Continuous Card Scanning for Fraud Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting financial card information on mobile devices are cumbersome and prone to errors due to small screen sizes and lack of continuous scanning capabilities, which complicates fraud prevention.
Innovation Solution
Implementing a computer-implemented method that uses continuous scanning, optical character recognition (OCR) on multiple images, blending, and three-dimensional modeling to accurately extract and verify card data, including embossed text and holograms, to enhance accuracy and prevent fraud.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If precise card positioning is required in a box, then image capture accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The patent transitions from a static box alignment approach to a dynamic continuous scanning approach. The camera continuously captures images as the card moves through the scan area, and the system dynamically identifies and tracks the card position across multiple frames. This eliminates the need for precise manual positioning while maintaining accurate image capture through real-time position detection and tracking.
Solution Approach 2:
The system performs preliminary actions by continuously capturing a sequence of images before final processing. Multiple candidate images are captured in advance, and the system then selects and processes the best candidate from these pre-captured images. This preliminary continuous scanning and image capture sequence prepares multiple options before the final extraction, eliminating the need for single-shot precise positioning.
2Measurement precision
If continuous scanning with multiple images is used, then extraction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent employs a universal image processing pipeline that handles multiple functions: continuous image capture, card detection, candidate selection, data extraction, and verification. The same processing system manages the entire workflow from raw video frames to verified card data, reducing the need for separate specialized components and simplifying the overall system architecture despite the complexity of continuous scanning.
Solution Approach 2:
The system performs self-service by automatically selecting the best candidate image from the continuous scan sequence based on detection confidence metrics. The algorithm autonomously evaluates multiple captured images, identifies the optimal candidate without user intervention, and proceeds with extraction. This self-selection mechanism reduces the need for complex manual control interfaces while maintaining high extraction accuracy.
3Reliability
If multiple images are captured and compared, then fraud prevention is improved, but loss of time increases
Solution Approach 1:
The patent applies partial action by capturing and processing only the necessary number of images to achieve sufficient fraud prevention. Rather than analyzing every single frame in a continuous scan, the system identifies and processes a limited subset of candidate images that provide adequate verification. This selective processing of a partial set of images maintains fraud prevention effectiveness while significantly reducing processing time compared to exhaustive analysis of all captured frames.
Solution Approach 2:
The system skips through the continuous image sequence rapidly, using efficient detection algorithms to quickly identify candidate images that warrant further processing. High-confidence candidates are selected and processed expediently, while low-confidence frames are quickly discarded. This rushing through the image sequence with selective processing maintains security verification while minimizing the time spent on unnecessary frame analysis.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach improves the accuracy of financial card data extraction, reduces errors, and effectively prevents fraudulent transactions by utilizing blended and 3D models to confirm card authenticity.
Implementation Method 1
performing an optical character recognition algorithm on each of the plurality of images
Data Source
AI summary
Comparing extracted card data from a continuous scan comprises receiving, by one or more computing devices, a digital scan of a card; obtaining a plurality of images of the card from the digital scan of the physical card; performing an optical character recognition algorithm on each of the plurality of images; comparing results of the application of the optical character recognition algorithm for each of the plurality of images; determining if a configured threshold of the results for each of the plurality of images match each other; and verifying the results when the results for each of the plurality of images match each other. Threshold confidence level for the extracted card data can be employed to determine the accuracy of the extraction. Data is further extracted from blended images and three-dimensional models of the card. Embossed text and holograms in the images may be used to prevent fraud.