Paper Title
Skin Disease Classification: A Comparative Study of Machine Learning and CNN Approaches

Abstract
Skin diseases are becoming increasingly common in today's world, and early detection and diagnosis are crucial to prevent the spread and severity of these diseases. Machine learning and Deep Learning techniques have been widely used in skin disease detection and classification. This research paper presents a comparative analysis of different machine learning and deep learning techniques used for skin disease detection and classification. The paper reviews different research papers and compares their methodologies, datasets, and results. The techniques compared in this paper are DCT, DWT, SVD, CNN, SVM, SURF, K-Means, Fuzzy C-Means, and Bag-of-features. The datasets used in these research papers consist of various skin diseases such as warts, tinea corporis, acne, vitiligo, nail psoriasis, eczema, melanoma, psoriasis, heat rash, seborrheic keratosis, actinic keratosis, rosacea, lupus erythematosus, basal cell carcinoma, and squamous cell carcinoma. The results of these techniques range from 72% to 100% accuracy rates. Keywords - Dermatology, Skin disease, Physical health, Convolutional Neural Network, Melanoma, Psoriasis, Classification