Detection of Hair Fall and Scalp Disorders Through Machine Learning and Image Processing

This study explores the use of deep learning, specifically a two-dimensional Convolutional Neural Network (CNN), to detect scalp conditions like alopecia, psoriasis, and folliculitis from images. Despite challenges such as limited literature, a small dataset of 150 images, and varying image quality, the CNN achieved a training accuracy of 96.2% and a validation accuracy of 91.1%. The research highlights the potential of AI in early diagnosis of hair and scalp disorders and introduces a new scalp scan dataset to aid future studies in developing AI-driven diagnostic tools.