How to use Feature2D (such as SimpleBlobDetector) correctly? (Python + OpenCV)

Question

I'm trying to run blob detection using some simple code:

img = cv2.imread(args["image"])
height, width, channels = img.shape

params = cv2.SimpleBlobDetector_Params()

params.filterByColor = True
params.blobColor = 0

blob_detector = cv2.SimpleBlobDetector(params)
keypoints = blob_detector.detect(img)

However I keep getting the following error:

Traceback (most recent call last):
  File "test2.py", line 37, in <module>
    keypoints = blob_detector.detect(img)
TypeError: Incorrect type of self (must be 'Feature2D' or its derivative)

Does anyone know what might be wrong?

@Saranraj Nambusubramaniyan It is RGB. I've already set filterByColor = True though. — John M.
– John M., Commented Jan 7, 2018 at 12:33

Kinght 金 · Accepted Answer · 2018-04-26 06:50:05Z

47

If your OpenCV version is 2.x, then use cv2.SimpleBlobDetector(). Otherwise if your OpenCV version 3.x (or 4.x), then use cv2.SimpleBlobDetector_create to create the detector.

## check opencv version and construct the detector
is_v2 = cv2.__version__.startswith("2.")
if is_v2:
    detector = cv2.SimpleBlobDetector()
else:
    detector = cv2.SimpleBlobDetector_create()

## detect 
kpts = detector.detect(img)

edited Apr 26, 2018 at 6:50

answered Jan 7, 2018 at 12:33

Kinght 金

18.4k5 gold badges63 silver badges77 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

John M. Over a year ago

Oh! That wasn't obvious at all. Do you know where that's documented? All of the other SO questions I saw use SimpleBlobDetector(params) to create the detector.

Collectives™ on Stack Overflow

How to use Feature2D (such as SimpleBlobDetector) correctly? (Python + OpenCV)

1 Answer 1

1 Comment

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Linked

Related