Edge detection

From neurov.is/on

Edge detection is a fundamental problem for visual systems. In computer vision, the Canny edge detector has came to dominate the field since its introduction in 1986. Hubel and Wiesel discovered cells in the V1 that they classified as simple cells, which have receptive fields that respond to oriented edges ^[1].

[edit] Simple Cells

[edit] Linear Models

Some of the linear models for simple cells include^[2]:

1. Difference of Gaussians ^[3][4]
2. Laplacian of a Gaussian ^[5]
3. Gabor ^{[6] [7] [8] [9]}
4. Cauchy ^[10]
5. 'Log Gabor' ^{[11] [12]}

[edit] References

1. ↑ Hubel, D. H.; Wiesel, T. N. (1962). "Receptive fields, binocular interaction and functional architecture in the cat's visual cortex". The Journal of Physiology 160: 106-154. 
2. ↑ Guy Wallis (2001). "Linear models of simple cells: Correspondence to real cell responses and space spanning properties". Spatial Vision 14: 237-260. 
3. ↑ Cite:Enroth-Cugell Robson 1966
4. ↑ D. Rose (1979). "Mechanisms underlying the receptive field properties of neurons in cat visual cortex". Vision Research 19 (1): 97-108. 
5. ↑ Cite:Marr Hildreth 1980
6. ↑ Cite:Marcelja 1980
7. ↑ Cite:Daugman 1980
8. ↑ Cite:Sakitt Barlow 1982
9. ↑ Cite:Watson 1983
10. ↑ Cite:Klein Levi 1985
11. ↑ Cite:Field 1987
12. ↑ Cite:Morrone Burr 1988