Image Retrieval Based on Multi-features

Abstract

This paper studies the visual feature extraction of image retrieval. According to HSV color space, we quantify the color space in non-equal intervals, construct one-dimensional feature vector and represent the color feature by cumulative histogram. In describing the image texture features, we use the gray-level co-occurrence matrix (GLCM) and Gabor wavelets respectively. Finally, the HSV color features are combined with GLCM and Gabor wavelets respectively for image retrieval. Experiment results show the effectiveness of the algorithm.