Anti-Theft Vehicle Starter on Face Detection

Anti-Theft Vehicle Starter on Face Detection

Aryan Garud*1, Prathamesh Nalawade*2, Sumedh Gaikwad *3,
Navin Wanare *4, Vishnukant Panchal*5, Prof. P.B Nagawade*6
*1,2,3,4,5,6Electrical Department, TSSM BSCOER POLY, Pune, Maharashtra, India.
*6Prof., Department of Electrical Engineering, TSSM’s BSCOER Poly Narhe Pune, Maharashtra, India.

ABSTRACT
The increasing vulnerability of conventional vehicle security systems, such as physical keys and keyless entry mechanisms, has necessitated the development of more secure and intelligent authentication solutions. This paper presents the design and implementation of a face recognition-based vehicle ignition system using a Raspberry Pi platform. The proposed system integrates computer vision, machine learning, and embedded hardware to enable a secure, keyless vehicle access mechanism. A USB camera captures real-time facial images of the user, which are processed using OpenCV and deep learning-based facial recognition algorithms to extract unique biometric features. These features are compared against a pre-trained database of authorized users using classification techniques such as k-Nearest Neighbors (k-NN) or Support Vector Machines (SVM).
Upon successful authentication, the system activates the vehicle ignition through GPIO-controlled motor driver circuitry, while unauthorized access attempts are denied and logged for security purposes. The system also supports alert mechanisms and can be extended with IoT-based notifications. The implementation demonstrates reliable performance under standard conditions, offering enhanced security, user convenience, and scalability compared to traditional systems. However, challenges such as varying lighting conditions, facial obstructions, and potential spoofing attacks are identified. The proposed solution highlights the feasibility of deploying low-cost, AI-enabled embedded systems for real-time automotive security applications and paves the way for future advancements in smart vehicle technologies.
Keywords: Face Recognition, Vehicle Security, Raspberry Pi, Computer Vision, Machine Learning, Biometric Authentication, OpenCV, Embedded Systems, IoT, k-NN, SVM, Smart Vehicle Technology