Reflection Symmetry Axis Detection Based on Improved Mean-Standard Deviation Curve Descriptor

LIU Hong-min; XIONG Wen-jun; ZHAO Wei; WANG Zhi-heng; WANG Jing

doi:10.3969/j.issn.0372-2112.2017.07.021

您当前的位置：

首页 >

文章列表页 >

Reflection Symmetry Axis Detection Based on Improved Mean-Standard Deviation Curve Descriptor

更新时间：2025-07-16

- Reflection Symmetry Axis Detection Based on Improved Mean-Standard Deviation Curve Descriptor
- Acta Electronica Sinica Vol. 45, Issue 7, Pages: 1701-1706(2017)
- 作者机构：
  
  1. 河南理工大学计算机科学与技术学院,河南,焦作,454000
  3. 西安电子科技大学计算机学院,陕西,西安,710071
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61272394, No.61472119, No.61572173, No.61472373, No.61401150);Innovative Research Team of Henan Polytechnic University (No.T014-3);Outstanding Youth Fund of Henan Polytechnic University (No.J2016-3)
- DOI：10.3969/j.issn.0372-2112.2017.07.021
  CLC： TP37
- Published Online：25 July 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
LIU Hong-min, XIONG Wen-jun, ZHAO Wei, et al. Reflection Symmetry Axis Detection Based on Improved Mean-Standard Deviation Curve Descriptor[J]. Acta Electronica Sinica, 2017, 45(7): 1701-1706.
DOI：

LIU Hong-min, XIONG Wen-jun, ZHAO Wei, et al. Reflection Symmetry Axis Detection Based on Improved Mean-Standard Deviation Curve Descriptor[J]. Acta Electronica Sinica, 2017, 45(7): 1701-1706. DOI： 10.3969/j.issn.0372-2112.2017.07.021.

摘要

针对反射对称轴难以检测的问题，该文提出一种基于改进均值标准差曲线描述子（Mean-Standard deviation Curve Descriptor，MSCD）的反射对称轴检测算法.该算法首先对MSCD曲线描述子进行改进，使其具有镜像反射不变性并实现对称曲线对检测；然后采用距离约束并使用Hough变换获取图像的局部对称轴；最后通过局部对称轴合并得到最终对称轴.实验结果表明，该算法可实现图像的单对称轴和多对称轴检测，在亮度变化、对比度变化、噪声污染、模糊以及形变情况下，均能够准确定位图像对称轴并具有较强鲁棒性.

Abstract

Due to the difficulty in detecting reflection symmetry axis

a detection algorithm based on improved mean-standard deviation curve descriptor (MSCD) is proposed.Firstly

the proposed algorithm improves the MSCD so that its mirror reflection invariance can guarantee the accurate detection of the symmetrical curve pairs.Then the distance constraint and Hough transform is used to gain local symmetry axis of the image.Finally

final symmetry axis can be acquired by merging the local ones.Experimental results show that the proposed algorithm can realize the symmetric axis detection for image with both single symmetric axis and multi ones.Besides

it can locate the image symmetry axis precisely and robustly under brightness changes

contrast changes

noise pollution

fuzzy and deformations.

关键词

Keywords

references

Views

227

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Matching of 3D Curve Based on the Hash Method

A New Curve Matching Method Based on Membrane Vibration Model

Related Author

LU Ke

GENG Guo-hua

ZHOU Ming-quan

ZHANG Gui-mei

MA Ke

CHU Jun

Related Institution

Dept.of computer science,Northwest University

School of Network Education,Ningxia University

Dept.of computer scienceNorthwest UniversityXi'anShaanxi 710069China

School of Network EducationNingxia UniversityYinchuanNingxia 750021China

Institute of Computer Vision Nanchang Hang kong University

⁰