计量学报2025，Vol.46Issue(5)：644-650,7.DOI:10.3969/j.issn.1000-1158.2025.05.04
基于嵌入特征优化的口腔点云异常区域分离
Precision Oral Point Cloud Abnormal Region Segmentation via Embedded Feature Optimization
摘要
Abstract
A method for separating abnormal regions in oral point clouds based on embedded feature optimization is proposed,where abnormal parts of each point cloud are removed while accurate parts are preserved.Firstly,2000 oral point cloud datasets are collected,and the abnormal regions to be removed are labeled,creating datasets for training,validation,and testing.Subsequently,an iterative optimization approach based on the Expectation-Maximization(EM)algorithm and the concept of contrastive learning is employed to enhance feature optimization in a point cloud denoising model,with training conducted over 200 iterations and results validated on the test set.Finally,quantitative analysis based on mean Intersection over union RmIoU and qualitative analysis based on point cloud visualization are used as evaluation metrics to compare the proposed method with several common point cloud segmentation and denoising models.The results demonstrate that the RmIoU of the method improved by 1.08%compared to other approaches,indicating superior performance in separating abnormal regions in oral point clouds.关键词
机械视觉测量/口腔点云/点云降噪/点云分割/数字化牙科/特征优化Key words
machine vision measurement/intraoral point cloud/point cloud denoising/point cloud segmentation/digital dentistry/feature optimization引用本文复制引用
李乐田,陈胜..基于嵌入特征优化的口腔点云异常区域分离[J].计量学报,2025,46(5):644-650,7.基金项目
国家自然科学基金青年基金(81101116) （81101116）
