Defect Reference Image Generation for Inspection Consistency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In structure inspection, maintaining consistent defect determination criteria is challenging due to variations in material and environmental factors, leading to inefficiencies in time and labor, as existing methods require extensive preparation of reference images and parameters.

Innovation Solution

An information processing apparatus that displays target and reference images side by side, allowing users to specify defects and adjust display parameters to match the appearance, generating new reference images based on user input for consistent defect determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If reference images and parameters are prepared in advance for each type and degree of abnormal portion, then consistent defect determination can be achieved, but time and labor for preparation increase significantly

Engineering Contradiction:

Improveconsistency of defect determinationVSAvoidpreparation time and labor

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system automatically generates reference images by capturing actual defect portions from inspected objects and storing them in the reference image storage unit. This self-service mechanism eliminates the need for manual preparation of reference images for each defect type, as the system builds its own reference library from real inspection data, thereby maintaining consistency while reducing preparation time and labor

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary capture and storage of defect portions during the inspection process itself. By capturing images of actual defects and storing them as reference images before subsequent inspections, the system prepares reference materials in advance automatically, enabling consistent defect determination without manual intervention for each new defect type

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If multiple reference images are prepared for different defect types and degrees, then accurate defect determination is possible, but the complexity of managing reference images increases

Engineering Contradiction:

Improveaccuracy of defect determinationVSAvoidcomplexity of reference image management

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The defect determination unit uses a universal approach by comparing captured images against stored reference images of actual defects. Instead of requiring separate management systems for different defect types, the same comparison mechanism handles all defect types and degrees by matching against the appropriate reference images from the unified storage, thereby reducing management complexity while maintaining determination accuracy

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system creates copies of actual defect portions from inspected objects and stores them as reference images. These copied images serve as templates for future comparisons, allowing accurate defect determination through image matching without requiring complex manual classification and management of reference materials for each defect category

Inventive Principle:

Principle #26Copying

3Reliability

If manual inspection and comparison of images is performed, then defect determination can be made, but productivity decreases due to the huge amount of images to check

Engineering Contradiction:

Improvedefect determination capabilityVSAvoidinspection speed and efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system replaces the mechanical process of manual image inspection and comparison with automated image processing. The defect determination unit automatically compares captured images against stored reference images using computational algorithms, eliminating the need for inspectors to manually examine huge numbers of images, thereby maintaining reliable defect detection while dramatically improving inspection productivity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements feedback by storing actual defect images captured during inspection as reference images for future comparisons. This creates a self-improving loop where each inspection contributes to enhancing the reference library, allowing the system to become progressively more accurate and efficient at identifying defects without increasing manual workload, thus improving both reliability and productivity

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11430107B2Information processing apparatus, information processing method, and non-transitory computer readable medium

Publication Date: 2022.08.30 CANON KK

AI summary

An information processing apparatus for supporting a user's task for identifying a defect in an object based on a target image that is a photographed image of the object, includes: a selecting unit that selects, based on an user's input, one from one or more reference images to which is referred by the user for identifying a defect in the object; a display unit that comparably displays the target image and the selected reference image on a certain display device; a specifying unit that receives an user's operation for specifying a defect in the target image displayed by the display unit; and a generating unit that generates a new reference image based on a partial area, of the target image, including the specified defect. A new reference image generated by the generating unit is added to the one or more reference images selectable by the selecting unit.