A new in-camera imaging model for color computer vision and its application

Seon Joo Kim, Hai Ting Lin, Zheng Lu, Sabine Süsstrunk, Stephen Lin, Michael S. Brown

Research output: Contribution to journalArticle

77 Citations (Scopus)

Abstract

We present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera.

Original languageEnglish
Article number6158647
Pages (from-to)2289-2302
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Volume34
Issue number12
DOIs
Publication statusPublished - 2012 Oct 29

Fingerprint

Color Vision
Computer Vision
Computer vision
Camera
Cameras
Imaging
Color
Imaging techniques
Convert
Calibration
Model
Radiometric Calibration
Charge coupled devices
Image Processing
Image processing
Output

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Kim, Seon Joo ; Lin, Hai Ting ; Lu, Zheng ; Süsstrunk, Sabine ; Lin, Stephen ; Brown, Michael S. / A new in-camera imaging model for color computer vision and its application. In: IEEE transactions on pattern analysis and machine intelligence. 2012 ; Vol. 34, No. 12. pp. 2289-2302.
@article{548d4ccd4fb94a92b8eb7842700a5f67,
title = "A new in-camera imaging model for color computer vision and its application",
abstract = "We present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera.",
author = "Kim, {Seon Joo} and Lin, {Hai Ting} and Zheng Lu and Sabine S{\"u}sstrunk and Stephen Lin and Brown, {Michael S.}",
year = "2012",
month = "10",
day = "29",
doi = "10.1109/TPAMI.2012.58",
language = "English",
volume = "34",
pages = "2289--2302",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "12",

}

A new in-camera imaging model for color computer vision and its application. / Kim, Seon Joo; Lin, Hai Ting; Lu, Zheng; Süsstrunk, Sabine; Lin, Stephen; Brown, Michael S.

In: IEEE transactions on pattern analysis and machine intelligence, Vol. 34, No. 12, 6158647, 29.10.2012, p. 2289-2302.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new in-camera imaging model for color computer vision and its application

AU - Kim, Seon Joo

AU - Lin, Hai Ting

AU - Lu, Zheng

AU - Süsstrunk, Sabine

AU - Lin, Stephen

AU - Brown, Michael S.

PY - 2012/10/29

Y1 - 2012/10/29

N2 - We present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera.

AB - We present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera.

UR - http://www.scopus.com/inward/record.url?scp=84867792519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867792519&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2012.58

DO - 10.1109/TPAMI.2012.58

M3 - Article

AN - SCOPUS:84867792519

VL - 34

SP - 2289

EP - 2302

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 12

M1 - 6158647

ER -