Evaluation method, search method, and search system
The area and distance methods provide a quantitative evaluation of cross-sectional shapes in microscopic images, addressing the subjectivity of manual grading and enabling efficient machine learning applications.
JP7874129B2Active Publication Date: 2026-06-15HITACHI HIGH TECH CORP
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- HITACHI HIGH TECH CORP
- Filing Date
- 2024-06-20
- Publication Date
- 2026-06-15
AI Technical Summary
⚠Technical Problem
Existing methods for evaluating the shape of patterns in microscopic images, such as those used in semiconductor manufacturing, are subjective and lack accuracy due to reliance on manual grading and qualitative assessments, which are not suitable for machine learning analysis.
⚗Method used
A method involving two quantitative approaches, the area and distance methods, to evaluate the shape of cross-sectional images by comparing them to a normalized template, using dimensionless indices to quantify the difference between the target and ideal shapes.
🎯Benefits of technology
Enables accurate, objective evaluation of cross-sectional shapes, allowing for efficient machine learning applications and reducing the complexity of optimizing processing conditions.
✦ Generated by Eureka AI based on patent content.
Abstract
To provide a technique for evaluating a shape that appears in a cross-sectional image.SOLUTION: One of the typical evaluation methods of the present invention evaluates a difference between a target shape and a cross-sectional shape of an electron microscopic image, and includes: a first step of measuring a characteristic dimension of the cross-sectional shape; after the first step, a second step of creating a template of the target shape in the cross-sectional shape obtained from the dimension; and a third step of comparing a difference between the template and the cross-sectional shape using a normalized index.SELECTED DRAWING: Figure 4
Need to check novelty before this filing date? Find Prior Art