Smart Tourist Surveillance System Using Face Recognition and Raspberry Pi

This project presents a Home Automation Security System that integrates face detection and recognition with RFID technology using a Raspberry Pi. The system aims to enhance security and access control in homes by automating the process of user authentication through facial recognition and RFID tags. The system utilizes a Raspberry Pi as the central control unit, a camera module for face detection and recognition, and an RFID reader to scan RFID tags for additional access control. The system functions by scanning an RFID tag, and upon detection of a valid tag, it activates the camera to capture the face of the person requesting access. The captured image is then processed using OpenCV and face_recognition libraries in Python to match the face with a pre-stored database of authorized individuals. If both the RFID tag and face match the stored data, the system grants access by performing automation actions such as unlocking doors or turning on lights. Keywords- Raspberry Pi, Pi Camera, Face Detection, Face Recognition, RFID Technology, RFID Tag Verification.

The use of facial recognition for different security systems is increasingly vital in various sectors, even where electronic security systems are prevalent. This project aims to address the need for cost-effective solutions, particularly pertinent due to high funding requirements for facial recognition systems. The prototype, based on a Raspberry Pi 3 system, utilizes locally sourced materials, showcasing feasibility and adaptability within the region. It employs microcontrollers, sensors, and an SD card for data management, with Python programming facilitating system operation. Additional components like a display screen and buzzer enhance user interaction and notifications. The methodology utilized draws from Dennis and Wixom’s prototype methodology (Dennis and Wixom, 2003), encompassing three phases: analysis, design, and implementation. During testing, the system effectively differentiated between authorized and unauthorized individuals, granting or denying access accordingly. However, improvements to the Raspberry Pi module, along with enhancements in memory capacity and camera quality, are recommended for optimized performance, especially for larger-scale deployments. This project also suggests potential expansions, such as integrating voice-based assistance and linking with police databases for enhanced security measures. Leveraging technologies like WhatsApp for notifications and implementing cloud-based storage to manage visitor records efficiently can further streamline operations and reduce costs. Recognizing the limitations of the current hardware, the project underscores the potential for significant improvement with better processing modules. Overall, the project demonstrates the feasibility of locally developed solutions for implementing robust security systems with facial recognition capabilities, offering practical insights for similar initiatives across Africa.

At present, face recognition has been widely used, and face recognition in mobile devices has a broad application prospect. We try to detect and extract faces by extracting Haar-like features and then put the face images into the Convolutional Neural Network (CNN) for training and recognition. We improve the MobileNetV2, use ArcFace for face recognition and classification, and test the CNN face classification program on Raspberry Pi 4B. The training in Raspberry Pi is based on the idea of transfer learning. The features extraction part of the network loads the weight file, and only the fully connected classification layers are trained. Finally, the accuracy of train set and test set reach 99.8% and 94.4% respectively after training 100 epochs in Raspberry Pi. When epoch=10, the accuracy rate reaches the predetermined value. We can consider training 10 epochs in Raspberry Pi, and the total time is about 1h33min.

Current attendance methods, though simple, are prone to manipulation and can be time consuming for both educators and students. For instance, manual systems and QR code based methods allow students to register attendance on behalf of others due to the lack of unique identification. While calling names individually improves security, it disrupts the learning process by consuming significant time. This study addresses these issues by developing an autonomous robot, CObot, equipped with a facial recognition system powered by a Raspberry Pi microcontroller. CObot navigates classrooms autonomously, avoiding obstacles, and efficiently records attendance without requiring movement from students or educators. The use of facial recognition ensures that only registered individuals can mark attendance, creating a secure and tamper-proof system. Additionally, the integration of Internet of Things (IoT) technology enables real-time data transfer to Google Sheets, simplifying record-keeping and reducing educators administrative workload. A 3D-printed, customizable car structure enhances the robot design, while the Raspberry Pi 5 was selected over alternatives like the ESP32-S3 for its superior processing power and faster data transfer speeds, ensuring smoother operations. In testing with 60 participants, the Raspberry Pi 5 demonstrated a 99% accuracy rate in facial recognition, outperforming the ESP32-S3 90% accuracy. By saving time, improving security, and reducing manual effort, CObot enhances the classroom environment, benefiting both students and educators. While the improvement in attendance systems may appear incremental, CObot represents a meaningful step toward fostering a more efficient and effective learning environment.

Transport infrastructure in Serbia constitutes an integral part of the material basis of tourism. The development of a tourist destination is impossible without the development of transport infrastructure. Traffic infrastructure is an integral part of a tourist destination and a condition for the development of all activities and processes in the destination. The attractive factors of the tourist destination itself cannot be successfully valorized if there is no good traffic infrastructure and traffic connections. In fact, the development of traffic contributed to the movement of people and the development of tourism, especially the construction of traffic infrastructure, railways, roads and airports, which have led to modern mass tourism. Improving the quality of traffic in terms of speed and comfort of travel is an extremely important factor in the tourist offer today. Destinations that have quality traffic infrastructure and good traffic connections are more attractive as destinations for tourists. An important prerequisite for the development of tourism in destinations is the development of traffic infrastructure, that is, the position of the destination in relation to the main traffic roads. The development of air traffic and the existence of an airport with flights to emitting markets is one of the important prerequisites for the development of tourism in Serbia. The region around the city of Kraljevo and the Zlatibor district have an extremely good position for the further development of Serbia's tourist offer. The construction of transport infrastructure is the first and decisive factor that affects the growth and development of tourism in a certain tourist destination. Traffic infrastructure extremely strongly defines and directs the economic and tourism development of Serbia. The inclusion of the airports in Kraljevo and Užice, as well as the further inclusion of other smaller airports, especially in those locations that gravitate towards a larger number of cities, will strongly influence the improvement of tourism at the country level. Multiple benefits from the inclusion of smaller airports in Serbia will be most easily seen through the increase in the number of passengers at these airports, but the real effects will be seen when the mobility of people, primarily from the region, will be noticed in the years to come.

Innovative soft computing-enabled cloud optimization for next-generation IoT in digital twins

This paper presents the development of an automated component detection system for quality control in Printed Circuit Boards (PCBs) by integrating the YOLO object detection algorithm with Internet of Things (IoT) real-time streaming on a Raspberry Pi platform. The proposed system aims to address the challenges associated with traditional manual inspection methods, including time inefficiency, human error, and limited accuracy in detecting faulty components. The YOLO model, renowned for its high-speed and accurate object detection capabilities, was trained to identify various PCB components and deployed on a Raspberry Pi due to its affordability, portability, and low power consumption. To enable real-time remote monitoring and analysis, IoT capabilities were incorporated using the MQTT protocol, allowing seamless data transmission to remote servers or devices. The experimental results demonstrated the effectiveness of the proposed system, achiev-ing an average detection accuracy of 95%, making it a reliable solution for real-time quality assurance in PCB manufacturing. The novelty of this study lies in the innovative integration of the YOLO algorithm with IoT technology on a cost-efficient platform, providing a scalable and practical solution for automating PCB inspection processes. This approach not only enhances inspection efficiency but also reduces operational costs, offering significant value to the electronics manufacturing industry. Future work will focus on scaling thesystem for broader applications and improving the detection capabilities for more complex PCB designs.

This study focuses on the development of an age range classification through facial recognition and Keras Model using a Raspberry Pi Camera. Keras Model and a convolutional neural network will be implemented to help the age range classification. Raspberry Pi 4 will be incorporated as the microprocessor that the device will use and process the deep learning through this study. The Raspberry Pi Camera v2 is used as the camera sensor that will take faces as input to classify the age range of a subject. Both the Raspberry Pi 4 and camera module will be used to detect a person’s face in real-time and predict the age range of the subject to which the researchers were able to build an age range classification through facial recognition using the Keras Model. The researchers were able to acquire an accuracy of 84.38% upon using Keras Model and convolutional neural network.

Our review paper highlights the design and creation of voice assistance and facial recognition smart glasses using raspberry pi for the benefit of those who are blind or visually impaired. It helps them recognize everyone around them even when their known person is silent. Also, it includes some excellent features like web browsing and songs playing. This idea makes their life simpler and works as a digital assistant. This device has the feature of recognize the face of that people or that object which is already inserted in our system. It takes our face as an input and it provide the output by speaking. We can implement our software by using Raspberry PI, it is also a extremely powerful ARM based system on a chip (SOC). The Raspberry Pi can execute Python and C++ programming and do graphical calculations using its built-in graphics. In this project we have used Raspberry pi 4 face recognition, speaker as a buzzer, google text to speech, Ultrasonic sensor for object detection and ESP 32 camera web server. Our suggested system is superior, extremely effective, extremely affordable, user-friendly, and light weight.

Our research describes the design and development of raspberry pi based smart glasses for the welfare of visually impaired people with face recognition and voice assistant. This idea helps them to recognize people around them even when their known person is not talking and also it has some cool features like playing songs, browsing etc. This makes their life easier and acts as a digital assistant. This device also has Hot word detection. To use this device, The user is requested to call the device using the hot words like "Hello iris", "ok iris" etc. and provide instruction. It takes their voice instruction as input and provides output by speaking. Our software is made to interact with the user like Alexa and google assistant. Using pre built python modules, it is easy for us to add many other features too. Our software can be implemented using Raspberry pi which is a very powerful ARM based SOC (System on a Chip). Raspberry pi can run python, C++ codes and it can also perform graphical calculation with its embedded graphics. In this system, we use Raspberry Pi Face Recognition, ESP 32 camera Web Server, face encodings, Pico voice console, porcupine engine, Google Text to Speech. Our proposed system is better, highly efficient, highly economical, User friendly and low weight.

Face recognition has numerous applications in the modern world. With recent developments in IoT devices, security, and biometric systems, many applications of face recognition are being used on devices like a raspberry pi. In this paper, we propose an efficient face recognition system that uses face detection and extraction of the face from image based on Single Shot Multibox Detector (SSD) and uses image enhancement techniques like bilateral filtering and histogram equalization to enhance the quality of face image after which Principal Component Analysis (PCA) is used for feature extraction and Linear Discriminant Analysis (LDA) is used as classifier. The experiments have been conducted on the Faces95 and Faces96 datasets to test the proposed system and the performance of the system is also compared with two other methods for face recognition namely LBPH and PCA with SVM classifier. The testing of the system in real-time shows great results while recognizing faces.

Face detection entails the technology that identifies the human face in digital images. Face detection can be used in various applications. One of the major areas of application of face recognition is in security systems. We know that a smart security system is the need of the hour and has become a necessity in today’s time. It is the basic need of humans to be able to protect one’s home and belongings. The security system needs to be smart and efficient. Hence, it avoids intruders and protects your possessions by minimizing break-ins. Installing a home security system helps in protecting your home and valuables from burglars. The security system developed has a camera module that will give access to only authenticated persons to unlock the main door of the house using facial recognition technology. This discrete system is developed using an electronic board called as Raspberry Pi can detect intruders as well as send off an alarm to nearby police stations using SMS or Email. Keywords: Home security; Face Recognition; Internet of Things (IoT); RaspberryPi Microcontroller; Control; Smartphones Cite this Article Ayush Yadav, Shaam Garg, Shivam Jamloki, Aanchal Sadana, Kusum Tharani. Home Security using Facial Recognition. Current Trends in Signal Processing. 2020; 10(2): 5–11p.

Objectives/Aim: The present paper deals with building a smart assistant with the aim of assisting the visually impaired people in mobility with confidence by realizing the nearby obstacles and also implement image processing techniques to recognize people. Methods: We use Raspberry Pi 4 which has increased computing performance and is interfaced to the picamera, GPS and GSM modules. Arduino pro mini with buzzer, ultrasonic sensors and vibration motors are used for obstacle detection. Certain libraries important for image processing are used such as OpenCV, Dlib, face detection (Haar cascades, HOG + Linear SVM, or CNNs), espeak for converting text to speech. Programming was implemented through Python and Arduino compiler. Findings: Analysis was carried out using the proposed system for the blind and visually impaired people who could move around comfortably with confidence and were also able to detect objects and recognize people. Hence the proposed system removes the use for the cumbersome white cane in exchange for small and handy modules which can be used in the form of wearables mounted on shoulders, hands and legs to detect the obstacles from multiple directions and provide for a comfortable wear. It was determined that the Raspberry pi 4 was incapable of running CNN detection for which ideally computer GPU was required, so HOG detection method was used instead. Application/Improvements: This project can be implemented mainly in the commercial field of helping visually impaired people with poor eyesight or being completely blind. Industrial applications can be devised and enhanced like robots and machineries along with Security, Identifying and Tracking. Keywords: Face Recognition; Obstacle Detection; Open Source Computer Vision (OpenCV); Deep Learning; Histogram of Oriented Gradients (HOG); Support Vector Machine (SVM); Convolutional Neural Network (CNN)

In this study, we introduce an innovative auto-stop car system empowered by deep learning technology, specifically employing two Convolutional Neural Networks (CNNs) for face recognition and travel drowsiness detection. Implemented on a Raspberry Pi 4, our system is designed to cater exclusively to certified drivers, ensuring enhanced safety through intelligent features. The face recognition CNN model accurately identifies authorized drivers, employing deep learning techniques to verify their identity before granting access to vehicle functions. This first model demonstrates a remarkable accuracy rate of 99.1%, surpassing existing solutions in secure driver authentication. Simultaneously, our second CNN focuses on real-time detecting+ of driver drowsiness, monitoring eye movements, and utilizing a touch sensor on the steering wheel. Upon detecting signs of drowsiness, the system issues an immediate alert through a speaker, initiating an emergency park and sending a distress message via Global Positioning System (GPS). The successful implementation of our proposed system on the Raspberry Pi 4, integrated with a real-time monitoring camera, attains an impressive accuracy of 99.1% for both deep learning models. This performance surpasses current industry benchmarks, showcasing the efficacy and reliability of our solution. Our auto-stop car system advances user convenience and establishes unparalleled safety standards, marking a significant stride in autonomous vehicle technology.

This paper presents how the Neural Compute Stick 2 processor is used in conjunction with a Raspberry Pi 3 B+ board for controlling an electromagnetic lock using deep learning techniques to generate an access control system with embedded facial recognition capabilities. The system is based on object detection and facial recognition code developed in Python programming language. Through a webcam, it obtains images in real-time to make a comparison with the faces stored in a database. For prototype implementation, an embedded platform (Raspberry Pi) was used to provide the base operating system for programming and provide an analog signal in response to the system. A proof of concept experimentation was carried out with 15 subjects to test the effectiveness of the proposed method, achieving an average accuracy of 88.75%.