Multi-Feature Facial Complexion Classification Algorithms Based on CNN

Variations in facial complexion serve as a telltale sign of the underlying health conditions. Precisely categorizing facial complexions poses a significant challenge due to the subtle distinctions in facial features. Three multi-feature facial complexion classification algorithms leveraging convolutional neural networks (CNN) are proposed. They fuses, splices, or independently trains the features extracted from distinctly facial regions of interest (ROI)，respectively. Innovative frameworks of the three algorithms can more effectively exploit facial features, improving the utilization rate of feature information and classification performance. The comprehensive evaluation reveals that multi-feature fusion and splicing classification algorithm achieve accuracies of 95.98% and 93.76%, respectively. The optimal approach combining multi-feature CNN with machine learning algorithms attains remarkable accuracy of 98.89%. Additionally, these experiments proved that multidomain combination was curial, and arrangement of ROI features including nose, forehead, philtrum, right and left cheek was the preferential choice for classification. Furthermore, we employed the EfficientNet model for training on the face image as a whole, which achieve a classification accuracy of 89.37%. The difference in accuracy underscores the superiority and efficacy of multi-feature classification algorithms. The employment of multi-feature fusion algorithms in facial complexion classification holds substantial advantages, ushering in fresh research directions in the field of facial complexion classification and deep learning.