Automatic contrast enhancement using pixel-based calibrating and mean shift clustering

Yu Yi Liao, Jzau Sheng Lin, Ping Jui Liu, Shen-Chuan Tai

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

Abstract

In this paper, we present the method for automatic contrast enhancement of color image. The base concept of method is that an image has its own reference luminance level and each pixel has its own characteristic luminance that is brighter or darker than reference luminance level. In the proposed method, a given color image is converted to HSV color space from RGB color space firstly. Next, each pixel in the image find out the own characteristic luminance based on the reference luminance level. The characteristic luminance is calibrated to the target luminance that will get the acceptable luminance. We apply alpha blending the original luminance and characteristic luminance to reduce the HALO artifact and preserve details of darker area by mean shift clustering.

Original languageEnglish
Title of host publicationRecent Advances in Computer Science and Information Engineering
Pages485-489
Number of pages5
Volume128 LNEE
EditionVOL. 5
DOIs
Publication statusPublished - 2012
Event2nd World Congress on Computer Science and Information Engineering, CSIE 2011 - Changchun, China
Duration: 2011 Jun 172011 Jun 19

Publication series

NameLecture Notes in Electrical Engineering
NumberVOL. 5
Volume128 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other2nd World Congress on Computer Science and Information Engineering, CSIE 2011
CountryChina
CityChangchun
Period11-06-1711-06-19

Fingerprint

Luminance
Pixels
Color

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Liao, Y. Y., Lin, J. S., Liu, P. J., & Tai, S-C. (2012). Automatic contrast enhancement using pixel-based calibrating and mean shift clustering. In Recent Advances in Computer Science and Information Engineering (VOL. 5 ed., Vol. 128 LNEE, pp. 485-489). (Lecture Notes in Electrical Engineering; Vol. 128 LNEE, No. VOL. 5). https://doi.org/10.1007/978-3-642-25792-6-73
Liao, Yu Yi ; Lin, Jzau Sheng ; Liu, Ping Jui ; Tai, Shen-Chuan. / Automatic contrast enhancement using pixel-based calibrating and mean shift clustering. Recent Advances in Computer Science and Information Engineering. Vol. 128 LNEE VOL. 5. ed. 2012. pp. 485-489 (Lecture Notes in Electrical Engineering; VOL. 5).
@inproceedings{9059d6c529ec462abd7fc2691dd0cc29,
title = "Automatic contrast enhancement using pixel-based calibrating and mean shift clustering",
abstract = "In this paper, we present the method for automatic contrast enhancement of color image. The base concept of method is that an image has its own reference luminance level and each pixel has its own characteristic luminance that is brighter or darker than reference luminance level. In the proposed method, a given color image is converted to HSV color space from RGB color space firstly. Next, each pixel in the image find out the own characteristic luminance based on the reference luminance level. The characteristic luminance is calibrated to the target luminance that will get the acceptable luminance. We apply alpha blending the original luminance and characteristic luminance to reduce the HALO artifact and preserve details of darker area by mean shift clustering.",
author = "Liao, {Yu Yi} and Lin, {Jzau Sheng} and Liu, {Ping Jui} and Shen-Chuan Tai",
year = "2012",
doi = "10.1007/978-3-642-25792-6-73",
language = "English",
isbn = "9783642257919",
volume = "128 LNEE",
series = "Lecture Notes in Electrical Engineering",
number = "VOL. 5",
pages = "485--489",
booktitle = "Recent Advances in Computer Science and Information Engineering",
edition = "VOL. 5",

}

Liao, YY, Lin, JS, Liu, PJ & Tai, S-C 2012, Automatic contrast enhancement using pixel-based calibrating and mean shift clustering. in Recent Advances in Computer Science and Information Engineering. VOL. 5 edn, vol. 128 LNEE, Lecture Notes in Electrical Engineering, no. VOL. 5, vol. 128 LNEE, pp. 485-489, 2nd World Congress on Computer Science and Information Engineering, CSIE 2011, Changchun, China, 11-06-17. https://doi.org/10.1007/978-3-642-25792-6-73

Automatic contrast enhancement using pixel-based calibrating and mean shift clustering. / Liao, Yu Yi; Lin, Jzau Sheng; Liu, Ping Jui; Tai, Shen-Chuan.

Recent Advances in Computer Science and Information Engineering. Vol. 128 LNEE VOL. 5. ed. 2012. p. 485-489 (Lecture Notes in Electrical Engineering; Vol. 128 LNEE, No. VOL. 5).

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

TY - GEN

T1 - Automatic contrast enhancement using pixel-based calibrating and mean shift clustering

AU - Liao, Yu Yi

AU - Lin, Jzau Sheng

AU - Liu, Ping Jui

AU - Tai, Shen-Chuan

PY - 2012

Y1 - 2012

N2 - In this paper, we present the method for automatic contrast enhancement of color image. The base concept of method is that an image has its own reference luminance level and each pixel has its own characteristic luminance that is brighter or darker than reference luminance level. In the proposed method, a given color image is converted to HSV color space from RGB color space firstly. Next, each pixel in the image find out the own characteristic luminance based on the reference luminance level. The characteristic luminance is calibrated to the target luminance that will get the acceptable luminance. We apply alpha blending the original luminance and characteristic luminance to reduce the HALO artifact and preserve details of darker area by mean shift clustering.

AB - In this paper, we present the method for automatic contrast enhancement of color image. The base concept of method is that an image has its own reference luminance level and each pixel has its own characteristic luminance that is brighter or darker than reference luminance level. In the proposed method, a given color image is converted to HSV color space from RGB color space firstly. Next, each pixel in the image find out the own characteristic luminance based on the reference luminance level. The characteristic luminance is calibrated to the target luminance that will get the acceptable luminance. We apply alpha blending the original luminance and characteristic luminance to reduce the HALO artifact and preserve details of darker area by mean shift clustering.

UR - http://www.scopus.com/inward/record.url?scp=84866276424&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866276424&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-25792-6-73

DO - 10.1007/978-3-642-25792-6-73

M3 - Conference contribution

SN - 9783642257919

VL - 128 LNEE

T3 - Lecture Notes in Electrical Engineering

SP - 485

EP - 489

BT - Recent Advances in Computer Science and Information Engineering

ER -

Liao YY, Lin JS, Liu PJ, Tai S-C. Automatic contrast enhancement using pixel-based calibrating and mean shift clustering. In Recent Advances in Computer Science and Information Engineering. VOL. 5 ed. Vol. 128 LNEE. 2012. p. 485-489. (Lecture Notes in Electrical Engineering; VOL. 5). https://doi.org/10.1007/978-3-642-25792-6-73