{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T12:29:02Z","timestamp":1776515342583,"version":"3.51.2"},"reference-count":38,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CSIR"},{"name":"MTN"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Knowledge of a person\u2019s level of skin pigmentation, or so-called \u201cskin tone\u201d, has proven to be an important building block in improving the performance and fairness of various applications that rely on computer vision. These include medical diagnosis of skin conditions, cosmetic and skincare support, and face recognition, especially for darker skin tones. However, the perception of skin tone, whether by the human eye or by an optoelectronic sensor, uses the reflection of light from the skin. The source of this light, or illumination, affects the skin tone that is perceived. This study aims to refine and assess a convolutional neural network-based skin tone estimation model that provides consistent accuracy across different skin tones under various lighting conditions. The 10-point Monk Skin Tone Scale was used to represent the skin tone spectrum. A dataset of 21,375 images was captured from volunteers across the pigmentation spectrum. Experimental results show that a regression model outperforms other models, with an estimated-to-target distance of 0.5. Using a threshold estimated-to-target skin tone distance of 2 for all lights results in average accuracy values of 85.45% and 97.16%. With the Monk Skin Tone Scale segmented into three groups, the lighter exhibits strong accuracy, the middle displays lower accuracy, and the dark falls between the two. The overall skin tone estimation achieves average error distances in the LAB space of 16.40\u00b120.62.<\/jats:p>","DOI":"10.3390\/jimaging10050109","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T08:02:22Z","timestamp":1714723342000},"page":"109","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Skin Tone Estimation under Diverse Lighting Conditions"],"prefix":"10.3390","volume":"10","author":[{"given":"Success K.","family":"Mbatha","sequence":"first","affiliation":[{"name":"Department of E&E, Stellenbosch University, Stellenbosch 7602, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-2069","authenticated-orcid":false,"given":"Marthinus J.","family":"Booysen","sequence":"additional","affiliation":[{"name":"Department of E&E, Stellenbosch University, Stellenbosch 7602, South Africa"},{"name":"Department of Industrial Engineering, Stellenbosch University, Stellenbosch 7602, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0508-1690","authenticated-orcid":false,"given":"Rensu P.","family":"Theart","sequence":"additional","affiliation":[{"name":"Department of E&E, Stellenbosch University, Stellenbosch 7602, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107039","DOI":"10.1016\/j.isci.2023.107039","article-title":"Using infrared to improve face recognition of individuals with highly pigmented skin","volume":"26","author":"Muthua","year":"2023","journal-title":"iScience"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Krishnapriya, K., King, M.C., and Bowyer, K.W. (2021). Analysis of Manual and Automated Skin Tone Assignments for Face Recognition Applications. arXiv.","DOI":"10.1109\/WACVW54805.2022.00049"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1186\/s13677-023-00550-3","article-title":"Exploring cross-cultural and gender differences in facial expressions: A skin tone analysis using RGB Values","volume":"12","author":"Ali","year":"2023","journal-title":"J. Cloud Comput."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sobhan, M., Leizaola, D., Godavarty, A., and Mondal, A. (2022, January 14\u201316). Subject Skin Tone Classification with Implications in Wound Imaging using Deep Learning. Proceedings of the 2022 International Conference on Computational Science and Computational Intelligence (CSCI), Los Alamitos, CA, USA.","DOI":"10.1109\/CSCI58124.2022.00293"},{"key":"ref_5","first-page":"22","article-title":"Complexion Classification Based on Convolutional Neural Network","volume":"3","author":"Lin","year":"2020","journal-title":"J. Artif. Intell. Pract."},{"key":"ref_6","unstructured":"Kinyanjui, N.M., Odonga, T., Cintas, C., Codella, N.C.F., Panda, R., Sattigeri, P., and Varshney, K.R. (2019). Estimating skin tone and effects on classification performance in dermatology datasets. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Borza, D.L., Darabant, A.S., and Danescu, R.G. (2018, January 27\u201329). Automatic Skin Tone Extraction for Visagism Applications. Proceedings of the VISIGRAPP, Madeira, Portugal.","DOI":"10.5220\/0006711104660473"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"188309","DOI":"10.1109\/ACCESS.2020.3030912","article-title":"Deep Learning-Based Computational Color Constancy With Convoluted Mixture of Deep Experts (CMoDE) Fusion Technique","volume":"8","author":"Choi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yang, Z., Xie, K., Li, T., He, Y., Li, T., and Sun, X. (2020, January 23). Color Constancy Using VGG Convolutional Neural Network. Proceedings of the 2020 International Conference on High Performance Big Data and Intelligent Systems (HPBD& IS), Shenzhen, China.","DOI":"10.1109\/HPBDIS49115.2020.9130582"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yuan, T., and Li, X. (2019, January 12\u201315). Full Convolutional Color Constancy with Adding Pooling. Proceedings of the 2019 IEEE 11th International Conference on Communication Software and Networks (ICCSN), Chongqing, China.","DOI":"10.1109\/ICCSN.2019.8905344"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1364\/JOSAA.31.001049","article-title":"Illuminant estimation for color constancy: Why spatial-domain methods work and the role of the color distribution","volume":"31","author":"Cheng","year":"2014","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Luo, M.R. (2016). Encyclopedia of Color Science and Technology, Springer.","DOI":"10.1007\/978-1-4419-8071-7"},{"key":"ref_13","unstructured":"Jmal, M., Mseddi, W., Attia, R., and Youssef, A. (2014, January 23\u201327). Classification of human skin color and its application to face recognition. Proceedings of the MMEDIA 2014: The Sixth International Conferences on Advances in Multimedia, Nice, France."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Alhallak, K., Abdulhafid, A., Tomi, S., and Omran, D. (2023). The Ultimate Guide for Laser and IPL in the Aesthetic Field, Springer International Publishing.","DOI":"10.1007\/978-3-031-27632-3"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Baron, E. (2009). Light-Based Therapies for Skin of Color, Springer.","DOI":"10.1007\/978-1-84882-328-0"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1007\/s00521-016-2281-0","article-title":"Light source detection for digital images in noisy scenes: A neural network approach","volume":"28","author":"Elizondo","year":"2017","journal-title":"Neural Comput. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1007\/s00371-019-01666-x","article-title":"DeepLight: Light source estimation for augmented reality using deep learning","volume":"35","author":"Kafumann","year":"2019","journal-title":"Vis. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kortylewski, A., Egger, B., Schneider, A., Gerig, T., Morel-Forster, A., and Vetter, T. (2019, January 16\u201317). Analyzing and Reducing the Damage of Dataset Bias to Face Recognition With Synthetic Data. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00279"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Robinson, J.P., Livitz, G., Henon, Y., Qin, C., Fu, Y., and Timoner, S. (2020, January 14\u201319). Face Recognition: Too Bias, or Not Too Bias?. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00008"},{"key":"ref_20","first-page":"art00005","article-title":"Beyond color correction: Skin color estimation in the wild through deep learning","volume":"32","author":"Kips","year":"2020","journal-title":"Soc. Imaging Sci. Technol."},{"key":"ref_21","unstructured":"Weber, M. (2023, September 01). Caltech Face Dataset 1999. Available online: https:\/\/doi.org\/10.22002\/D1.20237."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.3758\/s13428-014-0532-5","article-title":"The Chicago Face Database: A Free Stimulus Set of Faces and Norming Data","volume":"47","author":"Ma","year":"2015","journal-title":"Behav. Res. Methods"},{"key":"ref_23","unstructured":"GoogleResearch (2022, May 14). Monk Skin Tone Scale. Available online: https:\/\/skintone.google\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kasemann, M., Kokert, J., Torres, S., Ruhle, K., and Reindl, L. (2014, January 11\u201314). Monitoring of indoor light conditions for photovoltaic energy harvesting. Proceedings of the 2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14), Barcelona, Spain.","DOI":"10.1109\/SSD.2014.6808770"},{"key":"ref_25","unstructured":"Amazon (2023, September 25). Recommendations for Facial Comparison Input Images. Available online: https:\/\/docs.aws.amazon.com\/rekognition\/latest\/dg\/recommendations-facial-input-images.html."},{"key":"ref_26","unstructured":"Brownlee, J. (2023, September 01). How Much Training Data Is Required for Machine Learning?. Available online: https:\/\/machinelearningmastery.com\/much-training-data-required-machine-learning\/."},{"key":"ref_27","unstructured":"Mbatha, S.K. (2023, November 01). MEng-Skin-Tone-Estimation-Using-VGG-16. Available online: https:\/\/github.com\/skmbatha\/MEng-Skin-tone-estimation-using-VGG-16."},{"key":"ref_28","unstructured":"Brownlee, J. (2023, September 01). Train-Test Split for Evaluating Machine Learning Algorithms. Available online: https:\/\/machinelearningmastery.com\/train-test-split-for-evaluating-machine-learning-algorithms\/."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Vabalas, A., Gowen, E., Poliakoff, E., and Casson, A.J. (2019). Machine learning algorithm validation with a limited sample size. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0224365"},{"key":"ref_30","unstructured":"Kato, S., and Hotta, K. (2021). MSE Loss with Outlying Label for Imbalanced Classification. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"37","DOI":"10.4310\/CIS.2018.v18.n1.a2","article-title":"An investigation for loss functions widely used in machine learning","volume":"18","author":"Nie","year":"2018","journal-title":"Commun. Inf. Syst."},{"key":"ref_32","unstructured":"Karaba\u011f, A., Ter-Sarkisov, C., Alonso, A., Reyes-Aldasoro, E., and Carlos, C. (2020, January 19\u201322). Radiography Classification: A Comparison between Eleven Convolutional Neural Networks. Proceedings of the 2020 Fourth International Conference on Multimedia Computing, Networking and Applications (MCNA), Valencia, Spain."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abishek, R., Ajeyan, T.R., Aravinth, N., Gokul, M., and Dhiyanesh, B. (2023, January 17\u201319). Advanced Skin Category Prediction System for Cosmetic Suggestion using Deep Convolution Neural Network. Proceedings of the 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India.","DOI":"10.1109\/ICICCS56967.2023.10142521"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O.M., and Zisserman, A. (2018). VGGFace2: A dataset for recognising faces across pose and age. arXiv.","DOI":"10.1109\/FG.2018.00020"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Khan, K., Ali, J., Uddin, I., Khan, S., and Roh, B.H. (2021). A Facial Feature Discovery Framework for Race Classification Using Deep Learning. arXiv.","DOI":"10.32604\/cmc.2021.016535"},{"key":"ref_36","unstructured":"Klette, R., Rivera, M., and Satoh, S. Gray-World Assumption on Perceptual Color Spaces. Proceedings of the Image and Video Technology."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Bianco, S., Cusano, C., Napoletano, P., and Schettini, R. (2017). Improving CNN-Based Texture Classification by Color Balancing. J. Imaging, 3.","DOI":"10.3390\/jimaging3030033"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"180","DOI":"10.21273\/HORTSCI16823-22","article-title":"LED Lighting: A Grower\u2019s Guide to Light Spectra","volume":"58","author":"Stamford","year":"2023","journal-title":"HortScience"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/5\/109\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:37:47Z","timestamp":1760107067000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/10\/5\/109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,30]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["jimaging10050109"],"URL":"https:\/\/doi.org\/10.3390\/jimaging10050109","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,30]]}}}