Skew Correction Reference Point Selection for Scan Image Rotation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image forming apparatuses face challenges in accurately correcting skew in scan images, especially when detecting document boundaries is difficult, leading to content loss and increased complexity, particularly with varying document orientations and thick documents like books.

Innovation Solution

An image forming apparatus with a processor that detects skew angles by analyzing document boundaries and content gradients, allowing users to select detection methods and determining reference points for rotation to correct skew without losing content, and adjusts document orientations based on text region orientations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the entire content of the document is analyzed to detect skew angle, then the skew detection accuracy is improved, but the processing complexity is excessively increased

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

Solution Approach 1:

The patent extracts only the necessary portion of the document (boundary or specific content region) for skew detection rather than analyzing the entire document content. This extraction approach maintains accurate skew detection while significantly reducing processing complexity by focusing computational resources on relevant areas only.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the document analysis into distinct regions (boundary region or content region) and applies different detection strategies to each segment. By dividing the document into manageable segments with specific detection methods, the system achieves accurate skew detection without the computational burden of processing the entire document uniformly.

Inventive Principle:
Principle #1Segmentation

2Speed

If skew correction is performed without accurate boundary detection, then the processing speed is improved, but the document content is cut due to incorrect correction

Engineering Contradiction:
Improveprocessing speedVSAvoidcontent integrity
Core Design Contradiction:
SpeedVSManufacturing precision

Solution Approach 1:

The patent performs preliminary boundary detection and content region identification before executing skew correction. This preliminary action establishes accurate reference points and correction parameters in advance, ensuring that the subsequent skew correction maintains content integrity while proceeding efficiently without repeated adjustments.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary step that detects document boundaries and content regions to mediate between the skew correction process and the final output. This intermediary detection mechanism ensures accurate correction by providing reference information about document structure, preventing content cutting while maintaining processing efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple detection methods are provided for skew angle detection, then the adaptability to different document types is improved, but the device complexity is increased

Engineering Contradiction:
Improvedocument type adaptabilityVSAvoiddetection system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a dynamic detection system that automatically selects or switches between different detection methods (boundary-based detection and content-based detection) based on the characteristics of the input document. This dynamic adaptation allows the system to handle various document types effectively while managing complexity through intelligent method selection rather than maintaining all methods simultaneously active.

Inventive Principle:
Principle #15Dynamics

4Ease of manufacture

If the scan image is rotated around the center point for skew correction, then the correction process is simplified, but the document content is cut off

Engineering Contradiction:
Improvecorrection process simplicityVSAvoidcontent completeness
Core Design Contradiction:
Ease of manufactureVSManufacturing precision

Solution Approach 1:

The patent applies asymmetric correction by determining a reference point based on the actual document boundary or content region rather than using the geometric center of the scan image. This asymmetric approach adjusts the rotation center to match the document's actual structure, preventing content cutting while maintaining correction effectiveness. The asymmetry in reference point selection compensates for the simplicity of rotation transformation.

Inventive Principle:
Principle #4Asymmetry

Data Source

PatentEP3487159B1Image forming apparatus, scanned image correction method thereof, and non-transitory computer-readable recording medium
Publication Date: 2023.08.16 HEWLETT PACKARD DEVELOPMENT COMPANY LP
  • EP3487159B1 patent drawingFigure 1
  • EP3487159B1 patent drawingFigure 2
  • EP3487159B1 patent drawingFigure 3

AI summary

An image forming apparatus, a scan image correction method of an image forming apparatus, and a non-transitory computer-readable recording medium are provided. The image forming apparatus includes: a scan unit to scan a document to generate a scan image; and a processor to detect a skew angle of the scan image, determine a reference point on the basis of a position of a content in the scan image, and rotate the scan image around the determined reference point to correct the skew angle.