{"title":"Skin Tone Analysis Through Skin Tone Map Generation With Optical Approach and Deep Learning.","authors":"Geunho Jung, Semin Kim, Sangwook Yoo","doi":"10.1111/srt.70088","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Skin tone assessment is critical in both cosmetic and medical fields, yet traditional methods like the individual typology angle (ITA) have limitations, such as sensitivity to illuminants and insensitivity to skin redness.</p><p><strong>Methods: </strong>This study introduces an automated image-based method for skin tone mapping by applying optical approaches and deep learning. The method generates skin tone maps by leveraging the illuminant spectrum, segments the skin region from face images, and identifies the corresponding skin tone on the map. The method was evaluated by generating skin tone maps under three standard illuminants (D45, D65, and D85) and comparing the results with those obtained using ITA on skin tone simulation images.</p><p><strong>Results: </strong>The results showed that skin tone maps generated under the same lighting conditions as the image acquisition (D65) provided the highest accuracy, with a color difference of around 6, which is more than twice as small as those observed under other illuminants. The mapping positions also demonstrated a clear correlation with pigment levels. Compared to ITA, the proposed approach was particularly effective in distinguishing skin tones related to redness.</p><p><strong>Conclusion: </strong>Despite the need to measure the illuminant spectrum and for further physiological validation, the proposed approach shows potential for enhancing skin tone assessment. Its ability to mitigate the effects of illuminants and distinguish between the two dominant pigments offers promising applications in both cosmetic and medical diagnostics.</p>","PeriodicalId":21746,"journal":{"name":"Skin Research and Technology","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11452249/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Skin Research and Technology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/srt.70088","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"DERMATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Skin tone assessment is critical in both cosmetic and medical fields, yet traditional methods like the individual typology angle (ITA) have limitations, such as sensitivity to illuminants and insensitivity to skin redness.
Methods: This study introduces an automated image-based method for skin tone mapping by applying optical approaches and deep learning. The method generates skin tone maps by leveraging the illuminant spectrum, segments the skin region from face images, and identifies the corresponding skin tone on the map. The method was evaluated by generating skin tone maps under three standard illuminants (D45, D65, and D85) and comparing the results with those obtained using ITA on skin tone simulation images.
Results: The results showed that skin tone maps generated under the same lighting conditions as the image acquisition (D65) provided the highest accuracy, with a color difference of around 6, which is more than twice as small as those observed under other illuminants. The mapping positions also demonstrated a clear correlation with pigment levels. Compared to ITA, the proposed approach was particularly effective in distinguishing skin tones related to redness.
Conclusion: Despite the need to measure the illuminant spectrum and for further physiological validation, the proposed approach shows potential for enhancing skin tone assessment. Its ability to mitigate the effects of illuminants and distinguish between the two dominant pigments offers promising applications in both cosmetic and medical diagnostics.
背景:肤色评估在美容和医疗领域都至关重要,但传统方法(如个体类型学角度(ITA))存在局限性,如对光照度敏感、对皮肤泛红不敏感等:本研究通过应用光学方法和深度学习,介绍了一种基于图像的自动肤色映射方法。该方法利用光照光谱生成肤色图,从人脸图像中分割皮肤区域,并在肤色图上识别相应的肤色。该方法通过在三种标准光源(D45、D65 和 D85)下生成肤色图进行评估,并将结果与使用 ITA 在肤色模拟图像上获得的结果进行比较:结果表明,在与图像采集相同的照明条件下(D65)生成的肤色图准确度最高,色差约为 6,比在其他照明条件下观察到的色差小两倍多。映射位置与色素水平也有明显的相关性。与 ITA 相比,所提出的方法在区分与红色有关的肤色方面尤为有效:尽管还需要测量光源光谱和进一步的生理验证,但所提出的方法显示出了增强肤色评估的潜力。它能够减轻光源的影响并区分两种主要色素,在美容和医疗诊断方面都有广阔的应用前景。
期刊介绍:
Skin Research and Technology is a clinically-oriented journal on biophysical methods and imaging techniques and how they are used in dermatology, cosmetology and plastic surgery for noninvasive quantification of skin structure and functions. Papers are invited on the development and validation of methods and their application in the characterization of diseased, abnormal and normal skin.
Topics include blood flow, colorimetry, thermography, evaporimetry, epidermal humidity, desquamation, profilometry, skin mechanics, epiluminiscence microscopy, high-frequency ultrasonography, confocal microscopy, digital imaging, image analysis and computerized evaluation and magnetic resonance. Noninvasive biochemical methods (such as lipids, keratin and tissue water) and the instrumental evaluation of cytological and histological samples are also covered.
The journal has a wide scope and aims to link scientists, clinical researchers and technicians through original articles, communications, editorials and commentaries, letters, reviews, announcements and news. Contributions should be clear, experimentally sound and novel.