An iterative image enhancement algorithm and a new evaluation framework

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Image enhancement is important for images captured in low contrast and low illumination conditions. In this study, we propose a new iterative algorithm for image enhancement based on analysis on embedded surfaces of images. 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 Mean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) have been recognized as inadequate measures 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 gives better performance in most objective and subjective criteria than the conventional methods.

Original languageEnglish
Title of host publicationIEEE International Symposium on Industrial Electronics
Pages992-997
Number of pages6
DOIs
Publication statusPublished - 2008
Event2008 IEEE International Symposium on Industrial Electronics, ISIE 2008 - Cambridge
Duration: 2008 Jun 302008 Jul 2

Other

Other2008 IEEE International Symposium on Industrial Electronics, ISIE 2008
CityCambridge
Period08/6/3008/7/2

Fingerprint

Image enhancement
Lighting
Mean square error
Image quality
Signal to noise ratio

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Tian, L., & Kamata, S. (2008). An iterative image enhancement algorithm and a new evaluation framework. In IEEE International Symposium on Industrial Electronics (pp. 992-997). [4676952] https://doi.org/10.1109/ISIE.2008.4676952

An iterative image enhancement algorithm and a new evaluation framework. / Tian, Li; Kamata, Seiichiro.

IEEE International Symposium on Industrial Electronics. 2008. p. 992-997 4676952.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tian, L & Kamata, S 2008, An iterative image enhancement algorithm and a new evaluation framework. in IEEE International Symposium on Industrial Electronics., 4676952, pp. 992-997, 2008 IEEE International Symposium on Industrial Electronics, ISIE 2008, Cambridge, 08/6/30. https://doi.org/10.1109/ISIE.2008.4676952
Tian L, Kamata S. An iterative image enhancement algorithm and a new evaluation framework. In IEEE International Symposium on Industrial Electronics. 2008. p. 992-997. 4676952 https://doi.org/10.1109/ISIE.2008.4676952
Tian, Li ; Kamata, Seiichiro. / An iterative image enhancement algorithm and a new evaluation framework. IEEE International Symposium on Industrial Electronics. 2008. pp. 992-997
@inproceedings{1bd1f98a7dc2478e844db41fc2ac0564,
title = "An iterative image enhancement algorithm and a new evaluation framework",
abstract = "Image enhancement is important for images captured in low contrast and low illumination conditions. In this study, we propose a new iterative algorithm for image enhancement based on analysis on embedded surfaces of images. 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 Mean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) have been recognized as inadequate measures 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 gives better performance in most objective and subjective criteria than the conventional methods.",
author = "Li Tian and Seiichiro Kamata",
year = "2008",
doi = "10.1109/ISIE.2008.4676952",
language = "English",
isbn = "1424416655",
pages = "992--997",
booktitle = "IEEE International Symposium on Industrial Electronics",

}

TY - GEN

T1 - An iterative image enhancement algorithm and a new evaluation framework

AU - Tian, Li

AU - Kamata, Seiichiro

PY - 2008

Y1 - 2008

N2 - Image enhancement is important for images captured in low contrast and low illumination conditions. In this study, we propose a new iterative algorithm for image enhancement based on analysis on embedded surfaces of images. 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 Mean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) have been recognized as inadequate measures 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 gives better performance in most objective and subjective criteria than the conventional methods.

AB - Image enhancement is important for images captured in low contrast and low illumination conditions. In this study, we propose a new iterative algorithm for image enhancement based on analysis on embedded surfaces of images. 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 Mean Square Error (MSE) or Peak Signal-to-Noise-Ratio (PSNR) have been recognized as inadequate measures 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 gives better performance in most objective and subjective criteria than the conventional methods.

UR - http://www.scopus.com/inward/record.url?scp=57849153458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57849153458&partnerID=8YFLogxK

U2 - 10.1109/ISIE.2008.4676952

DO - 10.1109/ISIE.2008.4676952

M3 - Conference contribution

AN - SCOPUS:57849153458

SN - 1424416655

SN - 9781424416653

SP - 992

EP - 997

BT - IEEE International Symposium on Industrial Electronics

ER -