Identity Verification System using Deep Learning

One of the biggest uses of image processing is face recognition, which is essential to the industry. The ability to recognize a human face is a current concern for authentication, particularly when it comes to student attendance. Face biostatistics, which are based on high definition monitoring and other computer technologies, are used in the face recogn ition process of the attendance system to identify students. The goal of establishing this system is to digitally replace the conventional method of recording attendance by calling names and keeping paper records. The methods used today to record attendance are laborious and time-consuming. Manually recording attendance allows for easy manipulation of the records. Both the current biometric methods and the conventional method of taking attendance are susceptible to proxies. It is consequently suggested that this article address each of these issues. The suggested system uses Gabor filters, generative algorithms such as CNN, SVM, and KNN. Attendance reports will be created and saved in Excel format following face recognition. The system is evaluated in a variety of settings, including lighting, head motions, and changes in the student-camera distance. Following rigorous testing, the total accuracy and complexity are computed. Biometric technology, such as face recognition, relies on identifying an individual's facial characteristics. Individuals gather the facial picture data, which is then automatically processed by the recognition technology. The paper provides an overview of relevant facial recognition research from several angles. The report outlines the phases of development and associated facial recognition technology. We provide the general assessment standards, the general databases, and the research on face recognition in real-world situations.