Image Text Grouping for OCR Layer and Formatting Complexity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional optical character recognition techniques for digital images result in disjointed text recognition, excessive layer creation, and formatting complexities, requiring significant manual interaction and inefficient use of computational resources.
Innovation Solution
Digital image text grouping techniques automatically group text data based on similarity in font, color, size, and proximity using machine-learning models, enabling editing of text groups as a whole and reducing the number of layers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional optical character recognition techniques are used to identify and modify text in digital images, then text recognition is achieved, but the results are disjointed with excessive layer creation and formatting complexities
Solution Approach 1:
The patent merges multiple text elements that share common characteristics (font, color, size, proximity) into unified text groups. This combining approach reduces the number of separate layers needed and eliminates formatting complexities while maintaining accurate text recognition for each individual element within the group.
2Measurement precision
If conventional optical character recognition techniques are used to process digital images, then text identification is achieved, but significant manual interaction is required to correct results
Solution Approach 1:
The system performs self-correction by automatically grouping text elements with similar characteristics and applying consistent formatting rules. This self-service mechanism reduces the need for manual intervention to correct OCR errors and standardize text formatting across the digital image.
3Measurement precision
If conventional techniques process digital images with text modification needs, then text can be identified, but computational resources are used inefficiently
Solution Approach 1:
By grouping text elements that share characteristics into unified text groups, the system reduces the total number of processing operations needed. Instead of individually processing each text element, the system can apply transformations and corrections to entire groups simultaneously, significantly improving computational resource efficiency while maintaining accurate text detection.
Data Source
AI summary
Digital image text grouping techniques are described. A digital image depicting text is received and a plurality of items of text data are extracted from the digital image. A plurality of text characteristic data is detected, respectively, that is associated with the plurality of items of text data. At least one text group is generated that includes two or more of the plurality of items of text data. The text group is generated by determining similarity of the plurality of items of text data, one to another, based on the plurality of text characteristic data. The at least one text group is presented for display in a user interface.