远程教育物理虚拟图像有效提取仿真研究  

Simulation Research on Effective Extraction of Physical Virtual Image in Distance Education

作　　者：陈邦泽[1] 杨晓波[2] CHEN Bang - ze ANG Xiao - bo(Department of Education, Xizang Minzu University, Xianyang Shanxi 712082, China Department of Information Engineering, Xizang Minzu University, Xianyang Shanxi 712082, China)

机构地区：[1]西藏民族大学教育学院,陕西咸阳712082 [2]西藏民族大学信息工程学院,陕西咸阳712082

出　　处：《计算机仿真》2017年第4期204-207,共4页Computer Simulation

基　　金：全国教育科学规划项目(FCB150516);国家社科基金项目(16BMZ059)

摘　　要：对远程教育中的物理虚拟图像进行有效提取,可以更好提升远程教育的质量。对虚拟图像的有效提取,需要先获取虚拟图像特征的最优分类阈值,归一化处理全部的图像训练样本,完成对虚拟图像的有效提取。传统方法先将获得的二值化图像轮廓变换到固定的解析度,构成图像训练样本,但忽略了对其进行归一化处理,导致图像提取精度低。提出基于特征包支持向量机的虚拟实验室中的远程教育物理虚拟图像提取方法。利用SIFI方法得到图像的局部不变特征点,计算出其特征点的误差平方和准则函数,获取其最优分类阈值,归一化全部的训练样本,融合于Kinect传感器获取手心的位置坐标,计算出需要提取的虚拟图像的估计概率,以此为依据完成对虚拟实验室中的远程教育物理虚拟图像提取。实验结果表明,所提方法提取精度较高,可以为构建基于网络的虚拟实验室系统提供科学的依据。This artiele propose an extraction method for physical virtual image of distance education in virtual laboratory based on support vector machine. Firstly, the point of loeal invariant feature is obtained by using SIFI method, then its criterion function of sum of squared error is worked out in order to acquire optimal threshold of classification. All training samples are normalized to acquire position eoordinates of palm integrated with Kineet sensor and estimated probability of virtual image is worked out. Finally, the extraction of virtual image is eompleted based on that. Experimental results show that the method has high extraction precision. It can provide seientifie basis for establishing system of virtual laboratory based on network.

关 键 词：远程教育 物理虚拟图像 有效提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]