Image enhancement by analysis on embedded surfaces of images and a new framework for enhancement evaluation

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Image enhancement plays an important role in many machine vision applications on images captured in low contrast and low illumination conditions. In this study, we propose a new method for image enhancement based on analysis on embedded surfaces of images. The proposed method gives an insight into the relationship between the image intensity and image enhancement. In our method, scaled surface area and the surface volume are proposed and used to reconstruct the image iteratively for contrast enhancement, and the illumination of the reconstructed image can also be adjusted simultaneously. On the other hand, the most common methods for measuring the quality of enhanced images areMean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) in conventional works. The two measures have been recognized as inadequate ones because they do not evaluate the result in the way that the human vision system does. This paper also presents a new framework for evaluating image enhancement using both objective and subjective measures. This framework can also be used for other image quality evaluations such as denoising evaluation. We compare our enhancement method with some well-known enhancement algorithms, including wavelet and curvelet methods, using the new evaluation framework. The results show that our method can give better performance in most objective and subjective criteria than the conventional methods.

Original languageEnglish
Pages (from-to)1946-1954
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE91-D
Issue number7
DOIs
Publication statusPublished - 2008 Jul

Fingerprint

Image enhancement
Lighting
Image quality
Computer vision
Signal to noise ratio

Keywords

  • Enhancement evaluation
  • Human vision system
  • Image embedding
  • Image enhancement
  • Low contrast and low illumination

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

@article{2d13df38878a4df990dabf41ada2aab5,
title = "Image enhancement by analysis on embedded surfaces of images and a new framework for enhancement evaluation",
abstract = "Image enhancement plays an important role in many machine vision applications on images captured in low contrast and low illumination conditions. In this study, we propose a new method for image enhancement based on analysis on embedded surfaces of images. The proposed method gives an insight into the relationship between the image intensity and image enhancement. In our method, scaled surface area and the surface volume are proposed and used to reconstruct the image iteratively for contrast enhancement, and the illumination of the reconstructed image can also be adjusted simultaneously. On the other hand, the most common methods for measuring the quality of enhanced images areMean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) in conventional works. The two measures have been recognized as inadequate ones because they do not evaluate the result in the way that the human vision system does. This paper also presents a new framework for evaluating image enhancement using both objective and subjective measures. This framework can also be used for other image quality evaluations such as denoising evaluation. We compare our enhancement method with some well-known enhancement algorithms, including wavelet and curvelet methods, using the new evaluation framework. The results show that our method can give better performance in most objective and subjective criteria than the conventional methods.",
keywords = "Enhancement evaluation, Human vision system, Image embedding, Image enhancement, Low contrast and low illumination",
author = "Li Tian and Seiichiro Kamata",
year = "2008",
month = "7",
doi = "10.1093/ietisy/e91-d.7.1946",
language = "English",
volume = "E91-D",
pages = "1946--1954",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - Image enhancement by analysis on embedded surfaces of images and a new framework for enhancement evaluation

AU - Tian, Li

AU - Kamata, Seiichiro

PY - 2008/7

Y1 - 2008/7

N2 - Image enhancement plays an important role in many machine vision applications on images captured in low contrast and low illumination conditions. In this study, we propose a new method for image enhancement based on analysis on embedded surfaces of images. The proposed method gives an insight into the relationship between the image intensity and image enhancement. In our method, scaled surface area and the surface volume are proposed and used to reconstruct the image iteratively for contrast enhancement, and the illumination of the reconstructed image can also be adjusted simultaneously. On the other hand, the most common methods for measuring the quality of enhanced images areMean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) in conventional works. The two measures have been recognized as inadequate ones because they do not evaluate the result in the way that the human vision system does. This paper also presents a new framework for evaluating image enhancement using both objective and subjective measures. This framework can also be used for other image quality evaluations such as denoising evaluation. We compare our enhancement method with some well-known enhancement algorithms, including wavelet and curvelet methods, using the new evaluation framework. The results show that our method can give better performance in most objective and subjective criteria than the conventional methods.

AB - Image enhancement plays an important role in many machine vision applications on images captured in low contrast and low illumination conditions. In this study, we propose a new method for image enhancement based on analysis on embedded surfaces of images. The proposed method gives an insight into the relationship between the image intensity and image enhancement. In our method, scaled surface area and the surface volume are proposed and used to reconstruct the image iteratively for contrast enhancement, and the illumination of the reconstructed image can also be adjusted simultaneously. On the other hand, the most common methods for measuring the quality of enhanced images areMean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) in conventional works. The two measures have been recognized as inadequate ones because they do not evaluate the result in the way that the human vision system does. This paper also presents a new framework for evaluating image enhancement using both objective and subjective measures. This framework can also be used for other image quality evaluations such as denoising evaluation. We compare our enhancement method with some well-known enhancement algorithms, including wavelet and curvelet methods, using the new evaluation framework. The results show that our method can give better performance in most objective and subjective criteria than the conventional methods.

KW - Enhancement evaluation

KW - Human vision system

KW - Image embedding

KW - Image enhancement

KW - Low contrast and low illumination

UR - http://www.scopus.com/inward/record.url?scp=68149136652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68149136652&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.7.1946

DO - 10.1093/ietisy/e91-d.7.1946

M3 - Article

VL - E91-D

SP - 1946

EP - 1954

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -