Self-Checkout ID Verification Using Facial and Card Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customer identification verification at self-checkout terminals for age-restricted items is inefficient and poses health risks due to face-to-face contact, leading to long queues and potential misuse of fake identification cards.
Innovation Solution
A system utilizing facial recognition and AI/ML algorithms to verify customer identity by comparing live facial features with identification card images, ensuring minimal attendant interaction and reducing the need for physical card handling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If face-to-face identification verification is performed, then age verification accuracy is improved, but customer comfort deteriorates due to pathogen exposure concerns
Solution Approach 1:
The patent introduces an automated verification system as an intermediary between the customer and the employee. The system captures images of the customer's face and ID card, performs automated comparison and verification, and communicates the result to the employee without requiring direct contact. This intermediary system maintains verification accuracy while eliminating pathogen exposure risk.
Solution Approach 2:
The patent replaces the mechanical manual verification process (employee physically examining ID and comparing with customer) with an automated optical and computational system. Cameras capture images, software algorithms compare facial features and validate ID authenticity, and digital communication delivers results. This substitution eliminates the need for close physical interaction while maintaining or improving verification reliability.
2Reliability
If manual card verification by employees is performed, then identification accuracy is improved, but productivity deteriorates during high traffic periods
Solution Approach 1:
The system enables self-service verification where the customer's ID and facial features are automatically captured and verified without requiring employee intervention for the comparison process. The customer simply presents their ID and faces the camera, while the automated system performs the verification work that would otherwise require skilled employee judgment, thereby scaling verification capacity during high traffic periods.
Solution Approach 2:
The system performs preliminary verification actions by pre-capturing and storing reference images from ID cards, pre-configuring verification criteria, and pre-positioning cameras and sensors at the terminal. When verification is needed, the system rapidly compares live captures against pre-prepared reference data, eliminating the time employees would need to manually examine and analyze each ID during high-volume periods.
3Speed
If automated facial recognition is used, then verification speed is improved, but reliability may deteriorate due to fake photos or deepfakes
Solution Approach 1:
The patent merges multiple verification methods into a single comprehensive system: facial feature comparison, ID card image authenticity verification, text information validation, and liveness detection. By combining these independent verification layers, the system maintains high speed while compensating for individual method weaknesses - for example, if facial recognition could be fooled by a photo, the liveness detection and ID validation provide additional reliability checks.
Solution Approach 2:
The system incorporates feedback mechanisms where verification results, including confidence scores and detection of potential fraud indicators, are fed back to employees for final decision-making. The system continuously learns from verification outcomes and adjusts its algorithms to improve reliability against emerging fraud techniques while maintaining rapid processing speeds.
Data Source
AI summary
A transaction terminal captures at least one image of a customer during a checkout and the customer is asked to place a photo identification card in view of the camera where a second image is captured of the card. The second image is converted to text and various components of the card are validated. Any hologram on the card is verified from the second image. The photo on the card is compared to facial features in the customer image and a determination is made as to whether the customer's identification can or cannot be verified. When verified, a message is sent to an attendant's device with the determination that the customer and card were verified along with the customer image and card image. The attendant is asked to confirm the verification and when confirmed the terminal resumes processing the checkout on behalf of the customer.