OCR Error Correction via Third-Party Data Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Character-recognition techniques, such as OCR and ICR, often introduce errors when converting documents to digital formats, leading to increased processing complexity and user effort in reviewing and correcting errors, particularly in financial applications like income-tax documents.
Innovation Solution
A computer system that receives a document image, performs character recognition, accesses corresponding information from a third party based on document items like Social Security numbers, compares the recognized data with stored information to identify and correct errors, and uses predefined financial calculations to further validate accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If character recognition techniques are used to convert document images to digital text, then information extraction efficiency is improved, but error rate increases
Solution Approach 1:
The system performs multiple rounds of error correction by comparing OCR results against third-party data sources and using financial calculation validations. Each comparison round provides feedback that identifies and corrects errors, progressively improving accuracy while maintaining high extraction efficiency
Solution Approach 2:
The patent introduces third-party data sources (payroll providers, financial institutions) as intermediaries to verify and correct OCR output. These intermediaries provide authoritative reference data that mediates between the noisy OCR output and the desired accurate financial information
2Reliability
If manual review and correction of OCR errors is performed, then accuracy is improved, but user time and effort increase
Solution Approach 1:
The system performs automatic error detection and correction without requiring user intervention. The computer system independently compares OCR results with third-party data, identifies discrepancies, and corrects errors automatically, freeing users from manual review tasks while maintaining high accuracy
Solution Approach 2:
The system performs error correction before the user needs to review the data. By pre-processing the OCR output through multiple validation and correction passes, the system delivers corrected results ready for use, eliminating the need for subsequent manual correction efforts
3Reliability
If multiple error correction passes are performed, then accuracy is improved, but processing complexity increases
Solution Approach 1:
The error correction process is divided into distinct segments: first comparing against third-party data sources, then performing financial calculation validations, and finally cross-referencing with additional data sources. Each segment handles a specific type of validation, making the overall complex process manageable and systematic
Data Source
AI summary
Embodiments of a computer system, a method and a computer-program product (e.g., software) for use with the computer system are described. These embodiments allow a user to provide an image of a document for use with software, such as an image of a financial document for use with financial software. In particular, the user can provide the image of the document, for example, by taking a picture of the document using a cellular telephone. This image may be converted into an electronic format that is suitable for text and numerical processing using a character-recognition technique, such as optical character recognition or intelligent character recognition. Errors in the electronic version of the document, if present, may be identified and corrected by comparing the electronic version to information maintained by a third party. This information may be accessed based at least on one or more items in the electronic version of the document.