Retrieval of exact images from a bundle of images in the web for an object class

Keyword-based image search engines like Google Images are now very popular for getting large amount of images on the web. Because only the text information that are directly or indirectly linked to the images are used for image indexing and retrieval, most existing image search engines such as Google Images may return large amount of images which are irrelevant to the given queries. Search engines have become strikingly accurate at delivering relevant text-based information from the web, but the same cannot be said for web image content. There are billions of images on the web yet most of them are not indexed effectively. If relevant images are filtered from noisy search results, the web becomes an attractive source of training imagery for visual classifiers. The queries take the form of text keywords and images are indexed by their textual metadata. The drawback to this approach is found in the lack of quality metadata for images on the web. In the existing system they have maintained a database. Manually they have retrieved images from Google image search and stored into the separate folder. User supposes wants to get images for a given query they can access from the folder. If the given query images was not present in the stored folder then it will not access by the user. The main goal in this work is to retrieve a large number of images of a specified class automatically, and to achieve this with high precision using naive Bayes and SVM visual classifier.