A Performance Measure for Boundary Detection Algorithms

In this paper we discuss the issues involved when trying to compare the performance of algorithms which seek to find boundaries and boundary models between regions of differing mean gray-level value. The usefulness of such measures is not confined to comparing different approaches, but provides an important step to building self-optimizing vision systems that automatically adjust algorithm parameters at each level of the system to improve performance. We discuss the issues that such a performance measure should address, and then present a theoretical framework for the performance measure we proposed. We demonstrate the power of the measure by characterizing the performance of a three-stage medium level vision system for detecting straight line boundaries. Both synthetic imagery, for which ground truth is known, and real imagery are used to test the ability of the criterion to characterize the output of the system.

[1]  Peter de Souza,et al.  Edge detection using sliding statistical tests , 1983, Comput. Vis. Graph. Image Process..

[2]  J. Kittler,et al.  Accurate line parameters from an optimising Hough Transform for vanishing point detection , 1993, 1993 (4th) International Conference on Computer Vision.

[3]  Ioannis Pitas,et al.  Edge Detectors Based on Nonlinear Filters , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Radu Horaud,et al.  New Methods for Matching 3-D Objects with Single Perspective Views , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Josef Kittler,et al.  A Hough transform algorithm with a 2D hypothesis testing kernel , 1993 .

[6]  Arnold K. Griffith,et al.  Edge Detection in Simple Scenes Using a Priori Information , 1973, IEEE Transactions on Computers.

[7]  Christopher J. Taylor,et al.  Boundary Cue Operators for Model-based Image Processing , 1988, Alvey Vision Conference.

[8]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[9]  D. Petkovic.  The need for accuracy verification of machine vision algorithms and systems , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Dragutin Petkovic,et al.  On improving the accuracy of the Hough transform: theory, simulations, and experiments , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Robert M. Haralick.  Performance Characterization in Computer Vision , 1993, CAIP.

[12]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[13]  Libor Spacek,et al.  Edge detection and motion detection , 1986, Image Vis. Comput..

[14]  Josef Kittler,et al.  Optimal Edge Detectors for Ramp Edges , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Robert M. Haralick.  Methodology for experimental computer vision , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Tom J. Moir,et al.  A polynomial approach to optimal and adaptive filtering with application to speech , 1991, IEEE Trans. Signal Process..

[17]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[18]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

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