Document Image Display Mode Switching for OCR Verification Speed

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing character recognition technologies face a speed bottleneck when displaying recognition results for multiple documents, as they require acquiring and displaying multiple document images along with character recognition results, which slows down the screen display process.

Innovation Solution

An information processing apparatus with a processor that offers two display modes: one displaying character recognition results on a document basis with the document image, and another displaying results based on common characters across documents without showing the document images, thereby reducing data acquisition and display time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If document images are displayed together with character recognition results on a document basis, then verification accuracy is improved, but screen display speed deteriorates

Engineering Contradiction:

Improveverification accuracyVSAvoidscreen display speed

Core Design Contradiction:

Measurement precisionVSSpeed

Solution Approach 1:

The system dynamically switches between two display modes based on user needs: a first display mode that shows document images with character recognition results for accurate verification, and a second display mode that omits document images for fast screen display. This dynamic adaptability resolves the contradiction by allowing the system to optimize for either accuracy or speed depending on the operational context.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the display parameter (presence or absence of document images) to resolve the contradiction. In the first display mode, document images are included to ensure verification accuracy. In the second display mode, document images are excluded to improve screen display speed. This parameter change allows the system to adapt to different user requirements.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If document images of multiple documents are acquired and displayed with character recognition results, then verification completeness is improved, but data acquisition time deteriorates

Engineering Contradiction:

Improveverification completenessVSAvoiddata acquisition time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system segments the verification process into two distinct modes: comprehensive verification mode (first display mode) that acquires and displays document images for complete verification, and rapid review mode (second display mode) that omits document images to reduce data acquisition time. This segmentation allows users to choose the appropriate level of verification based on their needs.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies partial action by selectively acquiring only the necessary data for the current verification need. In the second display mode, the system performs partial verification by displaying character recognition results without acquiring document images, thus reducing data acquisition time while still providing useful verification information.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If character recognition results are collectively displayed on the basis of common characters across multiple documents, then operational efficiency is improved, but information context deteriorates

Engineering Contradiction:

Improveoperational efficiencyVSAvoidinformation context

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system provides a universal display framework that can accommodate both document-specific verification (first display mode) and collective character verification across multiple documents (second display mode). This multi-functionality allows the same interface to serve different verification needs, improving operational efficiency while preserving the option to access full contextual information when required.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11482026B2Information processing apparatus and non-transitory computer readable medium

Publication Date: 2022.10.25 FUJIFILM BUSINESS INNOVATION CORP

AI summary

Information processing apparatus including a processor configured to acquire a document image representing one of multiple documents, a partial image representing a part included in the document image and having a character written in the document, and a character recognition result regarding the character. The character recognition result includes a first character recognition result regarding a first character and a second character recognition result regarding a second character. The processor is configured to display the first document image, the first character recognition result, and a first partial image associated with the first character recognition result on a document basis in a first display mode. The processor is further configured to, in a second display mode, display the second character recognition result and a second partial image associated with the second character recognition result on a basis of a character common to the multiple documents and not display the document image.