Relief算法在关门车故障自动识别中的应用  

Application of Relief algorithm to valve closing trouble automatic recognition

作　　者：赖冰凌[1] 王新宇[2] 

机构地区：[1]哈尔滨铁路局哈尔滨科研所,哈尔滨150009 [2]北京交通大学交通运输学院,北京100044

出　　处：《铁路计算机应用》2007年第1期21-23,共3页Railway Computer Application

摘　　要：针对货车运行故障动态图像检测(TFDS)系统中的图像识别问题,提出一种基于Relief算法的解决方案。该方案采用梯度—共生矩阵的数字特征来描述一幅图像,然后通过Relief算法进行有效的特征选择,根据这些特征,通过模板匹配技术,最终检测出关门车故障。现场运用表明,该方案具有很高的实用性。A new method based on relief algorithm was proposed to solve image recognition problem in Trouble Frightcar of Moving Detection System （TFDS）. A single image was described by numerical characteristics of matrix. Relief algorithm was used to evaluate the importance of every characteristics. Template matching was used in image recognition in TFDS.Experimental results showed that this method was efficient and applied.

关 键 词：共生矩阵 RELIEF算法 模板匹配 图像识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]