{"title":"Artificial Attendance System with Two-Way Verification using QR Code Scanning and Face Recognition with Eye Blink Detection","authors":"Ghanbahadur, Gaurav Balu, C.Kalpana","doi":"10.46632/jdaai/2/2/6","DOIUrl":null,"url":null,"abstract":": The usage of biometric technology has grown in popularity recently across several industries, including attendance management systems. Utilising biometric technology has been shown to be a more dependable and secure technique of managing attendance. This study suggests an artificial attendance system that uses face recognition with eye blink detection, QR code scanning, and two-way verification. The objective of this system is to enhance the security, accuracy, and reliability of attendance management in various organisations. The suggested system manages attendance via two-way verification. The system first reads a unique QR code that is produced for each user. Second, the system uses face recognition with eye blink detection to confirm the user's identification. The presence and identity of the user are confirmed by the two-way verification. The system also keeps track of the user's attendance's date, time, and place. Deep learning techniques are the foundation of the facial recognition system employed in this study. The system extracts facial features from the user's face using a convolution neural network (CNN). For precise person recognition, the CNN is trained on a big collection of facial photos. Deep learning algorithms are also the foundation of the eye blink detection system. To recognise eye blinks, the system makes use of a long short-term memory (LSTM) neural network. A dataset of facial photos with labelled eye blink data is used to train the LSTM. The Open CV library and Python programming language were used to create the suggested system. A collection of 1000 facial photos with labelled eye blink data was used to test the system. Eye blink detection accuracy for the system was 95% and facial recognition accuracy was 98%. To increase the precision and dependability of attendance management, the proposed system can be implemented in a variety of organisations, such as businesses, schools, and universities. The system may also aid in lowering the time and effort needed for managing attendance and enhancing the security of attendance records","PeriodicalId":395450,"journal":{"name":"REST Journal on Data Analytics and Artificial Intelligence","volume":"105 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"REST Journal on Data Analytics and Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46632/jdaai/2/2/6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
: The usage of biometric technology has grown in popularity recently across several industries, including attendance management systems. Utilising biometric technology has been shown to be a more dependable and secure technique of managing attendance. This study suggests an artificial attendance system that uses face recognition with eye blink detection, QR code scanning, and two-way verification. The objective of this system is to enhance the security, accuracy, and reliability of attendance management in various organisations. The suggested system manages attendance via two-way verification. The system first reads a unique QR code that is produced for each user. Second, the system uses face recognition with eye blink detection to confirm the user's identification. The presence and identity of the user are confirmed by the two-way verification. The system also keeps track of the user's attendance's date, time, and place. Deep learning techniques are the foundation of the facial recognition system employed in this study. The system extracts facial features from the user's face using a convolution neural network (CNN). For precise person recognition, the CNN is trained on a big collection of facial photos. Deep learning algorithms are also the foundation of the eye blink detection system. To recognise eye blinks, the system makes use of a long short-term memory (LSTM) neural network. A dataset of facial photos with labelled eye blink data is used to train the LSTM. The Open CV library and Python programming language were used to create the suggested system. A collection of 1000 facial photos with labelled eye blink data was used to test the system. Eye blink detection accuracy for the system was 95% and facial recognition accuracy was 98%. To increase the precision and dependability of attendance management, the proposed system can be implemented in a variety of organisations, such as businesses, schools, and universities. The system may also aid in lowering the time and effort needed for managing attendance and enhancing the security of attendance records