This project aims to enhance the security and efficiency of virtual Know Your Customer (KYC) onboarding processes using advanced facial recognition algorithms and liveliness checks. The system integrates various machine learning techniques to provide a robust security framework that significantly reduces the risk of impersonation and fraud.
- 🔐 User Registration: Allows users to input basic personal details to initiate the KYC process.
- 🆔 ID Card Upload: Users upload a picture of their ID card, and the system uses machine learning algorithms like OpenCV to detect and extract the face from the ID card.
- 🤖 Liveliness Checks: Users are required to write a random 4-digit OTP on a piece of paper and display it in front of the camera. YOLO (You Only Look Once) is used for character recognition to read the OTP.
- 🧑💻 Face Matching: The captured face is matched with the face extracted from the ID card using face-matching algorithms to ensure the user matches the ID card holder.
- 📲 Automated Confirmation: Users receive a confirmation message upon successful completion of the virtual KYC process.
- 📡 Real-time Monitoring: Administrators can track the progress of KYC onboarding and intervene if any anomalies or suspicious activities are detected.
- ⚖️ Scalability and Flexibility: The system is scalable and capable of handling large volumes of KYC requests efficiently.
Python
Flask
HTML
CSS
JavaScript
MySQL
YOLO
- User Registration: Collecting basic personal details.
- ID Card Upload: Uploading and processing ID card images.
- Liveliness Check: Displaying OTP for character recognition.
- Face Matching: Verifying the user's identity.
- Confirmation: Providing feedback and confirmation of KYC completion.
Coming Soon!
- Study of Similar Work: Exploration of existing systems and their drawbacks.
- Proposed System: Description of the proposed system's features and functions.
- Requirements Specification: Detailed technical, operational, and behavioral requirements.
- Results: Significant reduction in fraud rates and enhanced security standards.
- Screenshots: Visual representation of the system's functionality.
The project successfully integrates liveliness checks and facial recognition to create a secure virtual KYC onboarding process. Future enhancements include improving algorithm accuracy and expanding the system's application to various sectors.
This project is licensed under the MIT License - see the LICENSE file for details.
- Ananthu Dev D V - GitHub Profile
Note: This project is a part of the Master's in Computer Applications curriculum at Lourdes Matha College of Science and Technology, affiliated with APJ Abdul Kalam Technological University, Kerala.
