Touchless Atm Authentication System Using Haar Cascade, Lbph And Mediapipe

Abstract

Automated Teller Machines (ATMs) Are Among The Most Common Banking Tools. They Mostly Rely On Physical Interaction Through Keypads And Touchscreens. This Can Raise Hygiene Concerns And Create Security Risks Like Shoulder Surfing And Keypad Tampering. This Paper Offers A Touchless ATM Access System That Combines Facial Recognition, Gesture-based Navigation, And A Virtual Keyboard For Secure Authentication And Transaction Processing. The System Applies The Haar Cascade Algorithm Along With Local Binary Pattern Histogram (LBPH) For User Identification, Followed By Password Confirmation Via A Gesture-based Virtual Keyboard. Hand Gesture Recognition, Powered By Computer Vision, Allows For Cursor Control And Menu Navigation Without Physical Contact. The Proposed Model Boosts Security With Multi-factor Authentication While Improving Accessibility And Hygiene By Removing Physical Touchpoints. Experiments Show Reliable User Authentication And Smooth Transaction Interaction With A Standard Webcam Setup. This Approach Provides A Practical And Scalable Framework For Future Contactless Banking.

Keywords