An Effective CBIR (Content Based Image Retrieval) System using Ripplet Transform

CBIR approach allows the user to extract an image from a huge database based upon a query. However, the current transform techniques such as Fourier transform, Wavelet transform, Cosine transform suffer from discontinuities such as edges in images. To overcome this problem, a recent technique called Ripplet Transform has been implemented. The Ripplet transform is a higher dimensional generalization of Curvlet transform, designed to represent images or two-dimensional signals at different scales and different directions. Ripplet transform can be used for feature extraction due to its efficiency in representing edges and textures. Specifically, the ripplet transform allows arbitrary support c and degree d while the curvlet transform is just a special case of the ripplet transform. Experiments in texture classification and image retrieval demonstrate that the Ripplet transform based scheme outperforms wavelet, ridglet and curvlet transform based approaches.