Why You Should Forget Luminance Conversion and Do Something Better

被引：10

作者：

Nguyen, Rang M. H. ^{[1
]}

Brown, Michael S. ^{[2
]}

机构：

[1] Natl Univ Singapore, Singapore, Singapore

[2] York Univ, N York, ON, Canada

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

关键词：

COLOR; ENHANCEMENT;

D O I：

10.1109/CVPR.2017.627

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One of the most frequently applied low-level operations in computer vision is the conversion of an RGB camera image into its luminance representation. This is also one of the most incorrectly applied operations. Even our most trusted softwares, Matlab and OpenCV, do not perform luminance conversion correctly. In this paper, we examine the main factors that make proper RGB to luminance conversion difficult, in particular: 1) incorrect white-balance, 2) incorrect gamma/tone-curve correction, and 3) incorrect equations. Our analysis shows errors up to 50% for various colors are not uncommon. As a result, we argue that for most computer vision problems there is no need to attempt luminance conversion; instead, there are better alternatives depending on the task.

引用

页码：5920 / 5928

页数：9

共 32 条

[11] Haussecker HW, 2000, PROC CVPR IEEE, P760, DOI 10.1109/CVPR.2000.854951
[12] NUMERICAL SHAPE FROM SHADING AND OCCLUDING BOUNDARIES
IKEUCHI, K
HORN, BKP
[J]. ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) : 141 - 184
[13] Jiang J, 2013, IEEE WORK APP COMP, P168, DOI 10.1109/WACV.2013.6475015
[14] Color-to-Grayscale: Does the Method Matter in Image Recognition?
Kanan, Christopher
Cottrell, Garrison W.
[J]. PLOS ONE, 2012, 7 (01): : 133 - 139
[15] A Software Platform for Manipulating the Camera Imaging Pipeline
Karaimer, Hakki Can
Brown, Michael S.
[J]. COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 : 429 - 444
[16] Robust radiometric calibration and vignetting correction
Kim, Seon Joo
Pollefeys, Marc
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (04) : 562 - 576
[17] A New In-Camera Imaging Model for Color Computer Vision and Its Application
Kim, Seon Joo
Lin, Hai Ting
Lu, Zheng
Suesstrunk, Sabine
Lin, Stephen
Brown, Michael S.
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (12) : 2289 - 2302
[18] Lin HT, 2011, IEEE I CONF COMP VIS, P129, DOI 10.1109/ICCV.2011.6126234
[19] LIN S, 2004, CVPR04, P938
[20] Lin S.-J., 2005, ECOLOGIC SCI, V1, P2

← 1 2 3 4 →