Linear structure centerline detection using distance propagation

Detecting centerlines and estimating widths of linear structures are useful in low level computer vision. In this paper we consider the detection of linear structures with two parallel borders in 2D images. During a distance propagation process, we use a novel method named centerline hit detection to select pixels on the centerlines. Experimental results show the effectiveness and efficiency of our method in various applications. The proposed method can readily serve as a preprocessing step for solving computer vision tasks such as enhancement, recognition and classification.

[1]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[2]  Azriel Rosenfeld,et al.  Sequential Operations in Digital Picture Processing , 1966, JACM.

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

[4]  José Manuel Bravo,et al.  A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features , 2011, IEEE Transactions on Medical Imaging.

[5]  Ming Wan,et al.  Distance-field based skeletons for virtual navigation , 2001, Proceedings Visualization, 2001. VIS '01..

[6]  Qiaoping Zhang,et al.  Accurate Centerline Detection and Line Width Estimation of Thick Lines Using the Radon Transform , 2007, IEEE Transactions on Image Processing.

[7]  Aly A. Farag,et al.  Robust centerline extraction framework using level sets , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Vincent Lepetit,et al.  Supervised Feature Learning for Curvilinear Structure Segmentation , 2013, MICCAI.

[9]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[10]  Arthur W. Toga,et al.  Three-dimensional skeleton and centerline generation based on an approximate minimum distance field , 1998, The Visual Computer.

[11]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[12]  Yoshinobu Sato,et al.  A Hessian-based filter for vascular segmentation of noisy hepatic CT scans , 2012, International Journal of Computer Assisted Radiology and Surgery.

[13]  Roberto Marcondes Cesar Junior,et al.  Retinal Vessel Segmentation Using the 2-D Morlet Wavelet and Supervised Classification , 2005, ArXiv.

[14]  Luciano da Fontoura Costa,et al.  2D Euclidean distance transform algorithms: A comparative survey , 2008, CSUR.

[15]  Vincent Lepetit,et al.  Multiscale Centerline Detection by Learning a Scale-Space Distance Transform , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Wim H. Hesselink,et al.  A General Algorithm for Computing Distance Transforms in Linear Time , 2000, ISMM.

[17]  Yonatan Wexler,et al.  Detecting text in natural scenes with stroke width transform , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[19]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[20]  Jun-ichiro Toriwaki,et al.  New algorithms for euclidean distance transformation of an n-dimensional digitized picture with applications , 1994, Pattern Recognit..