• Ramesh B E
• Shurthi M K
• Khazi Mujtaba Abdul Kabeer
• Chinmayee U
• Dhanush H

Abstract—Choosing a cosmetic product without knowing the actual condition of one's skin is a common problem, and most people end up buying on advertisement or on a friend's word. In this work we present a system that looks at a face photograph, finds the visible skin problems, and then suggests suitable cosmetics. The detection part is built on YOLO (You Only Look Once), a single-stage deep learning object detector that localises acne, dark spots and wrinkles in one forward pass. The detected issues are passed to a recommendation layer that maps them to products stored in a cosmetic product database, and the result is shown to the user through a simple interface. The paper explains the layered system architecture, the data flow design from Level 0 to Level 1, the role of the two data stores, and the way the detector output is converted into product suggestions. The design is modular, so that the detector, the database and the interface can be improved separately. The proposed system is meant to give quick, low-cost and non-clinical guidance to a user who has only a camera or a smartphone.

skin classification, skin problem detection, YOLO, deep learning, cosmetic recommendation, data flow diagram, computer vision

"AI-Based Skin Condition Detection and Personalized Cosmetic Recommendation Using the YOLO Deep Learning Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 10, page no.b423-b426, October-2026, Available :http://www.jetir.org/papers/JETIR2610143.pdf

"AI-Based Skin Condition Detection and Personalized Cosmetic Recommendation Using the YOLO Deep Learning Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 10, page no. ppb423-b426, October-2026, Available at : http://www.jetir.org/papers/JETIR2610143.pdf