图像栈的特征提取以及在线虫分类中的应用
作者:
作者单位:

湖南大学电气与信息工程学院长沙410082

中图分类号:

TP391.4

基金项目:

国家自然科学基金(61301254)、湖南省自然科学基金(14JJ3069)资助项目


Feature extraction of image stack and its application in nematode classification
Author:
Affiliation:

College of Electrical and Information Engineering, Hunan University, Changsha 410082, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    三维多焦距图像栈中的有效信息分布在不同的图像层上,其特征提取及分类跟普通二维图像有很大区别。针对图像栈的分类问题,提出了一种基于多方向图像融合的多线性特征提取和分类方法。首先,通过图像融合获取三维图像栈沿多个正交方向的融合图像,并从中提取特征;然后,通过典型相关分析(canonical correlation analysis, CCA)方法,将不同方向融合图像提取的特征进行融合并抽取组合的典型相关特征用于图像分类;其次,由于图像栈数据包含了样本、类别和方向等多个影响分类的因素,因此将多方向图像融合方法嵌入到多线性分析中,综合考虑多个因素交互作用时对图像栈分类的影响。本文提出的方法在线虫图像栈数据上进行了实验,识别率达到了97.0%,实验结果表明该方法具有较高的准确性。

    Abstract:

    The effective information of 3D multifocal image stack is distributed on different image layers, so the feature extraction and classification of image stacks are significantly different from that of 2D images. In this paper, an image fusion based multilinear analysis approach is presented to use for classification of multifocal image stacks. First, the image fusion techniques are used to combine the relevant information of multifocal images within a given image stack into a single image. Besides, multifocal images within a stack are fused along 3 orthogonal directions, and multiple features extracted from the fused images along different directions are combined by using canonical correlation analysis (CCA). Furthermore, because multifocal image stacks represent the effect of different factorstexture, shape, different instances within the same class and different classes of objects, the image fusion method within a multilinear framework is embeded to propose an image fusion based multilinear classifier. The experimental results demonstrate that the multidirection image fusion based multilinear classifier can reach a higher classification rate (97%) than other classification methods.

    参考文献
    [1]温翠红, 章兢, 程凡永. 基于DAGLDM的手写音乐符号分类[J]. 电子测量与仪器学报, 2016, 30(5): 764771. WEN C H, ZHANG J, CHENG F Y. Handwritten music symbol classification based on DAG LDM[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(5): 764771.
    [2]吴哲君, 赵忠华, 唐雷. 基于SVM的行人步态实时分类方法[J]. 电子测量技术, 2015, 38(7): 4144. WU ZH J, ZHAO ZH H, TANG L. SVM based method for real time classification of pedestrian gait[J]. Electronic Measurement Technology, 2015, 38(7): 4144.
    [3]张维坤, 叶伟, 劳国超. 基于SIFT特征的SAR图像飞机目标匹配分类方法研究[J]. 国外电子测量技术, 2016, 35(8): 1921. ZHANG W K, YE W, LAO G CH. Research on aircraft target matching classification method based on SIFT feature for SAR image[J]. Foreign Electronic Measurement Technology, 2016, 35(8): 1921.
    [4]LI W, TRAMEL E W, PRASAD S, et al. Nearest regularized subspace for hyperspectral classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 477489.
    [5]GUO H, WANG W. An active learningbased SVM multiclass classification model[J]. Pattern Recognition, 2015, 48(5): 15771597.
    [6]GU S H, LEI Z, ZUO W M, et al. Projective dictionary pair learning for pattern classification[C]. Neural Information Processing Systems, 2014: 793801.
    [7]杨文文, 毛建旭, 陈姜嘉旭. 基于分块LBP和分块PCA的指静脉识别方法[J]. 电子测量与仪器学报, 2016, 30(7): 10001007. YANG W W, MAO J X, CHEN J J X. Finger vein recognition based on block LBP and block PCA[J], Journal of Electronic Measurement and Instrumentation, 2016, 30(7): 10001007.
    [8]KLASER A, MARSZALEK M, SCHMID C. A spatiotemporal descriptor based on 3dgradients[C]. British Machine Vision Conference, 2008: 275285.
    [9]SCOVANNER P, ALI S, SHAH M. A 3dimensional sift descriptor and its application to action recognition[C]. 15th ACM International Conference on Multimedia, 2007: 357360.
    [10]LIU M, ROYCHOWDHURY A K. Multilinear feature extraction and classification of multifocal images, with applications in nematode taxonomy[C]. IEEE Conference Computer Vision and Pattern Recognition, 2010: 28232830.
    [11]LIU Y, LIU S P, WANG Z F. A general framework for image fusion based on multiscale transform and sparse representation[J]. Information Fusion, 2015(24): 147164.
    [12]YANG J, ZHANG X. Featurelevel fusion of fingerprint and fingervein for personal identification[J]. Pattern Recognition Letters, 2012, 33(5): 623628.
    [13]YANG B, LI S T. Multifocus image fusion and restoration with sparse representation[J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(4): 884892.
    [14]陈震, 杨小平, 张聪炫, 等. 基于补偿机制的NSCT域红外与可见光图像融合[J]. 仪器仪表学报, 2016, 37(4): 860870. CHEN ZH, YANG X P, ZHANG C X,et al. Infrared and visible image fusion based on the compensation mechanism in NSCT domain[J]. Chinese Journal of Scientific Instrument, 2016, 37(4): 860870.
    [15]李目, 何怡刚, 吴笑锋, 等. 基于奇异值分解的分数阶小波综合实现方法[J]. 电子测量与仪器学报, 2016, 30(2): 241248. LI M, HE Y G, WU X F, et al. Synthesis implementation method of fractional wavelet based on singular value decomposition algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(2): 241248.
    [16]ALSHIHA A A M, WOO W L, DLAY S S. Multilinear neighborhood preserving projection for face recognition[J]. Pattern Recognition, 2014, 47(2): 544555.
    [17]ZHU P F, ZHANG L, HU Q, et al. Multiscale patch based collaborative representation for face recognition with margin distribution optimization[C]. European Conference on Computer Vision, 2012: 822835.
    [18]WAGNER A, WRIGHT J, GANESH A, et al. Toward a practical face recognition system: Robust alignment and illumination by sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(12): 372386.
    [19]ZHUANG X H, BAI W J, SONG J J, et al. Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection[J]. Medical Physics, 2015, 42(7): 38223833.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王学平,刘敏.图像栈的特征提取以及在线虫分类中的应用[J].电子测量与仪器学报,2017,31(11):1753-1759

复制
分享
文章指标
  • 点击次数:2851
  • 下载次数: 14583
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2018-01-08
文章二维码