CNN image compression and reconstruction based on non-orthogonal wavelet transform

In a practical image processing such Wavelet Transform (WT), the function orthogonality, is required for reconstruction of the original image. The orthogonality has disadvantage that the selected filter is not necessarily optimal from a viewpoint from human retinal realization. Tt is not necessary to select an orthogonal templates in Cellular Neural Network (CNN) image processing, because the CNN is non-linear analog circuit to obtain epuilibrium points automatically and simultaneously. This paper describes CNN image compression and reconstruction based on a non-orthogonal WT. This system have an advantage of non-dependency of image scanning by spatio-temporal CNN dynamics. It is very important that the reconstruction of transmitted compression image is done simultaneously by parallel neurons based on the "regularization" of ill-posed problem, which is caused in a retinal system of a human brain.