Machine Vision Measurement Marking for Multi-Field Precision Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing precision machine vision systems face challenges in achieving micron or sub-micron accuracy when measuring distances between features that exceed a single field of view, relying heavily on position encoders which results in less precise and reliable measurements.
Innovation Solution
A machine vision inspection system utilizing a measurement marking device that includes a stage, imaging system, and encoder-based measurement portion, operating in two states: one for encoder-based measurements and another for enhanced accuracy by acquiring images with measurement markings to determine distance based on relative positions and marking distances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If encoder-based measurement is used for distances exceeding single field of view, then measurement range is extended, but measurement precision deteriorates
Solution Approach 1:
A measurement marking device is introduced as an intermediary element between the imaging system and the workpiece. This device includes reference markings that serve as mediators for establishing spatial relationships across multiple fields of view, enabling accurate measurement of distances exceeding the single field of view capability
Solution Approach 2:
The measurement marking device creates a known reference copy or pattern that can be imaged across multiple fields of view. By capturing and analyzing the positions of these reference markings in sequential images, the system can calculate stage movement distances with higher precision than encoder-based methods alone
2Area of stationary object
If stage movement is used to capture multiple fields of view, then measurement capability is extended, but measurement reliability deteriorates
Solution Approach 1:
The system uses the measurement marking device to provide feedback on actual stage position and movement. By comparing the observed positions of reference markings against expected positions based on stage movement commands, the system can detect and correct for positioning errors, improving measurement reliability
Solution Approach 2:
The patent replaces reliance on mechanical encoder systems with an optical measurement approach using the measurement marking device. This substitution eliminates dependencies on mechanical positioning accuracy and encoder calibration, replacing them with optical field-of-view overlap analysis and reference marking position detection
Data Source
AI summary
A machine vision inspection system and method perform operations including: acquire a first image at a first image position, wherein the first image includes a first feature of a workpiece and a first measurement marking set of a measurement marking device (MMD); determine a first relative position of the first feature in the first image; move a stage supporting the workpiece to acquire a second image at a second image position, wherein the second image includes a second feature of the workpiece and a second measurement marking set of the MMD; determine a second relative position of the second feature in the second image; and determine a distance between the first feature and the second feature based at least in part on the first relative position, the second relative position and a distance between a measurement marking of the first set and a measurement marking of the second set.