• Adrija Chattopadhyay
• Debangshi Palit
• Dev Jyoti Chakraborty
• Shreyashi Paul
• Soumya Subhra Ghosh

This paper proposes a deep learning approach to computerized diagnosis of 19 skin conditions through a convolutional neural network (CNN). The research is aimed at fulfilling the urgent need for precise diagnosis systems under a situation of scarce dermatologists. The model is trained on a dataset of clinical images through data preprocessing and augmentation to maximize performance. The CNN model consists of several convolutional layers, and the model achieved satisfactory accuracy up to 96%. Several metrics like precision, recall, and F1-score were used in the performance evaluation of the model extensively. The outcomes show the capability of CNNs in clinical diagnosis, revealing the possibility that the solution can enable early detection and better treatment planning. The future work will focus on the extension of the dataset significantly and integrating the model with real-time diagnosis systems.

CNN, Skin Disease Detection, Augmentation, Computer Vision, Image processing, Deep Learning

"Automated Detection of 19 Skin Diseases Using Convolutional Neural Network Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 2, page no.g381-g385, February-2025, Available :http://www.jetir.org/papers/JETIR2502640.pdf

"Automated Detection of 19 Skin Diseases Using Convolutional Neural Network Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 2, page no. ppg381-g385, February-2025, Available at : http://www.jetir.org/papers/JETIR2502640.pdf