计算机科学
人工智能
计算机视觉
树莓皮
定向梯度直方图
局部二进制模式
人脸检测
面部识别系统
直方图
类似哈尔的特征
鉴定(生物学)
面子(社会学概念)
模式识别(心理学)
图像(数学)
计算机安全
社会科学
植物
物联网
生物
社会学
作者
Jyotirmaya Ijaradar,Jǐnjīng Xǔ
标识
DOI:10.9734/cjast/2022/v41i531665
摘要
Home surveillance systems are still challenging, particularly for patrolling or tracking subjects through CCTV images despite recent developments. Therefore, it is crucial to instantly identify human faces based on captured facial images in protection and surveillance. Identification of people, intrusion detection, and follow up access control of objective sites are examples of applications of such systems. This paper represented a cost-efficient real-time facial recognition-based surveillance system for home and small offices using raspberry pi and computer vision. In the application, first, the system tracks the detected individuals' faces in the frame and only focuses on the image content in these facial regions. Then, a powerful algorithm for recognising detected faces is used using a pre-provided face database. For the implementation in this paper, the most common Haar Cascade and Local Binary Pattern Histogram (LBPH) algorithms are used for facial detection and recognition. The system works perfectly in normal lighting conditions with accepted accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI