计算机科学 ›› 2017, Vol. 44 ›› Issue (9): 315-319.doi: 10.11896/j.issn.1002-137X.2017.09.059
• 图形图像与模式识别 • 上一篇
郑建彬,白雅贤,詹恩奇,汪阳
ZHENG Jian-bin, BAI Ya-xian, ZHAN En-qi and WANG Yang
摘要： 利用尺度不变特征变换(SIFT)算法识别盒装乳制品时易产生误匹配,从而影响识别的准确率。为了消除误匹配点的影响并精确识别商品的种类和数量,提出了一种改进的SIFT误匹配点剔除方法。根据盒装乳制品图像形变较小、多数为刚性变换的特点,首先利用粗匹配对的主方向角度差进行筛选,再计算出模板图和测试图各自特征点两两之间的距离比,标记距离比出现异常的匹配点,最后通过投票剔除误匹配点。在自建商品图像数据库上将所提方法与改进的随机抽样一致性算法、基于图的消除误匹配点方法进行对比测试,结果表明,所提方法在匹配准确率和误剔除率方面有明显改善。
| [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! |
|
||
首页