Face detection and recognition is challenging due to the wide variety of faces and the complexity of noises and image backgrounds. In this paper an Internet of Things (IoT) based face detection system using Raspberry Pi is proposed. In this system face is detected in a live video and the system tries to extract features for face recognition. This system also secures offices/homes from theft by instantly detecting theft as well as allowing user to view the theft details. The camera is used to detect the motion and the proposed system uses video processing techniques to detect and recognize the face on the fly. The system now transmits the face details over IoT to be viewed by user online in his phone or tablet anywhere. This is a system which detects the human face and recognizes whether he is a known or unknown person. Mobile devices including smart phones or tablets could connect to the smart E-view where they will be notified about the person who is outdoor. This information can be accessed anywhere with Wi-Fi or Internet. He will also be notified the time when the person has come home. The proposed work can be useful to to the blind, deaf or even disabled people as the system includes voice recognition to help and guide them.
[1]
Yanyan Huang,et al.
Real-Time Face Detection and Recognition for Video Surveillance Applications
,
2009,
2009 WRI World Congress on Computer Science and Information Engineering.
[2]
Zeeshan Ahmed,et al.
Image-based Face Detection and Recognition: "State of the Art"
,
2013,
ArXiv.
[3]
S. T. Gandhe,et al.
Identification and Tracking of Facial Features
,
2015
.
[4]
A. Agrawal.
A Review on Feature Extraction Techniques and General Approach for Face Recognition
,
2016
.
[5]
C.Swetha,et al.
Effective Automatic Attendance Marking System Using Face Recognition With RFID
,
2016
.
[6]
Shruthi Nagendra,et al.
Video-Based Face Recognition and Face-Tracking using Sparse Representation Based Categorization☆
,
2015
.
[7]
Shrutika Shukla,et al.
Review of Face Recognition Technology Using Feature Fusion Vector
,
2016
.
[8]
Roshan Fernandes,et al.
A New Approach to Predict user Mobility Using Semantic Analysis and Machine Learning
,
2017,
Journal of Medical Systems.