TLDR The system can automatically identify different hair and scalp conditions using machine learning.
The project aims to develop an automatic and highly accurate machine learning-based recognition technique for the classification of healthy hair and damaged scalp. The system uses a machine learning algorithm to identify and classify various hair diseases, including alopecia areata, contact dermatitis, folliculitis, head lice, lichen planus, male-pattern baldness, psoriasis, seborrheic dermatitis, telogen effluvium, and tinea capitis. The VGG-19 model is used in this study to train and test the prediction of classifying each condition as one of the hair diseases. This system could potentially help in diagnosing hair loss, which results from at least 30% of scalp and hair issues caused by poor daily habits, an unbalanced diet, high stress levels, and environmental toxins.
3 citations
,
November 2022 in “European Journal of Human Genetics” New models predict male pattern baldness better than old ones but still need improvement.
8 citations
,
January 2022 in “Sensors” Deep learning can accurately automate hair density measurement, with YOLOv4 performing best.
133 citations
,
February 2017 in “PLoS Genetics” Genetic factors can help predict male pattern baldness risk.
1 citations
,
May 2025 in “Journal of Digital Information Management” VGG16 and VGG19 are the most accurate for classifying scalp and hair diseases.
October 2023 in “Sinkron” The system can accurately classify hair diseases with 94.5% accuracy using a CNN.
28 citations
,
November 2017 in “Skin appendage disorders” The document concludes that accurate diagnosis and treatment of scalp itch require differentiating between various conditions using a proposed five-step evaluation process.
The document is a detailed guide on skin conditions and treatments for dermatologists.
November 2019 in “Harper's Textbook of Pediatric Dermatology” The document is a detailed medical reference on skin and genetic disorders.
Use the least toxic, most specific treatments for skin diseases, considering side effects and individual patient needs.
