Text Recognition Verification via Related Document Cross-Reference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Text recognition systems often produce incorrect results even with high certainty factors due to dictionary and algorithm limitations, leading to potential misinterpretation of recognized text.

Innovation Solution

An information processing apparatus that acquires and confirms text recognition results using a certainty factor threshold, comparing them with corresponding results from related documents to issue warnings for discrepancies, ensuring accurate text recognition even with high certainty factors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If text recognition is performed using a certainty factor threshold, then processing efficiency is improved, but recognition accuracy deteriorates due to false high certainty results

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidrecognition accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

A relevant document is introduced as an intermediary to verify the text recognition result. The system acquires a relevant document related to the recognition target, extracts corresponding text from it, and uses this third-party information to validate whether the recognition result is correct, thereby resolving the unreliability of high certainty factors

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements a feedback mechanism by comparing the recognition result with text extracted from relevant documents. When discrepancies are detected, the system issues warnings and can request re-recognition, creating a closed-loop verification process that improves accuracy without sacrificing processing efficiency

Inventive Principle:

Principle #23Feedback

2Speed

If text recognition results are confirmed using only certainty factor thresholds, then processing speed is improved, but reliability deteriorates due to potential incorrect recognitions

Engineering Contradiction:

Improveprocessing speedVSAvoidrecognition reliability

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system performs preliminary verification by acquiring relevant documents and extracting reference text before final confirmation of recognition results. This advance preparation of verification data allows for quick validation without significantly impacting processing speed

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Relevant documents serve as intermediary verification sources that provide independent confirmation of recognition accuracy, enhancing reliability without requiring complex re-analysis of the original image

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11042733B2Information processing apparatus for text recognition, non-transitory computer readable medium for text recognition process and information processing method for text recognition

Publication Date: 2021.06.22 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An information processing apparatus includes an acquiring unit, a confirming unit, and a controller. The acquiring unit acquires a text recognition result with respect to a first image showing a document and a certainty factor indicating a certainty of the text recognition result. The confirming unit confirms the text recognition result if the certainty factor is above or equal to a threshold value. The controller controls an output of a warning for the text recognition result with respect to the first image in a case where the text recognition result and a text recognition result with respect to a second image showing a relevant document related to the document do not match even when the certainty factor is above or equal to the threshold value.