CAJ | 학술논문

为提高痛苦表情识别的准确率，提出一种基于监督保局投影(SLPP)与多核线性混合支持向量机(MKLMSVM)的识别方法。引入先验类标签信息的 SLPP 获取痛苦表情特征，以解决保局投影方法在未使用先验类标签信息的情况下忽略类内局部结构的问题，并采用MKLMSVM实现痛苦表情的分类。实验结果表明，该方法的识别准确率可达88.56%，明显优于主动外观模型方法，与一般的支持向量机分类相比，可以提升决策函数的可解释性及分类性能。
위제고통고표정식별적준학솔，제출일충기우감독보국투영(SLPP)여다핵선성혼합지지향량궤(MKLMSVM)적식별방법。인입선험류표첨신식적 SLPP 획취통고표정특정，이해결보국투영방법재미사용선험류표첨신식적정황하홀략류내국부결구적문제，병채용MKLMSVM실현통고표정적분류。실험결과표명，해방법적식별준학솔가체88.56%，명현우우주동외관모형방법，여일반적지지향량궤분류상비，가이제승결책함수적가해석성급분류성능。
In order to improve the accuracy rate of pain expression recognition, a method is proposed based on Supervised Locality Preserving Projections(SLPP) and Multiple Kernel Linear Mixture Support Vector Machines(MKLMSVM). The SLPP using prior class label information is adopted for extracting feature of pain expression, which can solve the problem that LPP ignores the within-class local structure without the use of the prior class label information, and then MKLMSVM is employed for recognizing pain expression. Experimental results demonstrate that the accuracy of the proposed approach can reach 88.56%, and is significantly better than the Active Appearance Models(AAM), compared with normal Support Vector Machine(SVM), which can improve the interpretability of decision function and classifier performance.