基于波谱的目标识别模型  

作　　者：任德昊[1] 

机构地区：[1]成都信息工程学院通信工程系,四川成都610225

出　　处：《科技信息》2010年第15期48-50,共3页Science & Technology Information

摘　　要：目标识别是很多研究人员追逐的一个研究热点,主要是因为目标识别应用于很多领域。本文介绍了一种基于波谱表示的目标识别模型。本文有三个方面的贡献:第一是建立基于波谱表示的目标识别集成模型;第二是设计了基于波谱表示的目标识别集成模型的算法;第三是从UCI数据库中选取真实数据,并把算法应用到这些真实数据上进行实验,实验结果表明,在目标识别方面,本算法比SVM好。Object recognition is a research hot pot which is pursued by many researchers. And it is applied in a lot of fields. This paper introduces a novel object recognition model based on spectral coefficient. There are three contributions of this paper. First, we design the object recognition model based on spectral coefficient; Second, we design the spectral algorithm based on the model; Third, we choose some real datasets from UCI for experiments. And the results show that spectral algorithm is better than SVM in object recognition.

关 键 词：目标识别 波谱算法 SVM 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]