Authors : Shrutika Narendra Vibhute; Prerana Pradip Shinde

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/4kf5pbw2

DOI : https://doi.org/10.38124/ijisrt/26jun628

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The rapid evolution of computer vision and cloud telemetry has opened new avenues for automated, non-invasive dermatological and aesthetic assessments. Traditional methods of selecting skincare routines heavily rely on subjective consumer choices, often leading to chemical mismatches and skin barrier degradation. This paper presents a cloud integrated biometric web platform designed to automate facial skin analysis and deliver personalized chemical compound recommendations. The proposed system features an imageprocessing pipeline that extracts region-of-interest (ROI) matrices from user-uploaded facial images. These visual metrics are analyzed alongside a localized classification model to identify specific dermatological indicators such as structural sebum levels, hyper-pigmentation zones, and active tissue anomalies. Upon classification, an automated recommendation engine maps these physiological parameters to a tailored skincare matrix, highlighting optimal active chemical ingredients (e.g., specific concentrations of beta-hydroxy acids, retinoids, or hydrating humectants) while dynamically filtering out hazardous ingredient conflicts. Experimental evaluation of the deployed prototype demonstrates stable web execution speeds, low processing latency, and high alignment with target clinical skincare guidelines, presenting a scalable edge tool for safe home-based skincare analytics.

Keywords : Computer Vision, Biometric Face Analysis, Skincare Recommendation Engine, Deep Learning, Web Telemetry, Automated Diagnostics.

References :

1. K. Chandana, N. Swathi, and V. V. Kumar, "Deep Learning for Facial Skin Analysis Using Custom Convolutional Neural Network Architecture," in Proceedings of the International Conference on Artificial Intelligence and Computer Vision (ICAICV), pp. 114–121, Mar. 2024.
2. R. Nadagoudar, S. R. Patil, and M. V. Vibhute, "Transparent Neural Networks for Surface Tissue and Lesion Classification: A Deep Learning Perspective," International Journal of Engineering Research and Applications (IJERA), vol. 14, no. 6, pp. 45–52, June 2024.
3. J. Smith and E. Johnson, "Feature Mapping and Spatial Boundary Tracking in Automated Image Extraction Systems," International Journal of Wearable Technology, vol. 12, no. 2, pp. 142–148, Feb. 2023.
4. A. Author, "A Deep Residual Learning Framework with Grad-CAM Explainability for Multi-Class Dermatological Image Classification," in 2026 Sixth International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies (ICAECT), IEEE, pp. 511–518, Jan. 2026.
5. J. Author, "Skincare Recommendation System based on User's Skin Characteristics Similarity using Collaborative Filtering Approach," ResearchGate Technical Report, pp. 12–19, 2025.
6. M. Abid, S. Najam, and S. Tabassum, "Skin Care Products Recommendation System Using ContentBased Filtering and Machine Learning," International Journal of Information Technology and Computer Engineering (IJITCE), vol. 13, no. 4, pp. 89–96, Dec. 2025.
7. S. Parde, "Personalized Skincare Recommendation System Based on Ontology, Ingredient Mapping, and User Preferences," Journal of Semantic Computing and Biotechnology, vol. 29, no. 1, pp. 203–211, Aug. 2025.
8. P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, 2001, pp. 511–518.
9. A. Sharma and R. Verma, "Design and Development of an Edge-Optimized Image Platform for Remote Cosmetic Intelligence," IEEE Transactions on Human-Machine Systems, vol. 31, no. 2, pp. 114–122, Jan. 2023.
10. B. Shinde, V. K. Patil, and A. S. Joshi, "Web Telemetry and Cloud Infrastructure Optimization for LowLatency Diagnostic Dashboards," International Research Journal of Engineering and Technology (IRJET), vol. 11, no. 8, pp. 604–609, Aug. 2024.