[1]毛玉妃,王斌,舒华忠.基于变换域形状描述子的图像检索方法的比较与分析[J].东南大学学报(自然科学版),2012,42(2):254-258.[doi:10.3969/j.issn.1001-0505.2012.02.012]
 Mao Yufei,Wang Bin,Shu Huazhong.Comparative study of transform domain image retrieval[J].Journal of Southeast University (Natural Science Edition),2012,42(2):254-258.[doi:10.3969/j.issn.1001-0505.2012.02.012]
点击复制

基于变换域形状描述子的图像检索方法的比较与分析()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第2期
页码:
254-258
栏目:
计算机科学与工程
出版日期:
2012-03-20

文章信息/Info

Title:
Comparative study of transform domain image retrieval
作者:
毛玉妃1 王斌12 舒华忠1
1 东南大学影像科学与技术实验室,南京 210096; 2 南京财经大学江苏省电子商务重点实验室,南京 210046
Author(s):
Mao Yufei1 Wang Bin12 Shu Huazhong1
1 Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
2 Jiangsu Key Laboratory of Electronic Business, Nanjing University of Finance and Economics, Nanjing 210046, China
关键词:
图像检索 形状描述 变换域分析 医学图像检索
Keywords:
image retrieval shape description transform domain analysis medical image retrieval
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2012.02.012
摘要:
为了更好地了解变换域方法在图像检索中的检索效果,比较分析了Zernike矩、GFD、PCET、RCFT和RFMT等现有的5种基于变换域的形状描述方法.分别在不变性、计算复杂性、噪声鲁棒性、有效特征数的选取方面对其进行了深入的分析和比较.选用MPEG7 CE Shape-1 Part B中的1400幅图像构成的图像库对这些方法进行检索和性能测试,并实际应用于由500幅病例图构成的图像库的医学图像检索.在研究噪声影响时,对各测试集图片加上不同程度的高斯噪声.通过比较分析及实验结果验证,Zernike矩和GFD方法的检索性能最好,有良好的抗噪性,因而适合于医学图像检索的实际应用.
Abstract:
In order to better understand the effect of transform domain method in image retrieval, we give a comparison of the five transform-based shape descriptors, which are Zernike moments, generic Fourier descriptor(GFD), polar complex exponential transform(PCET), Radon chamfer Fourier transform(RCFT)and Radon Fourier-Mellin transform(RFMT)were compared. Besides, analyses on invariance, computation complexity, noise robustness and effective number of features were conducted in detail. The five descriptors were tested by using 1400 images from MPEG7 CE Shape-1 Part B. Furthermore, these descriptors were practically used for the medical image database including 500 images. To study the effect of the noise on retrieval, the Gaussian noise was applied to the two databases. It can be seen from the comparative analysis and the experimental results that the performance of Zernike moments and GFD are the best. They have robust noise immunity and are suitable for the practical application of medical image retrieval.

参考文献/References:

[1] Hu M K.Visual pattern recognition by moment invariant[J].IRE Trans Information Theory,1962,8(2):179-187.
[2] Ye B,Peng J X.Analysis and improvement of invariance of Zernike moments[J].Infrared and Laser Engineering,2003,32(1):37-41.
[3] Teh C H,Chin R T.On image analysis by the method of moments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(4):496-513.
[4] Chao K,Mandyam D S.Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments[J].Pattern Recognition,2002,35(1):143-154.
[5] Khalil M I,Bayoumi M M.A dyadic wavelet affine invariant function for 2D shape recognition[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2001,23(10):1152-1164.
[6] Zhang D,Lu G.A comparative study of Fourier descriptors for shape representation and retrieval[C] //Proc 5th Asian Conference on Computer Vision.Melbourne,Australia,2002:646-651.
[7] Ricard J,Coeurjolly D,Baskurt A.Generalizations of angular radial transform for 2D and 3D shape retrieval[J].Pattern Recognition Letters,2005,26(14):2174-2186.
[8] Yap P T,Jiang X D,Kot A C.Two-dimensional polar harmonic transforms for invariant image representation[J].Pattern Analysis and Machine Intelligence,2010,32(7):1259-1270.
[9] Borgefors G.Distance transformations in digital images[J].Computer Vision,Graphics,and Image Processing,1986,34(3):344-371.
[10] Tabbone S,Wendling L,Salmon J P.A new shape descriptor defined on the radon transform[J].Comp Vis and Image Under,2006,102(1):42-51.
[11] Wang X,Xiao B,Ma J F,et al.Scaling and rotation invariant analysis approach to object recognition based on Radon and Fourier-Mellin transforms[J].Pattern Recognition,2007,40(12):3503-3508.
[12] Gu J,Shu H Z,Toumoulin C,et al.A novel algorithm for fast computation of Zernike moments[J].Pattern Recognition,2002,35(12):2905-2911.

备注/Memo

备注/Memo:
作者简介: 毛玉妃(1986—),女,硕士生; 舒华忠(联系人),男,博士,教授,博士生导师,shu.list@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(61073138,60911130370,61103141)、教育部博士点基金资助项目(20110092110023)、江苏省高校自然科学研究重大资助项目(11KJA520004).
引文格式: 毛玉妃,王斌,舒华忠.基于变换域形状描述子的图像检索方法的比较与分析[J].东南大学学报:自然科学版,2012,42(2):254-258. [doi:10.3969/j.issn.1001-0505.2012.02.012]
更新日期/Last Update: 2012-03-20