Extraction of Feature Lines for 3D Model Based on Conditional Random Fields

ZHANG Yao-ye; SUN Zheng-xing; LIU Kai; SONG Mo-fei; ZHANG Fei-qian

doi:10.3969/j.iss.0372-2012-2014.03.012

您当前的位置：

首页 >

文章列表页 >

Extraction of Feature Lines for 3D Model Based on Conditional Random Fields

更新时间：2025-07-16

- Extraction of Feature Lines for 3D Model Based on Conditional Random Fields
- Acta Electronica Sinica Vol. 42, Issue 3, Pages: 498-504(2014)
- 作者机构：
  
  南京大学计算机软件新技术国家重点实验室,江苏,南京,210046
- 作者简介：
- 基金信息：
- DOI：10.3969/j.iss.0372-2012-2014.03.012
  CLC： TP391
- Published：2014
- 稿件说明：
移动端阅览
ZHANG Yao-ye, SUN Zheng-xing, LIU Kai, et al. Extraction of Feature Lines for 3D Model Based on Conditional Random Fields[J]. Acta Electronica Sinica, 2014, 42(3): 498-504.
DOI：

ZHANG Yao-ye, SUN Zheng-xing, LIU Kai, et al. Extraction of Feature Lines for 3D Model Based on Conditional Random Fields[J]. Acta Electronica Sinica, 2014, 42(3): 498-504. DOI： 10.3969/j.iss.0372-2012-2014.03.012.

摘要

本文提出了一种草图指导的三维模型特征线提取方法，该方法特点在于：一方面，建立了笔画采样点与模型特征线点间的条件随机场匹配模型，将模型几何特征与形状相似性结合匹配，实现了草图信息与模型特征线提取的有效融合；另一方面，提出了基于结构相似性的模型特征线度量机制，并采用迭代优化方法实现了全局最优模型特征线的提取.实验结果表明：本文提出的方法能有效获取与草图结构形状相对应的模型特征线绘图.

Abstract

This paper proposed a 3D model feature lines extracting method guided by user's sketch.There are two main contributions of our method:on the one hand

a conditional random fields(CRF)-matching model with geometric features and shape similarity between stroke points and candidate feature points is established

and the user drawing purpose is combined with the model feature lines extraction effectively;on the other hand

a topological similarity based metrics is proposed to evaluate the rationality of extracted feature lines

and an iterative optimization process is applied to obtain global optimized model feature lines.The experimental results show that our method is efficient to extract reasonable 3D model feature lines which are similar to sketch strokes on shape and topological properties.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

MAP-Based Multi-Information Flow Gradient Update and Aggregation for Video Compressed Sensing Reconstruction

Study on the Chinese Named Entity Recognition Using Small Scale Character Tail Hints

Two-Stage Localization Algorithm Based on Greedy Idea for Wireless Sensor Networks

Automatic Abstraction of Image Sequences for Real-Time Visual Communication

Automatic Recognition of Chinese Organization Name Based on Cascaded Conditional Random Fields

Related Author

YANG Xin

YANG Chun-ling

LI Wen-bo

ZHANG Da-kun

SUN Le

FENG Yuan-yong

ZHAO Hong

WEN Ying-you

Related Institution

School of Electronic and Information Engineering， South China University of Technology

Graduate University of Chinese Academy of SciencesBeijing 100080China

Guangzhou UniversityGuangzhouGuangdong510006China

Institute of SoftwareChinese Academy of SciencesBeijing 100080China

Graduate University of Chinese Academy of Sciences

⁰