摘要
基于OpenCV的人脸识别算法,具体为局部二值模式直方图(LBPH),特征脸(Eigenface)以及Fisherface算法。介绍了各个算法的核心思想、具体实现步骤、应用场景以及优缺点,并在Open CV平台上采用Python语言对三种算法进行仿真调试。实验结果显示,LBPH、Eigenface、Fisherface三种算法的正确率分别可达98.56%、81.16%和89.13%。
Face recognition algorithm based on OpenCV,specifically Local Binary Pattern Histogram(LBPH),Eigenface and Fisher⁃face algorithms.The core ideas,specific implementation steps,application scenarios,advantages and disadvantages of each algo⁃rithm are introduced,and three algorithms are simulated and debugged on the OpenCV platform using Python.The experimental re⁃sults show that the correct rates of the three algorithms,LBPH,Eigenface,and Fisherface,can reach 98.56%,81.16%,and 89.13%respectively.
作者
冯婧
顾梅花
FENG Jing;GU Mei-hua(School of Electronics and Information,Xi'an Polytechnic University,Xi’an,710048,China)
出处
《电脑知识与技术》
2020年第14期3-5,共3页
Computer Knowledge and Technology
基金
西安工程大学“大学生创新创业训练计划”项目,省级(编号:S201910709017)。
