Image Processing Apparatus Contour Vertex Document Separation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional image processing apparatuses struggle to separate overlapping original documents during multi-cropping processing, often cutting them as a single document.

Innovation Solution

An image processing apparatus that extracts contour lines from scanned images, calculates vertices to identify document areas, and generates separate files for each document by forming rectangles from adjacent vertices, while deleting contained rectangles and calculating overlap to manage overlapping documents.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional multi-cropping processing is used to scan multiple documents at once, then scanning efficiency is improved, but overlapping documents cannot be separated and are cut out as a single document

Engineering Contradiction:
Improvescanning efficiencyVSAvoiddocument separation accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The patent segments the scanned image into multiple document regions by detecting contour lines and identifying vertices. The processor divides the image data based on geometric features (vertices forming rectangles) to separate overlapping documents, enabling each document to be extracted as an independent region even when they overlap in the scanned image.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If vertex extraction based on curvature calculation is implemented to identify document corners, then document area identification is improved, but processing complexity increases

Engineering Contradiction:
Improvevertex detection accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical or manual document separation methods with automated image processing algorithms. By using curvature calculation and geometric pattern recognition (identifying vertices that form rectangles), the system automatically separates documents without requiring manual intervention or complex physical mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Manufacturing precision

If rectangles are formed from vertices to define document boundaries, then document extraction accuracy is improved, but false detection of contained rectangles increases

Engineering Contradiction:
Improvedocument boundary accuracyVSAvoiddetection reliability
Core Design Contradiction:
Manufacturing precisionVSReliability

Solution Approach 1:

The patent performs preliminary actions by first detecting all potential vertices and forming candidate rectangles before final document identification. The system pre-processes the image data to identify geometric features, then uses these features to define document boundaries, ensuring accurate extraction while maintaining reliability through systematic verification of rectangle formation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3438930B1Image processing apparatus
Publication Date: 2022.02.16 KK TOSHIBA
  • EP3438930B1 patent drawingFigure 1~2
  • EP3438930B1 patent drawingFigure 3~4
  • EP3438930B1 patent drawingFigure 5~6

AI summary

An image processing apparatus comprises an interface through which scanned image data obtained by scanning a designated region, is acquired, and a processor. The processor extracts a contour line representing a document area from the scanned image data, extracts vertices of the contour line, determines whether a plurality of original documents is present in the document area based on the vertices, extracts document image data of each original document from the scanned image data, and generates a plurality of files, each of the files including document image data for one of the original documents.