Intrinsic image extraction from a single image

Yun Chung Chung, Cherng Shen, Robert Bailey, Sei-Wang Chen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

An image is often modeled as a product of two principal components: illumination and reflectance components. The former is related to the amount of light incident on the scene and the latter is associated with the scene characteristics. The images formed from the two components are referred to as the illumination and the reflectance images; both are called the intrinsic images of the original image. The illumination components of the images of a fixed scene vary from image to image, while the reflectance components of the images in principle remain constant. Both reflectance and illumination images have their own applications. Intrinsic image extraction has long been an important task for computer vision applications. However, this task is not at all simple because it is an ill- conditioned problem. The proposed approach convolves an input image with a prescribed set of derivative filters. The pixels of the derivative images are next classified as being reflectance or illumination according to three measures: chromatic, intensity contrast and edge sharpness, which are calculated in advance for each pixel from the input image. Finally, a de-convolution process is applied to the classified derivative images to obtain the intrinsic images. The results reveal the feasibility of the proposed technique in both rapidly and effectively decomposing intrinsic images from one single image.

Original languageEnglish
Pages (from-to)1939-1953
Number of pages15
JournalJournal of Information Science and Engineering
Volume25
Issue number6
Publication statusPublished - 2009 Nov 1

Fingerprint

Lighting
Derivatives
Pixels
Deconvolution
Computer vision
incident

Keywords

  • Chromatic measurement
  • Intensity contrast and edge sharpness measures
  • Intrinsic images
  • Photometric reflectance model
  • Reflectance and illumination components

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Library and Information Sciences
  • Computational Theory and Mathematics

Cite this

Intrinsic image extraction from a single image. / Chung, Yun Chung; Shen, Cherng; Bailey, Robert; Chen, Sei-Wang.

In: Journal of Information Science and Engineering, Vol. 25, No. 6, 01.11.2009, p. 1939-1953.

Research output: Contribution to journalArticle

Chung, YC, Shen, C, Bailey, R & Chen, S-W 2009, 'Intrinsic image extraction from a single image', Journal of Information Science and Engineering, vol. 25, no. 6, pp. 1939-1953.
Chung, Yun Chung ; Shen, Cherng ; Bailey, Robert ; Chen, Sei-Wang. / Intrinsic image extraction from a single image. In: Journal of Information Science and Engineering. 2009 ; Vol. 25, No. 6. pp. 1939-1953.
@article{256fbc2c4fa24371b8b43cafcbb838cc,
title = "Intrinsic image extraction from a single image",
abstract = "An image is often modeled as a product of two principal components: illumination and reflectance components. The former is related to the amount of light incident on the scene and the latter is associated with the scene characteristics. The images formed from the two components are referred to as the illumination and the reflectance images; both are called the intrinsic images of the original image. The illumination components of the images of a fixed scene vary from image to image, while the reflectance components of the images in principle remain constant. Both reflectance and illumination images have their own applications. Intrinsic image extraction has long been an important task for computer vision applications. However, this task is not at all simple because it is an ill- conditioned problem. The proposed approach convolves an input image with a prescribed set of derivative filters. The pixels of the derivative images are next classified as being reflectance or illumination according to three measures: chromatic, intensity contrast and edge sharpness, which are calculated in advance for each pixel from the input image. Finally, a de-convolution process is applied to the classified derivative images to obtain the intrinsic images. The results reveal the feasibility of the proposed technique in both rapidly and effectively decomposing intrinsic images from one single image.",
keywords = "Chromatic measurement, Intensity contrast and edge sharpness measures, Intrinsic images, Photometric reflectance model, Reflectance and illumination components",
author = "Chung, {Yun Chung} and Cherng Shen and Robert Bailey and Sei-Wang Chen",
year = "2009",
month = "11",
day = "1",
language = "English",
volume = "25",
pages = "1939--1953",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "6",

}

TY - JOUR

T1 - Intrinsic image extraction from a single image

AU - Chung, Yun Chung

AU - Shen, Cherng

AU - Bailey, Robert

AU - Chen, Sei-Wang

PY - 2009/11/1

Y1 - 2009/11/1

N2 - An image is often modeled as a product of two principal components: illumination and reflectance components. The former is related to the amount of light incident on the scene and the latter is associated with the scene characteristics. The images formed from the two components are referred to as the illumination and the reflectance images; both are called the intrinsic images of the original image. The illumination components of the images of a fixed scene vary from image to image, while the reflectance components of the images in principle remain constant. Both reflectance and illumination images have their own applications. Intrinsic image extraction has long been an important task for computer vision applications. However, this task is not at all simple because it is an ill- conditioned problem. The proposed approach convolves an input image with a prescribed set of derivative filters. The pixels of the derivative images are next classified as being reflectance or illumination according to three measures: chromatic, intensity contrast and edge sharpness, which are calculated in advance for each pixel from the input image. Finally, a de-convolution process is applied to the classified derivative images to obtain the intrinsic images. The results reveal the feasibility of the proposed technique in both rapidly and effectively decomposing intrinsic images from one single image.

AB - An image is often modeled as a product of two principal components: illumination and reflectance components. The former is related to the amount of light incident on the scene and the latter is associated with the scene characteristics. The images formed from the two components are referred to as the illumination and the reflectance images; both are called the intrinsic images of the original image. The illumination components of the images of a fixed scene vary from image to image, while the reflectance components of the images in principle remain constant. Both reflectance and illumination images have their own applications. Intrinsic image extraction has long been an important task for computer vision applications. However, this task is not at all simple because it is an ill- conditioned problem. The proposed approach convolves an input image with a prescribed set of derivative filters. The pixels of the derivative images are next classified as being reflectance or illumination according to three measures: chromatic, intensity contrast and edge sharpness, which are calculated in advance for each pixel from the input image. Finally, a de-convolution process is applied to the classified derivative images to obtain the intrinsic images. The results reveal the feasibility of the proposed technique in both rapidly and effectively decomposing intrinsic images from one single image.

KW - Chromatic measurement

KW - Intensity contrast and edge sharpness measures

KW - Intrinsic images

KW - Photometric reflectance model

KW - Reflectance and illumination components

UR - http://www.scopus.com/inward/record.url?scp=72549108827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72549108827&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:72549108827

VL - 25

SP - 1939

EP - 1953

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 6

ER -