SCN: A Novel Shape Classification Algorithm Based on Convolutional Neural Network

Shape classification and matching is an important branch of computer vision. It is widely used in image retrieval and target tracking. Shape context method, curvature scale space (CSS) operator and its improvement have been the main algorithms of shape matching and classification. The shape classification network (SCN) algorithm is proposed inspired by LeNet5 basic network structure. Then, the network structure of SCN is introduced and analyzed in detail, and the specific parameters of the network structure are explained. In the experimental part, SCN is used to perform classification tasks on three shape datasets, and the advantages and limitations of our algorithm are analyzed in detail according to the experimental results. SCN performs better than many traditional shape classification algorithms. Accordingly, a practical example is given to show that SCN can save computing resources.

[1]  Saeid Belkasim,et al.  Farthest point distance: A new shape signature for Fourier descriptors , 2009, Signal Process. Image Commun..

[2]  Anne Verroust-Blondet,et al.  A shape-based approach for leaf classification using multiscaletriangular representation , 2013, ICMR.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[5]  H. S. Nagendraswamy,et al.  Classification of medicinal plants: An approach using modified LBP with symbolic representation , 2016, Neurocomputing.

[6]  Wei Jia,et al.  Angular Pattern and Binary Angular Pattern for Shape Retrieval , 2014, IEEE Transactions on Image Processing.

[7]  Bin Wang,et al.  Hierarchical String Cuts: A Translation, Rotation, Scale, and Mirror Invariant Descriptor for Fast Shape Retrieval , 2014, IEEE Transactions on Image Processing.

[8]  Miroslaw Bober,et al.  Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization , 2011, Computational Imaging and Vision.

[9]  Guojun Lu,et al.  Study and evaluation of different Fourier methods for image retrieval , 2005, Image Vis. Comput..

[10]  Oskar Söderkvist,et al.  Computer Vision Classification of Leaves from Swedish Trees , 2001 .

[11]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[12]  Noel E. O'Connor,et al.  A multiscale representation method for nonrigid shapes with a single closed contour , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[13]  Davut Hanbay,et al.  Combination of Deep Features and KNN Algorithm for Classification of Leaf-Based Plant Species , 2019, 2019 International Artificial Intelligence and Data Processing Symposium (IDAP).

[14]  Bao-Long Guo,et al.  O2O Method for Fast 2D Shape Retrieval , 2019, IEEE Transactions on Image Processing.

[15]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[16]  Marco Lombardi,et al.  A Double-layer Approach for Historical Documents Archiving , 2018, 2018 Metrology for Archaeology and Cultural Heritage (MetroArchaeo).

[17]  Haibin Ling,et al.  Using the inner-distance for classification of articulated shapes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Longin Jan Latecki,et al.  Shape Similarity Measure Based on Correspondence of Visual Parts , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Fotopoulou Foteini,et al.  MULTIVARIATE ANGLE SCALE DESCRIPTOR FOR SHAPE RETRIEVAL , 2011 .

[20]  Graham W. Taylor,et al.  Deconvolutional networks , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Changming Sun,et al.  Can Walking and Measuring Along Chord Bunches Better Describe Leaf Shapes? , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[23]  Zhuowen Tu,et al.  Integrating contour and skeleton for shape classification , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[24]  Josef Kittler,et al.  Efficient and Robust Retrieval by Shape Content through Curvature Scale Space , 1998, Image Databases and Multi-Media Search.

[25]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[26]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[27]  Euripides G. M. Petrakis,et al.  Shape retrieval based on dynamic programming , 2000, IEEE Trans. Image Process..

[28]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[29]  Yunyi Yan,et al.  A Weighted Fourier and Wavelet-Like Shape Descriptor Based on IDSC for Object Recognition , 2019, Symmetry.

[30]  Wei Jia,et al.  Multiscale Distance Matrix for Fast Plant Leaf Recognition , 2012, IEEE Transactions on Image Processing.

[31]  Björn Stenger,et al.  Shape context and chamfer matching in cluttered scenes , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[32]  Naif Alajlan,et al.  Shape retrieval using triangle-area representation and dynamic space warping , 2007, Pattern Recognit..

[33]  Francesco Colace,et al.  How to Describe Cultural Heritage Resources in the Web 2.0 Era? , 2015, 2015 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[34]  Jinhee Chun,et al.  Distance interior ratio: A new shape signature for 2D shape retrieval , 2016, Pattern Recognit. Lett..

[35]  Graham W. Taylor,et al.  Adaptive deconvolutional networks for mid and high level feature learning , 2011, 2011 International Conference on Computer Vision.

[36]  Mohammad Reza Daliri,et al.  Robust symbolic representation for shape recognition and retrieval , 2008, Pattern Recognit..

[37]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Haibin Ling,et al.  Shape Classification Using the Inner-Distance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Bao-Long Guo,et al.  A Fourier Descriptor of 2D Shapes Based on Multiscale Centroid Contour Distances Used in Object Recognition in Remote Sensing Images , 2019, Sensors.