Chernoff Faces Classification Algorithms

摘要：

The novel classifier is proposed based on the fusion of subjective and objective classification ideas. The novel nearest Chernoff faces classifier is proposed based on the idea of the Chernoff faces and the nearest mean classifler. The nearest mean classifier is a typical template matching method, in which the mean is the representative point, and the Euclidean distance is the discriminant function. Moreover,The Chernoff faces auto classifier is proposed using the Adaptive NeuroFuzzy Inference Systems (ANFIS) and using the proposed graph feature, to improve the subjective classified shortcomings of Chernoff faces. The results of experiments of three UCI data sets and vegetable oil data show our methods are superior to the Chernoff faces classifier and nearest mean classifier.

作者: Jinjia Wang Xin Li Wenxue Hong

作者单位: Yanshan University Qinhuangdao, Hebei Province, China,006004

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）