Multiscale Ridgelet Transform for content based image retrieval

Abstract

In this paper, a new algorithm for image indexing and retrieval using Multi-scale Ridgelet Transform (MRT) is presented. In MRT, ridgelet transform has been implemented by using Gabor wavelet sub bands. This method captured image edge information more accurately than spectral method such as Gabor transform (GT). MRT is applied on Coral database and computed the low order statistics from the transformed images. Feature database has been generated by using this extracted texture features and the retrieval results demonstrate significant improvement in precision and average retrieval rate, compared to GT.