Automatic detection of acne scars: Preliminary results

Biman Chandra Dey, B. Nirmal, Ramesh R. Galigekere

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

6 Citations (Scopus)

Abstract

Acne scars are of great cosmetic concern, and there are several methods of treatment towards reducing the appearance of scars. Automatic detection of acne scar-pixels from digital color images would be helpful in quantitative assessment of the success of treatment. This paper addresses detection of acne scar-pixels based on color image processing. The RGB model is used to representing the data. Pixels from the background (skin) and from the lesions of interest (acne scars) were recorded from the images of 7 subjects, to build a knowledge-base i.e., clusters associated with the skin and acne scars, respectively. The clusters were found to be fairly distinct in the RGB space. Consequently, classification (segmentation) is performed by minimum-distance- rule in the RGB space, by using Mahalanobis distance (MD). We have also implemented Bayes' method. The results have been validated with respect to the ground-truth extracted by manual segmentation of scars. The classifier based on MD performs better than that based on Bayes, with the average values of sensitivity and specificity of the former being 90.36 and 93.82, respectively.

Original languageEnglish
Title of host publicationIEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies
Subtitle of host publicationSynergy Towards Better Global Healthcare, PHT 2013
Pages224-227
Number of pages4
DOIs
Publication statusPublished - 08-03-2013
Event1st IEEE-EMBS Conference on Point-of-Care Healthcare Technologies, PHT 2013 - Bangalore, India
Duration: 16-01-201318-01-2013

Conference

Conference1st IEEE-EMBS Conference on Point-of-Care Healthcare Technologies, PHT 2013
CountryIndia
CityBangalore
Period16-01-1318-01-13

Fingerprint

Acne Vulgaris
Cicatrix
Pixels
Skin
Color image processing
Classifiers
Color
Knowledge Bases
Cosmetics
Sensitivity and Specificity

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Dey, B. C., Nirmal, B., & Galigekere, R. R. (2013). Automatic detection of acne scars: Preliminary results. In IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies: Synergy Towards Better Global Healthcare, PHT 2013 (pp. 224-227). [6461325] https://doi.org/10.1109/PHT.2013.6461325
Dey, Biman Chandra ; Nirmal, B. ; Galigekere, Ramesh R. / Automatic detection of acne scars : Preliminary results. IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies: Synergy Towards Better Global Healthcare, PHT 2013. 2013. pp. 224-227
@inproceedings{58c1943c300843409162c40669d90f3c,
title = "Automatic detection of acne scars: Preliminary results",
abstract = "Acne scars are of great cosmetic concern, and there are several methods of treatment towards reducing the appearance of scars. Automatic detection of acne scar-pixels from digital color images would be helpful in quantitative assessment of the success of treatment. This paper addresses detection of acne scar-pixels based on color image processing. The RGB model is used to representing the data. Pixels from the background (skin) and from the lesions of interest (acne scars) were recorded from the images of 7 subjects, to build a knowledge-base i.e., clusters associated with the skin and acne scars, respectively. The clusters were found to be fairly distinct in the RGB space. Consequently, classification (segmentation) is performed by minimum-distance- rule in the RGB space, by using Mahalanobis distance (MD). We have also implemented Bayes' method. The results have been validated with respect to the ground-truth extracted by manual segmentation of scars. The classifier based on MD performs better than that based on Bayes, with the average values of sensitivity and specificity of the former being 90.36 and 93.82, respectively.",
author = "Dey, {Biman Chandra} and B. Nirmal and Galigekere, {Ramesh R.}",
year = "2013",
month = "3",
day = "8",
doi = "10.1109/PHT.2013.6461325",
language = "English",
isbn = "9781467327664",
pages = "224--227",
booktitle = "IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies",

}

Dey, BC, Nirmal, B & Galigekere, RR 2013, Automatic detection of acne scars: Preliminary results. in IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies: Synergy Towards Better Global Healthcare, PHT 2013., 6461325, pp. 224-227, 1st IEEE-EMBS Conference on Point-of-Care Healthcare Technologies, PHT 2013, Bangalore, India, 16-01-13. https://doi.org/10.1109/PHT.2013.6461325

Automatic detection of acne scars : Preliminary results. / Dey, Biman Chandra; Nirmal, B.; Galigekere, Ramesh R.

IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies: Synergy Towards Better Global Healthcare, PHT 2013. 2013. p. 224-227 6461325.

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

TY - GEN

T1 - Automatic detection of acne scars

T2 - Preliminary results

AU - Dey, Biman Chandra

AU - Nirmal, B.

AU - Galigekere, Ramesh R.

PY - 2013/3/8

Y1 - 2013/3/8

N2 - Acne scars are of great cosmetic concern, and there are several methods of treatment towards reducing the appearance of scars. Automatic detection of acne scar-pixels from digital color images would be helpful in quantitative assessment of the success of treatment. This paper addresses detection of acne scar-pixels based on color image processing. The RGB model is used to representing the data. Pixels from the background (skin) and from the lesions of interest (acne scars) were recorded from the images of 7 subjects, to build a knowledge-base i.e., clusters associated with the skin and acne scars, respectively. The clusters were found to be fairly distinct in the RGB space. Consequently, classification (segmentation) is performed by minimum-distance- rule in the RGB space, by using Mahalanobis distance (MD). We have also implemented Bayes' method. The results have been validated with respect to the ground-truth extracted by manual segmentation of scars. The classifier based on MD performs better than that based on Bayes, with the average values of sensitivity and specificity of the former being 90.36 and 93.82, respectively.

AB - Acne scars are of great cosmetic concern, and there are several methods of treatment towards reducing the appearance of scars. Automatic detection of acne scar-pixels from digital color images would be helpful in quantitative assessment of the success of treatment. This paper addresses detection of acne scar-pixels based on color image processing. The RGB model is used to representing the data. Pixels from the background (skin) and from the lesions of interest (acne scars) were recorded from the images of 7 subjects, to build a knowledge-base i.e., clusters associated with the skin and acne scars, respectively. The clusters were found to be fairly distinct in the RGB space. Consequently, classification (segmentation) is performed by minimum-distance- rule in the RGB space, by using Mahalanobis distance (MD). We have also implemented Bayes' method. The results have been validated with respect to the ground-truth extracted by manual segmentation of scars. The classifier based on MD performs better than that based on Bayes, with the average values of sensitivity and specificity of the former being 90.36 and 93.82, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84874555171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874555171&partnerID=8YFLogxK

U2 - 10.1109/PHT.2013.6461325

DO - 10.1109/PHT.2013.6461325

M3 - Conference contribution

AN - SCOPUS:84874555171

SN - 9781467327664

SP - 224

EP - 227

BT - IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies

ER -

Dey BC, Nirmal B, Galigekere RR. Automatic detection of acne scars: Preliminary results. In IEEE EMBS Special Topic Conference on Point-of-Care (POC) Healthcare Technologies: Synergy Towards Better Global Healthcare, PHT 2013. 2013. p. 224-227. 6461325 https://doi.org/10.1109/PHT.2013.6461325