用于目标识别的PCA-SC形状匹配算法

黄伟国; 顾超; 朱忠奎

doi:10.3788/OPE.20132108.2103

您当前的位置：

首页 >

文章列表页 >

用于目标识别的PCA-SC形状匹配算法

信息科学 | 更新时间：2020-08-12

- 用于目标识别的PCA-SC形状匹配算法
- PCA-SC Shape Matching for Object Recognition
- 光学精密工程 2013年21卷第8期页码：2103-2110
- 作者机构：
  
  苏州大学城市轨道交通学院,江苏苏州,215131
- 作者简介：
- 基金信息：
  
  江苏省产学研联合创新资金项目项目();江苏省基金资助项目()
- DOI：10.3788/OPE.20132108.2103
  中图分类号： TP391.4
- 收稿日期：2013-03-11，
  
  修回日期：2013-04-10，
  
  网络出版日期：2013-08-20，
  
  纸质出版日期：2013-08-15
- 稿件说明：
移动端阅览
黄伟国顾超朱忠奎. 用于目标识别的PCA-SC形状匹配算法[J]. 光学精密工程, 2013,21(8): 2103-2110

HUANG Wei-guo GU Chao ZHU Zhong-kui. PCA-SC Shape Matching for Object Recognition[J]. Editorial Office of Optics and Precision Engineering, 2013,21(8): 2103-2110
黄伟国顾超朱忠奎. 用于目标识别的PCA-SC形状匹配算法[J]. 光学精密工程, 2013,21(8): 2103-2110 DOI： 10.3788/OPE.20132108.2103.

HUANG Wei-guo GU Chao ZHU Zhong-kui. PCA-SC Shape Matching for Object Recognition[J]. Editorial Office of Optics and Precision Engineering, 2013,21(8): 2103-2110 DOI： 10.3788/OPE.20132108.2103.

摘要

基于形状上下文（Shape Context）算法并融合主成分分析（PCA）的降维思想，提出了一种PCA-SC算法来提高形状匹配和目标识别的速度和抗噪能力。该算法将SC算法获取的特征矩阵构成协方差矩阵，按照特征值由大到小的准则进行降维，形成新的特征矩阵用于匹配和识别，既抑制了噪声干扰，提高了识别准确率，又能够提高匹配速度，易于满足工程应用对实时性的要求。利用MNIST图像数据库中的图像进行了实验分析，结果表明，PCA-SC算法在保持了SC算法原有的定位准确、抑制噪声等优点的基础上，识别速度提高了1倍；准确率达到了96.15%，提高了约0.5%；而且抗噪性更强，可用于匹配和识别较复杂的形状和目标。该算法基本满足匹配和识别对速度、准确率和抗干扰性等方面的要求。

Abstract

A new algorithm based on Shape Context(SC) and Principal Component Analysis(PCA）called PCA-SC was proposed to improve the matching efficiency and anti-noise performance in shape matching and object recognition. The algorithm establishes a covariance matrix based on the feature matrix obtained by the SC

then reduces its dimensions according to the size of eigen value and forms a new feature matrix to implement the shape matching and object recognition. The proposed algorithm can not only remove noise interference and improve the recognition accuracy

but also can enhance the matching efficiency for real-time application. The experimental results of MNIST database indicate that the PCA-SC algorithm outperforms previous SC algorithm

and its recognition speed is doubled that of SC and the accuracy reaches to 96.15% increased by 0.5%. Furthermore

the anti-noise performance becomes stronger. Therefore

this novel algorithm shows better performance for shape matching and object recognition in efficiency

accuracy and anti-noise.

关键词

Keywords

references

孙浩,王程,王润生. 局部不变特征综述[J]. 中国图象图形学报,2011,16(2): 141-151.SUN H, WANG CH, WANG R SH. A rewiew of local invariant features [J]. Journal of Image and Graphics, 2011, 16(2):141-151.(in Chinese)[2]ZHANG D, LU G. Review of shape representation and description techniques[J]. Pattern Recognition, 2004, 37(1): 1-19.[3]杨恒,王庆. 一种新的局部不变特征检测和描述算法[J]. 计算机学报,2010,33(5): 935-944.YANG H, WANG Q. A novel local invariant feature detection and description algorithm [J]. Chinese Journal of Computers, 2010, 33(5):935-944.(in Chinese)[4]EDWARD H, ALVARO C, MARTIAL H. Making specific features less discriminative to improve point-based 3D object recognition [C]. IEEE International Conference on Compurter Vision and Pattern Recognition, 2010: 2653-2660.[5]杨晓敏,吴炜,卿粼波,等. 图像特征点提取及匹配技术[J]. 光学精密工程,2009,17(9): 2276-2282.YANG X M, WU W, QING L B, et al.. Image feature extraction and matching technology[J]. Opt. Precision Eng., 2009, 17(9): 2276-2282 .(in Chinese)[6]XU CH J,LIU J ZH,TANG X O. 2D Shape matching by contour flexibility[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 21(1):180-186.[7]丘文涛,赵建,刘杰. 结合区域分割的SIFT图像匹配方法[J]. 液晶与显示,2012,27(6): 827-831.QIU W T，ZHAO J，LIU J. Image matching algorithm combining SIFT with region segmentation [J]. Chinese Journal of Liquid Crystals and Displays. 2012, 27(6): 827-831 .(in Chinese)[8]吴君钦,刘昊,罗勇. 静态背景下的运动目标检测算法[J]. 液晶与显示,2012,27(5)：682-686.WU J Q, LIU H, LUO Y. Algorithm of moving object dection in static background[J]. Chinese Journal of Liquid Crystals and Displays,2012, 27(5):682-686.(in Chinese)[9]唐永鹤,卢焕章,胡谋法.基于 Laplacian 的局部特征描述算法[J].光学精密工程,2011,19(12): 2999-3006.TANG Y H, LU H ZH, HU M F. Local feature description algorithm based on Laplacian[J]. Opt. Precision Eng., 2011, 19(12): 2999-3006.(in Chinese)[10]BANERJEE A, DUTTA A. Fuzzy matching scheme on fourier descriptors for retrieval of 2 dimensional shapes [C]. National Conference on Computing and Communication Systems,2012:1-5.[11]CHUANG G C H, KUO C C J. Wavelet descriptor of planar curves: Theory and applications [J]. IEEE Transactions on Image Processing, 1996, 5(1): 56-70.[12]SERGE B, JITENDRA M, JAN P. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(24): 509-522.[13]王丽荣,王建蕾. 基于主成分分析的唇部轮廓建模[J]. 光学精密工程,2012,20(12): 2768-2772.WANG L R, WANG J L. Lip contour modeling based on PCA[J]. Opt. Precision Eng., 2012, 20(12): 2768-2772.(in Chinese)[14]GREG M, SERGE B, JITENDRA M. Efficient Shape Matching Using Shape Contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(11): 1832-1837.[15]KOKKINOS I, BRONSTEIN M M, LITMAN R, et al.. Intrinsic shape context descriptors for deformable shapes [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2012: 159-166.[16]CUN Y L. The MNIST database of handwritten digits[OL]. http://yann.lecun.com/exdb/mnist.[17]CANNY J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):679-698.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

改进YOLOv7的服务机器人密集遮挡目标识别

面向点云识别网络的显著图生成

高速微扫描图像超分辨重建

两栖球形机器人的路径规划策略

基于DRGAN和支持向量机的合成孔径雷达图像目标识别