International Journal of Applied Engineering Research

Image retrieval is known to be the main bottleneck in real time applications, and the search for an efficient retrieval algorithm has been challenge. CBIR is considered as the process of retrieving desired images from huge databases based on extracted features from the images themselves without restoring to a keyword. Relevance feedback is a way to effectively bridge the gap between the low level image features and high level human perception. Relevance feedback is a powerful tool to boost the retrieval performance in CBIR. Retrieving procedure can be significantly improved by introducing the user as a part of retrieval loop. The system will refine the retrieval results based on the feedback and present a new list of images to the user.In the project CBIR with relevance feedback, proposing an algorithm 2DPCA for feature extraction and dimensionality reduction and comparison is done by the distance measurement, and retrieved the images.In the retrieved images, if images are irrelevant use relevance feedback to improve the retrieval performance and repeat until to get relevant images. In this way, the “curse of dimensionality” is bypassed since redundant components of a query feature vector are rejected using 2DPCA.