Automated Micro Defect Detection via Illumination and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for detecting micro defects on surfaces are time-consuming, inconsistent, and may damage the object, requiring significant manual effort and lengthy detection times due to the small scale of defects.
Innovation Solution
A system and method utilizing a combination of ambient and dark field illumination sources, image processing techniques, and machine learning classifiers to detect and classify potential defects on an object's surface, allowing for automated detection of micro defects as small as micrometers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual detection methods are used, then detection accuracy may be achieved for micro defects, but detection time becomes considerably long and quality consistency deteriorates
Solution Approach 1:
The patent replaces manual mechanical detection with an automated optical imaging system. The imaging device captures images of the object surface under controlled illumination, and image processing algorithms automatically identify and classify defects, eliminating manual inspection and achieving both high accuracy and rapid detection.
Solution Approach 2:
The patent creates optical copies (images) of the object surface for analysis. By capturing visual representations and processing these copies through algorithms, the system can detect micro defects without physically manipulating or damaging the original object, enabling rapid repeated inspections.
2Reliability
If traditional detection methods are used, then detection can be performed, but quality consistency of detection deteriorates due to manual process variability
Solution Approach 1:
The patent substitutes variable manual operations with a standardized automated image processing system. The same imaging device and processing algorithms are applied consistently to all samples, eliminating human variability and ensuring reliable, repeatable detection results.
Solution Approach 2:
The system performs self-service through automated image capture and processing. The imaging device and processing algorithms independently complete the detection task without requiring skilled operators, ensuring consistent quality and reducing operational complexity.
3Difficulty of detecting and measuring
If chemicals are applied for defect detection, then detection capability is enhanced, but harmful factors are generated that may damage the object
Solution Approach 1:
The patent replaces chemical detection methods with optical imaging. The imaging device captures visual information about surface defects using light, and image processing algorithms analyze these images to identify defects, eliminating the need for harmful chemicals while maintaining or improving detection capability.
Solution Approach 2:
The patent uses optical copies (images) to detect defects without physical or chemical contact with the object. This non-contact approach allows defect detection while preserving the object's integrity, avoiding damage from chemical applications.
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 provides efficient, accurate, and consistent detection of micro defects, reducing detection time and manual effort while avoiding damage to the object, with higher accuracy and cost-effectiveness compared to traditional methods.
Implementation Method 1
illumination conditions with the illumination sources using an imaging device
Implementation Method 2
at least one dark field illumination source for illuminating the surface of the object
Data Source
AI summary
Method and system for detecting defects on surface of object are presented. An imaging device captures images of surface of object under ambient and dark field illumination conditions. The images are processed with a plurality of image operations to detect area of potential defect at location on surface of object based on predictable pattern consisting of bright and shadow regions. Kernels are defined corresponding to configurations of dark field illumination sources to enhance detecting potential defect. Areas of potential defect are cut from processed images to sub images. Sub images are stitched together to generate hypothesis of potential defect at location on surface of object. The hypothesis is classified with a classifier to determine whether the potential defect is true defect. The classifier is trained with training data having characteristics of true defect. The method provides efficient automated detection of micro defects on surface of object.