Image compression scheme based on curvelet transform and support vector machine

In this paper, we propose a novel scheme for image compression by means of the second generation curvelet transform and support vector machine (SVM) regression. Compression is achieved by using SVM regression to approximate curvelet coefficients with the predefined error. Based on characteristic of curvelet transform, we propose a new compression scheme by applying SVM into compressing curvelet coefficients. In this scheme, image is first translated by fast discrete curvelet transform, and then curvelet coefficients are quantized and approximated by SVM, at last adaptive arithmetic coding is introduced to encode model parameters of SVM. Compared with image compression method based on wavelet transform, experimental results show that the compression performance of our method gains much improvement. Moreover, the algorithm works fairly well for declining block effect at higher compression ratios.