An image retrieval with color and texture features of image sub-blocks

This title is printed to order. This book may have been self-published. If so, we cannot guarantee the quality of the content. In the main most books will have gone through the editing process however some may not. We therefore suggest that you be aware of this before ordering this book. If in doubt check either the author or publisher’s details as we are unable to accept any returns unless they are faulty. Please contact us if you have any questions.

Each image is partitioned into 4x6 grids of equal-sized sub-blocks. The size of the sub-block is maintained as 64x64 pixels. Further the size of the sub-block is fixed for all the images. Then the color and texture features of each sub-block are computed. A color feature descriptor Local AutoCorrelogram (LAC) which is invariant to translation and occlusion is proposed to represent the color of the sub-block. Similarly, the texture of the sub-block is extracted based on Edge Oriented Gray Tone Spatial Dependency Matrix (EOGTSDM) of an image. An image matching scheme based on Integrated Minimum Cost Sub-block Matching (IMCSM) principle is used to compare the query and the target image, which in turn reduces the cost of finding the integrated matching distance. The adjacency matrix of a bipartite graph is formed using the sub-blocks of query and target image, which is used for matching the images. To further improve the quality of retrieval, a Relevance Feedback approach based on a feature re-weighting scheme is used to improve the retrieval accuracy. The experimental results show that this method has improved retrieval precision and recall.