Abstract
Vitiligo is one of the most common skin diseases in the world. According to the World Health Organization (WHO), the number of people suffering from vitiligo is growing year by year and vitiligo becomes a worldwide problem. In order to helping doctors with vitiligo diagnosis, we propose a vitiligo artificial intelligence diagnosis system. It is able to generate vitiligo images in Wood Lamp with high resolution and classify these images with high precision. In our system, we employ Cycle-Consistent Adversarial Networks (Cycle GAN) to generate images in Wood Lamp. What’s more, we use an advanced super resolution method, Attention-Aware DenseNet with Residual Deconvolution (ADRD), to improve the resolution of images. Finally, we obtain fantastic classification results with Resnet50. Our system is found to achieve the classification performance of 85.69% accuracy, which is increased by 9.32% compared with using Resnet50 to classify original images directly. The optimization and expansion of the system depend on the increase of data set and the improvement of system’s modules.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Ambient Intelligence and Humanized Computing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
