特征集和分类器融合技术在表情识别中的应用

Facial Expression Recognition Based on Feature Sets and Classifiers

提出了一种新的人脸表情识别技术,即采用两个不同的特征集相结合的集成方法。首先,使用Gabor滤波器和局部二进制模式建立支持向量机分类器池,然后使用多目标遗传算法搜索最佳的集合作为目标函数,最佳集合确保了低错误率和集合规模的最小化。分别在JAFFE和Cohn-Kanade两个人脸库上设计实验。研究结果表明:本文所提出的方法比使用单一的特征集和单分类器的传统方法提高了5%和10%的识别率。

This paper presents a novel method for facial expression recognition that employs the combination of two different feature sets in an ensemble approach. A pool of base support vector machine classifiers was created using Gabor filters and local binary patterns. Then a multi-objective genetic algorithm was used to search for the best ensemble used as objective function,insuring the minimization of both the error rate and the size of the ensemble. Experimental results on JAFFE and Cohn-kanade databases show that the proposed strategy,improves the recognition rates by 5% and 10% than conventional approaches using single feature sets and single classifiers.