期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2014
卷号：3
期号：Special
出版社：IJECSCSE
摘要：Now a day’s requirement for development of CBIR isenhanced due to tremendous growth in volume of images as wellas the widespread application in multiple fields. Texture, color,shape and spatial layout are the underlying traits to represent andindex the images. These peculiar features of images are extractedand implemented for a similarity check among images. Theproblem of content based image retrieval is based on generationof peculiar query. For relevant images that meet their informationneed, an automated search is initiated by drawing a sketch orwith the submission of image having similar features. Similaritybetween extracted features can be measured by using differentalgorithms. This proposed approach is for Efficient ImageRetrieval with Feature Extraction Based on Multinewapproach to overcome Limitation of the well-CBIR methods. The effect of Co-occurrence Matrix of Color andEdge Orientation, multi-image queries and Local Tetra Patternsis used for enhancing precision and recall of an imasystem.
关键词：Co-occurrence Matrix; Local Tetra Patterns;Multi-Image Queries
