MLP interpolation for digital image processing using wavelet transform

In this paper, we present nonlinear interpolation schemes for image resolution enhancement. The Multilayer perceptron (MLP) interpolation schemes based on the wavelet transform and subband filtering are proposed. Because estimating each sub-image signal is more effective than estimating the whole image signal, pixels in the low-resolution image are used as input signal of the MLP to estimate all of the wavelet sub-image of the corresponding high-resolution image. The image of increased resolution is finally produced by the synthesis procedure of wavelet transform. As compared with other popular methods, the results show that the improvement is remarkable. The detail simulation results of interpolated images and image sequences can be found in web page: http://www.cs.ccu.edu.tw/~hyl/wmi/.