CAD-Driven Shape Inspection With Filtered Reference Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automatic inspection systems for manufactured objects face challenges in extracting data from CAD files, matching measured data with reference data, calibrating camera position, and inspecting larger objects than the measuring surface.

Innovation Solution

A method and system using a digital camera and computing system to derive measured data from images, obtain reference data from CAD files, and compare them to generate compliance or non-compliance outputs, with features like filtering CAD data based on characteristics, aligning measured data with entities, and compensating for camera position changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is extracted from CAD files for inspection, then reference data for comparison is obtained, but data extraction complexity and errors increase

Engineering Contradiction:
Improvereference data accuracyVSAvoiddata extraction process
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a simplified digital copy of the CAD model specifically for inspection purposes. Instead of extracting and processing complex CAD data directly, the system generates a simplified digital representation that retains only the essential geometric features needed for measurement comparison, eliminating extraction complexity while maintaining reference data accuracy

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent extracts only the necessary geometric entities and measurement features from the CAD model, separating essential inspection data from unnecessary CAD complexity. This selective extraction of relevant geometric information reduces data processing complexity while preserving the accuracy needed for reliable inspection references

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If measured data is matched with reference data, then compliance determination is achieved, but data matching complexity increases

Engineering Contradiction:
Improvecompliance determination accuracyVSAvoiddata matching process
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the complex data matching process into distinct segments: feature extraction from measured data, feature extraction from reference data, feature pairing based on geometric relationships, and compliance evaluation. This segmentation of the matching process reduces overall complexity while maintaining precision through systematic comparison of corresponding features

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediate feature pairing step that acts as a mediator between measured and reference data. By establishing corresponding feature relationships through geometric invariants and transformations before final comparison, the system simplifies the matching process while ensuring accurate compliance determination

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If camera position is calibrated with measuring surface, then measurement accuracy is improved, but calibration time and complexity increase

Engineering Contradiction:
Improvemeasurement accuracyVSAvoidcalibration time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs camera calibration and establishes the transformation between camera coordinates and measuring surface coordinates before actual inspection. By pre-calibrating the system and storing the transformation parameters, the time-consuming calibration process is done once beforehand, enabling rapid subsequent inspections without repeating the full calibration procedure

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent transforms the calibration problem from a complex geometric alignment task into a parameter-based transformation. By representing camera position and orientation as adjustable parameters and using optimization algorithms to find the best fit, the system reduces calibration complexity and time while maintaining measurement precision

Inventive Principle:
Principle #35Parameter changes

4Adaptability or versatility

If objects larger than measuring surface are inspected, then inspection versatility is improved, but measurement accuracy deteriorates

Engineering Contradiction:
Improveinspection capabilityVSAvoidmeasurement accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent divides large objects into multiple measurable sections that can be inspected separately within the camera's field of view. By segmenting the inspection task into manageable portions and processing each section independently with full accuracy, the system maintains measurement precision while enabling inspection of objects larger than the measuring surface

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extends the inspection capability from two-dimensional measuring surface coordinates to three-dimensional object coordinates through coordinate transformation. By introducing the transformation matrix that maps between camera view and object coordinate systems, the system enables accurate measurement of large objects across multiple dimensions while maintaining precision

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS20250238918A1Inspection system and method
Publication Date: 2025.07.24 INSPECVISION LTD
  • US20250238918A1 patent drawing
  • US20250238918A1 patent drawing
  • US20250238918A1 patent drawing

AI summary

A method of inspecting an object using a digital camera and a computing system involves comparing measured shape data obtained from a digital image of the object with digital reference data representing a nominal shape of the object, and generating an output indicating compliance or non-compliance of the measured shape of the object to the nominal shape of the object. The reference data is extracted from a CAD file by filtering CAD data based on characteristics of the entities that define the object in the CAD data. The filtering may involve extracting entity data based on the characteristics or excluding entity data from extraction based the characteristics.