Research On Image Compression Method Based On Contourlet Transform

In order to improve the visual effect of the reconstructed image,it is important to preserve the texture profile information.According to the principle of high frequency sub band in Contourlet transform,the image compression method based on Contourlet transform is studied.The image using a layer of LP transform high frequency subbands and low frequency subband,of high frequency sub zone was not the direction filter filtering by using Huffman coding compression for protection,for low frequency sub with no redundancy of Mallat transform and then using SPIHT coding for compression.Simulation results show that the proposed method is much lower than the wavelet transform in the PSNR value,but it is much better than the wavelet transform in texture detail preservation.In addition,aiming at the shortcoming that the traditional wavelet transform lacks the necessary direction and the Contourlet transform to image the spatial redundancy,an adaptive compression method based on standard deviation is proposed.Standard deviation directly reflects the richness of the image texture details,according to the theory of image segmentation,sub block adaptive selection of wavelet transform and Contourlet transform.Simulation experiments show that the method combines the advantages of wavelet transform and contourlet transform,in ensuring that the reconstructed images with more texture information,at the same time reduce the spatial redundancy contourlet transform,and the PSNR of the reconstructed image value in a certain extent increased.