Texture-Based Image Retrieval based on Multistage Sub-Image Matching

This paper presents an unsupervised texture image segmentation algorithm using clustering. Two criteria are proposed in order to construct a feature space of reduced dimensions for texture image segmentation, based on selected Gabor ?lter subset from a prede?ned Gabor ?lter set. An unsupervised clustering algorithm using the mean shift clustering method is then applied to the reduced feature space to obtain the number of clusters, i.e. the number of texture regions. A simple Euclidean distance classi?cation scheme is used to group the pixels into corresponding texture regions. Experiments on a mixture of Brodatz textures or mosaic of textures generated by random ?eld model show the proposed algorithm of using the reduced Gabor ?lter set and mean shift clustering gives satisfactory results in terms of the number of regions and region shapes. A mathematical programming based clustering approach that is applied to a digital platform company’s customer segmentation problem involving demographic and transactional attributes related to the customers. The clustering problem is formulated as a mixed-integer programming problem with the objective of minimizing the maximum cluster diameter among all clusters. In order to overcome issues related to computational complexity of the problem, a heuristic approach has been developed that improves computational times dramatically without compromising from optimality. The proposed method addresses this problem and employs texture as an additional feature. The method uses wavelet frames that provide translation invariant texture analysis. The method integrates additional texture feature to the colour and spatial space of standard mean shift segmentation algorithm. The algorithm with high dimensional extended feature space provides better results than standard mean shift segmentation algorithm as shown in experimental results. The process continues until the ?nal resolution of the image is equal to some predetermined value. Finally, a collection of sub images corresponding to di? erent image regions and scales is obtained. Several waveletbased feature extractors are tested with the multiscale technique. The analysis of the results indicates that the approach is computationally e? cient and creates meaningful segmentation. From the experiments, it is found that the multistage sub image matching method is an e? cient way to achieve e? ective texture retrieval for segmentation.