Texture Moment for Content-Based Image Retrieval

In this paper, a novel low-level feature, named texture moment, is designed to characterize the texture properties of grayscale images for content-based image retrieval. At first, seven attributes are defined for each pixel by applying seven orthogonal templates on its eight neighborhoods. The templates are derived from local Fourier transform. Then, the mean and variation of those seven attributes are calculated for all interior pixels respectively to form a 14-D feature vector. As this feature is highly complementary to other color features, properly combining it with color features together may produce good image retrieval results. Therefore, two feature combinations are also provided. Experiments on 5,000 general-purpose images demonstrate the effectiveness of the proposed texture moment feature and two feature combinations.