In a world of virtualization, where we are having a larger source of images and descriptions available to modern world and based on their requirement it has been utilized from stored information, data center or cloud to larger audience, but at same time rising number of images requires good tools to store the data and retrieve data. Along with this there is a major importance of Quick search and retrieval tools for these growing images to retrieve information quickly and accurately. High demand for automated or computer assisted classification, query and retrieval methods is required to access huge image databases because such method will try to overcome the drawback of higher cost of manual classification and retrieval of relevant image. Scope as researchers to develop automated methods in image features for indexing and retrieval of images related to texture, feature and color is in demand.
TopIntroduction
In many areas such as government, academia, commerce, and hospitals, huge repository of digital based images are being created. Most of these collections are the product of digitizing existing collections of analogue drawings, photographs, paintings, diagrams, and prints. Usually, the only way of searching these collection data was by keyword indexing, or simply by browsing the required data. Even though Digital image databases however are open to content-based searching. This content however, is about the functionality of present-day image retrieval systems in terms of the following technical aspects: querying, features extraction, matching, relevance feedback and result presentation. This interpretation exposes a short version of a much more comprehensive survey (Veltkamp & Tanase, 2000), which covers to a large extent more systems, and also treats the following aspects: indexing data structures, performance, and applications. There is thus a big potential to automate this process and many survey shows that a normal person with camera or image receiving devices are able to upload 7 to 10 images daily.
There are many keyword-based general WWW search engines which allow searching text based data, such as Google (http://www.faganfinder.com/img/) provides a list of different search engines collections as a tool to help in searching in Health, Stock Photographs, Photo sharing sites, News Blogs, science & education, Artwork and Regional and Historical related images. Further it has some more categories in image search engines such as clip art, Reverse Image search, Culture & Historical and Miscellaneous.
Criteria
Most image retrieval systems can be abstractly described by the framework portrayed in Figure 1. When user formulates a query, in what manner and how relevance feedback is possible is seen, how features from query image are extracted, what kind of features are used, and data base image are coordinated, and how the retrieval results are presented to the user.
Figure 1.
Content-based image retrieval frameworks
Most of user interface typically consists for two different things one query formulation and other is result presentation part. To retrieve images from the database can be done in different ways. One of the techniques is browsing database one-by-one. Or one can keyword related to the image, or by feature extraction from image such as color histogram. One way is to provide an image or sketch from which features are extracted and compared with the database images. Taxonomy of interaction models is given in (Vendrig, 1997).With the help of Relevance feedback we are able to get positive or negative feedback about the retrieval result, through this system can refine the search. In this chapter our main focus is on emerging research surrounding CBIR with High-level semantics and low-features extraction.