Smart Skin Health Detection: Psoriasis and Aging Analysis Using AI/ML

The Smart Skin Health Detection system successfully demonstrates the use of Artificial Intelligence and Machine Learning for healthcare and dermatology applications. The proposed system provides automated psoriasis detection and aging analysis using image processing and CNN-based prediction models.  The Streamlit application offers a simple and interactive platform for users to monitor skin health and receive skincare guidance. The system supports early disease detection, awareness, and preventive healthcare. Future enhancements may include live camera integration, multilingual support, cloud-based report generation, mobile applications, and detection of additional skin diseases such as eczema, acne, fungal infections, and skin cancer. Advanced deep learning architectures can also be integrated to improve prediction accuracy and real-time performance.

1.     A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115– 118, 2017. 2.     K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. IEEE CVPR, 2016. 3.     N. Codella et al., “Skin Lesion Analysis toward Melanoma Detection,” IEEE Journal of Biomedical and Health Informatics, 2018. 4.     I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. 5.     TensorFlow           Documentation,           Available: https://www.tensorflow.org 6.     OpenCV             Documentation,              Available: https://docs.opencv.org 7.     ISIC Archive Dataset, Available: https://www.isic- archive.com 8.     UTKFace                   Dataset,                   Available: https://www.kaggle.com 9.     PyTorch             Documentation,              Available: https://pytorch.org 10.  M. H. Yap et al., “Machine Learning Techniques for Skin Aging Analysis,” IEEE Transactions on Image Processing.