2.50
Hdl Handle:
http://hdl.handle.net/10755/159305
Type:
Presentation
Title:
Quantifying Skin Color from Digital Images: An Innovative Technique
Abstract:
Quantifying Skin Color from Digital Images: An Innovative Technique
Conference Sponsor:Midwest Nursing Research Society
Conference Year:2005
Author:Baker, Rachel, MSW, BSN
P.I. Institution Name:University of Cincinnati
Title:Predoctoral Student
Contact Address:College of Nursing, PO Box 210038, Cincinnati, OH, 45221-0038, USA
Contact Telephone:513-558-5269
Co-Authors:Marilyn Sommers, PhD, RN, FAAN and Jamison Fargo, PhD, Assistant Professor
Problem: The skin has been called the ôprimary interfaceö between patients and nurses. Nurses are involved in the evaluation of, and care for, patientsÆ skin. The analysis of skin color is relevant to the assessment of abrasions, tears, redness, and wounds. Skin color is quantified using subjective scales or objective reflectance spectrometers. The present study proposed a third method of skin color analysis that uses digital images taken to document and measure skin anomalies, injuries, and burns. Purpose: The present study examined the feasibility of quantifying skin color using digital images. Theoretical Framework: The Trichromatic Theory of Color Perception states that every color is a linear combination of the three primary colors. A standardized system of color classification, CIE L*(light-dark) a* (red-green) b*(yellow-blue), was developed from this theory. Design: Analysis of digital images taken of skin. Sample: Images of 52 subjectsÆ skin were analyzed (28 White and 24 Black subjects). Procedure: Using digital imaging software, two independent raters obtained CIE L*a*b* values. Results: Inter-rater reliabilities for L*, a*, and b* values among all subjects were: L: r=0.910, p=0.0001; a: r=0.897, p=0.0001; b: r=0.958, p=0.0001. The mean L* score for White subjects was 74.64 (SD=4.13) and for Black subjects was 50.44 (SD=8.65). The mean a* score for White subjects was 26.19 (SD=5.44) and for Black subjects was 16.72 (SD=7.58). The mean b* score for White subjects was 22.17 (SD=8.72) and for Black subjects was 15.38 (SD=11.84). The L*, a*, and b* values were significantly more variable among Black subjects than White subjects. Implication for nursing science: While this technique proved feasible and reliable, further validity work is needed. The metrics involved in this study have a wide application to scientists studying wounds and burns and to forensic nurses attempting to date injuries based on changes in skin color. (Poster Presentation)
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Midwest Nursing Research Society

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleQuantifying Skin Color from Digital Images: An Innovative Techniqueen_GB
dc.identifier.urihttp://hdl.handle.net/10755/159305-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Quantifying Skin Color from Digital Images: An Innovative Technique</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Midwest Nursing Research Society</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2005</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Baker, Rachel, MSW, BSN</td></tr><tr class="item-institute"><td class="label">P.I. Institution Name:</td><td class="value">University of Cincinnati</td></tr><tr class="item-author-title"><td class="label">Title:</td><td class="value">Predoctoral Student</td></tr><tr class="item-address"><td class="label">Contact Address:</td><td class="value">College of Nursing, PO Box 210038, Cincinnati, OH, 45221-0038, USA</td></tr><tr class="item-phone"><td class="label">Contact Telephone:</td><td class="value">513-558-5269</td></tr><tr class="item-email"><td class="label">Email:</td><td class="value">rachelbbaker@hotmail.com</td></tr><tr class="item-co-authors"><td class="label">Co-Authors:</td><td class="value">Marilyn Sommers, PhD, RN, FAAN and Jamison Fargo, PhD, Assistant Professor</td></tr><tr><td colspan="2" class="item-abstract">Problem: The skin has been called the &ocirc;primary interface&ouml; between patients and nurses. Nurses are involved in the evaluation of, and care for, patients&AElig; skin. The analysis of skin color is relevant to the assessment of abrasions, tears, redness, and wounds. Skin color is quantified using subjective scales or objective reflectance spectrometers. The present study proposed a third method of skin color analysis that uses digital images taken to document and measure skin anomalies, injuries, and burns. Purpose: The present study examined the feasibility of quantifying skin color using digital images. Theoretical Framework: The Trichromatic Theory of Color Perception states that every color is a linear combination of the three primary colors. A standardized system of color classification, CIE L*(light-dark) a* (red-green) b*(yellow-blue), was developed from this theory. Design: Analysis of digital images taken of skin. Sample: Images of 52 subjects&AElig; skin were analyzed (28 White and 24 Black subjects). Procedure: Using digital imaging software, two independent raters obtained CIE L*a*b* values. Results: Inter-rater reliabilities for L*, a*, and b* values among all subjects were: L: r=0.910, p=0.0001; a: r=0.897, p=0.0001; b: r=0.958, p=0.0001. The mean L* score for White subjects was 74.64 (SD=4.13) and for Black subjects was 50.44 (SD=8.65). The mean a* score for White subjects was 26.19 (SD=5.44) and for Black subjects was 16.72 (SD=7.58). The mean b* score for White subjects was 22.17 (SD=8.72) and for Black subjects was 15.38 (SD=11.84). The L*, a*, and b* values were significantly more variable among Black subjects than White subjects. Implication for nursing science: While this technique proved feasible and reliable, further validity work is needed. The metrics involved in this study have a wide application to scientists studying wounds and burns and to forensic nurses attempting to date injuries based on changes in skin color. (Poster Presentation)</td></tr></table>en_GB
dc.date.available2011-10-26T21:53:34Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T21:53:34Z-
dc.description.sponsorshipMidwest Nursing Research Societyen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.