Open AccessHow to deal with color in super resolution reconstruction of images
Author(s) -
Rui Gong,
Yi Wang,
Yaqi Cai,
Xiaopeng Shao
Publication year - 2017
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.25.011144
Subject(s) - ycbcr , rgb color model , color space , artificial intelligence , computer vision , hsl and hsv , computer science , color image , resolution (logic) , optics , image processing , image (mathematics) , physics , virus , virology , biology
Super resolution (SR) reconstruction is a profitable technology to acquire high resolution images from low resolution images without replacing devices. This study was concentrated on searching strategies of dealing with color information in the SR reconstruction process. Based on an algorithm with dictionary learning, different algorithms were designed to test which color coordinate systems could obtain better image reconstruction quality, involving color spaces of RGB, YIQ, YCbCr, HSI, HSV, and CIELAB. Their results were compared via typical numerical measures, and the recommended strategies are to adopt merely L* coordinate in CIELAB space or merely Y coordinate of YIQ system.