摘要
将朴素贝叶斯分类器用于人体行为图像识别之中,利用高斯模糊、灰度化处理、二值化处理、直方统计函数等图像处理技术对图像数据进行约简、特征提取,然后使用朴素贝叶斯与半朴素贝叶斯对数据进行测试。利用KTH数据库做了两组对比实验,对朴素贝叶斯分类器和半朴素贝叶斯分类器的性能做了比较。实验结果表明,半朴素贝叶斯分类器比朴素贝叶斯分类器分类能力强,但与此同时,半朴素贝叶斯分类器计算所花费的时间比朴素贝叶斯分类器更多。
The Naive Bayes classifier is used in human behavior image recognition,and image processing techniques such as Gaussian blur,grayscale processing,binarization and histogram function are used to reduce and extract image data features.And then Naive Bayes classifier and SemiNaive Bayesian classifier are used to test the data.Based on the KTH database,two groups of comparative experiments were performed,and the performance of the Naive Bayes classifier and the SemiNaive Bayes classifier were statistically analyzed.The experimental results show that the SemiNaive Bayesian classifier has stronger classification ability than the Naive Bayes classifier,but at the same time,the SemiNaive Bayesian classifier takes more time than the Naive Bayes classifier in calculation.
作者
刘闯
Liu Chuang(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China)
出处
《信息技术与网络安全》
2018年第12期44-47,共4页
Information Technology and Network Security
