Presentation 2013-07-11
Colorization based on Non-Local Means
Takashi UENO, Taichi YOSHIDA, Masaaki IKEHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Colorization is a method which adds color components to grayscale images via few color information provided by users. In a conventional method, chrominance of target pixels is estimated based on the assumption that neighboring pixels which have similar luminance also have similar chrominance. However, this method does not take advantage of structural similarity. The Non-Local Means is a noise reduction method which uses structural similarity of images. In this paper, we proposed a colorization method based on structural similarity such as the Non-Local Means. In the simulations, colorization results show that the proposed method obviously outperforms the conventional method in the objective and perceptual quality.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Colorization / Non-Local Means / Structural similarity
Paper # CAS2013-9,VLD2013-19,SIP2013-39,MSS2013-9
Date of Issue

Conference Information
Committee MSS
Conference Date 2013/7/4(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) Colorization based on Non-Local Means
Sub Title (in English)
Keyword(1) Colorization
Keyword(2) Non-Local Means
Keyword(3) Structural similarity
1st Author's Name Takashi UENO
1st Author's Affiliation Deparatment of Electronics and Erectrical Engineering, Keio University()
2nd Author's Name Taichi YOSHIDA
2nd Author's Affiliation Deparatment of Electronics and Erectrical Engineering, Keio University
3rd Author's Name Masaaki IKEHARA
3rd Author's Affiliation Deparatment of Electronics and Erectrical Engineering, Keio University
Date 2013-07-11
Paper # CAS2013-9,VLD2013-19,SIP2013-39,MSS2013-9
Volume (vol) vol.113
Number (no) 121
Page pp.pp.-
#Pages 5
Date of Issue