Computer Science ›› 2017, Vol. 44 ›› Issue (9): 315-319.doi: 10.11896/j.issn.1002-137X.2017.09.059

Previous Articles    

Improved SIFT Matching Method for Milk Beverage Recognition in Grocery

ZHENG Jian-bin, BAI Ya-xian, ZHAN En-qi and WANG Yang   

  • Online:2018-11-13 Published:2018-11-13

Abstract: Using scale-invariant feature transform (SIFT) to identify boxed milk beverages is vulnerable to errors caused by mismatching,which will affect the accuracy of identification.To reduce the impact of mismatching and increase the recognition rates,a new method was put forward to eliminate the mismatching points.Since the deformation of boxed milk beverage images is mostly rigid transformation,the angle differences of the key-points between reference image and observation image are calculated in order to remove some mismatching points.Then the ratios of pairwise distances between reference image and observation image are used to mark the abnormal ratios,and the mismatching points are removed by majority vote method.The proposed method is compared with SC-RANSAC(spatially consistent random sample consensus) algorithm and graph transformation matching method through experiments.The results show that the proposed method could improve the recognition accuracy effectively.

Key words: Retail product recognition,Scale-invariant feature transform (SIFT),Mismatching,Spatially consistent random sample consensus (SC-RANSAC),Graph transformation matching method(GTM)

[1] MOORTHY R,BEHERA S,VERMA S,et al.Applying image processing for detecting on-shelf availability and product positioning in retail stores[C]∥International Symposium on Women in Computing and Informatics.India:ACM,2015:451-457.
[2] LIU S,LI W,DAVIS S,et al.Planogram compliance checkingbased on detection of recurring patterns[J].IEEE Multimedia,2016,23(2):54-63.
[3] LIU J,LIU Y.Grasp recurring patterns from a single view[C]∥IEEE Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE,2010:2003-2010.
[4] VAROL G,KUZU R S.Toward retail product recognition on grocery shelves[C]∥International Conference on Graphic & Image Processing.Singapore:American Society for Research (ASR),2015:72-79.
[5] KEJRIWAL N,GARG S,KUMAR S.Product counting using images with application to robot-based retail stock assessment[C]∥IEEE International Conference on Technologies for Practical Robot Applications.Massachusetts:IEEE,2015:1-6.
[6] WINLOCK T,CHRISTIANSEN E,BELONGIE S.Towardreal-time grocery detection for the visually impaired[C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition Workshops.San Francisco:IEEE,2010:49-56.
[7] BAY H,ESS A,TUYTELAARS T,et al.Speeded-Up robustfeatures (SURF)[J].Computer Vision & Image Understan-ding,2008,110(3):346-359.
[8] SARAN A,HASSAN E,MAURYA A K.Robust visual analysis for planogram compliance problem[C]∥International Conference on Machine Vision Applications.Tokyo:IEEE,2015:576-579.
[9] JIANG S Q,MIN W Q,WANG S H.Survey and prospect of intelligent interaction-oriented image recognition techniques[J].Journal of Computer Research and Development,2016,53(1):113-122.(in Chinese) 蒋树强,闵巍庆,王树徽.面向智能交互的图像识别技术综述与展望[J].计算机研究与发展,2016,53(1):113-122.
[10] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(60):91-110.
[11] ZHAO Y,JIANG J G,HONG R C.An optimized SIFT matching based on ransac [J].Opto-Electronic Engineering,2014,41(8):58-65.(in Chinese) 赵烨,蒋建国,洪日昌.基于RANSAC的SIFT匹配优化[J].光电工程,2014,41(8):58-65.
[12] YANG J,LI R N,HUANG C Y,et al.Fast image registration algorithm based on locally significant edge feature [J].Journal of Computer Applications,2014,34(1):149-153.(in Chinese) 杨健,李若楠,黄晨阳,等.基于局部显著边缘特征的快速图像配准算法[J].计算机应用,2014,34(1):149-153.
[13] KIM T,IM Y J.Automatic satellite image registration by combination of matching and random sample consensus[J].IEEE Transactions on Geoscience & Remote Sensing,2003,41(5):1111-1117.
[14] YANG H Y,LUO W C,LIU G D.Image registration based on SURF algorithm and SC-RANSAC algorithm [J].Application Research of Computers,2013,30(5):1586-1588.(in Chinese) 杨海燕,罗文超,刘国栋.基于SURF算法和SC-RANSAC算法的图像配准[J].计算机应用研究,2013,30(5):1586-1588.
[15] CHEN S W,YANG X G,ZHANG S X,et al.Relative positioning method of target based on adaptive context information[J].Systems Engineering and Electronics,2016,38(5):984-989.(in Chinese) 陈世伟,杨小冈,张胜修,等.基于自适应上下文信息的目标相对定位方法[J].系统工程与电子技术,2016,38(5):984-989.
[16] LI W,NIU Z,WU C Y,et al.A robust multisource image automatic registration system based on the SIFT descriptor[J].International Journal of Remote Sensing,2012,33(12) :3850-3869.
[17] LIU Z X,AN J B,MENG F R.A robust point matching algorithm for image registration[C]∥Proc of the 4th International Conference on Machine Vision.2011:66-70

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!