Image Comparison Device Using Feature Point Misalignment Allowable Ranges

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current image comparison technologies, such as distance transform and elastic matching, face challenges in accurately matching variable-shape objects due to limitations in allowing shape deformation and feature point correspondence, leading to false matching and inability to consider detailed shape changes.

Innovation Solution

The proposed solution involves an image comparison device that allows for fine adjustments in positional and directional misalignment of feature points, enabling more accurate comparison of variable-shape objects by setting allowable ranges for positional and luminance gradient direction misalignments, which can be rectangular, circular, or elliptical, and allowing different misalignment angles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If distance transform is used to allow edge position coordinate flexibility, then matching adaptability is improved, but false matching increases due to lack of deformation control

Engineering Contradiction:
Improvematching adaptabilityVSAvoidmatching accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The invention changes the parameters of edge point matching by introducing two new parameters: positional misalignment allowable amount and directional misalignment allowable amount. These parameters control the flexibility of matching, allowing the system to adapt to shape variations while maintaining accuracy by constraining deformation within specified limits.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The invention makes the matching criteria dynamic by allowing different misalignment allowable amounts for different edge points and different directions. This dynamic approach enables the system to adapt to local shape variations while maintaining overall matching accuracy, resolving the contradiction between adaptability and reliability.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If elastic matching is used to ensure strict feature point correspondence, then matching precision is improved, but applicability is reduced to only objects with clear feature points

Engineering Contradiction:
Improvematching precisionVSAvoidobject applicability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The invention applies local quality by allowing different misalignment allowable amounts for different edge points based on their local characteristics. This enables strict correspondence where needed while providing flexibility where objects vary in shape, expanding applicability to various object types including those without clear feature points.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

By introducing adjustable misalignment allowable amount parameters, the invention transforms elastic matching from a rigid strict-correspondence method into a flexible system that can adapt to different object types while maintaining precision where required.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If fine allowable scale is provided for shape change to improve matching accuracy, then matching precision is improved, but device complexity increases

Engineering Contradiction:
Improvematching accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The invention achieves fine control over shape change allowance by introducing misalignment allowable amount parameters rather than complex deformation models. This parameter-based approach provides fine matching accuracy while keeping the processing relatively simple by avoiding complex mathematical transformations.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3096289B1Image comparison device, image sensor, processing system, and image comparison method
Publication Date: 2019.09.04 OMRON CORP
  • EP3096289B1 patent drawingFigure 1~2
  • EP3096289B1 patent drawingFigure 3
  • EP3096289B1 patent drawingFigure 4

AI summary

An image comparison device includes: a storage in which a model image is stored, the model image including a position of a feature point of a comparison object and a luminance gradient direction at the position of the feature point; a feature amount acquisition unit configured to acquire the position of the feature point and the luminance gradient direction at the position of the feature point from an input image; and an image comparison unit configured to compare the model image and the input image. The image comparison unit performs image comparison by providing an allowable range in both the position of the feature point and the luminance gradient direction at the position of the feature point position. Preferably the image comparison device further includes an allowable range setting unit configured to cause a user to set the allowable range of the position of the feature point and the allowable range of the luminance gradient direction at the position of the feature point in the image comparison. Therefore, comparison of a variable shape object can be performed while an allowable shape change is finely specified.