Facial Beauty Prediction Combining Dual-Branch Feature Fusion With a Stacked Broad Learning System

Facial beauty prediction (FBP) is a key computer vision task that uses algorithms to assess facial attractiveness. Current models rely on single feature extraction, such as using a single convolutional neural network to extract local feature, failing to capture other potentially more important information contained within facial data and limiting feature diversity. Dual-branch feature fusion complements key features from multiple models, reducing reliance on single features. A stacked broad learning system (BLS) increases network depth with residual connections, addressing the feature insensitivity of traditional BLS. Therefore, this paper combines dual-branch feature fusion with a stacked BLS for FBP. First, facial features are extracted by the ConvNeXtBase and MobileNetV3Large models through transfer learning. Second, a squeeze-and-excitation (SE) network attention-based connection layer dynamically adjusts feature weights, emphasizing important features and reducing irrelevant ones. Then, facial features are input into the BLS network, and the outputs are horizontally concatenated to form fused features. Finally, the fused features are reinput into the BLS to obtain the final FBP result. This model is referred to as DB-BLS (dual branch broad learning system). Building upon DB-BLS, this paper introduces a stacked BLS module to replace the BLS module. Stacked BLS enhancing the network’s ability to perceive features at different levels. This model is named SDB-BLS (stacked dual branch broad learning system). Experiments show that DB-BLS and SDB-BLS outperform traditional methods, respectively achieving accuracies of 76.86% and 78.78% on the SCUT-FBP5500 dataset, with potential applications in image classification and object detection.