Classification based histogram specification framework for image contrast enhancement

Sung Ho Lee; Kang A. Choi; Sung-Jea Ko

doi:10.1109/ICCAIS.2014.7020541

Classification based histogram specification framework for image contrast enhancement

Sung Ho Lee, Kang A. Choi, Sung-Jea Ko

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a novel contrast enhancement technique, referred to as the classification based histogram specification framework (CHSF). CHSF consists of offline training and online enhancement processes. In the offline training process, training images are classified into multiple classes, and then the feature vector that can discriminate the classes is generated and stored along with its most appropriate target histogram. In the online enhancement process, the best matching class is determined by comparing the feature vector of each class and that of the input image, then the corresponding target histogram of the class is adopted for histogram specification (HS). Experimental results show that the proposed method effectively enhances the image contrast by bringing out image details without amplifying noise in flat regions.

Original language	English
Title of host publication	2014 International Conference on Control, Automation and Information Sciences, ICCAIS 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	121-126
Number of pages	6
ISBN (Print)	9781479972043
DOIs	https://doi.org/10.1109/ICCAIS.2014.7020541
Publication status	Published - 2014 Jan 23
Event	3rd International Conference on Control, Automation and Information Sciences, ICCAIS 2014 - Gwangju, Korea, Republic of Duration: 2014 Dec 2 → 2014 Dec 5

Other

Other	3rd International Conference on Control, Automation and Information Sciences, ICCAIS 2014
Country/Territory	Korea, Republic of
City	Gwangju
Period	14/12/2 → 14/12/5

ASJC Scopus subject areas

Artificial Intelligence
Information Systems
Control and Systems Engineering

Access to Document

10.1109/ICCAIS.2014.7020541

Cite this

Classification based histogram specification framework for image contrast enhancement. / Lee, Sung Ho; Choi, Kang A.; Ko, Sung-Jea.
2014 International Conference on Control, Automation and Information Sciences, ICCAIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 121-126 7020541.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, SH, Choi, KA & Ko, S-J 2014, Classification based histogram specification framework for image contrast enhancement. in 2014 International Conference on Control, Automation and Information Sciences, ICCAIS 2014., 7020541, Institute of Electrical and Electronics Engineers Inc., pp. 121-126, 3rd International Conference on Control, Automation and Information Sciences, ICCAIS 2014, Gwangju, Korea, Republic of, 14/12/2. https://doi.org/10.1109/ICCAIS.2014.7020541

@inproceedings{7a60942242fd49eeb4a198b187e653eb,

title = "Classification based histogram specification framework for image contrast enhancement",

abstract = "In this paper, we propose a novel contrast enhancement technique, referred to as the classification based histogram specification framework (CHSF). CHSF consists of offline training and online enhancement processes. In the offline training process, training images are classified into multiple classes, and then the feature vector that can discriminate the classes is generated and stored along with its most appropriate target histogram. In the online enhancement process, the best matching class is determined by comparing the feature vector of each class and that of the input image, then the corresponding target histogram of the class is adopted for histogram specification (HS). Experimental results show that the proposed method effectively enhances the image contrast by bringing out image details without amplifying noise in flat regions.",

author = "Lee, {Sung Ho} and Choi, {Kang A.} and Sung-Jea Ko",

year = "2014",

month = jan,

day = "23",

doi = "10.1109/ICCAIS.2014.7020541",

language = "English",

isbn = "9781479972043",

pages = "121--126",

booktitle = "2014 International Conference on Control, Automation and Information Sciences, ICCAIS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "3rd International Conference on Control, Automation and Information Sciences, ICCAIS 2014 ; Conference date: 02-12-2014 Through 05-12-2014",

}

TY - GEN

T1 - Classification based histogram specification framework for image contrast enhancement

AU - Lee, Sung Ho

AU - Choi, Kang A.

AU - Ko, Sung-Jea

PY - 2014/1/23

Y1 - 2014/1/23

N2 - In this paper, we propose a novel contrast enhancement technique, referred to as the classification based histogram specification framework (CHSF). CHSF consists of offline training and online enhancement processes. In the offline training process, training images are classified into multiple classes, and then the feature vector that can discriminate the classes is generated and stored along with its most appropriate target histogram. In the online enhancement process, the best matching class is determined by comparing the feature vector of each class and that of the input image, then the corresponding target histogram of the class is adopted for histogram specification (HS). Experimental results show that the proposed method effectively enhances the image contrast by bringing out image details without amplifying noise in flat regions.

AB - In this paper, we propose a novel contrast enhancement technique, referred to as the classification based histogram specification framework (CHSF). CHSF consists of offline training and online enhancement processes. In the offline training process, training images are classified into multiple classes, and then the feature vector that can discriminate the classes is generated and stored along with its most appropriate target histogram. In the online enhancement process, the best matching class is determined by comparing the feature vector of each class and that of the input image, then the corresponding target histogram of the class is adopted for histogram specification (HS). Experimental results show that the proposed method effectively enhances the image contrast by bringing out image details without amplifying noise in flat regions.

UR - http://www.scopus.com/inward/record.url?scp=84949922861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949922861&partnerID=8YFLogxK

U2 - 10.1109/ICCAIS.2014.7020541

DO - 10.1109/ICCAIS.2014.7020541

M3 - Conference contribution

AN - SCOPUS:84949922861

SN - 9781479972043

SP - 121

EP - 126

BT - 2014 International Conference on Control, Automation and Information Sciences, ICCAIS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Control, Automation and Information Sciences, ICCAIS 2014

Y2 - 2 December 2014 through 5 December 2014

ER -

Classification based histogram specification framework for image contrast enhancement

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this