A Novel Approach for Image Retrieval using Back Propagation Neural Network

This technique uses visual contents to search images from large scale image databases according to the user’s interest. The features refers to color, shape, texture that can be derived from the image. In this paper an image retrieval system using artificial neural network (ANN) in MATLAB with the help of wavelet transforms is contemplated. In the proposed system, mean and standard deviation of the images are calculated later to the filtering process of the images using wavelet transforms. Using the neural network classifier the system is trained and tested and classifies the images from a vast database relevant to the requirement. A database having 1000 images spread across ten categories is taken for the implementation purpose. Net average precision and recall values are computed for the database query. The obtained results show the performance improvement with higher precision and recall values.