Multi-Class Skin Disease Image Dataset with Severity Levels

Description

This dataset consists of labeled skin disease images designed for multi-class medical image classification tasks using machine learning and deep learning models. The dataset includes images of Acne and Eczema categorized into three severity levels (Mild, Moderate, and Severe), along with Normal skin images and an additional Xyz class representing miscellaneous. The primary objective of this dataset is to support research in automated skin disease classification, severity assessment, and computer-aided dermatological diagnosis. It can be used for training, validation, and evaluation of convolutional neural networks (CNNs) and transfer learning models. All images are organized into class-wise directories, making the dataset compatible with standard deep learning frameworks such as PyTorch and TensorFlow. This dataset is intended strictly for academic and research purposes and does not replace professional medical diagnosis.

Institutions

• Bahria University

  Islamabad, Islamabad

Categories

Licence