Image Denoising Based on Combining Neighbouring Wavelet Coefficients

This paper proposes a new image thresholding function which exploits spatial correlation among image wavelet coefficients and classification technique. This approach is valid because a large wavelet coefficient will probably have large wavelet coefficients as its neighbours, so that estimation accuracy is increased and the new function overcomes the shortcomings of the hard thresholding function and the soft thresholding function. Experimental results show that the performance of the proposed method can be competitive to the conventional wavelet denoising approaches: hard threshold and soft threshold.