Multi-Class Support Vector Machine Classification for Detecting Alopecia Areata and Scalp Diseases

The study presents a novel method for detecting and classifying alopecia areata and other scalp diseases using a multiclass support vector machine (SVM) classification approach. By capturing and preprocessing images of individuals with alopecia, the method extracts distinctive features from scalp images and feeds them into a Multi-class SVM classifier. The machine learning model trained with this approach achieves an accuracy of 89.3% in classifying various conditions associated with alopecia areata, outperforming other models in terms of classification accuracy. This method aims to improve the timely identification and precise diagnosis of alopecia areata, which affects about 2% of the global population.