Applicability of Complementary Colors in Skin Tone Correction for Young Chinese Adults Based on Image Processing and Machine Learning

ABSTRACT Background and Objective Skin tone correction is an essential focus within dermatology and cosmetology, particularly in achieving a balanced and even facial appearance. The application of complementary color theory in skin tone correction remains predominantly subjective, relying on individual user experiences rather than systematic and quantitative assessments. This study aims to evaluate the applicability of complementary color theory among young Chinese individuals and develop predictive models for personalized skin tone correction. Methods Sixteen young Chinese female participants aged 20–25 were recruited. Standardized facial images were captured using the VISIA‐CR system under standardized lighting conditions, both before and after the application of six color‐correcting primers (orange, pink, blue, white, purple, and green). Four facial regions of interest (ROIs), defined as the forehead, under‐eye circles, cheeks, and near‐nose, were analyzed. Five colorimetric indices ( L *, a *, b *, ITA°, and Hab°) were quantified across each ROI. State‐of‐the‐art machine learning regression models were developed to predict post‐application ITA° and Hab° values based on pre‐application skin tone and primer characteristics. Results Under‐eye circles exhibited the darkest and most yellowish‐red skin tone compared to other regions. Complementary color primers demonstrated statistically significant improvements in ITA° and Hab° values across all ROIs. Pink primers were most effective for under‐eye dark circles, while purple, pink, and blue primers resulted in greater improvements in overall skin tone. LightGBM and XGBoost regression models demonstrated superior performance, with R 2 values reaching 0.824 for ITA° and 0.850 for Hab°. Conclusion This study robustly validates the efficacy of complementary color primers in skin tone correction among young Chinese individuals. The integration of machine learning offers a robust framework for personalized cosmetic recommendations, paving the way for innovative and data‐driven advancements in skincare and makeup applications.