An almost complete curvature scale space representation: Euclidean case

Abstract Here, we intend to propose local shape curve features which are invariant under planar Euclidean transformations and independent with respect to the original curve parameterization. The present work generalizes the family of Curvature Scale Space descriptors in order to increase the shape information quantity to tend to the completeness property. For this, a more pragmatic criterion is introduced in this paper which we call the almost completeness. We define it as a pre-completeness for a given resolution of features. Such descriptors are formed by the curvatures on the set of curve points obtained from the antecedents of different curvature levels. This level set is fixed with a given rule. The idea of the almost completeness is to make a compromise between the cardinal of the set of curvature’s levels and the optimal number of scales. The rule is submitted to an unsupervised statistical study and the scales are obtained with a spectral analysis. Experiments are conducted on several known datasets. Promising results in the sense of shape retrieval and shape recognition rates are demonstrated.

[1]  Guojun Lu,et al.  Generic Fourier descriptor for shape-based image retrieval , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[2]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[4]  Philip N. Klein,et al.  Recognition of shapes by editing their shock graphs , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Gösta H. Granlund,et al.  Fourier Preprocessing for Hand Print Character Recognition , 1972, IEEE Transactions on Computers.

[6]  Faouzi Ghorbel,et al.  Robust and Efficient Fourier-Mellin Transform Approximations for Gray-Level Image Reconstruction and Complete Invariant Description , 2001, Comput. Vis. Image Underst..

[7]  Andrew Zisserman,et al.  Scene Classification Via pLSA , 2006, ECCV.

[8]  Faouzi Ghorbel.  Stability of invariant Fourier descriptors and its inference in the shape classification , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[9]  Xiaoou Tang,et al.  2D Shape Matching by Contour Flexibility , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  D. Kendall.  SHAPE MANIFOLDS, PROCRUSTEAN METRICS, AND COMPLEX PROJECTIVE SPACES , 1984 .

[11]  Eamonn J. Keogh,et al.  Everything you know about Dynamic Time Warping is Wrong , 2004 .

[12]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Sinisa Todorovic,et al.  Matching Hierarchies of Deformable Shapes , 2009, GbRPR.

[14]  Horst Bunke,et al.  Simple and fast computation of moments , 1991, Pattern Recognit..

[15]  Joshua D. Schwartz,et al.  Hierarchical Matching of Deformable Shapes , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Whoi-Yul Kim,et al.  A region-based shape descriptor using Zernike moments , 2000, Signal Process. Image Commun..

[17]  Josef Kittler,et al.  Robust and Efficient Shape Indexing through Curvature Scale Space , 1996, BMVC.

[18]  Xiaojun Wu,et al.  A novel contour descriptor for 2D shape matching and its application to image retrieval , 2011, Image Vis. Comput..

[19]  Paramesran Raveendran,et al.  Chebyshev moments as a new set of moments for image reconstruction , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[20]  Huazhong Shu,et al.  Efficient Legendre moment computation for grey level images , 2014, Pattern Recognit..

[21]  Thomas R. Crimmins.  A Complete Set of Fourier Descriptors for Two-Dimensional Shapes , 1982, IEEE Transactions on Systems, Man, and Cybernetics.

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

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  Hassan Silkan,et al.  A Novel Shape Descriptor Based on Extreme Curvature Scale Space Map Approach for Efficient Shape Similarity Retrieval , 2009, 2009 Fifth International Conference on Signal Image Technology and Internet Based Systems.

[25]  Stefano Soatto,et al.  Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[26]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[27]  Faouzi Ghorbel,et al.  A Novel 2D Contour Description Generalized Curvature Scale Space , 2016, RFMI.

[28]  Maher Ahmed,et al.  Shape representation and description using the Hilbert curve , 2009, Pattern Recognit. Lett..

[29]  Kaleem Siddiqi,et al.  A shock grammar for recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[30]  B. Chandra Mohan,et al.  Content Based Image Retrieval Using Exact Legendre Moments and Support Vector Machine , 2010, ArXiv.

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

[32]  Mário A. T. Figueiredo,et al.  Similarity-based classification of sequences using hidden Markov models , 2004, Pattern Recognit..

[33]  Mohammad Reza Daliri,et al.  Classification of silhouettes using contour fragments , 2009, Comput. Vis. Image Underst..

[34]  King-Sun Fu,et al.  Shape Discrimination Using Fourier Descriptors , 1977, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Slimane Larabi,et al.  Curve normalization for shape retrieval , 2014, Signal Process. Image Commun..

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

[37]  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.

[38]  Philip N. Klein,et al.  On Aligning Curves , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[40]  Cordelia Schmid,et al.  A sparse texture representation using local affine regions , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Sharad Mehrotra,et al.  Similar shape retrieval in MARS , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[42]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[43]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[44]  Smit Marvaniya,et al.  Adaptive locally affine-invariant shape matching , 2018, Machine Vision and Applications.

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

[46]  Ninad Thakoor,et al.  Hidden Markov Model-Based Weighted Likelihood Discriminant for 2-D Shape Classification , 2007, IEEE Transactions on Image Processing.

[47]  Faouzi Ghorbel,et al.  Image reconstruction from a complete set of similarity invariants extracted from complex moments , 2006, Pattern Recognit. Lett..

[48]  Song Wang,et al.  Two perceptually motivated strategies for shape classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[49]  Alberto Del Bimbo,et al.  Retrieval by Shape Similarity with Perceptual Distance and Effective Indexing , 2000, IEEE Trans. Multim..

[50]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[51]  Mubarak Shah,et al.  Shape matching and modeling using skeletal context , 2008, Pattern Recognit..

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

[53]  Guojun Lu,et al.  Enhanced Generic Fourier Descriptors for object-based image retrieval , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[54]  Peter Meer,et al.  Designing a Boosted Classifier on Riemannian Manifolds , 2016 .

[55]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[56]  Kaiming He,et al.  Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour , 2017, ArXiv.

[57]  Ulrich Eckhardt,et al.  Shape descriptors for non-rigid shapes with a single closed contour , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[58]  Kaleem Siddiqi,et al.  Parts of Visual Form: Computational Aspects , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[59]  Célia A. Zorzo Barcelos,et al.  Image feature descriptor based on shape salience points , 2013, Neurocomputing.

[60]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[61]  M. Nixon,et al.  Shape classification using multiscale Fourier-based description in 2-D space , 2008, 2008 9th International Conference on Signal Processing.

[62]  P. Wintz,et al.  An efficient three-dimensional aircraft recognition algorithm using normalized fourier descriptors , 1980 .

[63]  Junwei Wang,et al.  Shape matching and classification using height functions , 2012, Pattern Recognit. Lett..

[64]  Dengsheng Zhang.  Image retrieval based on shape , 2002 .

[65]  Shantanu H. Joshi,et al.  Elastic Shape Analysis of Functions, Curves and Trajectories , 2016 .

[66]  Qian Yu,et al.  Multiscale Fourier descriptor based on triangular features for shape retrieval , 2019, Signal Process. Image Commun..

[67]  Xiang Bai,et al.  Shape Vocabulary: A Robust and Efficient Shape Representation for Shape Matching , 2014, IEEE Transactions on Image Processing.

[68]  Anuj Srivastava,et al.  Analysis of planar shapes using geodesic paths on shape spaces , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[70]  Faouzi Ghorbel.  Towards a unitary formulation for invariant image description: application to image coding , 1998, Ann. des Télécommunications.

[71]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[72]  Anuj Srivastava,et al.  Shape Analysis of Elastic Curves in Euclidean Spaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[73]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..