基于M-Sift特征的元器件目标检测及其在点胶机中的应用Object detection and localization method based on modified Sift and its application in dispensing machine
漆志亮,贾楠,张烨,吴建华
摘要(Abstract)：
针对工业生产线上自动点胶机、产品质量检测或自动焊接等任务的需求,提出一种基于改进的Sift(M-Sift)特征的目标检测算法。所提算法以图像块为基本匹配单位代替Sift特征的关键点检测,图像块的特征提取采用M-Sift特征,既提高了计算效率又保持了Sift特征的优势。对大量、多种类的目标检测和定位实验表明,提出的基于M-Sift特征的目标检测与定位算法达到了很高的性能,优于传统基于模型的目标定位和识别方法。
关键词(KeyWords)： Sift特征;M-Sift特征;目标检测;目标定位;相关匹配;点胶机
基金项目(Foundation): 国家自然科学基金资助项目(61662047)~~
作者(Author): 漆志亮,贾楠,张烨,吴建华
DOI: 10.16652/j.issn.1004-373x.2018.23.033
参考文献(References)：
- [1]LOWE D G.Object recognition from local scale-invariant features[C]//Proceedings of the 7th IEEE International Conference on Computer Vision.Kerkyra:IEEE,1999:1150-1157.
- [2]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International journal of computer vision,2004,60(2):91-110.
- [3]BAY H,TUYTELAARS T,GOOL L V.SURF:speeded up robust features[C]//2006 European Conference on Computer Vision.[S.l.]:Springer,2006:404-417.
- [4]BAY H,ESS A,TUYTELAARS T,et al.Speeded up robust features(SURF)[J].Computer vision and image understanding,2008,110(3):346-359.
- [5]王永明,王贵锦.图像局部不变性特征与描述[M].北京:国防工业出版社,2010.WANG Y M,WANG G J.Image local invariant features and descriptors[M].Beijing:National Defense Industry Press,2010.
- [6]杨化超.图像局部不变性特征及其匹配问题研究与应用[M].北京:测绘出版社,2013.YANG H C.Research and application of local invariant image features and matching problems[M].Beijing:Surveying and Mapping Press,2013.
- [7]DOUCH I A,AL-BTOUSH S.Currency recognition using a smartphone:comparison between color SIFT and gray scale SIFT algorithms[J].Journal of King Saud University Computer and Information Sciences,2016,29(4):484-492.
- [8]RAMALHO G L B,FERREIRA D S,FILHO P P R,et al.Rotation-invariant feature extraction using a structural co-occurrence matrix[J].Measurements,2016,94:406-415.
- [9]GRAGNANIELLO D,SANSONE C,VERDOLIVA L.Cell image classification by a scale and rotation invariant dense local descriptor[J].Pattern recognition letters,2016,82:72-78.
- [10]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//2011 International Conference on Computer Vision.Barcelona:IEEE,2011:2564-2571.
- [11]TOMA?EV N,PRACNER D,BREHAR R,et al.Object recognition in wikimage data based on local invariant image features[C]//2013 IEEE the 9th International Conference on Intelligent Computer Communication and Processing.ClujNapoca:IEEE,2013:139-146.
- [12]YU Jun,CHENG Peng,YIN Xuefeng.A matching algorithm based on improved SIFT for the air mobility platform[C]//2013 IEEE the 4th International Conference on Software Engineering and Service Science.Beijing,China:IEEE,2013:775-778.
- [13]YU Dongdong,YANG Feng,YANG Caiyun,et al.Fast rotation-free feature-based image registration using improved N-Sift and GMM-based parallel optimization[J].IEEE transactions on biomedical engineering,2016,63(8):1653-1663.
- [14]OTSU N.A threshold selection method from gray-level histogram[J].IEEE transactions on systems,man and cybernetics,1979,9(1):62-66.