Canny's goal is to find an optimal
edge
detection algorithm. The meaning of optimal edge detection is:
Good Detection
- Algorithms are able to identify as many actual edges in the image as possible.
Good localization
- The identified edges are as close as possible to the actual edges in the actual image.
Minimal Response
- Edges in the image should only be identified once, and possible image noise should not be identified as edges.
To meet these requirements Canny uses
variational
methods , a method of finding functions that satisfy a specific function. Optimal detection is expressed using the sum of four
exponential
terms, but it is very close to the first derivative of the
Gaussian
function .
import
matplotlib.pyplot
as
plt
import
matplotlib.image
as
mpimg
import
cv2
import
numpy
as
np
image
=
cv2.imread(
"./imgs/2.jpg"
)
gray
=
cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
wide
=
cv2.Canny(gray,
30
,
100
)
tight
=
cv2.Canny(gray,
180
,
240
)
f,(a1,a2)
=
plt.subplots(
1
,
2
,
figsize
=
(
200
,
200
))
a1.set_title(
"wide"
)
a1.imshow(wide,
cmap
=
'gray'
)
a2.set_title(
"tight"
)
a2.imshow(tight,
cmap
=
'gray'
)
plt.show()
