Skin diseases are illnesses that affect the skin, which is the largest organ in the body. Determining the correct skin disease takes a long time when a large dataset of hospital record patients with skin samples is provided. In this paper, we use anomaly detection followed by deep learning classification models to classify the correct skin disease type. The anomaly detection module detects variations in our skin samples, which is essential for assisting our deep learning classification models in processing the skin samples. Following the identification of the variants, we employ multiclassification models to ascertain the patient’s type of skin condition and the most appropriate course of action. In our research, we are using multi-class models like VGG19, Inceptionv3, and Resnet50 to determine the correct skin disease. We assess which skin disease is accurate based on the precision and recall metrics of each model. Our results show that the Inception-V3 model outperforms other models with an accuracy of 95% ....