Image Retrieval Based on Two-Tuples Histogram

Human visual system (HSV) puts more attentions to color and edge orientation. The repeat pattern between color and edge orientation covers on rich of visual information, it plays an important role in visual attention and image understanding. This paper presents a novel image feature representation method, called Two-Tuples Histogram (TTH), for image retrieval. The Two-Tuples Histogram has taken advantages of co-occurrence matrix and color histogram, and can represent the repeat pattern between color and edge orientation. The proposed TTH method is extensively tested on the Corel dataset with 15000 natural images. Image retrieval experimental results have shown that the Two-Tuples Histogram has the discrimination power of color, texture, shape features and spatial relationship, and the performance is better than that of the edge histogram descriptor and LBP method significantly.