Content-Based Image Retrieval Using Color Co-occurrence Matrices and Wavelet Transform Subbands

International Journal of Computer Science and Technology | Vol. 7, No. 4, April 2005 | pp. 25–32

DOI: 10.46882/2005/IJCST/070407

Research Article

Title: Content-Based Image Retrieval Using Color Co-occurrence Matrices and Wavelet Transform Subbands

Names of Authors: Min-Seok Kim¹, Fatma Al-Jahani²

Authors’ Affiliations: ¹Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea; ²Department of Computer Science, Qatar University, Doha, Qatar

Abstract:
As large digital image repositories become increasingly common, standard textual indexing approaches are no longer sufficient for precise image search and retrieval. This paper presents an integrated Content-Based Image Retrieval (CBIR) method that captures spatial color structures and high-frequency textural properties simultaneously. Spatial color distributions are computed using customized Color Co-occurrence Matrices (CCCM), while micro-texture feature extractions are derived from Discrete Wavelet Transform (DWT) subband coefficient variances. The system was validated against the Corel 1,000-image benchmark dataset. Experimental results demonstrate a mean precision rate of P = 89.4% and a recall index of R = 82.1% across ten distinct semantic image categories. This configuration outperformed standard color histogram indexing frameworks by 16.3% in precision. The average indexing query response execution time was recorded at t = 68 ms per retrieval iteration, establishing a reliable baseline for large-scale multimedia search tasks.

Keywords: Content-Based Image Retrieval, Color Co-occurrence Matrix, Discrete Wavelet Transform, Texture Features, Multimedia Databases

Manuscript Timeline: Received January 05, 2005; Revised February 18, 2005; Accepted March 12, 2005; Published April 21, 2005

Citation: Kim, M. S., & Al-Jahani, F. (2005). Content-Based Image Retrieval Using Color Co-occurrence Matrices and Wavelet Transform Subbands. International Journal of Computer Science and Technology, 7(4), 25–32.

Subscribe to read the full article: https://internationalscholarsjournals.org/subscribe-to-read