Presentation 2012-07-02
Image Colorization Based on The Mixed L0/L1 Norm Minimization
Kazunori URUMA, Katsumi KONISHI, Tomohiro TAKAHASHI, Toshihiro FURUKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report proposes a new image colorization algorithm based on the mixed l_0/l_1 norm minimization. Introducing some assumptions, a problem of recovering a color image from a grayscale image with the small number of known color pixels is formulated as a mixed l_0/l_1 norm minimization, which is solved approximately by an iterative reweighted least squares algorithm. Moreover, for improving the quality of colorization, we guess the black and white pixel using the value of grayscale. Numerical examples show that the proposed algorithm colorizes a grayscale image well using a small number of color pixels.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image colorization / sparse optimization / l_0/l_1 norm minimization
Paper # CAS2012-5,VLD2012-15,SIP2012-37,MSS2012-5
Date of Issue

Conference Information
Committee MSS
Conference Date 2012/6/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Mathematical Systems Science and its applications(MSS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Colorization Based on The Mixed L0/L1 Norm Minimization
Sub Title (in English)
Keyword(1) image colorization
Keyword(2) sparse optimization
Keyword(3) l_0/l_1 norm minimization
1st Author's Name Kazunori URUMA
1st Author's Affiliation Tokyo University of Science()
2nd Author's Name Katsumi KONISHI
2nd Author's Affiliation Kogakuin University
3rd Author's Name Tomohiro TAKAHASHI
3rd Author's Affiliation Tokyo University of Science
4th Author's Name Toshihiro FURUKAWA
4th Author's Affiliation Tokyo University of Science
Date 2012-07-02
Paper # CAS2012-5,VLD2012-15,SIP2012-37,MSS2012-5
Volume (vol) vol.112
Number (no) 116
Page pp.pp.-
#Pages 6
Date of Issue