DeepErythema: A Study on the Consistent Evaluation Method of UV SPF Index Through Deep Learning

Abstract

This study presents a deep learning-based approach for consistent Sun Protection Factor (SPF) grading by quantifying skin erythema. Despite strict international standards, the current human-based Minimum Erythema Dose (MED) determination method for SPF evaluation suffers from inconsistency due to subjective criteria and the visual characteristics of erythema’s large variance. We propose DeepErythema, a novel method that uses erythema quantification for MED determination. The proposed method comprises pre-processing methods, a deep learning segmentation model, and post-processing methods. The pre-processing methods include the UV irradiation area pointing, which accurately detects the inspection area as a UV-irradiated port. Additionally, the Median Gradation Reduction eliminates the gradation that arises due to the digital image collection environment. The deep learning segmentation model parts introduce a methodology for improving performance using various feature extractors and methodologies such as SeLu, Reverse Attention Gate, and MixedLoss. For post-processing, Perspective Transform Rectangle Restoration restores a distorted inspection area, and Relative Density Evaluation calculates a density score to consider skin characteristics and tone. We verified that utilizing the DeepErythema score in the UV SPF MED Evaluation (USME) dataset reduced the distribution of human-based MED decisions from 36 to 9 in the experimental results. This reduction in MED decision scope leads to improved consistency in SPF Index grading. Overall, the study contributes to the development of an objective and consistent evaluation method for SPF grading.

Keywords

• Computer vision
• deep learning
• semantic segmentation
• UV SPF index