Abstract
In this research present the digital image compression using by Karhunen-Loève Transform (KLT), by convert a color digital image to a gray square digital image, then select the no. of eigen values and eigen vectors that can reconstruct the image, that be very near to the original image.
And then calculate compression ratio and a high result reach it, after applied fidelity criteria on image produce from compression represented by (PSNR, MSE, correlation coefficient and compression ratio), and using a matlab language programming for execute this research.