Detection of Curvilinear Structures by Tensor Voting Applied to Fiber Characterization

The paper presents a framework for the detection of curvilinear objects in images. Such objects are challenging to be described by a geometrical model, and although they appear in a number of applications, the problem of detecting curvilinear objects has drawn limited attention. The proposed approach starts with an edge detection algorithm after which the task of object detection becomes a problem of edge linking. A state-of-the-art local linking approach called tensor voting is used to estimate the edge point saliency describing the likelihood of a point belonging to a curve, and to extract the end points and junction points of these curves. After the tensor voting, the curves are grown from high-saliency seed points utilizing a linking method proposed in this paper. In the experimental part of the work, the method was systematically tested on pulp suspension images to characterize fibers based on their length and curl index. The fiber length was estimated with the accuracy of 71.5% and the fiber curvature with the accuracy of 70.7%.

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

[2]  David Gavaghan,et al.  Contrast-Independent Curvilinear Structure Detection in Biomedical Images , 2012, IEEE Transactions on Image Processing.

[3]  Nurcan Durak,et al.  Extracting salient contour groups from cluttered solar images via Markov Random Fields , 2011, 2011 18th IEEE International Conference on Image Processing.

[4]  Hongdong Li,et al.  Connected contours: A new contour completion model that respects the closure effect , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  R. J. Trepanier,et al.  Automatic fiber length and shape measurement by image analysis , 1998 .

[6]  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.

[7]  Mi-Suen Lee,et al.  A Computational Framework for Segmentation and Grouping , 2000 .

[8]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[9]  Wolfgang Bauer,et al.  A REVIEW OF IMAGE ANALYSIS BASED METHODS TO EVALUATE FIBER PROPERTIES , 2006 .

[10]  Gérard G. Medioni,et al.  First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Davide Pico,et al.  CHARACTERIZATION OF SHORT FIBERS , 2009 .

[12]  Ki-Sang Hong,et al.  Detection of curvilinear structures and reconstruction of their regions in gray-scale images , 2002, Pattern Recognit..

[13]  Srikanth Saripalli,et al.  Road detection from aerial imagery , 2012, 2012 IEEE International Conference on Robotics and Automation.

[14]  Mathias Kölsch,et al.  Emerging Topics in Computer Vision , 2004 .

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

[16]  Nancy Ross Sutherland,et al.  Comparison of fiber length analyzers , 2005 .

[17]  Gérard G. Medioni,et al.  Junction Inference and Classification for Figure Completion using Tensor Voting , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[18]  Costas Panagiotakis,et al.  Curvilinear Structure Enhancement and Detection in Geophysical Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.