Fast and Robust 2D-Shape Extraction Using Discrete-Point Sampling and Centerline Grouping in Complex Images

This paper initially develops the discrete-point sampling operator's concept, model, and parameters that we have previously proposed, and makes its belt-shaped regions in a discrete-point sampling map more salient and appropriate for centerline extraction. The cross-sectional features of these belt-shaped regions are then analyzed and seven types of feature points are defined to facilitate descriptions of such features. Based on these feature points, a three-level detection system is proposed, including feature points, line segments, and centerlines, to extract centerlines from the belt-shaped regions. Eight basic types of centerlines and five types of relationships among the centerlines are defined by computational geometry algorithms, and Gestalt laws are used to cluster them into groupings. If some prior information about a desired shape is available, retrieval grouping may be carried out by a discrete-point sampling map, the purpose of which is to find centerlines by best matching with prior information. Discrete-point sampling effectually overcomes the influences of interference from noise, textures, and uneven illumination, and greatly reduces the difficulty of centerline extraction. Centerline clustered groupings and retrieval grouping can offer a strong anti-interference ability with nonlinear deformations such as articulation and occlusion. This method can extract large-scale complex shapes combined of lines and planes from complex images. The wheel location results of noise test and other shape extraction experiments show that our method has a strong capability to persist with nonlinear deformations.

[1]  ZuWhan Kim,et al.  Robust Lane Detection and Tracking in Challenging Scenarios , 2008, IEEE Transactions on Intelligent Transportation Systems.

[2]  Nando de Freitas,et al.  A Statistical Model for General Contextual Object Recognition , 2004, ECCV.

[3]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  James H. Johnson,et al.  Just Noticeable Difference , 2010 .

[5]  Cunlu Xu,et al.  Contour Grouping: Focusing on Image Patches Around Edges , 2006, VSMM.

[6]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Peng-Lang Shui,et al.  Noise-robust edge detector combining isotropic and anisotropic Gaussian kernels , 2012, Pattern Recognit..

[8]  Jiri Matas,et al.  Detection and matching of curvilinear structures , 2011, Pattern Recognit..

[9]  Frank Nielsen,et al.  Shape Retrieval Using Hierarchical Total Bregman Soft Clustering , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Zhihong Liu,et al.  Displacement fault detection of bearing weight saddle in TFDS based on hough transform and symmetry validation , 2012, 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery.

[11]  W. Clem Karl,et al.  Line detection in images through regularized hough transform , 2006, IEEE Transactions on Image Processing.

[12]  David H. Eberly,et al.  Ridges for image analysis , 1994, Journal of Mathematical Imaging and Vision.

[13]  David Zhang,et al.  Detecting Wide Lines Using Isotropic Nonlinear Filtering , 2007, IEEE Transactions on Image Processing.

[14]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Y. J. Zhang Two new concepts for N/sub 16/ space , 1999, IEEE Signal Processing Letters.

[16]  Xavier Cufí,et al.  Yet Another Survey on Image Segmentation: Region and Boundary Information Integration , 2002, ECCV.

[17]  Jianhong Shen,et al.  On the foundations of vision modeling: I. Weber’s law and Weberized TV restoration , 2003 .

[18]  Frédéric Jurie,et al.  Groups of Adjacent Contour Segments for Object Detection , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Xudong Yang,et al.  Research of Computer Vision Fault Recognition Algorithm of Center Plate Bolts of Train , 2011, 2011 First International Conference on Instrumentation, Measurement, Computer, Communication and Control.

[20]  David A. Clausi,et al.  Decoupled Active Contour (DAC) for Boundary Detection , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Song Wang,et al.  Edge Grouping Combining Boundary and Region Information , 2007, IEEE Transactions on Image Processing.

[22]  Nicolai Petkov,et al.  Adaptive Pseudo Dilation for Gestalt Edge Grouping and Contour Detection , 2008, IEEE Transactions on Image Processing.

[23]  Cuneyt Akinlar,et al.  EDContours: High-Speed Parameter-Free Contour Detector Using EDPF , 2012, 2012 IEEE International Symposium on Multimedia.

[24]  Azriel Rosenfeld,et al.  Histogram concavity analysis as an aid in threshold selection , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[25]  Djemel Ziou,et al.  Contextual and non-contextual performance evaluation of edge detectors , 2000, Pattern Recognit. Lett..

[26]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[27]  Deniz Erdogmus,et al.  Contour-based shape representation using principal curves , 2013, Pattern Recognit..

[28]  Carsten Steger,et al.  An Unbiased Detector of Curvilinear Structures , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Nicolai Petkov,et al.  Edge and line oriented contour detection: State of the art , 2011, Image Vis. Comput..

[30]  Guoyou Wang,et al.  Object detection based on multiscale discrete points sampling and grouping , 2009, International Symposium on Multispectral Image Processing and Pattern Recognition.

[31]  Ryszard Jakubowski Extraction of shape features for syntactic recognition of mechanical parts , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

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

[33]  Cuneyt Akinlar,et al.  Edpf: a Real-Time parameter-Free Edge Segment Detector with a False Detection Control , 2012, Int. J. Pattern Recognit. Artif. Intell..

[34]  David S. Doermann,et al.  A parallel-line detection algorithm based on HMM decoding , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[36]  Yakup Genc,et al.  Edge Drawing: A Heuristic Approach to Robust Real-Time Edge Detection , 2010, 2010 20th International Conference on Pattern Recognition.

[37]  Thomas C. M. Lee,et al.  Extraction of curvilinear features from noisy point patterns using principal curves , 2008, Pattern Recognit. Lett..

[38]  Shuxiao Li,et al.  Fast curvilinear structure extraction and delineation using density estimation , 2009, Comput. Vis. Image Underst..

[39]  Mauro Ursino,et al.  A model of contextual interactions and contour detection in primary visual cortex , 2004, Neural Networks.