PROJECT TITLE :

Color Demosaicking Via Nonlocal Tensor Representation - 2017

ABSTRACT:

One sensor camera can capture scenes by means that of color filter array. Each pixel samples solely one amongst the 3 primary colours. Color demosaicking (CDM) could be a method of reconstruction a full color image from this sensor data. In this paper, we propose a unique CDM scheme based mostly on learned simultaneous sparse coding over nonlocal tensor representation. First, similar 2D patches are grouped to form a three-order tensor, that is, 3D array. Then, three sub-dictionaries, which characterize the coherent structures that appear in each dimension of the grouped tensor, are learned jointly by using Tucker decomposition. The consequent coefficient tensor is imposed by the grouped-block-sparsity constraint, which forces the similar patches to share the same atoms of the dictionaries in their sparse decomposition. Experimental results demonstrate the effectiveness both in the average CPSNR and visual quality.