Line fitting based segmentation and its application to skin image analysis

Jae Ho Jeon, Jae Young Lee, Ji Sang Bae, Jong-Ok Kim

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

Abstract

As mobile devices are recently equipped with advanced image sensors, it is expected that they would make it possible to diagnose one's skin condition conveniently anywhere and anytime. For this application it is necessary to classify the skin features from a skin image accurately. Although two conventional thresholding methods Otsu and Kapur perform well in a range of applications, we found that they are inappropriate for the specific skin analysis application of our interest. Otsu poorly works for non-bi-modal distributions while Kapur shows poor performance for long-tailed distributions. So, we propose a new line-fitting based thresholding method to detect pigments and pores from a skin image where the image histogram is simply modeled by two lines. Experimental results show that the proposed method finds better threshold which leads to the most visually plausible detection, compared to Otsu and Kapur.

Original languageEnglish
Title of host publication5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages60-63
Number of pages4
ISBN (Electronic)9781479987481
DOIs
Publication statusPublished - 2016 Jan 25
Event5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015 - Berlin, Germany
Duration: 2015 Sep 62015 Sep 9

Other

Other5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015
CountryGermany
CityBerlin
Period15/9/615/9/9

Fingerprint

Image analysis
Skin
Image sensors
Pigments
Mobile devices

Keywords

  • line-fitting
  • pigments
  • pores
  • segmentation
  • skin image

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Media Technology

Cite this

Jeon, J. H., Lee, J. Y., Bae, J. S., & Kim, J-O. (2016). Line fitting based segmentation and its application to skin image analysis. In 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015 (pp. 60-63). [7391333] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Berlin.2015.7391333

Line fitting based segmentation and its application to skin image analysis. / Jeon, Jae Ho; Lee, Jae Young; Bae, Ji Sang; Kim, Jong-Ok.

5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 60-63 7391333.

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

Jeon, JH, Lee, JY, Bae, JS & Kim, J-O 2016, Line fitting based segmentation and its application to skin image analysis. in 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015., 7391333, Institute of Electrical and Electronics Engineers Inc., pp. 60-63, 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015, Berlin, Germany, 15/9/6. https://doi.org/10.1109/ICCE-Berlin.2015.7391333
Jeon JH, Lee JY, Bae JS, Kim J-O. Line fitting based segmentation and its application to skin image analysis. In 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 60-63. 7391333 https://doi.org/10.1109/ICCE-Berlin.2015.7391333
Jeon, Jae Ho ; Lee, Jae Young ; Bae, Ji Sang ; Kim, Jong-Ok. / Line fitting based segmentation and its application to skin image analysis. 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 60-63
@inproceedings{e343695198294593b71b367710f21356,
title = "Line fitting based segmentation and its application to skin image analysis",
abstract = "As mobile devices are recently equipped with advanced image sensors, it is expected that they would make it possible to diagnose one's skin condition conveniently anywhere and anytime. For this application it is necessary to classify the skin features from a skin image accurately. Although two conventional thresholding methods Otsu and Kapur perform well in a range of applications, we found that they are inappropriate for the specific skin analysis application of our interest. Otsu poorly works for non-bi-modal distributions while Kapur shows poor performance for long-tailed distributions. So, we propose a new line-fitting based thresholding method to detect pigments and pores from a skin image where the image histogram is simply modeled by two lines. Experimental results show that the proposed method finds better threshold which leads to the most visually plausible detection, compared to Otsu and Kapur.",
keywords = "line-fitting, pigments, pores, segmentation, skin image",
author = "Jeon, {Jae Ho} and Lee, {Jae Young} and Bae, {Ji Sang} and Jong-Ok Kim",
year = "2016",
month = "1",
day = "25",
doi = "10.1109/ICCE-Berlin.2015.7391333",
language = "English",
pages = "60--63",
booktitle = "5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Line fitting based segmentation and its application to skin image analysis

AU - Jeon, Jae Ho

AU - Lee, Jae Young

AU - Bae, Ji Sang

AU - Kim, Jong-Ok

PY - 2016/1/25

Y1 - 2016/1/25

N2 - As mobile devices are recently equipped with advanced image sensors, it is expected that they would make it possible to diagnose one's skin condition conveniently anywhere and anytime. For this application it is necessary to classify the skin features from a skin image accurately. Although two conventional thresholding methods Otsu and Kapur perform well in a range of applications, we found that they are inappropriate for the specific skin analysis application of our interest. Otsu poorly works for non-bi-modal distributions while Kapur shows poor performance for long-tailed distributions. So, we propose a new line-fitting based thresholding method to detect pigments and pores from a skin image where the image histogram is simply modeled by two lines. Experimental results show that the proposed method finds better threshold which leads to the most visually plausible detection, compared to Otsu and Kapur.

AB - As mobile devices are recently equipped with advanced image sensors, it is expected that they would make it possible to diagnose one's skin condition conveniently anywhere and anytime. For this application it is necessary to classify the skin features from a skin image accurately. Although two conventional thresholding methods Otsu and Kapur perform well in a range of applications, we found that they are inappropriate for the specific skin analysis application of our interest. Otsu poorly works for non-bi-modal distributions while Kapur shows poor performance for long-tailed distributions. So, we propose a new line-fitting based thresholding method to detect pigments and pores from a skin image where the image histogram is simply modeled by two lines. Experimental results show that the proposed method finds better threshold which leads to the most visually plausible detection, compared to Otsu and Kapur.

KW - line-fitting

KW - pigments

KW - pores

KW - segmentation

KW - skin image

UR - http://www.scopus.com/inward/record.url?scp=84977650825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977650825&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Berlin.2015.7391333

DO - 10.1109/ICCE-Berlin.2015.7391333

M3 - Conference contribution

SP - 60

EP - 63

BT - 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -