Optimized VGG19 Architecture for Precise and Efficient Multi-Class Hair Disease Classification

The study developed an optimized VGG19 deep learning model for classifying hair diseases, achieving a high classification accuracy of 98.64% using a balanced dataset of 12,000 images across 10 hair disease classes. The model effectively distinguishes conditions like Alopecia Areata, Folliculitis, and Male Pattern Baldness, with high precision, recall, and F1-scores. Key strategies included data pre-processing, strategic dataset splitting, and the use of callbacks to optimize learning rates and model performance. This robust model minimizes overfitting and represents a significant advancement in hair disease diagnosis, with potential for integration into mobile diagnostics for clinical and remote use. Future work may enhance robustness by incorporating diverse datasets and advanced architectures.