An Effective CBIR (Content Based Image Retrieval) Approach Using Ripplet Transforms

Content-based image retrieval (CBIR) approach allows the user to extract an image from a huge database based upon a query. An efficient and effective retrieval performance is achieved by choosing the best transform and classification techniques. However, the current transform techniques such as Fourier Transform, Cosine Transform, Wavelet Transform suffer from discontinuities such as edges in images. To overcome this problem, a recent technique called Ripplet Transform(RT) has been implemented along with the Neural network based classifier called Multilayered perceptron(MLP) for finding an effective retrieval of image. The Ripplet transform is a higher dimensional generalization of the Curvelet Transform, designed to represent images or two-dimensional signals at different scales and different directions and therefore resolves two-dimensional (2D) singularities. Classification using Multilayered perceptron(MLP) with the Manhattan Distance measure showed varying experimental results for different sets of Images.