The image ray transform for structural feature detection

The use of analogies to physical phenomena is an exciting paradigm in computer vision that allows unorthodox approaches to feature extraction, creating new techniques with unique properties. A technique known as the ''image ray transform'' has been developed based upon an analogy to the propagation of light as rays. The transform analogises an image to a set of glass blocks with refractive index linked to pixel properties and then casts a large number of rays through the image. The course of these rays is accumulated into an output image. The technique can successfully extract tubular and circular features and we show successful circle detection, ear biometrics and retinal vessel extraction. The transform has also been extended through the use of multiple rays arranged as a beam to increase robustness to noise, and we show quantitative results for fully automatic ear recognition, achieving 95.2% rank one recognition across 63 subjects.

[1]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[2]  L. Mazorra,et al.  Fitting ear contour using an ovoid model , 2005, Proceedings 39th Annual 2005 International Carnahan Conference on Security Technology.

[3]  Alfred M. Bruckstein,et al.  DigiDürer — a digital engraving system , 1993, The Visual Computer.

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

[5]  Bram van Ginneken,et al.  Comparative study of retinal vessel segmentation methods on a new publicly available database , 2004, SPIE Medical Imaging.

[6]  Ping Yan,et al.  Empirical Evaluation of Advanced Ear Biometrics , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[7]  JiangXiaoyi,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003 .

[8]  Xiaoyi Jiang,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Mark S. Nixon,et al.  Circle Detection Using the Image Ray Transform , 2010 .

[10]  M.S. Nixon,et al.  Robust 2D Ear Registration and Recognition Based on SIFT Point Matching , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[11]  E. R. Davies,et al.  A modified Hough scheme for general circle location , 1988, Pattern Recognit. Lett..

[12]  Josef Kittler,et al.  A Comparative Study of Hough Transform Methods for Circle Finding , 1989, Alvey Vision Conference.

[13]  Petros Maragos,et al.  Multiscale Morphological Segmentations Based on Watershed, Flooding, and Eikonal PDE , 1999, Scale-Space.

[14]  P. Jonathon Phillips,et al.  Empirical Evaluation Methods in Computer Vision , 2002 .

[15]  David J. Hurley,et al.  Force Field Feature Extraction for Ear Biometrics , 2005, Image Pattern Recognition.

[16]  Mark S. Nixon,et al.  On Using Physical Analogies for Feature and Shape Extraction in Computer Vision , 2008, BCS Int. Acad. Conf..

[17]  Mark S. Nixon,et al.  On Shape-Mediated Enrolment in Ear Biometrics , 2007, ISVC.

[18]  Mark S. Nixon,et al.  Retinal Vessel Extraction with the Image Ray Transform , 2010, ISVC.

[19]  Sudeep Sarkar,et al.  Comparison and Combination of Ear and Face Images in Appearance-Based Biometrics , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

[21]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[22]  Mohammed Bennamoun,et al.  Fast and Fully Automatic Ear Detection Using Cascaded AdaBoost , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[23]  Francis J. Hill.  Computer Graphics Using Open GL , 1990 .

[24]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[25]  Mark S. Nixon,et al.  A novel ray analogy for enrolment of ear biometrics , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

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

[27]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[28]  M.S. Nixon,et al.  On Model-Based Analysis of Ear Biometrics , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[29]  Bruce A. Draper,et al.  The CSU Face Identification Evaluation System , 2005, Machine Vision and Applications.