Skin Disease Classification using VGG-16 model optimized ADAM, GD, RMSprop and YOLOv8

Skin disease classification is a hard task in medical health, leveraging the potential of machine learning to get accuracy and efficiency of disease detection. We employ optimizing algorithms such as Gradient Descent(GD), ADAM, and RMSprop leading to improved performance in terms of accuracy of VGG-16 Model, We also made a comparison of our study with YOLOv8 using ADAM optimizer which outperformed the performance with VGG-16. Our preprocessing techniques for these images is to get features extracted, following the implementation of neural networks. We also compare and validate the efficiency of Gradient Descent (GD), Adam, and RMSprop optimizers and update the network values. he optimized trained models have achieved significant improvements in classification techniques, including metrics like accuracy, precision, recall and f1-score. It shows the importance of optimizers in skin disease classification and gives the way for more effective and efficient skin disease detection systems.