Facial Recognition Security System in Automotive Vehicle

Project Title

Facial Recognition Security System in Automotive Vehicle

Project Area of Specialization Artificial IntelligenceProject Summary

OVERVIEW OF THE SYSTEM

From this, we have implemented theft control techniques that can provide the important functions required for advanced intelligent Car Security, to avoid vehicle theft and protect from the usage of unauthenticated users. A secured and safety environment system for automobile users and also the key points for the investigators can be easily found out with the hijacker’s image. We can predict the theft by using this system in our day to day life. This work will help to reduce the complexity and improve security, also much cheaper and smarter than traditional ones. Experiment results show that it takes about 6 seconds to detect one 320*240 color jpeg image by software which is running on Raspberry Pi. It seems to be too long to be used in real-time detection.

A low-cost web camera mounted on the window on the driver’s side is used to capture the face image. During the authentication process, the driver is asked to look straight ahead at the camera. The mobile App is used as a platform for the face recognition system. The system processes the received data, compares them to the stored data in the template and sends control signals to the entry-components, which are the latch and ignition switch.

The face recognition system must do two major tasks: face detection and face recognition. The face detection module is main engine of the system. It receives an input image and then examines each part of the image at several scales looking for locations that might contain a human face. Once a face has been localized and segmented within an image, it must be standardized or normalized to ensure good performance in the next module that performs the face recognition task. Normalization includes an adjustment of illumination and of image shape by rescaling to a standard size. To recognize the identity of the normalized face, the face recognition module is used to find the best match in a database of registered face models. Finally, a binary output decides whether to reject or to accept the subject as the person authorized to operate the car.

Project Objectives

From this, we have implemented theft control techniques that can provide the important functions required for advanced intelligent Car Security, to avoid vehicle theft and protect from the usage of unauthenticated users. A secured and safety environment system for automobile users and also the key points for the investigators can be easily found out with the hijacker’s image. We can predict the theft by using this system in our day to day life. This work will help to reduce the complexity and improve security, also much cheaper and smarter than traditional ones. Experiment results show that it takes about 6 seconds to detect one 320*240 color jpeg image by software which is running on Raspberry Pi. It seems to be too long to be used in real-time detection.

Project Implementation Method

The task of the proposed system is to capture the face of each driver those that owner wants to store and to store it in the database. The face of the driver needs to be captured in such a manner that all the feature of the drivers faces needs to be detected. In this proposed system, a low-cost extendable framework for smart car security system is proposed, which consists of an FDS (Face Detection Subsystem), a GPS (Global Positioning System) module, Bluetooth in the Raspberry Pi, and a control platform. The system described in this paper automatically take photos of driver and compares his/her face with database to check whether he is an authenticated driver or not. The face detection subsystem bases on optimized PCA algorithm and can detect faces in cars. The other modules transmit necessary information to users and help to keep eyes on cars all the time, even when the car is lost.

Benefits of the Project

The use of vehicle becomes important everywhere in the world and also preventing it from theft is required. Vehicle manufacturers are attaining the security features of their products by introducing advanced automated technologies to avoid the thefts particularly in case of cars. Biometric and non-biometric methods usually provide such security features. Sometimes these systems fail due to hacked password and encryption of decrypted data, but it is almost impossible to make replica of distinctive characteristics. Biometric systems are modern and use techniques like fingerprint recognition, iris recognition and face recognition. Of these face recognition and detection systems are more sophisticated, easy to deploy and people can be identified without their knowledge. Some advantages of facial recognition method for vehicle security application are:-

1. More convenient, sensed as soon as one is seated in position.

2. Low cost and a better approach to be used with existing methods.

3. Requires no active part of the user.

Technical Details of Final Deliverable

This is an advanced system which can be utilized in many cars. Today, it is not difficult to make duplicates of vehicle keys and using such keys increases the risk of robbery. For such problem, we have come up with a solution. Our system uses face recognition system to identify the authorized users of the vehicles and only the authorized users are allowed to use the vehicle. System uses raspberry pi circuit, it consists of LCD display, & a buzzer alarm, it also consists of a camera. When we turn on the system authority provided by 3 options that is registration, start and clear data, while registering, it first scans the owner’s face. After successful registration, the owner can start the vehicle. To stop the vehicle, the owner needs to press the back command. If an unauthorized user tries to use the car, the system scans the person’s face, and checks whether face matches with the authorized face, if it does not match the system denies and the buzzer starts. In this way system helps to secure such intelligent vehicles.

Final Deliverable of the Project Hardware SystemCore Industry SecurityOther Industries Transportation Core Technology Internet of Things (IoT)Other Technologies Artificial Intelligence(AI)Sustainable Development Goals Partnerships to achieve the GoalRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	80000
Rasberry PI Circuit	Equipment	1	30000	30000
LCD Display	Equipment	1	8000	8000
Camera	Equipment	2	7500	15000
Cable and Connectors	Equipment	2	750	1500
Central Lock Door Actuator Motors	Equipment	4	2000	8000
Integrated Circuit	Equipment	4	250	1000
Auxiliary Battery	Equipment	1	4500	4500
Buzzers	Equipment	2	500	1000
Diodes	Equipment	2	500	1000
Miscellaneous Damage sensor/ item	Miscellaneous	1	10000	10000