zbMATH — the first resource for mathematics

The canny edge detector revisited. (English) Zbl 1235.68277
Summary: Canny suggested that an optimal edge detector should maximize both signal-to-noise ratio and localization, and he derived mathematical expressions for these criteria. Based on these criteria, he claimed that the optimal step edge detector was similar to a derivative of a Gaussian. However, Canny’s work suffers from two problems. First, his derivation of localization criterion is incorrect. Here we provide a more accurate localization criterion and derive the optimal detector from it. Second, and more seriously, the Canny criteria yield an infinitely wide optimal edge detector. The width of the optimal detector can however be limited by considering the effect of the neighbouring edges in the image. If we do so, we find that the optimal step edge detector, according to the Canny criteria, is the derivative of an ISEF filter, proposed by Shen and Castan. In addition, if we also consider detecting blurred (or non-sharp) Gaussian edges of different widths, we find that the optimal blurred-edge detector is the above optimal step edge detector convolved with a gaussian. This implies that edge detection must be performed at multiple scales to cover all the blur widths in the image. We derive a simple scale selection procedure for edge detection, and demonstrate it in one and two dimensions.

68T45 Machine vision and scene understanding
94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
Full Text: DOI
[1] Bracewell, R. N. (1986). The Fourier transform and its applications. New York: McGraw-Hill. · Zbl 0608.42001
[2] Burton, G. J., & Moorhead, IR (1987). Color and spatial structure in natural scenes. Applied Optics, 26, 157–170. · doi:10.1364/AO.26.000157
[3] Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Image Processing, 8(6), 679–698. · doi:10.1109/TPAMI.1986.4767851
[4] Deriche, R. (1987). Using Canny’s criteria to derive a recursively implemented optimal edge detector. International Journal of Computer Vision, 1(2), 167–187. · doi:10.1007/BF00123164
[5] Elder, J., & Zucker, S. (1998). Local scale control for edge detection and blur estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(7), 699–716. · doi:10.1109/34.689301
[6] Elder, J. (1999). Are Edges Incomplete? International Journal of Computer Vision, 34, 97–122. · doi:10.1023/A:1008183703117
[7] Field, D. (1987). Relations between the statistics of natural images and the response properties of cortical cells. Journal of the Optical Society of America A, 4, 2379–2394. · doi:10.1364/JOSAA.4.002379
[8] Georgeson, M. A., May, K. A., Freeman, T. C. A., & Hesse, G. S. (2007). From filters to features: Scale–space analysis of edge and blur coding in human vision. Journal of Vision, 7(13), 1–21. · doi:10.1167/7.13.7
[9] Hinkley, D. V. (1969). On the ratio of two correlated normal random variables. Biometrika, 56, 635–639. · Zbl 0183.48101 · doi:10.1093/biomet/56.3.635
[10] Koplowitz, J., & Greco, V. (1994). On the edge location error for local maximum and zero-crossing edge detectors. IEEE Transactions on Pattern Analysis and Image Processing, 16(12), 1207–1212. · Zbl 05112954 · doi:10.1109/34.387487
[11] Lindeberg, T. (1998). Edge detection and ridge detection with automatic scale selection. International Journal of Computer Vision, 30(2), 117–154. · Zbl 05469780 · doi:10.1023/A:1008097225773
[12] Marsaglia, G. (1965). Ratios of normal variables and ratios of sums of uniform variables. Journal of the American Statistical Association, 60, 193–204. · Zbl 0126.35302 · doi:10.1080/01621459.1965.10480783
[13] Marsaglia, G. (2006). Ratios of normal variables. Journal of Statistical Software, 16(4), 1–10.
[14] May, K., & Georgeson, M. (2007). Blurred edges look faint, and faint edges look sharp. Vision Research, 47, 1705–1720. · doi:10.1016/j.visres.2007.02.012
[15] Peli, T., & Malah, D. (1982). A study of edge detection algorithms. Computer Graphics and Image Processing, 20, 1–21. · Zbl 0532.68083 · doi:10.1016/0146-664X(82)90070-3
[16] Sarkar, S., & Boyer, K. L. (1991). On optimal infinite impulse response edge detection filters. IEEE Transactions on Pattern Analysis Machine Intelligence, 13, 1154–1171. · Zbl 05112708 · doi:10.1109/34.103275
[17] Shen, J., & Castan, S. (1992). An optimal linear operator for step edge detection. Graphical Models and Image Processing, 54, 112–133. · doi:10.1016/1049-9652(92)90060-B
[18] Shen, J. (1995). Multi-edge detection by isotropical 2-D ISEF cascade. Pattern Recognition, 28, 1871–1885. · Zbl 05478200 · doi:10.1016/0031-3203(95)00056-9
[19] Tadmor, Y., & Tolhurst, D. J. (1993). Both the phase and the amplitude spectrum may determine the appearance of natural images. Vision Research, 33(1), 141–145. · doi:10.1016/0042-6989(93)90067-7
[20] Tagare, H., & deFigueiredo, R. (1990). On the localization performance measure and edge detection. IEEE Transactions on Pattern Analysis and Image Processing, 12(12), 1186–1190. · Zbl 05112916 · doi:10.1109/34.62607
[21] Wainwright, M. J. (1999). Visual adaptation as optimal information transmission. Vision Research, 39, 3960–3974. · doi:10.1016/S0042-6989(99)00101-7
[22] Webster, M. A., Georgeson, M., & Webster, S. M. (2002). Neural adjustments to image blur. Nature Neuroscience, 5(9), 839–840. · doi:10.1038/nn906
[23] Witkin, A. P. (1983). Scale–space filtering. In Proceedings of the 8th international joint conference on artificial intelligence (pp. 1019–1022).
[24] Ziou, D., & Tabbone, S. (1998). Edge detection techniques–an overview. International Journal of Pattern Recognition and Image Analysis, 8, 537–559.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.