Local oppugnant color space extrema patterns for content based natural and texture image retrieval

This paper proposes a novel feature descriptor called local oppugnant color space extrema patterns (LOCSEP) for image indexing retrieval. The existing directional local extrema pattern (DLEP) extracts the directional edge information based on local extrema in 0°, 45°, 90°, and 135° directions in an image. The proposed method integrates the concepts of color and texture features. First, the color image is converted into RGB (red, green and blue) and HSV (hue, saturation and value) color spaces. Then oppugnant color spaces, RV, GV, BV are used for the extract of oppugnant DLEP features (LOCSEP). The performance of the proposed method is tested by conducting two experiments on benchmark databases viz. Corel-1K and MIT VisTex databases. The performance of the proposed method is compared with the state-of-the-art methods for image retrieval and face recognition applications in terms of average retrieval precision (ARP) and average retrieval rate (ARR). The results after being investigated show a significant improvement in terms of their evaluation measures as compared to state-of-the-art methods on respective databases.