AI-Based Personalised Facial Skincare Recommendation System

Abstract

The influence of intelligence in skincare and dermatology is growing. This project introduces a system that uses intelligence to analyze facial images and provide personalized skincare recommendations. The system uses computer vision and deep learning to identify skin characteristics such as acne, pigmentation, wrinkles and more. It determines the users skin type. Connects detected issues with suitable skincare ingredients and products. The goal is to provide affordable skincare guidance.

Introduction

It highlights that traditional skincare advice from dermatologists is often expensive, time-consuming, and not always accessible. In contrast, modern AI and computer vision techniques can analyze facial images to detect skin conditions such as acne, pigmentation, wrinkles, pores, and dark circles more quickly and consistently. The system also considers environmental factors like weather to provide more personalized skincare recommendations.

The proposed system uses a mobile application (Flutter-based) where users upload or capture facial images. These images are processed through steps like face detection (using ML Kit), preprocessing (cropping, resizing, noise removal), and AI-based analysis. The system then identifies skin issues and feeds the results into a rule-based recommendation engine that suggests customized skincare routines and products.

Conclusion

The Personalized Skincare Recommendation System, developed through the application of AI and computer vision, is a clear example of the application of Artificial Intelligence and computer vision technology to a particular domain, namely, skincare analysis. The system effectively performs image analysis, identifying important skin characteristics such as acne, pigmentation, oiliness, moisture, and dark circles, and offers personalized recommendations to the end users. The system, through the application of image analysis, image feature extraction, and rule-based recommendation, offers a comprehensive and easy-to-use system for skincare analysis and recommendations. The application of mobile technology is also an important contribution, as the system offers a convenient platform for users to analyze their skin without the need for any additional equipment or consultation. The system, apart from improving decision-making for choosing the right skincare products, also promotes awareness among individuals regarding skincare through personalized skincare routines and advice. The system, compared to traditional methods, is efficient, cost-effective, and convenient.The experimental results indicate that the system is functioning well under normal circumstances and is offering meaningful results that can be used to maintain healthy skin. In conclusion, the system bridges the gap between manual skincare analysis and intelligent technology, and offers a practical and innovative approach to skincare analysis and recommendations. The system, with further enhancements, is capable of becoming a comprehensive dermatology system for individuals and professionals alike.

References

[1] S. Sylvagno and T. H. Rochadiani, “Skincare Recommendation System Based on Facial Skin Type with Real- Time Weather Integration,” 2025. [2] Yadav and K. Singh, “Smart Dermatology: CNN-Based Detection and Product Recommendation,” International Research Journal of Engineering and Technology (IRJET), 2025. [3] Yadav, R. E. H. Khan, and K.Singh, “YOLO-Based Detection of Skin Anomalies with AI Recommendation Engine,” International Research Journal of Computer Science (IRJCS), 2025. [4] R. E. H. Khan and K. Singh, “AI-Driven Personalized Skincare: Enhancing Skin Analysis and Product Recommendation Systems,” 2025. [5] M. Rajegowda et al., “AI-Assisted Skincare Routine Recommendation System in XR,” Journal of Emerging Technologies and Innovative Research, 2025. [6] S. Supe, V. A. Agaskar, R. R. Mestry, and K. B. Rokade, “DermaTech: Skincare Product Recommendation System Using Machine Learning and Deep Learning,” 2025. [7] A. Jannatin and C. I. Ratnasari, “Personalized Skincare Recommendation System Based on Ontology and User Preferences,” 2025. [8] K. Vishwanth et al., “Smart Mirror Skin Care Recommendation Using Machine Learning,” International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 2025. [9] P. Krishnamoorthy, “Personalized Skincare Recommendations Using Deep Learning,” Master’s Thesis, 2024. [10] Fajrizal et al., “Web-Based Expert System Application in Determining Facial Care,” IOP Conference Series, 2020 [11] S. H. Kassani, P. H. Kassani, R. Khazaeinezhad, M. J. Wesolowski, and K. A. Schneider, “A Comparative Study of Deep Learning Architectures for Skin Disease Classification,” IEEE Access, vol. 7, pp. 150530–150543, 2019. [12] Esteva et al., “Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks,” Nature, vol. 542, pp. 115–118, 2017. [13] T. Yu and Y. Zhao, “Deep Learning- Based Skin Lesion Analysis for MobileHealthcare Applications,” IEEE Transactions on Biomedical Engineering, vol. 67, no. 5, pp. 1300–1310, 2020. [14] M. Codella et al., “Skin Lesion Analysis Toward Melanoma Detection Using Deep Learning,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 2, pp. 501–512, 2019. [15] N. Codella, D. Gutman, M. Celebi, et al., “Deep Learning Ensembles for Melanoma Recognition,” IEEE ISBI Conference, 2018. [16] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, 2015. [17] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv, 2014. [18] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” MICCAI, 2015. [19] Google, “ML Kit for Mobile Developers,” Available: https://developers.google.com/ml-kit

Copyright

Copyright © 2026 Mrs. Saba Noor Ayesha Khanum, M. Prathik, K. Smiley, G. Layasai. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.