Desired Image Retrieval Using Multiple Local Features of Query Images

In this paper, desired images retrieval method using multiple local features of query images is proposed. Multiple color and texture features in local windows are extracted from an image. Color moment is calculated to use for color feature. Texture histogram based on local binary pattern of dual-tree complex wavelet transform is calculated to use for texture feature. When user's interest points of window in query images are selected, similarity between multiple local features of query images and those of blocks of database images is measured by weighted Euclidean norm. Our system is implemented using graphical user interface. In simulations, performance of our method is analyzed with a standard image database. Effectiveness is verified by evaluating retrieval accuracy.