An Improved FREAK Algorithm for Image Feature Point Matching

Ye Zhi-jian; Wang Fu-long

doi:10.12052/gdutxb.170034

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

An Improved FREAK Algorithm for Image Feature Point Matching

更新时间：2026-05-27

- An Improved FREAK Algorithm for Image Feature Point Matching
- Vol. 34, Issue 6, Pages: 37-42(2017)
- 作者机构：
  
  广东工业大学应用数学学院,广东,广州,510520
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.170034
  CLC： TP391
- Online First：09 November 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
叶志坚, 王福龙. 一种改进的FREAK算法的图像特征点匹配[J]. 广东工业大学学报, 2017, 34(6): 37-42.

Ye Zhi-jian, Wang Fu-long. An Improved FREAK Algorithm for Image Feature Point Matching[J]. 2017, 34(6): 37-42.
叶志坚, 王福龙. 一种改进的FREAK算法的图像特征点匹配[J]. 广东工业大学学报, 2017, 34(6): 37-42. DOI： 10.12052/gdutxb.170034.

Ye Zhi-jian, Wang Fu-long. An Improved FREAK Algorithm for Image Feature Point Matching[J]. 2017, 34(6): 37-42. DOI： 10.12052/gdutxb.170034.

摘要

由于FREAK算法存在不具备尺度不变性的缺陷

特征点匹配策略单一容易出现匹配效果不理想的问题

鉴于SIFT和RANSAC算法思想

本文提出一种改进的FREAK算法: SFREAK (SIFT and FREAK). 首先

生成高斯差分金字塔图像

使检测出来的特征点具有尺度不变性; 然后采用FREAK描述符对特征点进行描述

获得二进制描述子; 最后

在特征点匹配过程中通过Hamming距离匹配进行粗匹配

并结合RANSAC算法对匹配点对进行提纯

实现两幅图像的特征点匹配. 实验结果表明

本文提出的改进算法有效解决了FREAK不具备尺度不变性的缺陷

在图像发生尺度变化时

SFREAK算法特征点匹配准确率达到95.7%

相比于FREAK提高了61.9%. 另外

本文改进的算法与传统SIFT、FREAK算法相比，表现出更好的鲁棒性.

Abstract

FREAK algorithm has the defects of not having scale invariance and single feature point matching strategy

and being prone to unsatisfactory results. Based on SIFT and RANSAC algorithm

an improved FREAK algorithm is proposed: SFREAK (SIFT and FREAK). First of all

in the generation of Gauss differential Pyramid image

the feature points are detected with scale invariance; then the feature points are described with FREAK descriptor

obtaining binary descriptor; finally

in the process of feature points matching using Hamming distance matching for coarse matching

the matching points are purified with RANSAC algorithm

and the feature points of two images are matched. The experimental results show that the proposed algorithm can effectively solve the FREAK not having scale invariance in image scaling

and SFREAK algorithm for feature point matching accuracy rate reached 95.7%

increased by 61.9% compared with FREAK. Therefore

compared with the traditional SIFT algorithm and FREAK algorithm

the improved algorithm shows better robustness.

关键词

Keywords

references

FU C, DENG L, LU G, et al . Improved image matching based on fast retina keypoint algorithm [J ] . Computer Engineering and Applications, 2016, 52(19): 208-212.

XIE H, WANG S C, XIE W. Feature points matching in images based on improved FREAK [J]. Applied Science and Technology, 2016, 43(4): 35-40.

MORAVEC H P. Rover visual obstacle avoidance[C]//International joint conference on artificial intelligence.[S.l.]: Morgan Kaufmann Publishers Inc. 1981: 785-790.

HARRIS C G, STEPHENS M J. A combined corner and edge detector[C]//Alvey Vision Conference.[S.l.]: [s.n.] 1988: 147-151.

SMITH S M, BRADY J M. SUSAN—A new approach to low level image processing [J]. International Journal of Computer Vision, 1997, 23(1): 45-78.

ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection[M]//Computer Vision-ECCV 2006. Berlin: Springer Heidelberg, 2006: 430-443.

LOWE D G. Distinctive image features from scale-invariant key points [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

BAY H, ESS A, TUYTELAARS T, et al . Speeded-up robust features (SURF) [J ] . Computer Vision and Image Understanding, 2008, 110(3): 346-359.

CALONDER M, LEPTIT V, STRECDA C, et al. BRIEF: Binary robust independent elementary features[C]//European Conference on Computer Vision.[s.n.]: Springer-Verlag, 2010: 778-792.

RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: An efficient alternative to SIFT or SURF[C]//IEEE International Conference on Computer Vision.[S.l.]: IEEE, 2012: 2564-2571.

LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK: Binary robust invariant scalable keypoints[C]//International Conference on Computer Vision.[S.l.]:IEEE Computer Society, 2011: 2548-2555.

ORTIZ R. FREAK: Fast retina keypoint[C]//Computer Vision and Pattern Recognition.[S.l.]: IEEE, 2012: 510-517.

YANG Y K. Research on detection and matching algorithm of the BRISK feature point [J]. Product Technology, 2016(5): 77-80.

LU Y W, HU J. Research on medical image matching based on SIFT and SURF features [J]. China Medical Devices, 2016, 31(4): 40-44.

LI D L, LIU W. Object location for binocular stereo vision based on improved [J]. Journal of Guangdong University of Technology, 2017, 34(1): 90-94.

WANG C J, SUN T, CHEN J. Rapid scene matching based on FREAK descriptor [J]. Journal of Electronic Measurement and Instrumentation, 2015(2): 204-212.

CHEN T H, WANG F L, ZHANG B B. Image keypoints matching based on improved ORB and symmetrical match [J]. Computer Systems Applications, 2016, 25(5): 147-152.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Comparative Study of Close-Range Image Feature Points Matching Methods

Efficient Temporal Modeling for RGB-T Tracking

Modeling of 3D NAND Memory Cells with Taper Angle and Programming Strategy Optimization

Energy Management Strategy of Hybrid Locomotive Based on Road Condition Parameters

A Resource Allocation Optimization Method for Multi-UAV Integrated Sensing, Computing, and Communication Towards Disaster Relief

Related Author

Yu Jun-peng

Lin Jie-hong

Zhan Song-hui

Yao Nai-wen

Related Institution

School of Transportation and Traffic Engineering, Guangdong University of Technology

AI问答

⁰