论文部分内容阅读
为提高煤矿井下人员身份识别率,在局部保持投影(LPP)算法的基础上,提出监督局部映射(SLP)算法。该方法充分利用数据的局部和非局部信息及类别信息,对数据进行维数约简,使特征空间同类数据间的距离更小,不同类数据间的距离更大。该方法能够克服煤矿井下艰苦、空间受限环境中人脸、虹膜和指纹识别率不高的问题。在真实步态数据库上的实验结果表明,基于步态的煤矿井下人员身份鉴别是可行的。
In order to improve the identification rate of underground coal miners, this paper proposes a supervised local mapping (SLP) algorithm based on LPP algorithm. This method makes full use of the local and non-local information and category information of the data to reduce the dimension of the data so that the distance between similar data in the feature space is smaller and the distance between different types of data is larger. The method can overcome the problem of low recognition rate of human face, iris and fingerprint in the hard and space-constrained coal mine environment. The experimental results on the real gait database show that it is feasible to identify the underground coal mine personnel based on gait.