A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation

ZHAO Xiao-qiang; YUE Zong-da

doi:10.3969/j.issn.0372-2112.2017.09.015

您当前的位置：

首页 >

文章列表页 >

A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation

更新时间：2025-07-16

- A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation
- Acta Electronica Sinica Vol. 45, Issue 9, Pages: 2156-2161(2017)
- 作者机构：
  
  兰州理工大学电气工程与信息工程学院,甘肃,兰州,730050
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.51265032, No.61263003)
- DOI：10.3969/j.issn.0372-2112.2017.09.015
  CLC： TG156
- Published Online：25 September 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
ZHAO Xiao-qiang, YUE Zong-da. A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation[J]. Acta Electronica Sinica, 2017, 45(9): 2156-2161.
DOI：

ZHAO Xiao-qiang, YUE Zong-da. A Fast Matching Algorithm Based on Local Binary Patterns and Graph Transformation[J]. Acta Electronica Sinica, 2017, 45(9): 2156-2161. DOI： 10.3969/j.issn.0372-2112.2017.09.015.

摘要

针对图像匹配在图像拼接、目标识别等领域的应用中尺度不变特征变换（Scale Invariant Feature Transform，SIFT）算法计算复杂度高、实时性较差的问题，提出了一种基于局部二进制模式（Local Binary Patterns，LBP）和图变换（Graph Transformation Matching，GTM）的匹配算法.首先采用SIFT特征检测提取特征点并以特征点为中心取1313的图像块作为特征区域；然后用本文提出的局部旋转不变二进制模式（Local Rotation Invariant Binary Patterns，LRIBP）描述子对特征区域进行描述产生29维的特征描述向量，降低了描述子的复杂度，并以欧氏距离为度量准则进行初始匹配；最后采用图变换匹配算法剔除误匹配点，从而提高算法的运算速率和匹配精度.仿真结果表明，本文所提算法不仅具有较高的精度和较强的鲁棒性，并且减少了算法的运算量，提高了算法的实时性.

Abstract

Aiming at problems of large computation and poor real-time of scale invariant feature transform (SIFT) algorithm for image matching application in image matching

object recognition and other fields

a matching algorithm based on local binary patterns (LBP) and graph transformation matching (GTM) is proposed.Firstly

SIFT is used to extract initial feature points.1313 pixel blocks around the feature points are used as the feature regions.Secondly

in order to reduce complexity of descriptors

the local rotation invariant binary patterns (LRIBP) descriptor is used to produce feature vectors of 29 dimensions for a feature region.Euclidean distance is adopted as measure criterion of the descriptors to fulfil initial match.Finally

GTM is adopted to eliminate mismatching points.Simulation results show that the proposed algorithm not only improves accuracy and robustness and real-time

but also reduces the amount of calculation.

关键词

Keywords

references

Views

433

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Aerospace Heterogeneous Image Matching Algorithm Based on Improved SuperPoint

A Review of Vision-Based UAV Localization and Navigation Methods

A New Non-Rigid Image Matching Algorithm Using Thin-Plate Spline

Research on Registration Accuracy of Distance Transformation Matching Method for Geometrically Distorted Scene Images

Related Author

HUANG Kun

WU Guo-qiang

JIANG Liang

LIU Geng-chen

ZHENG Jin

BAI Xiao

ZHANG Jia-wei

LI Hang

Related Institution

Aerospace Times Feihong Technology Limited Company

China Aerospace Science and Technology Corporation Limited Intelligent Unmanned System Overall Technology Research and Development Center

China Aerospace Science and Technology Corporation 9th Institute

School of Mechanical and Electrical Engineering, Beijing Institute of Technology

School of Computer,Beihang University

⁰