Hybrid Color Image Demosaicking using Densely Connected Residual Sub-pixel CNN with Iterative Ring Resonator-based Gaussian Filter

Main Article Content

Chatla Raja Rao, Soumitra Kumar Mandal


Digital camerasare essential devices in current digital era, where all the cameras capture the images using color filter array (CFA) approach. Usually, while capturing an RGB image, only one color is stored in the pixel and remaining two colors will be missed. Thus, these missed colors in that position must be restored to the fully coloured image, which is referred as the concept of demosaicking. This article focuses on development of advanced demosaicking using deep convolutional neural network (D-CNN) model with self-ensemble method to reduce the computational complexities. The proposed D-CNN model consisting of densely connected residual blocks with the densely connected residual network (DRDN) for the training of various mosaic patterns and CFAs. Thus, this architecture reduces the vanishing-gradient problems generated during the training process with the utilization of efficient sub-pixel convolutional neural network (ESPCN) layer. The test images are applied to the D-CNN+DRDN architecture and performs the initial demosaicking operation using the local features of block-wise convolutional layers. Finally, iterative ring resonator based Gaussian filter (IRRGF) method is employed to generate the high intensity output demosaicked image. Extensive simulation results shows that proposed hybrid color image demosaicking model gives the enhancive subjective and objective performance with least mosaic pattern effects and reduced color errors. Performance evaluation compared to the demosaicking approaches from the literature like DDEMO, DRDN, and DRDN+ in terms color peak signal-to-noise ratio (CPSNR), and structural similarity (SSIM) index.

Article Details