A Textural Feature-Based Image Retrieval Algorithm

In this paper, we propose an effective content-based image retrieval (CBIR) method based on textural features. Compared with color and shape features, texture features can indicate the spatial distribution of the pixels in an image. Firstly, gray level co-occurrence matrix (GLCM) is constructed, which indicates the associated probability density of two different neighboring pixels. Secondly, we extract several features from the GLCM and index the feature vectors. Then the wanted images can be efficiently retrieved from the image database by measuring the similarity between the query image and others based on a matching rule, such as the Minkowski-form distance metrics.