Hair and Scalp Disease Detection Using Machine Learning and Image Processing

This study used a deep learning approach to predict three main types of hair loss and scalp-related diseases: alopecia, psoriasis, and folliculitis. The researchers faced challenges due to limited previous studies, lack of a proper dataset, and variety among images available online. They collected 150 images from various sources and preprocessed them by denoising, image equalization, enhancement, and data balancing to minimize the error rate. These processed images were then fed into a 2D convolutional neural network (CNN) model. The model achieved an overall training accuracy of 96.2% and a validation accuracy of 91.1%. The precision and recall score for alopecia, psoriasis, and folliculitis were 0.895, 0.846, and 1.0, respectively. The researchers also created a dataset of the scalp images for future research.