Defect Inspection System Using Pseudo Defect Images for Automated Parameter Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current semiconductor defect detection systems require manual adjustment of process parameters, which is labor-intensive and skill-dependent, and struggle with accurate defect detection in low SNR images, leading to reduced defect detection rates.
Innovation Solution
A defect inspecting system that automatically adjusts process parameters by generating pseudo defect images and using image quality enhancement techniques to improve detection accuracy, allowing for fully automated defect site identification without relying on user instruction or high SNR images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustment of process parameters is performed, then defect detection accuracy can be optimized, but user workload and skill dependence increase
Solution Approach 1:
The system performs self-adjustment of process parameters by automatically analyzing inspection images and reference images to determine optimal detection parameters. The parameter determination unit automatically selects and adjusts parameters without requiring manual intervention, enabling the system to serve itself and eliminate dependency on user skill level.
Solution Approach 2:
The system automatically changes process parameters by analyzing image characteristics and dynamically determining optimal detection parameters. The parameter determination unit modifies parameters such as detection thresholds and image processing settings based on automated analysis of the actual inspection images and reference images, eliminating the need for manual parameter adjustment.
2Measurement precision
If trial and error method is used for parameter adjustment, then detection accuracy can be improved, but time consumption increases
Solution Approach 1:
The system performs preliminary analysis by automatically analyzing inspection images and reference images before final parameter determination. The parameter determination unit pre-processes images to extract characteristics and pre-determines optimal parameters, eliminating the need for time-consuming trial and error adjustments during the actual detection process.
Solution Approach 2:
The system replaces the mechanical trial-and-error adjustment process with an automated computational approach. Instead of manual iteration, the parameter determination unit uses image analysis algorithms to automatically calculate optimal parameters, substituting human-based mechanical adjustment with automated digital processing that is both faster and more consistent.
3Measurement precision
If detection parameters are adjusted for specific defect types, then detection accuracy improves, but adaptability to various defect appearances decreases
Solution Approach 1:
The parameter determination unit performs universal analysis by processing both inspection images and reference images through the same automated pipeline. This multi-functional approach allows the system to adapt to various defect types and appearances using a single unified parameter determination method, eliminating the need for separate adjustment procedures for different defect categories.
Solution Approach 2:
The system uses feedback from analyzing both inspection images and reference images to automatically determine optimal parameters. The parameter determination unit receives feedback from the image analysis process and continuously adjusts parameters based on the actual image characteristics, enabling adaptive detection across various defect types without manual reconfiguration.
Data Source
AI summary
A defect inspecting system includes a detector configured to image a sample and a host control device that acquires an inspection image including a defect and a plurality of reference images not including a defect site and generates a pseudo defect image by editing a predetermined reference image among the plurality of acquired reference images. An initial parameter is determined with which the pseudo defect site is detectable from the pseudo defect image. The host control device acquires a defect candidate site from the inspection image using the initial parameter, estimates a high-quality image from an image of a site corresponding to the defect candidate site using the parameter acquired in image quality enhancement, and specifies an actual defect site in the inspection image by executing defect discrimination. A parameter is determined with which a site close to the specified actual defect site is detectable using the inspection image.