快速极坐标形状描述子研究与应用

doi:10.3969/j.issn.1006-2475.2015.03.020

计算机与现代化

快速极坐标形状描述子研究与应用

广州番禺职业技术学院信息工程学院，广东广州511483

收稿日期:2014-11-11 出版日期:2015-03-23 发布日期:2015-03-26
作者简介:胡耀民(1975-),男,湖南宁乡人,广州番禺职业技术学院信息工程学院副教授,博士,研究方向:智能算法,车辆图像处理,模式识别。
基金资助:
广东省交通运输厅科技计划项目(科技2012-02-084); 广州市教育系统创新学术团队项目(13C18); 广州市番禺区科技计划项目(2010-专-12-10)

Research and Application of Fast Polar Shape Descriptor

School of Information Engineering, Guangzhou Panyu Polytechnic, Guangzhou 511483, China

Received:2014-11-11 Online:2015-03-23 Published:2015-03-26

摘要/Abstract

摘要： 基于视频进行实时形状识别时，要求形状描述子既能准确地描述形状，又能快速地被提取出来。针对该问题，本文研究一种可用来进行形状识别的快速极坐标形状描述子(FPSD)。FPSD在每种角度频率上只采样一个值，相对Zernike矩(ZM)来说，提高了形状描述角向采样频率,并且简化了计算。使用车型识别视频进行验证性实验，结果表明，使用FPSD作分类特征时，车型间距离比使用ZM和Hu矩(HuM)时更大，更有利于准确地分类，而计算复杂度远低于ZM。

关键词: 快速极坐标形状描述子, 泽尼克矩, 车型识别

Abstract: In real-time shape recognition based on video, the shape descriptor is desired to characterize the shape accurately, and can be extracted fast. To solve this problem, the fast polar shape descriptor (FPSD) is proposed for shape recognition. FPSD sampled one value at each angle frequency, and improved the sampling angle frequencies compared to Zernike Moments (ZM). Vehicle classification video was used for verifying experiments. When the FPSD is used as features for classification, experiments show that the performance of FPSD can be achieved even better than that of ZM, while the computational complexity is much lower than ZM.

Key words: fast polar shape descriptor, Zernike moments, vehicle classification

中图分类号:

TP301.6

胡耀民. 快速极坐标形状描述子研究与应用[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2015.03.020.

HU Yao-min. Research and Application of Fast Polar Shape Descriptor[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2015.03.020.

参考文献

［1]胡炜炜,李树广,吴舟舟. 基于边缘轮廓特征的实时车型分类［J]. 计算机工程, 2007,33(13):185-187.
［2]卢玥,刘学军,晋蓓. 基于视频的车辆几何参数提取与车型分类［J]. 计算机工程, 2009,35(20):173-175.
［3]秦钟. 基于图像不变矩特征和BP神经网络的车型分类［J]. 华南理工大学学报(自然科学版), 2009,37(2):87-91.
［4]葛广英. 基于SVM的车型检测和识别算法［J]. 计算机工程, 2007,33(6):6-9.
［5]Teh C H, Chin R T. On image analysis by the methods of moments［J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(4):496-513.
［6]Kim W Y, Kim Y S. A region-based shape descriptor using Zernike moments ［J]. Signal Processing： Image Communication, 2000,16(1-2):95-102.
［7]〖JP2〗Tahmasbi A, Saki F, Shokouhi S B. Classification of benign and malignant masses based on Zernike moments［J]. Computers in Biology and Medicine, 2011,41(8):726-735.
［8]Papakostas G A, Boutalis Y S, Karras D A, et al. Pattern classification by using improved wavelet compressed Zernike moments［J]. Applied Mathematics and Computation, 2009,212(1):162-176
［9]Chen Beijing, Shu Huazhong, Zhang Hui, et al. Quaternion Zernike moments and their invariants for color image analysis and object recognition［J]. Signal Processing, 2012,92(2):308-318.
［10]Radhika K R, Venkatesha M K, Sekhar G N. An approach for on-line signature authentication using Zernike moments［J]. Pattern Recognition Letters, 2011,32(5):749-760.
［11]Amayeh G, Erol A, Bebis G, et al. Accurate and efficient computation of high order Zernike moments［C]// First International Symposium on Advances in Visual Computing, 2005. 2005,3804:462-469.
［12]Singh C, Walia E. Fast and numerically stable methods for the computation of Zernike moments［J]. Pattern Recognition, 2010,43(7):2497-2506.
［13]〖JP2〗Singh C, Walia E, Upneja R. Accurate calculation of Zernike moments［J]. Information Sciences, 2013,233:255-275.
［14]Hu M K. Visual pattern recognition by moment invariants［J]. IRE Transactions on Information Theory, 1962,8(2):179-187.
［15]Dudani S A, Breeding K J, McGhee R B. Aircraft identification by moment invariants［J]. IEEE Transactions on Computers-TC, 1977,26(1):39-46.
［16]Belkasim S O, Shridhar M, Ahmadi M. Pattern recognition with moment invariants: A comparative study and new results［J]. Pattern Recognition, 1991,24(12):1117-1138.
［17]Prokop R J, Reeves A P. A survey of moment-based techniques for unoccluded object representation recognition［J]. CVGIP: Graphical Models and Image Processing, 1992,54(5):438-460.
［18]Kennedy R L, Lee Y, Van Roy B, et al. Solving Data Mining Problems Through Pattern Recognition［M]. Prentice-Hall, 1998:11-16.
［19]Teague M R. Image analysis via the general theory of moments［J]. Journal of the Optical Society of America, 1980,70(8):920-930.

[1]	王喜龙，张伟伟，吴训成 . 基于双相机协同的管制车型抓拍系统[J]. 计算机与现代化, 2019, 0(03): 23-.
[2]	杜华英. 基于车型识别的BP算法Matlab实现[J]. 计算机与现代化, 2012, 1(201): 20-22.

快速极坐标形状描述子研究与应用

Research and Application of Fast Polar Shape Descriptor

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价