Character Area Segmentation for Precise Text Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing character recognition techniques struggle to accurately select specific character strings from images, often including unwanted symbols like spaces and punctuation marks due to imprecise range selection methods, such as finger operations on touch panels or camera recognition.

Innovation Solution

The system identifies character areas within an image, performs character recognition, and adjusts the size of individual character-based areas to prevent unintended inclusion of symbols during range selection by extending the areas of specific characters and their adjacent characters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a user specifies a range by finger operation on a touch panel or by recognizing finger movement, then the user can easily select a desired character string, but adjacent symbols such as spaces and punctuation marks are unintentionally included in the selected range

Engineering Contradiction:

Improveease of range selectionVSAvoidprecision of character range selection

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system segments the character area into individual character regions, allowing precise identification and selection of each character. By dividing the continuous character area into discrete character units, the system enables accurate range selection that excludes adjacent symbols while maintaining ease of user operation through touch panel interaction.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies different selection criteria to different parts of the character area. By identifying specific character regions and their boundaries, the system allows users to select ranges with precision, ensuring that only intended characters are included while excluding adjacent symbols through localized boundary detection.

Inventive Principle:

Principle #3Local quality

2Productivity

If character recognition processing is performed on the entire character area, then all characters are recognized, but it becomes difficult to extract only a specific character string

Engineering Contradiction:

Improveefficiency of character recognitionVSAvoidinclusion of unwanted symbols

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system segments the character area into individual character regions before performing recognition processing. This segmentation enables the system to efficiently process only the necessary character ranges while excluding unwanted symbols, thereby maintaining high productivity in character recognition while preventing loss of information through selective extraction.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system extracts only the specific character strings that are needed from the recognized character areas. By taking out the desired character ranges and excluding adjacent symbols through precise boundary detection, the system achieves efficient character recognition processing while maintaining data purity.

Inventive Principle:

Principle #2Taking out (Extraction)

3Reliability

If the character area boundaries are set to include all visible characters, then no character is left out, but adjacent symbols are unintentionally included in the selection

Engineering Contradiction:

Improvecompleteness of character recognitionVSAvoidprecision of selected range

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system applies localized boundary detection to character areas, identifying precise boundaries for each character region. This approach maintains reliability by ensuring all intended characters are included while achieving measurement precision by excluding adjacent symbols through careful boundary definition in specific local regions.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

By segmenting the character area into discrete character regions with clearly defined boundaries, the system achieves both completeness and precision. Each segment represents a specific character or character group, allowing the system to include all necessary characters while excluding adjacent symbols through precise segment boundary management.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10395131B2Apparatus, method and non-transitory storage medium for changing position coordinates of a character area stored in association with a character recognition result

Publication Date: 2019.08.27 CANON KK

AI summary

In the case where a user extracts a desired character string by specifying a range by using a finger or the like of him/herself on an image including a character, a specific character (space or the like) located at a position adjacent to the desired character string is prevented from being included unintendedly in the selected range. The character area corresponding to each character included in the image is identified and character recognition processing is performed for each of the identified character areas. Then, from results of the character recognition processing, a specific character is determined and the character area corresponding to the determined specific character is extended. Then, the range selected by the user in the displayed image is acquired and character recognition results corresponding to a plurality of character areas included in the selected range are output.