ADMM optimizer for integrating wavelet-patch and group-based sparse representation for image inpainting

Recovery or filling in of missing pixels in damaged images is a challenging problem known as image inpainting. Many currently used techniques still suffer from artifacts and other visual defects. In the proposed inpainting approach, the authors have combined wavelet patch-based and group-based sparse representation learning so as to exploit the benefits of (a) multiresolution decomposition using wavelets, (b) sparsity and (c) coherence. The proposed method creates multiple dictionaries employing adaptive K-SVD (K-singular value decomposition) on wavelet decomposed components. The method also creates another dictionary employing PCA (principal component analysis) on group-based image patches. Finally, to accomplish the operation of inpainting, dictionaries of both types are integrated using the ADMM (alternating direction method of multipliers). The proposed method has been tested on images with varying degrees of degradation in terms of the percentage of missing pixels or blocks. We have rated the performance and compared proposed method with other state-of-the-art inpainting methods based on measures like the peak signal-to-noise ratio, the structural similarity index measure, and the figure of merit. The high values of the performance measures establish the efficacy of the proposed method.