SkinProfiler: Low-Cost 3D Scanner for Skin Health Monitoring with Mobile Devices
Name
3539494.3542757.pdf
Size
1.68 MB
Format
Adobe PDF
Checksum (MD5)
9a52a1c01bce27406b1c3216ed5def9c
Author(s)
Li, Zhiying
Viswanath, Tejas
Yan, Zihan
Zhang, Yang
Date Issued
June 27, 2022
Publisher
Association for Computing Machinery
Citation
Zhiying Li, Tejas Viswanath, Zihan Yan, and Yang Zhang. 2022. SkinProfiler: low-cost 3D scanner for skin health monitoring with mobile devices. In Proceedings of the 2022 Workshop on Emerging Devices for Digital Biomarkers (DigiBiom '22). Association for Computing Machinery, New York, NY, USA, 1–6.
Version
Final published version
Abstract
Melanoma is one of the top three most common skin cancers, originating from skin lesions and moles. Keeping track of skin lesion and mole developments in a precise and long-term manner has long been recommended but overlooked for the lack of accurate and easy-to-access tools. In response, we develop SkinProfiler, a low-cost mobile profiling tool for long-term skin health monitoring. To use SkinProfiler, users clamp an LED ring accessory onto smartphone cameras and take photos of the skin region of interest using the SkinProfiler app. Our modified photometric stereo algorithm leverages 17 photos taken with the skin surface lightened under various conditions to reconstruct 3D models of the skin surfaces. Our system stores 3D information for skin lesion and mole monitoring and diagnosis. The total cost of hardware assembly is under 20 dollars. We ran a preliminary evaluation to verify the performance of our tool. Based on the results, we propose several future steps including evaluations in clinical settings to complete this research.
Description
DigiBiom’22, July 1, 2022, Portland, OR, USA
Terms of Use
Creative Commons Attribution-NonCommercial
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3539494.3542757
