基于改进ORB-FLANN算法的工件图像识别方法

doi:10.16180/j.cnki.issn1007-7820.2024.04.008

电子科技 ›› 2024, Vol. 37 ›› Issue (4): 55-61.doi: 10.16180/j.cnki.issn1007-7820.2024.04.008

基于改进ORB-FLANN算法的工件图像识别方法

朱志浩¹, 鹿志旭¹, 郭毓², 高直³

1.盐城工学院电气工程学院,江苏盐城 224051
2.南京理工大学自动化学院,江苏南京 210000
3.盐城工学院信息工程学院,江苏盐城 224051

收稿日期:2022-11-02 出版日期:2024-04-15 发布日期:2024-04-19
作者简介:朱志浩(1984-),男,博士,讲师。研究方向:机器人控制、航天器编队控制、机器视觉。
鹿志旭(1996-),男,硕士研究生。研究方向:机器视觉。
郭毓(1964-),女,博士,教授。研究方向:智能机器人控制、机器视觉。
基金资助:
国家自然科学基金(61973167);盐城工学院校级科研项目(XJR2020041)

Workpiece Image Recognition Method Based on Improved ORB-FLANN Algorithm

ZHU Zhihao¹, LU Zhixu¹, GUO Yu², GAO Zhi³

1. School of Electrical Engineering,Yancheng Institute of Technology,Yancheng 224051,China
2. School of Automation,Nanjing University of Technology,Nanjing 210000,China
3. School of Information Engineering,Yancheng Institute of Science and Technology,Yancheng 224051,China

Received:2022-11-02 Online:2024-04-15 Published:2024-04-19
Supported by:
National Natural Science Foundation of China(61973167);University-Level Scientific Research Project of Yancheng Institute of Technology(XJR2020041)

摘要/Abstract

摘要：

针对传统图像识别算法匹配正确率低、运行时间较长等问题,文中提出了基于改进ORB-FLANN(Oriented FAST and Rotated BRIEF-Fast Library for Approximate Nearest Neighbors)的工件图像识别方法。对ORB算法特征描述、图像特征匹配算法进行修改,解决传统图像识别算法在图像存在尺度和旋转变换情况下存在的弊端并降低误匹配率。该方法对ORB算法检测到的特征点采用SURF(Speeded Up Robust Features)算法添加方向信息并完成特征描述,得到旋转尺度不变性的特征点,结合FLANN算法并引入双向匹配策略进行特征点粗匹配,最后利用渐进采样一致算法进一步剔除误匹配点对完成精匹配。实验结果表明,与其他方法相比,改进算法在处理尺度、旋转等变换图像时,匹配正确率分别提高了2.6%~18.8%和29.5%~43.9%,运行时长均在4 s以内,提高了对工件图像的识别效率和精准性。

关键词: 图像识别, ORB算法, SURF算法, FLANN算法, 双向匹配, 渐进采样一致, 匹配正确率, 工件图像

Abstract:

In view of the problems of low matching rate and long running time of traditional image recognition algorithms, an improved ORB-FLANN(Oriented FAST and Rotated BRIEF-Fast Library for Approximate Nearest Neighbors) based workpiece image recognition method is proposed. The feature description of ORB algorithm and image feature matching algorithm are modified to solve the disadvantages of traditional image recognition algorithm in the case of scale and rotation transformation and reduce the mismatching rate of matching. For the feature points detected by ORB algorithm, SURF (Speeded Up Robust Features) algorithm is used to add orientation information and complete the feature description, so as to obtain the feature points with rotation-scale invariance. FLANN algorithm is combined with bidirectional matching strategy for coarse matching of feature points. Finally, the progressive sampling-congruence algorithm is used to further eliminate the mismatched point pairs and complete the fine matching. The experimental results show that compared with other methods, the improved algorithm can improve the matching accuracy of 2.6%~18.8% and 29.5%~43.9%, respectively, when processing scale and rotation transform images, and the running time is within 4s, improving the efficiency and accuracy of workpiece image recognition.

Key words: image recognition, ORB algorithm, SURF algorithm, FLANN algorithm, bidirectional matching, PROSAC, rate of matching, workpiece image

中图分类号:

TP391

朱志浩, 鹿志旭, 郭毓, 高直. 基于改进ORB-FLANN算法的工件图像识别方法[J]. 电子科技, 2024, 37(4): 55-61.

ZHU Zhihao, LU Zhixu, GUO Yu, GAO Zhi. Workpiece Image Recognition Method Based on Improved ORB-FLANN Algorithm[J]. Electronic Science and Technology, 2024, 37(4): 55-61.

图/表 8

图1

图2

图3

图4

表1

图5

图6

表2

参考文献 18

[1]	刘正琼, 万鹏, 凌琳, 等. 基于机器视觉的超视场工件识别抓取系统[J]. 机器人, 2018, 40(3):294-300,308.
	Liu Zhengqiong, Wan Peng, Ling Lin, et al. Recognition and grabbing system for workpieces exceeding the visual field based on machine vision[J]. Robot, 2018, 40(3):294-300,308.
[2]	白丰, 张明路, 张小俊. 卫星装配中基于强区分性描述子的识别方法[J]. 仪器仪表学报, 2014, 35(12):2653-2662.
	Bai Feng, Zhang Minglu, Zhang Xiaojun. Identification method based on strong distinguishing descriptor in satellite assembly[J]. Chinese Journal of Scientific Instrument, 2014, 35(12):2653-2662.
[3]	姚锡凡, 蓝宏宇, 陶韬, 等. 基于云雾结合的工件深度学习识别问题研究[J]. 华南理工大学学报(自然科学版), 2019, 47(12):1-8. doi: 10.12141/j.issn.1000-565X.180161
	Yao Xifan, Lan Hongyu, Tao Tao, et al. Deep-learning recognition of workpieces based on cloud and fog computing[J]. Journal of South China University of Technology(Natural Science Edition), 2019, 47(12):1-8. doi: 10.12141/j.issn.1000-565X.180161
[4]	杨倩兰, 宋丽梅, 黄浩珍, 等. 面向集成制造的改进ORB图像匹配方法[J]. 计算机集成制造系统, 2022, 28(7):2242-2249.
	Yang Qianlan, Song Limei, Huang Haozhen, et al. Improved ORB image matching method for integrated manufacturing[J]. Computer Integrated Manufacturing System, 2022, 28(7):2242-2249.
[5]	Pang Y, Wei L, Yuan Y, et al. Fully affine invariant SU-RF for image matching[J]. Neurocomputing, 2012, 85(5):6-10. doi: 10.1016/j.neucom.2011.12.006
[6]	刘群坡, 席秀蕾, 杨凌霄. 基于LK光流和网格运动统计的图像匹配改进算法[J]. 电子科技, 2022, 35(5):1-6,13.
	Liu Qunpo, Xi Xiulei, Yang Lingxiao. Improved image matching algorithm based on LK optical flow ang grid motion statistics[J], Electronic Science and Technology, 2022, 35(5):1-6,13.
[7]	王招娣, 王贤立, 杨数强. 基于颜色和SURF特征的图像匹配算法[J]. 电子科技, 2017, 30(12):67-70.
	Wang Zhaodi, Wang Xianli, Yang Shuqiang. Image matching algorithm based on color and SURF feature[J]. Electronic Science and Technology, 2017, 30(12):67-70.
[8]	Bay H, Tuytelaars T, Van Gool L. Surf:Speeded up robust features[C]. Graz: The Ninth European Conference on Computer Vision, 2006:596-605.
[9]	Rublee E, Rabaud V, Konolige K, et al. ORB:An efficient alternative to sift or surf[C]. Barcelona: IEEE International Conference on Computer Vision, 2011:493-502.
[10]	赵璐璐, 耿国华, 李康, 等. 基于SURF和快速近似最近邻搜索的图像匹配算法[J]. 计算机应用研究, 2013, 30(3):921-923.
	Zhao Lulu, Geng Guohua, Li Kang, et al. Image matching algorithm based on SURF and fast approximate nearest neighbor search[J]. Application Research of Computers, 2013, 30(3):921-923.
[11]	Zhou J, Cheng X, Han R, et al. Image precise matching with illumination robust in vehicle visual navigation[J]. IEEE Access, 2020, 8(5):92503-92513.
[12]	Zou J, Wang X. A nearest neighbor search method for image matching based on ORB[J]. Journal of Information & Computational Science, 2015, 12(7):2691-2700.
[13]	钟鹏程, 李伟, 刘敬华. 基于改进的ORB算法的工件图像识别方法[J]. 机床与液压, 2020, 48(21):12-16. doi: 10.3969/j.issn.1001-3881.2020.21.003
	Zhong Pengcheng, Li Wei, Liu Jinghua. Workpiece image recognition method based on improved ORB algorithm[J]. Machine Tool & Hydraulics, 2020, 48(21):12-16.
[14]	王卫兵, 白小玲, 徐倩. SURF和RANSAC的特征图像匹配[J]. 哈尔滨理工大学学报, 2018, 23(1):117-121.
	Wang Weibing, Bai Xiaoling, Xu Qian. Features image matching SURF and RANSAC[J]. Journal of Harbin University of Science and Technology, 2018, 23(1):117-121.
[15]	陈文佑, 章伟, 史晓帆, 等. 一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法[J]. 电子科技, 2021, 34(12):62-67.
	Chen Wenyou, Zhang Wei, Shi Xiaofan, et al. A semidense 3D reconstruction ORB-SLAM algorithm with improved ORB feature matching[J]. Electronic Science and Technology, 2021, 34(12):62-67.
[16]	徐明, 刁燕. 基于SURF算子与FLANN搜索的图像匹配方法研究[J]. 现代计算机, 2020(14):49-52,57.
	Xu Ming, Diao Yan. Image matching method based on SURF operator and FLANN search[J]. Modern Computer, 2020(14):49-52,57.
[17]	任克强, 胡梦云. 基于改进SURF算子的彩色图像配准算法[J]. 电子测量与仪器学报, 2016, 30(5):748-756
	Ren Keqiang, Hu Mengyun. Color image registration algorithm based on improved SURF[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(5):748-756.
[18]	张志敏, 李彬, 田联房, 等. 基于SURF的改进FLANN匹配算法[J]. 计算机工程与设计, 2022, 43(4):941-948.
	Zhang Zhimin, Li Bin, Tian Lianfang, et al. Improved FLANN matching algorithm based on SURF[J]. Computer Engineering and Design, 2022, 43(4):941-948.

实验	算法	匹配对数	正确率/%	时间/s
组别1	本文	280/270	96.4	3.6
	文献[14]	338/304	89.9	4.1
	文献[16]	563/377	66.9	4.3
组别2	本文	148/140	94.5	3.8
	文献[14]	417/316	75.7	7.6
	文献[16]	1026/545	53.1	7.9
组别3	本文	90/71	78.8	3.7
	文献[14]	104/63	60.5	5.8
	文献[16]	541/189	34.9	5.2

算法	匹配对数	正确率/%	时间/s
本文	39/35	89.7	3.7
文献[14]	70/61	87.1	4.2
文献[16]	148/86	58.1	4.4

基于改进ORB-FLANN算法的工件图像识别方法

Workpiece Image Recognition Method Based on Improved ORB-FLANN Algorithm

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	梁陈烨, 张轩雄. 基于改进MobileNet网络的多类别垃圾分类算法[J]. 电子科技, 2024, 37(4): 38-46.
[2]	郭齐成,沈拓,张轩雄. 基于图像处理的轨旁组合信号灯识别方法[J]. 电子科技, 2023, 36(7): 8-15.
[3]	唐政,张会林,马立新,刘金芝,王昊. 轻量级网络算法对输电线路上异物目标的识别[J]. 电子科技, 2023, 36(4): 71-77.
[4]	代进洪,向振文,喻会福. 基于Apriltag的室外抗干扰识别定位系统研究[J]. 电子科技, 2023, 36(11): 47-55.
[5]	刘群坡,席秀蕾,杨凌霄. 基于LK光流和网格运动统计的图像匹配改进算法[J]. 电子科技, 2022, 35(5): 1-6.
[6]	袁子昂,倪伟,冉敬楠. 基于Winograd算法的可重构卷积神经网络加速器[J]. 电子科技, 2022, 35(12): 35-42.
[7]	张杨帆,郝钰鑫,李隐峰,田鑫雨,郑春红,李泽昊. 基于图像识别的失物招领微信小程序设计[J]. 电子科技, 2022, 35(10): 33-38.
[8]	薛永杰,巨志勇. 基于改进AlexNet的鱼类识别算法[J]. 电子科技, 2021, 34(4): 12-17.
[9]	陈文佑,章伟,史晓帆,宋芳. 一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法[J]. 电子科技, 2021, 34(12): 62-67.
[10]	王正军,姚一鸣,陈龙. 基于卷积神经网络的PCB板通用分拣算法[J]. 电子科技, 2020, 33(2): 60-65.
[11]	程俊华,曾国辉,刘瑾. 基于深度学习的复杂背景图像分类方法研究[J]. 电子科技, 2020, 33(12): 59-66.
[12]	张长青,杨楠. 一种面向交通标志识别系统的图像识别算法[J]. 电子科技, 2019, 32(7): 60-64.
[13]	李荣瑞,施霖,赵薇. 基于卷积神经网络的少数民族头饰识别[J]. 电子科技, 2019, 32(2): 51-55.
[14]	张国光. 基于神经网络的有遮挡图像分割方法[J]. , 2015, 28(5): 132-.
[15]	时培弘,董淑福,单勇. 一种基于改进SURF特征描述子的快速算法[J]. , 2015, 28(10): 8-.