SEM图像轮廓提取方法、SEM图像轮廓优化方法及计算机介质
By calculating the mean and standard deviation of gray values in SEM images, defining confidence intervals and performing noise filtering, the problem of noise affecting contour extraction in SEM images is solved, achieving clearer and more accurate contour extraction.
CN115661180BActive Publication Date: 2026-07-17ORIENTAL CRYSTAL MICROELECTRONICS TECH (SHANGHAI) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ORIENTAL CRYSTAL MICROELECTRONICS TECH (SHANGHAI) CO LTD
- Filing Date
- 2022-11-03
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing techniques suffer from severe noise in SEM images, which significantly affects the accuracy of contour extraction. While traditional Gaussian convolution methods smooth the image, they also result in large errors.
Method used
By calculating the mean and standard deviation of the gray values of each pixel in the SEM image, a confidence interval is defined. Contours with mean values within the confidence interval are extracted, and optimization is performed based on the confidence interval and a noise filtering threshold to eliminate noise points.
Benefits of technology
It improves the clarity and accuracy of SEM image contour extraction, enhances noise filtering, and ensures that image points are not mistakenly eliminated.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115661180B_ABST
Abstract
本发明涉及SEM图像提取领域，特别涉及一种SEM图像轮廓提取方法、SEM图像轮廓优化方法及计算机介质，本发明的SEM图像轮廓提取方法，包括以下步骤：获取初始SEM灰度图像；统计SEM图像各像素点的灰度值，计算出各像素点灰度值的均值与标准差；将均值在基于标准差的预设可信范围内覆盖区域定义为置信区间；提取均值在置信区间内的SEM图像的轮廓作为第一次SEM图像提取轮廓。通过此方法，在置信区间外的像素点直接判断为噪声点，能直接在不影响图像点的情况下消除部分噪声点，大大提高了消除噪声的效率，进而使得轮廓能更清晰。
Need to check novelty before this filing date? Find Prior Art