Card Data Extraction via OCR and Barcode Cross-Validation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for extracting card information from mobile devices are cumbersome and prone to errors due to small screen sizes and keyboard interfaces, and do not effectively utilize barcode data to improve the extraction process.

Innovation Solution

A computer-implemented method using optical character recognition (OCR) that compares extracted alphanumeric characters from card images to machine-readable code data, corrects discrepancies, and utilizes adaptive metadata models to improve data extraction accuracy and autofill digital wallet applications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual card information entry is used on mobile devices, then users can input payment data, but the process becomes cumbersome and error-prone due to small screen sizes and keyboard interfaces

Engineering Contradiction:

Improveease of card information entryVSAvoidaccuracy of card information entry

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent replaces manual mechanical keyboard input with optical scanning technology. The mobile device captures an image of the card using its camera, and optical character recognition (OCR) algorithms automatically extract card information from the image, eliminating the need for manual typing on small keyboards.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the card information to extract and populate fields automatically through image recognition. The user simply positions the card within a guide box, and the system autonomously performs data extraction, validation, and form population without requiring manual intervention.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If precise card positioning within a guide box is required, then the scanning system can recognize the card, but the user interface becomes more complex and user-friendly

Engineering Contradiction:

Improveprecision of card positioningVSAvoidease of card positioning

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system performs preliminary actions by providing visual guidance before the actual scanning occurs. The guide box is displayed on the screen to show users exactly where to position the card, and the system may perform test detections to ensure proper positioning before final data extraction.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The guide box acts as an intermediary visual element between the user and the scanning system. It translates the technical requirement for precise positioning into a simple visual cue that users can easily understand and follow, mediating between the precision requirements and user convenience.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If traditional optical character recognition is used alone, then card data can be extracted, but errors occur due to incorrect character recognition and lack of validation

Engineering Contradiction:

Improvespeed of data extractionVSAvoidaccuracy of extracted data

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements feedback by comparing OCR-extracted data against known card data patterns, formats, and validation rules. When discrepancies are detected, the system can prompt the user to reposition the card or manually correct specific fields, providing continuous feedback to improve accuracy.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent merges multiple data extraction methods: optical character recognition for alphanumeric characters, barcode scanning for machine-readable data, and format-based validation. These complementary techniques work together to cross-validate information and correct errors that any single method might produce alone.

Inventive Principle:

Principle #5Merging (Combining)

4Device complexity

If barcode data is not utilized, then the extraction process is simpler, but accuracy is reduced and discrepancies cannot be corrected

Engineering Contradiction:

Improvecomplexity of extraction processVSAvoidaccuracy of card information

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system achieves universality by designing the extraction process to handle multiple card types and data formats (alphanumeric characters, barcodes, different card layouts). The guide box and validation algorithms are configured to adapt to various card formats, making the system versatile across different card types while maintaining accuracy.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10296799B2Extracting card identification data

Publication Date: 2019.05.21 GOOGLE LLC

AI summary

Extracting card information comprises a server at an optical character recognition (“OCR”) system that interprets data from a card. The OCR system performs an optical character recognition algorithm an image of a card and performs a data recognition algorithm on a machine-readable code on the image of the card. The OCR system compares a series of extracted alphanumeric characters obtained via the optical character recognition process to data extracted from the machine-readable code via the data recognition process and matches the alphanumeric series of characters to a particular series of characters extracted from the machine-readable code. The OCR system determines if the alphanumeric series and the matching series of characters extracted from the machine-readable code comprise any discrepancies and corrects the alphanumeric series of characters based on the particular series of characters extracted from the machine-readable code upon a determination that a discrepancy exists.