Shape Context Descriptors for Semiconductor Feature Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current manufacturing processes for semiconductor devices face challenges in efficiently identifying and comparing features on substrates and patterning devices, particularly in terms of shape, which affects reproducibility and quality control.
Innovation Solution
The method involves creating shape context descriptors for features using a hardware computer, allowing for the identification of features with the same or similar shapes by analyzing the location of points on the perimeter of shapes within a shape context descriptor framework, and using clustering analysis to determine similarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional feature identification methods are used in semiconductor manufacturing, then the inspection process can be completed, but the efficiency and accuracy of identifying and comparing feature shapes is insufficient
Solution Approach 1:
The patent segments the feature identification process into distinct components: extracting shape context descriptors for individual features, clustering similar features based on their descriptors, and comparing clusters to identify defects. This segmentation allows parallel processing of multiple features simultaneously, improving inspection efficiency while maintaining high identification accuracy through specialized analysis at each stage.
Solution Approach 2:
The patent creates shape context descriptors that serve as abstract representations or 'copies' of the actual feature shapes. These descriptors capture the essential geometric characteristics without requiring direct manipulation of the original complex shape data, enabling efficient comparison and clustering operations while preserving measurement precision.
2Measurement precision
If detailed shape analysis is performed on all features, then identification accuracy improves, but processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary extraction of shape context descriptors for all features before the actual comparison and identification process. This preliminary action pre-processes the shape data into a standardized format that facilitates rapid subsequent clustering and matching operations, reducing the computational burden during critical inspection phases while maintaining detailed shape analysis capability.
Solution Approach 2:
The patent applies clustering analysis to group similar features together, performing detailed shape comparison primarily on representative features from each cluster rather than every individual feature. This partial action approach maintains high identification accuracy for critical features while reducing overall processing time by leveraging the similarity within clusters.
Data Source
AI summary
A method including selecting a shaped feature from a set of shaped features, each shaped feature of the set of shaped features having a set of points on a perimeter of the shape of the shaped feature, creating a plurality of shape context descriptors for the selected shaped feature, wherein each shape context descriptor provides an indication of a location in a shape context descriptor framework of a first focus point of the set of points in relation to a second point of the set of points, and identifying a shaped feature from the set of shaped features having a same or similar shape as the selected shaped feature based on data from the plurality of shape context descriptors.