Holistic Approach to Facial Acne Classification: CNN-SVM Integration

The purpose of this research work is to present and access a comprehensive analysis of an advanced facial acne classification method that is focused on machine learning. Hormonal acne, pustules, papules, cysts, blackheads (open comedones), and whiteheads (closed comedones) were all included in the dataset that was used to train and evaluate the algorithm. Accuracy, recall, and F1-Score provide evidence that the model correctly recognizes a variety of acne types, with scores ranging from 93.98% to 95.86%. Other evaluation metrics also suggest that the model displays this accuracy and efficiency. As an additional point of interest, the support percentage demonstrates how samples are spread within each acne class, hence demonstrating the balanced distribution of classes within the dataset. The model demonstrated that it was very accurate, obtaining a total score of 98% for its performance. The usefulness and reliability of this product in real-world circumstances is shown by this situation and quality of life. In addition, aggregate performance metrics such as micro, weighted, and macro averages provide further evidence that the algorithm is capable of providing a diagnosis of acne that is both accurate and trustworthy across all types of acne. The research contributes to the development of automated systems for detecting acne on the face, and dermatologists may find it beneficial to utilize the data acquired to improve their ability to diagnose and treat patients who suffer from facial acne and health issues.