Color Filter Array Directional Demosaicking with Compression using Artificial Neural Network

Autor:	M. S. Safna Asiq, W. R. Sam Emmanuel
Rok vydání:	2018
Předmět:	Demosaicing Bayer filter Artificial neural network Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Full color Backpropagation Compression (functional analysis) Color filter array Computer vision Bilateral filter Artificial intelligence business
Zdroj:	2018 International Conference on Smart Systems and Inventive Technology (ICSSIT).
DOI:	10.1109/icssit.2018.8748306
Popis:	The images of a single sensor camera have only one color component in a pixel array the missing two color components are reconstructed into a full color image by demosaicking. A new framework of combining an efficient Artificial Neural network Back propagation (ANN-BP) compression and Directional Demosaicking (DD). A three layered neural network is employed in the proposed work for achieving good compression strategy and a four directional demosaicking with bilateral filtering which helps to obtain good demosaicking results comparatively. The work is analyzed using the Kodak dataset.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a428e50c09ed953c85b332b868125fd7 https://doi.org/10.1109/icssit.2018.8748306 Zobrazit plný text záznamu