[1]赵腾飞,辛大欣,华瑾.改进SURF算法的特征提取与匹配方法研究[J].机械与电子,2017,(09):77-80.[doi:1001-2257(2017)09-0077-04]
 ZHAO Tengfei,XIN Daxin,HUA Jin.Research on Feature Extraction and Matching Method of Improved SURF Algorithm[J].Machinery & Electronics,2017,(09):77-80.[doi:1001-2257(2017)09-0077-04]
点击复制

改进SURF算法的特征提取与匹配方法研究
分享到:

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2017年09期
页码:
77-80
栏目:
智能工程
出版日期:
2017-09-25

文章信息/Info

Title:
Research on Feature Extraction and Matching Method of Improved SURF Algorithm
作者:
赵腾飞辛大欣华瑾
(西安工业大学电子信息工程学院,陕西 西安 710021)
Author(s):
ZHAO TengfeiXIN DaxinHUA Jin
(School of Electronic Information Engineering,Xi'an Technological University, Xi'an 710021,China)
关键词:
改进SURF算法 特征提取 图像匹配 图像处理
Keywords:
improved SURF algorithm feature extraction image matching image processing
分类号:
TP39
DOI:
1001-2257(2017)09-0077-04
文献标志码:
A
摘要:
针对门把手图像特征点提取与匹配对快速性和准确性的要求,提出一种改进SURF算法。该算法主要对图像较平滑区域难以提取出大量信息点的问题进行改进。增加了边缘检测算法,得到图像边缘信息后进行形态学处理,并通过膨胀运算和开运算后获得门把手图像边缘区域信息并提取出关键点,进而获得较多特征明显的信息。改进SURF算法和原始SURF算法相比,在平滑区域能够较好提取出特征点,匹配准确率也有明显的提升,并且增强了算法的实时性。
Abstract:
To meet the requirement of fastness and accuracy of doorknob image feature extraction and matching, an improved SURF algorithm is proposed, which mainly targets the problem that it is hard to extract a large number of information points at the smooth area of the image. In addition, the edge detection algorithm is added. With morphological processing, dilation operation and open operation, the image edge information of doorknob was obtained and the key point was extracted, hence some more featured information were collected. The results show that the improved SURF algorithm can extract feature points in the smooth area in real time with obvious improvement in the accuracy rate of matching.

参考文献/References:

[1]马颂德,张正友.计算机视觉[M].北京:科学出版社,1998.
[2]吴立德.计算机视觉[M].上海:复旦大学出版社,1993.
[3]姜昊.基于图像滤波器的多尺度图像分解[D]. 上海:复旦大学,2012.
[4]彭辉,文友先,翟瑞芳,等.结合SURF算子和极线约束的柑橘立体图像对匹配[J].计算机工程与应用,2011,47(8):157-160.
[5]庄路路.基于改进SURF算法和神经网络的水果识别技术研究[D].哈尔滨:哈尔滨理工大学,2016.
[6]梁进,刘泉,艾青松.基于SURF和全局特征融合的图像分类研究[J].计算机工程与应用,2013,49(17):174-177,194.
[7]王莹.双目立体视觉图像匹配与目标定位方法研究[D].哈尔滨:哈尔滨工业大学,2013.
[8]章海兵,刘士荣,张波涛.H-S直方图反向投影结合特征点提取的双目视觉定位算法[J].控制理论与应用,2014,31(5):614-623.
[9]杜振鹏,李德华.基于KD-Tree搜索和SURF特征的图像匹配算法研究[J].计算机与数字工程,2012,40(2):96-98,126.
[10]王智文.几种边缘检测算子的性能比较研究[J].制造业自动化,2012,34(11):14-16.
[11]赵振兵,金思新,刘亚春.基于NSCT的航拍绝缘子图像边缘提取方法[J].仪器仪表学报,2012,33(9):2045-2052.

相似文献/References:

[1]赵乾,赵硕伟.基于计算机视觉的药片实时检测系统[J].机械与电子,2018,(03):49.
 ZHAO Qian,ZHAO Shuowei.Study on Real-Time Tablet Detection System Based on Computer Vision[J].Machinery & Electronics,2018,(09):49.
[2]袁 涛,张尚斌,何清波.时变奇异值分解在轴承故障特征提取中的应用研究[J].机械与电子,2017,(06):8.
 YUAN Tao,ZHANG Shangbin,HE Qingbo.Application of Time-varying Singular Value Decomposition in Feature Extraction of Bearing Fault[J].Machinery & Electronics,2017,(09):8.
[3]杨纯平,张文斌,周年荣,等.时间序列特征提取的高压输电线电压等级识别方法[J].机械与电子,2017,(12):47.
 YANG Chunping,ZHANG Wenbin,ZHOU Nianrong,et al.Voltage Level Identification for High Voltage Transmission Line Based onTime Series Feature Extraction[J].Machinery & Electronics,2017,(09):47.
[4]马益书,黄亚宇,吴 政.基于包络分析的滚动轴承故障诊断研究[J].机械与电子,2016,(01):63.
 MA Yishu,HUANG Yayu,WU Zheng.Study on Fault Diagnosis of Rolling Bearing Based on Envelope Analysis[J].Machinery & Electronics,2016,(09):63.

备注/Memo

备注/Memo:
收稿日期:2017-06-16
作者简介:赵腾飞(1992-),女,陕西咸阳人,硕士研究生,研究方向为智能控制理论与应用;辛大欣(1966-),男,河南灵宝人,副教授,硕士研究生导师,研究方向为人工智能、计算机控制;华瑾(1985-),女,陕西西安人,助教,研究方向为机器人控制和智能系统。
更新日期/Last Update: 2017-09-25