Personal Identification using Facial Recognition and visualizing details on HUD
Facial Recognition is an effective technology and is used for biometric authentication and recognition of a person. It has a variety of applications. One of them is security. In this project smart glasses have been introduced that can perform facial recognition to serve as an aid in security measure
2025-06-28 16:34:27 - Adil Khan
Personal Identification using Facial Recognition and visualizing details on HUD
Project Area of Specialization Wearables and ImplantableProject SummaryFacial Recognition is an effective technology and is used for biometric authentication and recognition of a person. It has a variety of applications. One of them is security. In this project smart glasses have been introduced that can perform facial recognition to serve as an aid in security measures. This smart device can easily capture the face frontal view which is difficult for security cameras and it is also portable. The techniques used to achieve face recognition are deep learning based due to their high accuracy as compared with old techniques like Eigen Faces, Principle Component Analysis, Local Binary Pattern Histogram, Fisher Faces and Linear Discriminant Analysis. Deep learning is subfield of machine learning that is training multiple layer neural network to perform a specified task. This device can easily recognize the person and is very effective in security and confidential areas for ensuring their safety.
Facial Recognition is the matching of input image with a stored database and showing the result based on that comparison. Trained neural networks serve as a database for recognition. They compare the input image with trained model and predict the result. Human face pattern is an example of complex image. For dealing complex images Convolutional Neural Networks (CNN’s) are used. Transfer learning of CNN’s can be done to achieve this task. In this project transfer learning of a pre-trained CNN “FaceNet” is performed to achieve face recognition. FaceNet has the highest accuracy among all CNN’s while performing face recognition. Training of this network also requires a smaller number of images as compare to other convolutional neural networks.
The device hardware includes a camera mounted on glasses. It takes input in the form of image/video and send it to the processing unit (Raspberry Pi 3 B). The processing unit placed in the user’s pocket perform the face recognition and show the output result on display (0.96 inches O-LED) mounted on glasses, giving its projection on a reflector. Both camera and display are connected to processing unit wirelessly. The main objective is to enhance and improve the security system through this portable device.
Project ObjectivesThe Objective of project is to construct facial recognition based smart glasses with eye mounted display that can be used for various applications of facial recognition like security, personal identifcation and autonomous attendance system.
Project Implementation MethodAs the project include facial recognition. The face recognition system was implemented using convollutional neural networks. After the face recognition system is made the need is implement it in glasses. For this purpose glasses have camera in them that take an input image, send it to processing unit to perform face recognition, the proceessing unit after recognition send the results to glasses and the results are projected in front of eye using O-LED.
The tools and technology used in our project includes both hardware and software parts which are given as follows:
- Raspberry Pi 3B
- Raspberry Pi Zero
- 8MP Camera
- 0.96 Inches OLED
- 16 Gb Micro SD card
- Raspbian
- MATLAB 2018a
- Corel Draw
- Python
- Deep Learning
- Transparent Glass
- Mirror
- Acrylic Sheet
Problem Statement:
Personal Identification at rush or crowded places like different security check points, universities or any other educational institutes entrances, entry point of different events and safe city project areas is a very difficult task. The job of every security department is to avoid any inconvenience and protect the people of particular area from any terrorist attack but unfortunately it is very difficult for security and law enforcement agencies to identify a criminal or a terrorist among hundreds of people. Likewise, problems in other institutes or sectors related to this includes identifying genuine student on university gate, genuine ticket holders or participants during sports matches or concerts, taking attendance of the students of a particular class, good care of patients in hospitals.
Solutions:
To all the problems mentioned in the above sections these smart glasses with the feature of facial recognition can identify the person in the blink of an eye and its results gives 99.69% accuracy. It can easily identify a criminal or a terrorist on security checkpoints, can be used at the gates of educational institutes for entry of students, for entry of participants during sports matches or for identification of ticket holders during different events like concerts etc., for taking good care of patients in hospitals and can easily mark the attendance of a particular class.
Technical Details of Final Deliverable- The glasses have an 8MP camera to captuer input.
- 0.96 inches O-LED for display.
- Raspberry Pi Zero W for sending and receiving information between glasses and processing unit through Wi-Fi.
- Processing Unit (Laptop) for performing face recognition.
- Convolutional Neural Networks are used to perform face recognition
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 45270 | |||
| Raspberry Pi 3B | Equipment | 1 | 6000 | 6000 |
| Raspberry Pi 3B casing | Equipment | 1 | 400 | 400 |
| Raspberry Pi Camera Module | Equipment | 1 | 3500 | 3500 |
| HDMI to VGA Converter | Equipment | 1 | 400 | 400 |
| HDMI Cable | Equipment | 1 | 350 | 350 |
| Memory Cards for Pi | Equipment | 4 | 800 | 3200 |
| Mouse for Pi interfacing | Equipment | 1 | 650 | 650 |
| Raspberry Pi Camera Cable | Equipment | 1 | 300 | 300 |
| NodeMcu v2 ESP8266 | Equipment | 1 | 450 | 450 |
| 1.44” Serial LCD Display | Equipment | 1 | 850 | 850 |
| 1000maH 3.7V LiPo battery | Equipment | 1 | 150 | 150 |
| 1500maH 3.7V LiPo battery | Equipment | 1 | 300 | 300 |
| 2000maH 3.7V LiPo battery | Equipment | 1 | 450 | 450 |
| Connecting wires | Equipment | 1 | 245 | 245 |
| 3.7V charging module | Equipment | 1 | 50 | 50 |
| Arduino Pro mini | Equipment | 2 | 250 | 500 |
| CH340G Usb to TTL converter | Equipment | 1 | 110 | 110 |
| TP4056 LiPo battery charge module | Equipment | 1 | 40 | 40 |
| Raspberry Pi zero Camera Cable 30cm | Equipment | 1 | 450 | 450 |
| Raspberry Pi zero W | Equipment | 1 | 2800 | 2800 |
| shipping | Miscellaneous | 1 | 250 | 250 |
| Micro USB to Type C converter | Equipment | 1 | 35 | 35 |
| Mini HDMI to HDMI Adapter for raspberry Pi zero | Equipment | 1 | 180 | 180 |
| USB OTG cable | Equipment | 1 | 40 | 40 |
| USB to Serial CP2102 Module | Equipment | 1 | 190 | 190 |
| White Color I2C OLED Display Modules | Equipment | 4 | 470 | 1880 |
| Female Micro usb to DIP 5 | Equipment | 1 | 60 | 60 |
| Male Micro USB | Equipment | 1 | 10 | 10 |
| Raspberry Pi Camera Cable 16cm Ribbon | Equipment | 1 | 150 | 150 |
| Raspberry Pi zero W | Equipment | 1 | 2900 | 2900 |
| Raspberry Pi Heat Sink Cooler | Equipment | 1 | 140 | 140 |
| USB Extension | Equipment | 1 | 350 | 350 |
| NRF 24L01 x 2 | Equipment | 1 | 500 | 500 |
| Arduino NANO | Equipment | 2 | 450 | 900 |
| ESP 8266 | Equipment | 3 | 350 | 1050 |
| Arduino Cable | Equipment | 1 | 50 | 50 |
| Arduino UNO | Equipment | 1 | 500 | 500 |
| Panaflex | Miscellaneous | 1 | 1700 | 1700 |
| Brochure | Miscellaneous | 1 | 1050 | 1050 |
| Glass Box | Miscellaneous | 1 | 1000 | 1000 |
| Project Casing, Designing and Finishing | Equipment | 1 | 3200 | 3200 |
| Camouflage Sheet | Equipment | 1 | 300 | 300 |
| Data Cable 2m | Equipment | 1 | 300 | 300 |
| Glasses 1 | Equipment | 1 | 1000 | 1000 |
| BOSS Glasses zero | Equipment | 1 | 4000 | 4000 |
| Shipping | Miscellaneous | 1 | 1010 | 1010 |
| Double Tape | Equipment | 1 | 150 | 150 |
| Pi Charger | Equipment | 1 | 450 | 450 |
| Magnifying Glass | Equipment | 1 | 80 | 80 |
| Acrylic Transparent Piece | Equipment | 1 | 100 | 100 |
| Reflecting Mirrors | Equipment | 1 | 380 | 380 |
| Glass Cutter | Equipment | 1 | 170 | 170 |