Fast, feature-based wavelet shrinkage algorithm for image denoising

We present a selective wavelet shrinkage algorithm for digital image denoising. The performance of this method is an improvement upon other methods proposed in the literature and is algorithmically simple for large computational savings. The improved performance and computational speed of the proposed wavelet shrinkage algorithm is presented and experimentally compared with established methods. The denoising methodology incorporated in this new algorithm involves a two-threshold validation process for real-time selection of wavelet coefficients. The two-threshold criteria selects wavelet coefficients based on their absolute value, spatial regularity, and regularity across multiresolutional scales. The proposed algorithm takes image features into consideration in the selection process. Statistically, most images have regular features resulting in connected subband coefficients. Therefore, the resulting subbands of wavelet transformed images in large part do not contain isolated coefficients. In the proposed algorithm, after coefficients are selected due to their magnitude, image features in terms of spatial regularity are used to further reduce the number of coefficients kept for image reconstruction. The proposed wavelet denoising technique is unique in that its performance improved upon several other established wavelet denoising techniques as well as being computationally efficient to facilitate realtime image processing applications.