Recognition of Clinical Skin Disease Images

SD-198 is an image dataset for automatic recognition and diagnosis of skin diseases. It contains 198 skin diseases and 6,584 clinical images, which are collected by digital cameras and mobile phones. The images are various in color, exposure, illumination and scale. Moreover, images in our dataset cover a lot of situations for patients such as age (child, adult, old), sex, disease site (hand, feet, head, nails), color of skin(white, yellow, brown, black) and different periods of lesions(early, middle, late). We also choose the classes with more than 20 image samples as a subset, namely SD-128, which contains 5,619 images.



The Readme file explains everything. For more information about our work and dataset, please drop us an email (


Datasets Presentation



X. Sun, J.Yang, M Sun, K Wang.

A benchmark for automatic visual calssification of clinical skin disease images.

European Conference on Computer Vision(ECCV), 2016

Document: PDF