期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2016
卷号：5
期号：1
页码：15457-15462
DOI：10.18535/Ijecs/v5i1.10
出版社：IJECS
摘要：There is a huge demand for the efficient content based image retrieval system because of theavailability of large image databases. In this paper we have present an efficient CBIR framework byextracting the Dominant-color, Texture, edge features and by clustering feature database. We have appliedthe dominant color extraction using color-quantization technique. Initially the image is divided into somepartitions using the color quantization algorithm, here we are dividing into eight partitions and the eightdominant colors are obtained from that partition. Next for shape feature extraction sobel color edgedetection technique is used. And local binary pattern (LBP) is performed on gray scale image to extract thetexture feature. Then all features discussed above of image are combined to form a single feature vector. Kmeansclustering is applied over combined feature vector of database images. Finally, to retrieve similarimages from database similarity matching is performed by Euclidian distance which compares feature vectorof clustered database images with that of query image. The result of this proposed approach providesefficient, more accurate result.
关键词：Dominant color; K-means clustering; Local Binary Pattern (LBP); Euclidian Distances.
