Accurate wrinkle representation scheme for skin age estimation

Young Hwan Choi, Yoon Sik Tak, Seungmin Rho, Een Jun Hwang

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

2 Citations (Scopus)

Abstract

Among many features that can be observed from human skin, wrinkles are known to be very effective for assessing a subject's physical condition, surroundings, or lifestyle. In our previous work, we showed how to extract various wrinkle-related features such as total length, average width, depth, and size from magnified skin images and use them to estimate the degree of skin aging. To represent wrinkles on the skin images, we used a watershed algorithm and constructed its skeleton image, in which wrinkles are represented by 1-pixel lines. A skeleton image consists of polygons, which we call wrinkle cells. Since most wrinkle-related features are deduced from this skeleton image, accurate wrinkle representation is very critical. However, we found that the watershed algorithm produces over-segmentation for skin images; i.e., one wrinkle is represented by multiple smaller wrinkles in the skeleton image. To solve this problem, in this paper we propose an accurate skin wrinkle representation scheme that identifies and merges over-segmented cells in the skeleton image. Various experiments on our prototype system show that our scheme provides accurate skin wrinkle representation and thus improves the accuracy of skin age estimation.

Original languageEnglish
Title of host publicationProceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011
Pages226-231
Number of pages6
DOIs
Publication statusPublished - 2011 Sep 14
Event2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011 - Loutraki, Greece
Duration: 2011 Jun 282011 Jun 30

Other

Other2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011
CountryGreece
CityLoutraki
Period11/6/2811/6/30

Fingerprint

Skin
Watersheds
Aging of materials
Pixels
Experiments

Keywords

  • Image processing
  • Pattern recognition
  • Skin age
  • SVM classifier
  • Watershed algorithm
  • Wrinkle feature

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Choi, Y. H., Tak, Y. S., Rho, S., & Hwang, E. J. (2011). Accurate wrinkle representation scheme for skin age estimation. In Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011 (pp. 226-231). [5992194] https://doi.org/10.1109/MUE.2011.48

Accurate wrinkle representation scheme for skin age estimation. / Choi, Young Hwan; Tak, Yoon Sik; Rho, Seungmin; Hwang, Een Jun.

Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011. 2011. p. 226-231 5992194.

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

Choi, YH, Tak, YS, Rho, S & Hwang, EJ 2011, Accurate wrinkle representation scheme for skin age estimation. in Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011., 5992194, pp. 226-231, 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011, Loutraki, Greece, 11/6/28. https://doi.org/10.1109/MUE.2011.48
Choi YH, Tak YS, Rho S, Hwang EJ. Accurate wrinkle representation scheme for skin age estimation. In Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011. 2011. p. 226-231. 5992194 https://doi.org/10.1109/MUE.2011.48
Choi, Young Hwan ; Tak, Yoon Sik ; Rho, Seungmin ; Hwang, Een Jun. / Accurate wrinkle representation scheme for skin age estimation. Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011. 2011. pp. 226-231
@inproceedings{1de08ac71c6e4d008abbab9dc531bfe1,
title = "Accurate wrinkle representation scheme for skin age estimation",
abstract = "Among many features that can be observed from human skin, wrinkles are known to be very effective for assessing a subject's physical condition, surroundings, or lifestyle. In our previous work, we showed how to extract various wrinkle-related features such as total length, average width, depth, and size from magnified skin images and use them to estimate the degree of skin aging. To represent wrinkles on the skin images, we used a watershed algorithm and constructed its skeleton image, in which wrinkles are represented by 1-pixel lines. A skeleton image consists of polygons, which we call wrinkle cells. Since most wrinkle-related features are deduced from this skeleton image, accurate wrinkle representation is very critical. However, we found that the watershed algorithm produces over-segmentation for skin images; i.e., one wrinkle is represented by multiple smaller wrinkles in the skeleton image. To solve this problem, in this paper we propose an accurate skin wrinkle representation scheme that identifies and merges over-segmented cells in the skeleton image. Various experiments on our prototype system show that our scheme provides accurate skin wrinkle representation and thus improves the accuracy of skin age estimation.",
keywords = "Image processing, Pattern recognition, Skin age, SVM classifier, Watershed algorithm, Wrinkle feature",
author = "Choi, {Young Hwan} and Tak, {Yoon Sik} and Seungmin Rho and Hwang, {Een Jun}",
year = "2011",
month = "9",
day = "14",
doi = "10.1109/MUE.2011.48",
language = "English",
isbn = "9780769544700",
pages = "226--231",
booktitle = "Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011",

}

TY - GEN

T1 - Accurate wrinkle representation scheme for skin age estimation

AU - Choi, Young Hwan

AU - Tak, Yoon Sik

AU - Rho, Seungmin

AU - Hwang, Een Jun

PY - 2011/9/14

Y1 - 2011/9/14

N2 - Among many features that can be observed from human skin, wrinkles are known to be very effective for assessing a subject's physical condition, surroundings, or lifestyle. In our previous work, we showed how to extract various wrinkle-related features such as total length, average width, depth, and size from magnified skin images and use them to estimate the degree of skin aging. To represent wrinkles on the skin images, we used a watershed algorithm and constructed its skeleton image, in which wrinkles are represented by 1-pixel lines. A skeleton image consists of polygons, which we call wrinkle cells. Since most wrinkle-related features are deduced from this skeleton image, accurate wrinkle representation is very critical. However, we found that the watershed algorithm produces over-segmentation for skin images; i.e., one wrinkle is represented by multiple smaller wrinkles in the skeleton image. To solve this problem, in this paper we propose an accurate skin wrinkle representation scheme that identifies and merges over-segmented cells in the skeleton image. Various experiments on our prototype system show that our scheme provides accurate skin wrinkle representation and thus improves the accuracy of skin age estimation.

AB - Among many features that can be observed from human skin, wrinkles are known to be very effective for assessing a subject's physical condition, surroundings, or lifestyle. In our previous work, we showed how to extract various wrinkle-related features such as total length, average width, depth, and size from magnified skin images and use them to estimate the degree of skin aging. To represent wrinkles on the skin images, we used a watershed algorithm and constructed its skeleton image, in which wrinkles are represented by 1-pixel lines. A skeleton image consists of polygons, which we call wrinkle cells. Since most wrinkle-related features are deduced from this skeleton image, accurate wrinkle representation is very critical. However, we found that the watershed algorithm produces over-segmentation for skin images; i.e., one wrinkle is represented by multiple smaller wrinkles in the skeleton image. To solve this problem, in this paper we propose an accurate skin wrinkle representation scheme that identifies and merges over-segmented cells in the skeleton image. Various experiments on our prototype system show that our scheme provides accurate skin wrinkle representation and thus improves the accuracy of skin age estimation.

KW - Image processing

KW - Pattern recognition

KW - Skin age

KW - SVM classifier

KW - Watershed algorithm

KW - Wrinkle feature

UR - http://www.scopus.com/inward/record.url?scp=80052574207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052574207&partnerID=8YFLogxK

U2 - 10.1109/MUE.2011.48

DO - 10.1109/MUE.2011.48

M3 - Conference contribution

AN - SCOPUS:80052574207

SN - 9780769544700

SP - 226

EP - 231

BT - Proceedings of the 2011 5th FTRA International Conference on Multimedia and Ubiquitous Engineering, MUE 2011

ER -