Wafer Defect Detection Using Geometric Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wafer inspection systems face challenges in detecting defects, particularly in array areas, due to limitations in stage accuracy and resolution, and manual setup of regions of interest becomes impractical as design rules shrink, leading to inefficient defect detection and nuisance noise issues.
Innovation Solution
A computer-implemented method that acquires raw output from a wafer using multiple optics modes, identifies geometrical characteristics, assigns individual output to different segments, and applies specific defect detection parameters to each segment to enhance defect detection, allowing for automatic segmentation and improved sensitivity across different geometrical patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual setup of regions of interest is used, then defect detection can be performed, but it becomes impossible as design rules shrink and stage accuracy limitations increase
Solution Approach 1:
The system automatically identifies and segments regions of interest based on image characteristics without requiring manual user input. The algorithm analyzes the raw output images, detects geometric patterns, and autonomously defines segmentation regions, allowing the system to serve itself rather than requiring operator intervention for setup.
Solution Approach 2:
The patent divides the wafer image into multiple segments based on geometric characteristics and pattern recognition. By segmenting the image into distinct regions with different geometric properties, the system can apply appropriate detection parameters to each segment automatically, resolving the contradiction between precision and ease of operation.
2Productivity
If the same set of parameters is applied for defect detection in all regions, then simplicity is maintained, but detection sensitivity decreases for specific geometric patterns
Solution Approach 1:
The system applies different defect detection parameters to different segments of the wafer image based on their geometric characteristics. Each segment receives customized detection parameters optimized for its specific pattern type, improving local detection sensitivity while maintaining overall efficiency through automated parameter assignment.
3Ease of operation
If intensity-based segmentation is used, then similar intensity pixels are grouped together, but it fails when geometry features scatter uniformly
Solution Approach 1:
The patent changes the segmentation parameter from intensity-based to geometry-based characteristics. By analyzing geometric properties such as shape, orientation, and spatial arrangement rather than just intensity values, the system can accurately segment regions even when intensity varies uniformly, improving segmentation accuracy while maintaining operational simplicity through automated geometric analysis.
Data Source
AI summary
Methods and systems for detecting defects on a wafer are provided. One method includes identifying one or more characteristics of first raw output generated for a wafer that correspond to one or more geometrical characteristics of patterned features formed on the wafer and assigning individual output in second raw output generated for the wafer to different segments based on the identified one or more characteristics of the first raw output and based on the individual output in the second raw output and individual output in the first raw output that were generated at substantially the same locations on the wafer such that the one or more geometrical characteristics of the patterned features that correspond to each of the different segments in the second raw output are different.