基于图像处理的井下人员身份识别  

Identification of Underground Personnel Based on Image Processing

作　　者：杨米娜 YANG Mi-na(Shanxi Architectural College,Jinzhong 030619,China)

机构地区：[1]山西建筑职业技术学院,山西晋中030619

出　　处：《煤炭技术》2018年第9期339-342,共4页Coal Technology

摘　　要：针对当前井下人员身份识别方法存在的误识率高、效率低等不足,设计了基于图像处理的井下人员身份识别方法。首先采集井下人员的图像,并对图像进行预处理,提取人员轮廓,然后从图像中提取井下人员身份识别的多种特征,对特征进行去冗余处理,最后采用支持向量机建立井下人员身份识别的分类器,并与其他井下人员身份识别方法进行了对比测试。结果表明,这种方法提高了井下人员身份识别的准确性,误识率不仅远远小于其他井下人员身份识别方法,而且井下人员身份识别效率更优,具有更高的实际应用价值。In view of the shortcomings of the high error rate and low efficiency in the current underground personnel identification method, the identification method of underground personnel based on image processing is designed. First of all, the image of downhole personnel is collected, and image is preprocessed and the contour is extracted; then the characteristics of the underground personnel identification are extracted from the image, and the features are degenerated; finally, the support vector machine is used to establish the classifier for the identification of the downhole personnel. The method of identity identification was tested. The results show that this method improves the accuracy of identification of underground personnel, and the error rate is far less than the identification method of other downhole personnel, and the identification efficiency of underground personnel is better and has higher practical application value.

关 键 词：井下人员 身份识别 特征向量 误识率 图像去噪 支持向量机 

分 类 号：TD391.41[矿业工程—矿井建设] TD76