavelet Saliency, Color and DCT Coefficients for Content-Based Image Retrieval
This paper presents an approach for content-based image retrieval extracting salient points and regions from images, and also aggregating color and DCT values in a signature descriptor for recognition. Salient points and regions are extracted from each image by a wavelet decomposition over the color channels where the highest coefficients in coarsest levels are the centers of salient regions in finest resolution. These local regions are support for extracting color histograms and a set of DCT magnitudes in order to derive a signature for the image. A feature vector combining histograms of color channels and DCT values is proposed and tested as signature of the image. Public COIL, Caltech, and ZuBuD images datasets are used for testing. Results comparing variations of the descriptor based on wavelet saliency are given on all those image datasets supporting potential for the proposed method.
Keywordscontent-based image retrieval wavelet salient points global signature category recognition
- 1.Bimbo, A.D.: Visual Information Retrieval. Morgan Kaufmann (1999)Google Scholar
- 2.Caltech: Caltech Categories Site (2014), http://www.vision.caltech.edu/html-files/archive.html (accessed May 4, 2014)
- 6.Loupias, E., Sebe, N., Brest, S., Jolion, J.: Wavelet-based salient points for image retrieval. In: ICIP 2000, vol. 2, pp. 518–521. IEEE (2000)Google Scholar
- 10.Nayar, S., Nene, S., Murase, H.: Columbia object image library (coil 100). Tech. rep., Dept Computer Science, Columbia University, USA (1996)Google Scholar
- 12.Shao, H., Svoboda, T., Van Gool, L.: Zubud: zurich buildings database for image based recognition. Tech. rep., Computer Vision Lab, Swiss Federal Institute of Technology, Switzerland (2003)Google Scholar