SkinSight: Design and Implementation of an Intelligent Skin Type Detection System

Year : 2026 | Volume : 13 | Issue : 01 | Page : 35 45
    By

    Diya Goswami,

  • Sayantika Laskar,

  1. Computing Science and Engineering with Specialization in Health Informatics, VIT Bhopal University, Bhopal, Madhya Pradesh, India
  2. Computing Science and Engineering with Specialization in Health Informatics, VIT Bhopal University, Bhopal, Madhya Pradesh, India

Abstract

Identifying an individual’s skin type accurately is essential for creating personalized dermatological treatments and formulating skincare products that genuinely meet user needs. In this project, a real- time skin type classification system is developed using a combination of convolutional neural networks (CNNs) and modern computer vision techniques. The system processes live video streams, isolates the facial region through Haar cascade–based detection, and applies a series of preprocessing steps to enhance clarity and highlight essential skin features. Once the facial area is prepared, the trained CNN model classifies the skin into one of three categories: dry, normal, or oily. During evaluation, the model demonstrates strong accuracy and consistent performance, making it suitable for real-time use on consumer devices or clinical tools. Beyond simple classification, this technology has the potential to support personalized skincare recommendations, assist dermatologists with initial screenings, and improve automated beauty or health applications. Future enhancements may include expanding the model to recognize additional skin concerns, improving robustness under varying lighting conditions, and integrating more advanced feature-extraction methods to further increase reliability.

Keywords: Skin type, haar cascade, CNN, dermatology, skinsight

[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]

How to cite this article:
Diya Goswami, Sayantika Laskar. SkinSight: Design and Implementation of an Intelligent Skin Type Detection System. Journal of Image Processing & Pattern Recognition Progress. 2026; 13(01):35-45.
How to cite this URL:
Diya Goswami, Sayantika Laskar. SkinSight: Design and Implementation of an Intelligent Skin Type Detection System. Journal of Image Processing & Pattern Recognition Progress. 2026; 13(01):35-45. Available from: https://journals.stmjournals.com/joipprp/article=2026/view=240049


References

  1. Saiwaeo S, Arwatchananukul S, Mungmai L, Preedalikit W, Aunsri N. Human skin type classification using image processing and deep learning approaches. Heliyon. 2023;9(11):e21176. doi:10.1016/j.heliyon.2023.e21176. PubMed PMID: 38027689.
  2. Kara FB, Kara R, Sakaci Çelik S. Skin type detection with deep learning: A comparative analysis. Düzce Univ Bilim Teknol Derg. 2023;11:729–742. doi:10.29130/dubited.930096.
  3. Ran J, Dong G, Yi F, Li L, Wu Y. Automatic measurement of comprehensive skin types based on image processing and deep learning. Electronics. 2024;14(1):49. doi:10.3390/electronics14010049.
  4. Efata R, Loka WI, Wijaya N, Suhartono D. Facial skin type prediction based on Baumann skin type solutions theory using machine learning. TEM J. 2023;12(1):96–103. doi:10.18421/TEM121-13.
  5. Göçeri E. Convolutional neural network based desktop applications to classify dermatological diseases. 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy. 2020. p. 138–143. doi: 10.1109/IPAS50080.2020.9334956.
  6. Goceri E. Automated skin cancer detection: Where we are and the way to the future. 2021 44th International Conference on Telecommunications and Signal Processing (TSP), Brno, Czech Republic. 2021. p. 48–51. doi:10.1109/TSP52935.2021.9522605.
  7. Goceri E, Karakas AA. Comparative evaluations of CNN based networks for skin lesion classification. In: Xiao Y, Abraham AP, Roth J, editors. Proceedings of the IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2020; Big Data Analytics, Data Mining and Computational Intelligence 2020; and Theory and Practice in Modern Computing 2020; 2020 Jul 23–25; Virtual Conference. Lisbon: IADIS – International Association for Development of the Information Society; 2020. p. 237–242.
  8. Xie P, Li T, Liu J, Li F, Zhou J, Zuo K. Analyze skin histopathology images using multiple deep learning methods. 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC), Greenville, SC, USA. 2021. p. 374–377. doi:10.1109/ICFTIC54370.2021.9647425.
  9. Zhang B, Zhou X, Luo Y, Zhang H, Yang H, Ma J, Ma L. Opportunities and challenges: Classification of skin disease based on deep learning. Chin J Mech Eng. 2021;34(1):112. doi:10.1186/s10033-021-00629-5.
  10. Ravnbak MH. Objective determination of Fitzpatrick skin type. Dan Med Bull. 2010;57(8):B4153. PubMed PMID: 20682135.
  11. Yook D, Lee H, Yoo IC. A survey on parallel training algorithms for deep neural networks. J Acoust Soc Korea. 2020;39(6):505–514.
  12. Vinod S, Thomas MV. A comparative analysis on deep learning techniques for skin cancer detection and skin lesion segmentation. 2021 International Conference on Communication, Control and Information Sciences (ICCISc), Idukki, India. 2021. p. 1–6. doi:10.1109/ICCISc52257.2021.9484873.
  13. Cho SI, Kim D, Lee H, Um TT, Kim H. Explore highly relevant questions in the Baumann skin type questionnaire through the digital skin analyzer: A retrospective single-center study in South Korea. J Cosmet Dermatol. 2023;22(11):3159–3167. doi:10.1111/jocd.15820. PubMed PMID: 37313638.
  14. Srimaharaj W, Chaising S. Distance-based integration method for human skin type identification. Comput Biol Med. 2024;178:108575. doi:10.1016/j.compbiomed.2024.108575. PubMed PMID: 38861893.
  15. Hossain MS, Shahriar GM, Syeed MMM, Uddin MF, Hasan M, Shivam S, Advani S. Region of interest (ROI) selection using vision transformer for automatic analysis using whole slide images. Sci Rep. 2023;13(1):11314. doi:10.1038/s41598-023-38109-6. PubMed PMID: 37443188.
  16. Indriyani, Sudarma IM. Classification of facial skin type using discrete wavelet transform, contrast, local binary pattern and support vector machine. J Theor Appl Inf Technol. 2020 Mar 15;98(5):768– 799.
  17. Cui H, Feng C, Zhang T, Martínez-Ríos V, Martorell P, Tortajada M, Cheng S, Cheng S, Duan Z. Effects of a lotion containing probiotic ferment lysate as the main functional ingredient on enhancing skin barrier: A randomized, self-control study. Sci Rep. 2023;13(1):16879. doi:10.1038/s41598-023-43336-y. PubMed PMID: 37803101.
  18. Nusantara TF, Atmaja RD, Azizah A. [Klasifikasi jenis kulit wajah pria berdasarkan tekstur menggunakan metode gray level co-occurrence matrix (GLCM) dan support vector machine]. Classification of men’s face skin types based on the texture using gray level co-occurrence matrix (GLCM) and support vector machine method. eProceedings Eng. 2018 Aug;5(2):2130–2137. [Indonesian].
  19. Baumann L. Understanding and treating various skin types: The Baumann skin type indicator. Dermatol Clin. 2008;26(3):359–373. doi:10.1016/j.det.2008.03.007. PubMed PMID: 18555952.
  20. Hoshyar AN, Al-Jumaily A, Sulaiman R. Review on automatic early skin cancer detection. 2011 International Conference on Computer Science and Service System (CSSS), Nanjing, China. 2011. p. 4036–4039. doi: 10.1109/CSSS.2011.5974581.
  21. Goceri E. Image augmentation for deep learning based lesion classification from skin images. 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy. 2020. p. 144–148. doi:10.1109/IPAS50080.2020.9334937.
  22. Savchenko AV. Probabilistic neural network with complex exponential activation functions in image recognition. IEEE Trans Neural Netw Learn Syst. 2019;31(2):651–660. doi:10.1109/TNNLS.2019.2908973.
  23. Wang Z, Yan M, Chen J, Liu S, Zhang D. Deep learning library testing via effective model generation. In: Devanbu P, Cohen M, editors. Proceedings of the 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE ‘20); 2020 Nov 8–13; Virtual Event, USA. New York (NY): Association for Computing Machinery; 2020. p. 788–799. doi:10.1145/3368089.3409761.
  24. Yao R, Li J, Hui M, Bai L, Wu Q. Feature selection based on random forest for partial discharges characteristic set. IEEE Access. 2020;8:159151–159161. doi:10.1109/ACCESS.2020.3019377.
  25. Ding DM, Tu Y, Man MQ, Wu WJ, Lu FY, Li X, et al. Association between lactic acid sting test scores, self-assessed sensitive skin scores and biophysical properties in Chinese females. Int J Cosmet Sci. 2019;41(4):398–404. doi:10.1111/ics.12550.
  26. Ahuja R, Sharma SC. Exploiting machine learning and feature selection algorithms to predict instructor performance in higher education. J Inf Sci Eng. 2021;37(5):993–1009. doi:10.6688/JISE.20210937(5).0001.
  27. Liu J, Zhang X, Li Y, Wang J, Kim HJ. Deep learning-based reasoning with multi-ontology for IoT applications. IEEE Access. 2019;7:124688–124701. doi:10.1109/ACCESS.2019.2937353.
  28. Bhadula S, Sharma S, Juyal P, Kulshrestha C. Machine learning algorithms based skin disease detection. Int J Innov Technol Explor Eng. 2019;9(2):4044–4049. doi:10.35940/ijitee.B7686.129219.
  29. Kolkur MS, Kalbande DR, Kharkar V. Machine learning approaches to multi-class human skin disease detection. Int J Comput Intell Res. 2018;14(1):29–39.
  30. Badr M, Elkasaby A, Alrahmawy M, El-Metwally S. A multi-model deep learning architecture for diagnosing multi-class skin diseases. J Imaging Inform Med. 2025;38(3):1776–1795. doi:10.1007/s10278-024-01300-w.
Regular Issue Subscription Review Article
Volume 13
Issue 01
Received 28/06/2025
Accepted 02/08/2025
Published 26/02/2026
Publication Time 243 Days
3

Login


My IP

PlumX Metrics