Visual Feature Extraction for Content-Based Image Retrieval

In this age of computers, virtually all spheres of human life including commerce, government, academics, hospitals, crime prevention, surveillance, engineering, architecture, journalism, fashion and graphic design, and historical research use images for efficient services. In the medical profession, X-rays and scanned image database are kept for diagnosis, monitoring, and research purposes. In architectural and engineering design, image database exists for design projects, finished projects, and machine parts. Most leading academic institutions and many researchers of information-technology-giants focuses on having a general purpose and an efficient CBIR system which is used for searching large image collection. Images are more expressive than words, to express the contents; images are used by most of the websites. With the help of simple searching for an image, image can easily be identified in a small collection of images. But this is not the case with large and random image collections. Effective and efficient retrieval techniques of images are needed because of the explosive growth of digital images. There are two basic approaches used for the information retrieval i-e text-based and content-based image retrieval technique. Text based image retrieval (TBIR) means to search the images with the help of textual metadata associated with the image to sp ecify its characteristics. While CBIR search relies totally on the image searching and retrieval by extracting the contents of the image. The main idea behind the CBIR is efficiency enhancement during image indexing and retrieval, reducing the need for human interruption during image indexing and retrieval process. Contentbased image retrieval system is most widely used in area of Architectural and engineering design , Crime prevention , Medical diagnosis, Art collections, Retail catalogs, Photograph archives, The military, Entertainment and Geographical information and remote sensing systems. It is also efficient for simple user searching on web. In this paper the proposed system includes the design of an image database and extraction of visual features from the images for the content based image retrieval system. And then the validation and analysis of the system by using color histogram technique and the Euclidian distance measure on the designed database images. The proposed content based image retrieval system consists of design of image database, feature extraction and distance measure techniques for the storage and automat ic retrieval of images . Keywordsimage retreval, conten t based approach , TBIR, CBI R Paper typeResearch paper Content Based Image Retrieval