Providing security to the citizens is one of the most important and complex task for the governments around the world which they have to deal with Street crimes and theft are the biggest threats f

https://journals.sagepub.com/doi/pdf/10.1177/0020294020932344

Facial recognition system using LBPH face recognizer for anti-theft and surveillance application based on drone technology:

Many sophisticated smart door lock systems have been made. Still, most of them required the user to use an additional device such as a smartphone, tag, smartcard, or accessing some user interfaces, which is complicated to use for inexperienced elderly. This condition creates a gap between the elderly and technology which makes it difficult for the elderly to accept and use the technology. In this paper, we proposed a smart and real-time door lock system for an elderly user based on local binary pattern histogram as a face recognition algorithm with modular system architecture design. The novelty in our proposed system design, it does not require any additional device, it does not use any user interface, and the least user participation by automating the processes. All the user needs to do just walk toward the door and stand in front of it and the door will automatically unlock and locked back after the user enters the house and close the door. The system resulted in an accuracy of 98%, with an average processing time is 1.449 seconds for the entire process. Additional advantages, the system is designed with a modular approach that makes it flexible and scalable for further development.

https://beei.org/index.php/EEI/article/download/2955/2178

Smart and real-time door lock system for an elderly user based on face recognition

Online learning has grown exponentially since the Covid-19 outbreak. Educational organizations are forced to stop their regular curriculum. Using remote communication software, students are able to pursue their educational curriculums. This paper proposes a multimedia exam proctoring system based on face recognition and object capturing systems. System hardware includes a webcam only. Dlib is used for facial detection and face landmark detection. The OpenCV Caffe model is then utilised to appropriately locate and sketch the face. YOLOv3 is used to detect objects. Onfocus event is used for tab detection. By combining all these, an exam proctoring system is developed which can classify if the student is found cheating and is then informed to the examiner.

Automated Exam Proctoring using Support Vector Machine and Histogram of Oriented Gradients

In recent years, the number of troublesome people with provocative behaviour has been increased. This necessitates the need to increase the public security. CCTV cameras are gradually being deployed on streets, banks, and other areas to protect people’s safety in public areas like shopping malls. Since it is practically impossible to continuously monitor the security cameras, the crowd monitoring system must be computerized with high accuracy. Moreover, if a criminal is running, it is difficult to detect and track down by only using the capture CCTV image is a time-consuming process. To solve these challenges, the proposed system will scan real-time CCTV surveillance footage and use criminal reference information to identify the criminals. To recognize the uniqueness, it is highly required to precisely automate this activity. It is also necessary to show which frames and sections of the recording contain the unexpected behaviour.

Detection and Tracking the Criminal Activity using Network of CCTV cameras

Facial recognition is widely used for identification of people as one of the biometric authentications. Biometric authentication consists of two types physiological and behavioral features. In physiological biometrics, faces, iris, and fingerprints are used for identifying the person. In behavioral biometrics, their characteristic features namely voice, DNA and hand writing is used. While using facial recognition, an individual can be identified using the previously trained model using deep learning based on the Haar cascade algorithm. Biometric authentication has been generally used for surveillance purposes. However, due to the COVID 19 pandemic, people of each nation are in need to wear face masks for their safety. Our project uses deep learning and open cv to recognize the person and to identify whether he wears a face mask or not by using transfer learning techniques and convolution neural network. One large dataset of people with mask and people without a mask was used as a training model. Our project was able to achieve an accuracy of 96.8% during the training and testing phase.

Deep Learning Based Intelligent Screening Mechanism

The importance of a properly maintained attendance system is very high. Although many systems are already existing, there are many loopholes present. This paper presents an attendance system using face recognition, which is the best foot forward to reduce the loopholes encountered by these systems. The Attendance system using face recognition consists of two phases, face detection and face recognition. The performance of detection algorithms such as Viola Jones and deep learning-based detection was compared and deep learning-based detection was preferred. On the recognition front, deep learning-based face recognition was used and optimum results were obtained. It was found that dlib using Convolutional Neural Networks (CNN) yielded better results than dlib using Histogram Oriented Gradients (HOG) because HOG only detects a frontal image, while CNN detects faces from all angles and ensures no discrepancies during face detection and recognition. Also, it was observed that the speed of training datasets was higher in CNN as it uses GPU as compared to HOG, which uses CPU for training the dataset as well as recognition.

Gauraang Prabhu

Papers

Automation of Attendance System Using Facial Recognition