Image Processing Apparatus Dual Identification Mark Character Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing methods face errors in character recognition when using a single identification mark for designating regions, leading to incorrect recognition of character strings and requiring manual designation of storage destinations for image data.

Innovation Solution

An image processing apparatus and program that utilize a first and second identification mark for character recognition, where the second mark differs from the first, to accurately identify character strings and automate the storage of image data by matching them with folder names, eliminating the need for manual destination designation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single identification mark is used for character recognition, then the device complexity is reduced, but the measurement precision of character string identification deteriorates leading to erroneous recognition

Engineering Contradiction:

Improveidentification mark systemVSAvoidcharacter string identification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The identification mark is divided into two distinct parts: a first identification mark (such as a colored line or frame) that designates the region containing the character string, and a second identification mark (such as a checkmark or symbol) that is added to the recognized character string to confirm accuracy. This segmentation allows the system to separate the functions of region designation and recognition confirmation, thereby improving identification precision without excessive complexity increase.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The second identification mark acts as an intermediary element between the OCR process and the final result. It serves as a visual confirmation that the character string has been successfully and accurately recognized, providing an additional layer of verification that reduces erroneous recognition while maintaining system simplicity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If manual designation of storage destinations is required, then the adaptability to different storage locations is improved, but the ease of operation deteriorates due to repeated user input

Engineering Contradiction:

Improvestorage location flexibilityVSAvoiduser input frequency

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs automatic storage destination selection based on the recognized character string content. Instead of requiring manual user input for each file, the system autonomously determines the appropriate folder or location for storing the scanned document, thereby eliminating repeated user input while maintaining flexible adaptability to different storage locations through content-based routing.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system pre-configures multiple possible storage destinations and establishes rules for automatic selection. Before the user needs to store a file, the system has already prepared the storage structure and can automatically select the appropriate destination based on the recognized content, eliminating the need for real-time user decision-making about storage locations.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If character recognition is performed on all marked regions, then the productivity is improved, but the reliability deteriorates due to wrong recognition of non-target character strings

Engineering Contradiction:

Improvecharacter recognition throughputVSAvoidcharacter recognition accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The first identification mark (such as a colored line or frame) is applied selectively to specific regions containing target character strings that need to be recognized. This local marking approach allows the OCR system to focus only on designated areas, improving both productivity by avoiding unnecessary processing of irrelevant regions and reliability by ensuring that only intended character strings are recognized.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The identification marks utilize different colors or visual characteristics to distinguish between target and non-target regions. By using color-coded or visually distinct marks, the system can reliably identify which character strings should be processed, preventing wrong recognition of non-target strings while maintaining high productivity through selective processing.

Inventive Principle:

Principle #32Color changes

Data Source

PatentUS20240127615A1Image processing apparatus and non-transitory computer-readable storage medium storing image processing program

Publication Date: 2024.04.18 SEIKO EPSON CORP

AI summary

An image processing apparatus includes a control unit configured to acquire image data generated through reading of an original document, and acquire, through character recognition, a character string included in the image data. The control unit performs a first process and a second process. The first process is configured to acquire, through character recognition, the character string of which region is designated with a first identification mark in the image data, and a second identification mark differing from the first identification mark is further added to the character string. The second process uses the character string acquired in the first process.