期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2014
卷号：3
期号：6
页码：13987
出版社：S&S Publications
摘要：The image retrieval system is used for browsing, searching and retrieving images from a large database ofdigital images. In the proposed system, Content-Based Image Retrieval (CBIR) handles the predefined classes using lowlevel features. To improve the accuracy of the retrieval, color and texture features of the image is extracted, which isrepresented as color co-occurrence matrices. In retrieval, complexity of selecting a query object in single image query ishigh. To avoid this problem, multi-image query is used to perform the retrieval. Support Vector Machine (SVM) is used toconstruct the classifier for pre-defined classes. However, in a large-scale image collection, some image classes may beunseen. These unseen image classes are termed as hidden classes. In order to handle the hidden classes, the unclassifiedimages are clustered, based on color and texture feature using K-means clustering algorithm. The queries associated withthe hidden classes cannot be accurately answered using a traditional CBIR system. To handle these hidden classes, a robustCBIR scheme is proposed that incorporates a novel query detection technique, which is used to identify a query as acommon query or a novel query. In this work, Majority Vote Rule and Bayes Sum Rule are applied to implement the imagequery detection technique. For a common query, a relevant predefined image class will be predicted and within the class therelevant images are ranked. For hidden classes, during the retrieval process the features of the query image are extracted,then matched with the centroid of the each cluster. Among these clusters, features extracted from the query image that arenearest to the centroid of the cluster is selected. Then the query image is compared with the nearest images to the centroidof the selected cluster and the more relevant images are ranked.
