Workpiece Inspection System Anomaly Classification for Defect Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Precision machine vision systems face challenges in accurately detecting defects in workpieces due to variations in workpiece types, surfaces, and changing inspection conditions, leading to reduced accuracy and reliability in defect detection.
Innovation Solution
A workpiece inspection system incorporating a light source, lens, camera, and processors that acquire training images to determine anomaly detector classification characteristics, allowing for the classification of images as anomalous or non-anomalous, and adjusting imaging conditions such as brightness and lens position to maintain accurate defect detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional machine vision systems are used to inspect workpieces, then the system structure is simple, but the defect detection accuracy decreases due to variations in workpiece types, surfaces, and changing inspection conditions
Solution Approach 1:
The system performs preliminary classification of images as anomalous or non-anomalous before conducting detailed defect detection. This preliminary action filters out images with abnormal imaging conditions (such as incorrect focus, exposure, or lighting) before they can affect defect detection accuracy, thereby improving overall measurement precision while adapting to various workpiece characteristics.
2Reliability
If the system adjusts imaging conditions to maintain accuracy, then the defect detection reliability improves, but the system complexity increases due to additional monitoring and adjustment mechanisms
Solution Approach 1:
The system implements a feedback mechanism where the anomaly detector continuously monitors imaging conditions and provides feedback to adjust imaging parameters. When anomalies are detected in run mode images (such as focus issues or lighting problems), the system automatically adjusts imaging conditions to maintain optimal defect detection reliability, creating a closed-loop control system that improves reliability through intelligent feedback rather than complex mechanical adjustments.
3Measurement precision
If training images are acquired and processed to determine anomaly detector classification characteristics, then the system can classify images as anomalous or non-anomalous improving accuracy, but the inspection time increases
Solution Approach 1:
The system applies partial action by first performing a quick anomaly classification on all images to identify only those that require detailed defect detection. By filtering out non-anomalous images early in the process, the system reduces the total inspection time while maintaining high classification accuracy for the subset of images that actually require thorough examination, rather than applying full defect detection analysis to every single image.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system enhances the accuracy and reliability of defect detection by classifying images as anomalous or non-anomalous, enabling adjustments to imaging conditions and maintaining robust performance despite variations in workpiece characteristics and inspection conditions.
Implementation Method 1
a light source, a lens, a camera... The lens inputs image light arising from a surface of a workpiece which is illuminated by the light source
Implementation Method 2
The lens inputs image light arising from a surface of a workpiece which is illuminated by the light source, and transmits the image light along an imaging optical path
Implementation Method 3
The camera receives imaging light transmitted along the imaging optical path and provides an image of the workpiece
Data Source
AI summary
A workpiece inspection and defect detection system includes a light source, a lens that inputs image light arising from a surface of a workpiece, and a camera that receives imaging light transmitted along an imaging optical path. The system utilizes images of workpieces acquired with the camera as training images to train a defect detection portion to detect defect images that include workpieces with defects. Anomaly detector classification characteristics are determined based on features of the training images. Run mode images of workpieces are acquired with the camera, and based on determined features from the images, the anomaly detector classification characteristics are utilized to determine if the images of the workpieces are classified as anomalous. In addition, the defect detection portion determines if images are defect images that include workpieces with defects and for which additional operations may be performed (e.g., metrology operations for measuring dimensions of the defects, etc.)