Welcome to Journal of Beijing Institute of Technology
Advance Search
Volume 27Issue 4
.
Turn off MathJax
Article Contents
Article Navigation> JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY> 2018> 27(4): 630-636
Gaihua Wang, Meng Lü, Tao Li, Guoliang Yuan, Wenzhou Liu. Convolutional Neural Network Based on Spatial Pyramid for Image Classification[J]. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2018, 27(4): 630-636. doi: 10.15918/j.jbit1004-0579.17140
Citation: Gaihua Wang, Meng Lü, Tao Li, Guoliang Yuan, Wenzhou Liu. Convolutional Neural Network Based on Spatial Pyramid for Image Classification[J].JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2018, 27(4): 630-636.doi:10.15918/j.jbit1004-0579.17140
shu

Convolutional Neural Network Based on Spatial Pyramid for Image Classification

doi:10.15918/j.jbit1004-0579.17140
  • 1.

    Hubei Collaborative Innovation Centre for High-Efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan 430068, China;School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China

  • 2.

    School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China

  • Received Date:2017-09-14
    Abstract
  • A novel convolutional neural network based on spatial pyramid for image classification is proposed. The network exploits image features with spatial pyramid representation. First, it extracts global features from an original image, and then different layers of grids are utilized to extract feature maps from different convolutional layers. Inspired by the spatial pyramid, the new network contains two parts, one of which is just like a standard convolutional neural network, composing of alternating convolutions and subsampling layers. But those convolution layers would be averagely pooled by the grid way to obtain feature maps, and then concatenated into a feature vector individually. Finally, those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection layer. This generated feature vector derives benefits from the classic and previous convolution layer, while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the network. Experimental results demonstrate that this model improves the accuracy and applicability compared with the traditional model.
    • FullText(HTML)
  • loading
    • References (24)
  • [1]
    Jarrett K, Kavukcuoglu K, Ranzato M, et al. What is the best multi-stage architecture for object recognition?[C]//IEEE, International Conference on Computer Vision, IEEE, 2010:2146-2153.
    [2]
    Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition, June, 2009:1597-1604.
    [3]
    Han B, Chen Y, Gao X B. Aurora image classification based on LDA combining with saliency information[J]. Journal of Software, 2013, 24(11):2758-2766.
    [4]
    Gemert J C V, Geusebroek J M, Veenman C J, et al. Kernel codebooks for scene categorization[C]//European Conference on Computer Vision, Springer, Berlin Heidelberg, 2008:696-709.
    [5]
    Macqueen J. Some methods for classification and analysis of multivariate observations[C]//Proc of Berkeley Symposium on Mathematical Statistics and Probability, 1966:281-297.
    [6]
    Ojala T, Harwood I. A comparative study of texture measures with classification based on feature distributions[J]. Pattern Recognition, 1996, 29(1):51-59.
    [7]
    Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition, IEEE Computer Society, 2005:886-893.
    [8]
    Marengo E, Robotti E, Righetti P G, et al. Study of proteomic changes associated with healthy and tumoral murine samples in neuroblastoma by principal component analysis and classification methods[J]. Clinica Chimica Acta, 2004, 345(1-2):55-67.
    [9]
    Shi B, Bai X, Yao C. Script identification in the wild via discriminative convolutional neural network[M]. New York:Elsevier Science Inc, 2016.
    [10]
    Andrearczyk V, Whelan P F. Using filter banks in convolutional neural networks for texture classification [J]. Pattern Recognition Letters, 2016, 84:63-69.
    [11]
    Barat C, Ducottet C. String representations and distances in deep convolutional neural networks for image classification[J]. Pattern Recognition, 2016, 54(C):104-115.
    [12]
    Haykin S, Kosko B. Gradient based learning applied to document recognition[J]. Proceedings of the IEEE, 2009,86(11):306-351.
    [13]
    Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems, Curran Associates Inc, 2012:1097-1105.
    [14]
    Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2014, 115(3):211-252.
    [15]
    Wan L, Zeiler M, Zhang S, et al. Regularization of neural networks using dropconnect[C]//International Conference on Machine Learning, 2013:1058-1066.
    [16]
    Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014. arXiv Preprint arXiv:1409.1556,2014.https://arxiv.org/pdf/1409.1556.pdf.
    [17]
    He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Computer Vision and Pattern Recognition, IEEE,2016:770-778.
    [18]
    Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Computer Vision and Pattern Recognition, IEEE, 2015:1-9.
    [19]
    Springenberg J T, Dosovitskiy A, Brox T, et al. Striving for simplicity:the all convolutional net[J]. EprintArxiv, 2014.http://cn.arxiv.org/pdf/1412.6806v3.
    [20]
    Lazebnik S, Schmid C, Ponce J. Beyond bags of features:spatial pyramid matching for recognizing natural scene categories[J]. Cvpr, 2006, 2(1/2):2169-2178.
    [21]
    He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//European Conference on Computer Vision, Springer, Cham, 2014:346-361.
    [22]
    Bu S, Han P, Liu Z, et al. Scene parsing using inference embedded deep networks[J]. Pattern Recognition, 2016, 59(C):188-198.
    [23]
    Zhao F, Liu H, Fan J. A multiobjective spatial fuzzy clustering algorithm for image segmentation[M]. New York:Elsevier Science Publishers, 2015.
    [24]
    Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4):640-651.
    • Relative Articles
  • Supplements (0)
  • Cited By
  • 加载中

Catalog

    通讯作者:陈斌, bchen63@163.com
    • 1.

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML

    Article Metrics

    Article views (718) PDF downloads(343) Cited by()
    Proportional views
    Related

    Address:5 Zhongguancun South Street, Haidian District, Beijing

    Tel:86-10-68914374

    Email:blgywb@bit.edu.cn

    Copy Right © Journal of Beijing Institute of Technology

    Supported by:Beijing Renhe Information Technology Co. Ltd

    /

      Return
      Return
        Baidu
        map