Machine Vision and Applications Evaluating Contour Segment Descriptors

Contour segment (CS) is the fundamental element of partial boundaries or edges in shapes and images. So far, CS has been widely used in many applications, including object detection/matching and open curve matching. To increase the matching accuracy and efficiency, a variety of CS descriptors have been proposed. A CS descriptor is formed by a chain of boundary or edge points and is able to encode the geometric configuration of a CS. Because many different CS descriptors exist, a structured overview and quantitative evaluation are required in the context of CS matching. This paper assesses 27 CS descriptors in a structured way. Firstly, the analytical invariance properties of CS descriptors are explored with respect to scaling, rotation and transformation. Secondly, their distinctiveness is evaluated experimentally on three datasets. Lastly, their computation complexity is studied. Based on results, we find that both CS lengths and matching algorithms affect the CS matching performance while matching algorithms have higher affection. The results also reveal that, with different combinations of CS descriptors and matching algorithms, several requirements in terms of matching speed and accuracy can be fulfilled. Furthermore, a proper combination of CS descriptors can improve the matching accuracy over the individuals.

[1]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[2]  Wageeh Boles,et al.  Recognition of 2D object contours using the wavelet transform zero-crossing representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

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

[4]  Jianbo Shi,et al.  DeepEdge: A multi-scale bifurcated deep network for top-down contour detection , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Aljoscha Smolic,et al.  A set of visual feature descriptors and their combination in a low-level description scheme , 2000, Signal Process. Image Commun..

[6]  Longin Jan Latecki,et al.  From partial shape matching through local deformation to robust global shape similarity for object detection , 2011, CVPR 2011.

[7]  Alfred M. Bruckstein,et al.  Partial Similarity of Objects, or How to Compare a Centaur to a Horse , 2009, International Journal of Computer Vision.

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

[9]  Jianbo Shi,et al.  Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach , 2008, ECCV.

[10]  Steven Homer,et al.  Introduction to Complexity Theory , 2011 .

[11]  Udo Kelter,et al.  Shape-based object retrieval by contour segment matching , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[12]  Hans-Peter Seidel,et al.  Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Rama Chellappa,et al.  Fourier Coding of Image Boundaries , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Wenyu Liu,et al.  Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  M. Kendall,et al.  An Introduction to the Theory of Statistics. , 1911 .

[16]  Sang Uk Lee,et al.  Recognition of 2D Object Contours Using Starting-Point-Independent Wavelet Coefficient Matching , 1998, J. Vis. Commun. Image Represent..

[17]  Marc Alexa,et al.  Sketch-based shape retrieval , 2012, ACM Trans. Graph..

[18]  Rogério Schmidt Feris,et al.  Efficient partial shape matching using Smith-Waterman algorithm , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[19]  B. Weiner,et al.  CANDELS: CORRELATIONS OF SPECTRAL ENERGY DISTRIBUTIONS AND MORPHOLOGIES WITH STAR FORMATION STATUS FOR MASSIVE GALAXIES AT z ∼ 2 , 2012, 1204.4194.

[20]  Luc Van Gool,et al.  Object Detection by Contour Segment Networks , 2006, ECCV.

[21]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[22]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Mohammad Reza Daliri,et al.  Shape recognition based on Kernel-edit distance , 2010, Comput. Vis. Image Underst..

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

[25]  Peter H. Sellers,et al.  The Theory and Computation of Evolutionary Distances: Pattern Recognition , 1980, J. Algorithms.

[26]  Fang Wang,et al.  Sketch-based 3D shape retrieval using Convolutional Neural Networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Stefan Carlsson,et al.  Appearance Based Qualitative Image Description for Object Class Recognition , 2004, ECCV.

[28]  M KurtzbergJerome.  On Approximation Methods for the Assignment Problem , 1962 .

[29]  Hayko Riemenschneider,et al.  Using Partial Edge Contour Matches for Efficient Object Category Localization , 2010, ECCV.

[30]  Nobuyuki Otsu,et al.  ATlreshold Selection Method fromGray-Level Histograms , 1979 .

[31]  Sinisa Todorovic,et al.  From a Set of Shapes to Object Discovery , 2010, ECCV.

[32]  Dylan A. Shell,et al.  Assessing Optimal Assignment under Uncertainty: An Interval-based Algorithm , 2010, Robotics: Science and Systems.

[33]  Andrew Blake,et al.  Multiscale Categorical Object Recognition Using Contour Fragments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Stan Salvador,et al.  FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space , 2004 .

[35]  Witold Pedrycz,et al.  Chain Code-Based Local Descriptor for Face Recognition , 2015, CORES.

[36]  Jitendra Malik,et al.  Hypercolumns for object segmentation and fine-grained localization , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Kpalma Kidiyo,et al.  A Survey of Shape Feature Extraction Techniques , 2008 .

[38]  A. M. Andrew,et al.  Another Efficient Algorithm for Convex Hulls in Two Dimensions , 1979, Inf. Process. Lett..

[39]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[40]  R Bellman,et al.  On the Theory of Dynamic Programming. , 1952, Proceedings of the National Academy of Sciences of the United States of America.

[41]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[43]  Peter J. van Otterloo,et al.  A contour-oriented approach to shape analysis , 1991 .

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

[45]  Mauro Dell'Amico,et al.  Assignment Problems , 1998, IFIP Congress: Fundamentals - Foundations of Computer Science.

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

[47]  Ian T. Young,et al.  An Analysis Technique for Biological Shape. I , 1974, Inf. Control..

[48]  Timothy F. Cootes,et al.  Trainable method of parametric shape description , 1992, Image Vis. Comput..

[49]  Jerome M. Kurtzberg,et al.  On Approximation Methods for the Assignment Problem , 1962, JACM.

[50]  J. Wolfowitz,et al.  Introduction to the Theory of Statistics. , 1951 .

[51]  Javid Taheri,et al.  SparseDTW: A Novel Approach to Speed up Dynamic Time Warping , 2009, AusDM.

[52]  H. Kuhn.  The Hungarian method for the assignment problem , 1955 .

[53]  Udo Kelter,et al.  Shape-based Object Retrieval and Classification with Supervised Optimisation , 2015, ICPRAM.

[54]  Hayko Riemenschneider,et al.  Efficient Partial Shape Matching of Outer Contours , 2009, ACCV.

[55]  Nassir Navab,et al.  Total variation regularization of shape signals , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[56]  Wenyu Liu,et al.  Bag of contour fragments for robust shape classification , 2014, Pattern Recognit..

[57]  Longin Jan Latecki,et al.  Shape guided contour grouping with particle filters , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[58]  Jörg-Rüdiger Sack,et al.  Improved Algorithms for Partial Curve Matching , 2011, ESA.

[59]  Adam Krzyzak,et al.  Reconstruction of two-dimensional patterns from Fourier descriptors , 2005, Machine Vision and Applications.

[60]  D. Cox.  Karl Pearson and the Chi-Squared Test , 2002 .

[61]  Mauro Dell'Amico,et al.  8. Quadratic Assignment Problems: Algorithms , 2009 .

[62]  J. IIVARINENHelsinki.  Efficiency of Simple Shape Descriptors , 1997 .

[63]  André Ricardo Backes,et al.  Shape classification using line segment statistics , 2015, Inf. Sci..

[64]  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).

[65]  Matti Pietikäinen,et al.  An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

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

[67]  Hayko Riemenschneider,et al.  Discriminative Learning of Contour Fragments for Object Detection , 2011, BMVC.