Shape retrieval through normalized B-splines curves

This paper proposes a new technique for 2D shape modeling and retrieval based only on curves defined from shape boundary. Firstly, a shape representation system is build based on the decomposition of the outline into its constituent parts and their geometric description. The process decomposition is done using high curvature points located along the boundary. These obtained parts are then described by parametric curves using the B-spline approximation and normalized in order to eliminate scaling transformation. Finally, the resulting curves allow matching of shapes and retrieving that is robust to rotation, scale change and deformation. Experiments conducted on a variety of shape databases including Kimia-99, Kimia-216, MPEG-7 and our database created from a selection of ETH-80 shape database, illustrate the performance of the proposed approach when compared with existing algorithms in literature. Obtained results are presented and discussed.

[1]  Dmitry Chetverikov,et al.  A Simple and Efficient Algorithm for Detection of High Curvature Points in Planar Curves , 2003, CAIP.

[2]  Ricardo da Silva Torres,et al.  Shape feature extraction and description based on tensor scale , 2010, Pattern Recognit..

[3]  Jianyu Yang,et al.  Invariant multi-scale descriptor for shape representation, matching and retrieval , 2016, Comput. Vis. Image Underst..

[4]  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.

[5]  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..

[6]  Yujie Liu,et al.  Multiscale shape context and re-ranking for deformable shape retrieval , 2016, Comput. Graph..

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

[8]  Helmut Pottmann,et al.  Fitting B-spline curves to point clouds by curvature-based squared distance minimization , 2006, TOGS.

[9]  Guoyou Wang,et al.  Contour descriptor based on space symmetry and its matching technique , 2013 .

[10]  Joviša Žunić,et al.  The distance between shape centroids is less than a quarter of the shape perimeter , 2011, Pattern Recognit..

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

[12]  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).

[13]  Alan Hanjalic,et al.  Rate distortion optimal contour compression using cubic B-splines , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[14]  Naif Alajlan,et al.  Fast shape matching and retrieval based on approximate dynamic space warping , 2010, Artificial Life and Robotics.

[15]  W. Hayward.  Effects of outline shape in object recognition , 1998 .

[16]  Nancy M. Amato,et al.  alpha-Decomposition of polygons , 2012, Comput. Graph..

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

[18]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Slimane Larabi,et al.  2D shape matching based on B-spline curves and Dynamic Programming , 2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

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

[21]  R. Krishnamoorthi,et al.  Image retrieval using edge based shape similarity with multiresolution enhanced orthogonal polynomials model , 2013, Digit. Signal Process..

[22]  David Zhang,et al.  Hand shape recognition based on coherent distance shape contexts , 2012, Pattern Recognit..

[23]  Zhuowen Tu,et al.  Learning Context-Sensitive Shape Similarity by Graph Transduction , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Ehud Rivlin,et al.  Local Invariants For Recognition , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Francisco José Madrid-Cuevas,et al.  Polygonal approximation of digital planar curves through break point suppression , 2010, Pattern Recognit..

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

[27]  Mark S. Nixon,et al.  Shape classification via image-based multiscale description , 2011, Pattern Recognit..

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

[29]  Chakarida Nukoolkit,et al.  Represent Image Contents Using Curves and Chain Code , 2007, MVA.

[30]  Imre Juhász,et al.  A class of generalized B-spline curves , 2013, Comput. Aided Geom. Des..

[31]  R. Klette,et al.  Distance between Shape Centroids versus Shape Diameter , 2012 .

[32]  Fatos T. Yarman-Vural,et al.  BAS: a perceptual shape descriptor based on the beam angle statistics , 2003, Pattern Recognit. Lett..

[33]  Borut Zalik,et al.  Compressed vertex chain codes , 2007, Pattern Recognit..

[34]  Zhengwei Yang,et al.  Invariant matching and identification of curves using B-splines curve representation , 1995, IEEE Trans. Image Process..

[35]  Hyungjun Park,et al.  B-spline curve fitting based on adaptive curve refinement using dominant points , 2007, Comput. Aided Des..

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

[37]  Kurt Merzweiler,et al.  Contents lists available at SciVerse ScienceDirect , 2013 .

[38]  Irene Y. H. Gu,et al.  Coarse-to-fine planar object identification using invariant curve features and B-spline modeling , 2000, Pattern Recognit..

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

[40]  L. Piegl,et al.  The NURBS Book , 1995, Monographs in Visual Communications.

[41]  Wayne Niblack,et al.  Generating skeletons and centerlines from the distance transform , 1992, CVGIP Graph. Model. Image Process..

[42]  Jitendra Malik,et al.  Efficient shape matching using shape contexts , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[44]  Zongmin Ma,et al.  Shape feature descriptor using modified Zernike moments , 2011, Pattern Analysis and Applications.

[45]  Loris Nanni,et al.  Local phase quantization descriptor for improving shape retrieval/classification , 2012, Pattern Recognit. Lett..

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

[47]  Slimane Larabi,et al.  Retrieval of 2D objects and shape matching using the B-splines representation , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[48]  Laurent D. Cohen,et al.  Matching 2D and 3D articulated shapes using the eccentricity transform , 2011, Comput. Vis. Image Underst..

[49]  Reinhard Klette,et al.  ADR shape descriptor - Distance between shape centroids versus shape diameter , 2012, Comput. Vis. Image Underst..

[50]  Ronald L. Graham,et al.  An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set , 1972, Inf. Process. Lett..

[51]  Wenping Wang,et al.  Control point adjustment for B-spline curve approximation , 2004, Comput. Aided Des..

[52]  Jean-Claude Paul,et al.  Cubic B-spline curve approximation by curve unclamping , 2010, Comput. Aided Des..