摘要
本文对现有人脸识别技术进行调查分类,首先总结对比了两类技术,第一类为传统的依赖人工设计的特征检测方法,第二类为基于卷积神经网络的最新方法。然后对两类技术做分别综述,总结每一大类的细分子类。经过比较分析,我们对当前人脸识别技术种类有了更深入理解,对后续人脸识别技术研究将更深入。
In this paper,the existing face recognition technology to investigate classification,first analyzed the rely on artificial design characteristics of the traditional detection method with the difference based on convolution neural network recognition method,and then based on the characteristics of the detection of the traditional method of classification comparison,finally to the deep learning method based on convolution neural network classification comparison After comparison,we can on the current face recognition technology types have a deeper understanding,on subsequent facial recognition technology research will be deeper.
作者
黄兴晗
杜小甫
刘沂杰
Huang Xinghan;Du Xiaofu;Liu Yijie(School of Information Science and Technology,Xiamen University Tan Kah Kee College,Zhangzhou Fujian,363105)
出处
《电子测试》
2021年第17期96-97,29,共3页
Electronic Test
基金
厦门大学嘉庚学院大学生创新创业训练计划项目(196)
厦门大学嘉庚学院大学生创新创业训练计划项目(219)
漳州市自然科学基金(ZZ2020J30)
厦门大学嘉庚学院预研项目(YY2019L02)。
关键词
人脸识别
特征检测
卷积神经网络
机器学习
Face recognition
Feature detection
Convolutional neural network
Machine learning
