计算机工程与应用2019，Vol.55Issue(11)：142-146,243,6.DOI:10.3778/j.issn.1002-8331.1803-0012
改进KNN算法对人体身份的识别
Human Identity Recognition Using Improved KNN Method
连天友 1余勤1
作者信息
- 1. 四川大学 电气信息学院,成都 610065
- 折叠
摘要
Abstract
In order to understand the features learning process, reduce storage of data and improve recognition accuracy, an improved KNN method is proposed for human identification based on Kinect v2’s facial data and skeletal data. First of all, 3-D position information of facial feature points and skeletal joints is extracted by Kinect v2 and then the characteris-tic information of strong understanding like eye width and arm length can be calculated. It is proposed that an improved truncated mean method can restrain singular values by sorting data and intercepting the intermediate data, and an im-proved KNN method based on the accuracy of matching recognition is applied to predict human identity. Experimental re-sults show that the proposed clustering method has higher accuracy of matching recognition and the improved classifica-tion method improves the accuracy of recognition.关键词
人体身份识别/脸部数据/骨骼数据/排序截断均值法/匹配识别准确度Key words
human identity recognition/facial data/skeletal data/sort truncated mean method/accuracy of matching recognition分类
信息技术与安全科学引用本文复制引用
连天友,余勤..改进KNN算法对人体身份的识别[J].计算机工程与应用,2019,55(11):142-146,243,6.
