Using Tucker Decomposition to Compress Color Images

Traditional image compression methods handle vectored data to compress, but the process undermines the spacial intrinsic structures of high dimensional data. In order to overcome the shortcomings of traditional methods, we presented a novel method of color image compression. In this paper, the color images were encoded into 3-order tensors ( 1 2 3 I I I A × × ). We did the tucker decomposition of tensor to get the largest n K sub-tensors and their eigenvectors, and then used Huffman coding to compress the color images. Experimental results show that at the same compression ratio, the Peak Signal to Noise Ratio (PSNR) of the reconstructed images of our method are much better than the traditional JPEG compression, and we lose less color information visually. Keywords-Tensor; tucker decomposition; color image compression; traditional JPEG compression; Peak Signal to Noise Ratio (PSNR); the ratio of the compression.