Retrieval by Color Features in Image Databases

• Published in: International journal of computer applications 2010-02, Vol.1 (26), p.140-142
• Main Authors: Deshmukh, Prof. Ms. V.M., Bhura, Sohel A., Satav, Pravin R., Asole, Suresh S., Agrawal, Sachin
• Format: Article
• Language: English
• Subjects: Color; Preserves; Query processing; Representations; Retrieval; Searching; Visual
• ISSN: 0975-8887; 0975-8887
• DOI: 10.5120/468-773

Content-based search and retrieval techniques for multimedia content utilize various descriptors for different image features. However, most content-based image retrieval systems use low-level visual features for representation and retrieval of images. The color content, being one of the easily computable features is often used in content-based search for retrieving images in large image databases. The paper presents a simple and fast technique for image indexing and retrieval based on a description of the spatial distribution of dominant colors. The idea in this study is to empirically evaluate the effect of color features to the query. Furthermore, some similarity measures are defined that allow the definition of effective visual queries for fast interactive image database browsing applications We use the image histograms to characterize the global and local color properties of an image and to preserve its intrinsic geometric information. The color feature is probably the most visible visual feature for the most humans. This is the new approach in the image organization and retrieval of image, in image databases. Our approach combines the representation of the color as the global image feature and the color as the representation of the spatial information in the images.