Layout Analysis Method for Text Line Ordering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing layout analysis methods for images are slow due to their reliance on original image processing, which hinders efficient text recognition and ordering in images, particularly for visually impaired assistance applications.

Innovation Solution

A layout analysis method that obtains coordinate information of text lines, creates a layout model, and analyzes the layout structure based on this information to determine the order of text lines, without requiring semantic analysis or operation on the original image, allowing for faster and more efficient text recognition and ordering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If layout analysis is performed based on original image processing, then analysis accuracy is maintained, but processing speed becomes slow

Engineering Contradiction:
Improveprocessing speedVSAvoidlayout analysis accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The patent creates a simplified layout model that copies only the essential coordinate information of text lines from the original image, rather than processing the complete image data. This selective copying approach maintains the necessary spatial relationships for accurate layout analysis while dramatically reducing processing complexity and time requirements.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent extracts only the coordinate information of text lines from the original image, separating this critical data from the rest of the image content. By taking out only the necessary spatial parameters (coordinates, width, height) and discarding redundant pixel data, the system achieves fast processing without sacrificing layout analysis accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If comprehensive image processing is performed, then text recognition accuracy is improved, but processing time increases

Engineering Contradiction:
Improvetext recognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the image processing task into two distinct phases: first, extracting coordinate information of text lines from the original image; second, analyzing the layout structure using only this extracted coordinate data. This segmentation allows the system to perform accurate text recognition through coordinate-based analysis without the time-consuming processing of complete image data.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary extraction of text line coordinate information before conducting the main layout analysis. This preliminary action prepares a simplified data structure that contains all necessary spatial relationships, enabling the subsequent layout analysis to proceed rapidly without needing to re-process the original image data.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3940589B1Layout analysis method, electronic device and computer program product
Publication Date: 2023.10.25 NEXTVPU (SHANGHAI) CO LTD
  • EP3940589B1 patent drawingFigure 1
  • EP3940589B1 patent drawingFigure 2
  • EP3940589B1 patent drawingFigure 3

AI summary

A layout analysis method, an electronic device, and a computer program product are provided. The layout analysis method includes: obtaining coordinate information of a plurality of text lines in an image; creating a layout model of the image according to the coordinate information; analyzing a layout structure of the text lines based on the layout model; and determining an order of the text lines relative to each other based on the layout structure.