基于数据生成增强与多特征融合的微表情识别方法及系统

By using data generation enhancement and multi-feature fusion methods, the motion amplification coefficient and feature fusion are dynamically adjusted, which solves the problems of insufficient data and individual differences in micro-expression recognition, and improves the recognition accuracy and robustness.

CN121214515BActive Publication Date: 2026-07-17XI AN JIAOTONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XI AN JIAOTONG UNIV
Filing Date
2025-09-11
Publication Date
2026-07-17

Smart Images

  • Figure CN121214515B_ABST
    Figure CN121214515B_ABST
Patent Text Reader

Abstract

本发明提供基于数据生成增强与多特征融合的微表情识别方法及系统，包括：获取包括包含起始帧和数据集中标注峰值帧的待识别的微表情视频；以标注的峰值帧为中心，提取一包含多个连续帧的伪峰值帧序列；针对伪峰值帧序列中的每一伪峰值帧，与起始帧构成一个图像对，并提取该伪峰值帧的融合特征；对所有伪峰值帧得到的融合特征所构成的序列进行加权融合，得到平滑特征；将平滑特征输入至一个预先训练好的分类器中，输出所述微表情视频的类别作为识别结果。本发明提出的方法最终能够显著提高识别准确率，在多个公开微表情数据集上的识别性能优于现有先进方法，展现了其在实际应用中的巨大潜力。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Micro-expression recognition method based on feature fusion and structure re-parameterization

    CN117456580A

  • Micro-expression recognition method based on facial pose constraint

    CN118736642A