Harsh Nagoriya

In the current ongoing situation of the pandemic, it has become necessary for people to wear a mask in order to protect themselves from exposure of the wide spread Novel-CoronaVirus, however many people do not wear it. The aim of this paper is to depict a system created which detects whether a person has worn a mask or not. For achieving this aim, a dataset consisting of 18236 images of people wearing a mask and without a mask is created. Using the same dataset, 101 layers deep, ResNet-101 convolutional neural network is trained. Indeed, the algorithm step regarding mask detection accomplished an accuracy rate of 96.02%. Lastly, the model is deployed to the RaspberryPI board.

The higher death rate in motorbike accidents is credited to carelessness in wearing a head protector (helmet) by bike riders. Identification of helmetless riders continuously is a necessary task to forestall the event of such accidents. This paper presents an automated framework to distinguish motor bikers without a head protector (helmet) from traffic observation recordings progressively. In this paper, a Single shot multibox detector (SSD) model is applied to the helmet detection problem. This model can utilize just one single CNN system to distinguish the bounding box area of motorbike and rider. When the area is chosen we classify whether the biker is wearing or not wearing a helmet on real-time. Convolutional Neural Network is applied to select motorbikers among the moving objects and recognition of motorbikers without a helmet. Further applying the You only look once (YOLO) model, I recognize the License Plates of motorbikers without a helmet. So I have applied three models in...

Face recognition Technology is being appealing field in recent years. Taking attendance is a real-world task, which needs a creative solution to reduce time, efforts and resources. Face recognition Attendance is a technique to detect and recognize the students' or employees' face for marking their attendance by using unique face features extracted from the images captured. In proposed face recognition project, a raspberry PI based system will be able to detect and recognize human faces in a quick and accurate way via images or videos that are being captured through a Camera. It detects the faces within the image and compares it with the listed faces in the database. On recognition of a registered face on the captured image assortments, the attendance of that student is marked present otherwise absent. The system is developed on Open Source image processing library hence; it is not hardware nor software dependent. Many algorithms are used to ameliorate the performance of the system but the concept to be implemented here is Eigen matrix concept (Eigen Faces). It is used to convert the images into the matrix, based on the features of the images, to easily recognize the faces of the students, so that the attendance database can be easily updated. I. INTRODUCTION Presently, attendance management is important task in every educational organization. Managing students' attendance during lecture period is time consuming task. The most of the institutions uses pen-paper based approach and some have adopted automated methods such as fingerprint biometric techniques and RFID based attendance System. However, these techniques make students to wait in a queue that depletes time and it is intrusive. Some institutions still use manual attendance approach in which a subject teachers call out the students' name and mark the attendance manually. This approach may be considered as a time-consuming or sometimes it happens for the teacher to miss someone to mark present or students may answer multiple times to make proxy attendance of their friends. So, the problem of accuracy and reliability arise when we think about the traditional process of taking attendance in the classroom. Face recognition technology is one of the least intrusive and fastest growing technology. Face recognition based attendance is an approach to automatically mark the presence or the absence of the student in the classroom by recognizing their faces. It can also be implemented in the exam sessions to ensure the presence of the real student who has registered for exam. It works by identification of humans using the most unique characteristics of their faces via images captured through camera, so it becomes highly reliable for the machine to mark the presence of all the students available within the room. The concept of this paper is aimed towards developing a less intrusive, economical and more efficient automated student attendance managing system using face recognition. II. EXISTING METHODS Some systems exist in automated attendance technique. However, only a few are enforced implementing a less intrusive approach. Some existing systems include Finger print based attendance, Iris based attendance and RFID based attendance. In this research, my focus is on face recognition and a cost effective architecture for its implementation. Face recognition based attendance system with raspberry pi 3A+ using Eigen faces algorithm has been proposed. In the work, a camera is placed at top position of the class that cover whole class which is interfaced with a raspberry pi 3A+ module for capturing students entering the class. The images are stored in the raspberry pi 3A+. The raspberry pi 3A+ module is used to achieve high speed of operation.