Blob detection not working

Question

I'm trying to detect blobs in an image but its not working somehow. Basically I want to determine number of circles.

Code:

import cv2
import numpy as np
import sys
# Read image
im = cv2.imread("K.jpg", cv2.IMREAD_GRAYSCALE)

# Setup SimpleBlobDetector parameters.
params = cv2.SimpleBlobDetector_Params()

# Change thresholds
params.minThreshold = 10
params.maxThreshold = 200

# Filter by Area.
params.filterByArea = True
params.minArea = 50

# Filter by Circularity
params.filterByCircularity = True
params.minCircularity = 0.75

# Filter by Convexity
params.filterByConvexity = True
params.minConvexity = 0.87

# Filter by Inertia
params.filterByInertia = True
params.minInertiaRatio = 0.7

detector = cv2.SimpleBlobDetector_create(params)


# Detect blobs.
keypoints = detector.detect(im)
print len(keypoints)
# Draw detected blobs as red circles.
# cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS ensures
# the size of the circle corresponds to the size of blob

im_with_keypoints = cv2.drawKeypoints(im, keypoints, np.array([]), (0, 0, 255),
                                      cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

# Show blobs
cv2.imshow("Keypoints", im_with_keypoints)
if cv2.waitKey(0) and 0xff==27:
    cv2.destroyAllWindows()

Here's the input image:

You seem to be on the right path. Here is some material you can read to figure out why it's not working for you: Blob detection using openCV — jVincent
– jVincent, Commented Feb 23, 2017 at 8:33

Community · Accepted Answer · 2020-06-20 09:12:55Z

8

I have figured out the solution.

When it comes to detection of blobs; you are identifying outliers/unwanted objects in the image. Hence these so called blobs/outliers are assumed to be black/grayish on a plain background. In other words, blobs are assumed to be easily identifiable against a white background.

When you perform blob detection against a gray scale image of the original image, the background present is black as shown:

Against a black background blob detection finds nothing :(

What do I do?

This is what I did. It was just a single line of a hack. I blurred the gray scale image and then inverted it using inverted_img = cv2.bitwise_not(blur)

I then passed the obtained image to the blob detection function. And this is what I got:

I am able to obtain the number of blobs present as well:

number = 0
for i in keypoints[0:]:
    number = number + 1    

print "Number of blobs:",number

And this is what I got in the console screen:

edited Jun 20, 2020 at 9:12

CommunityBot

11 silver badge

answered Feb 23, 2017 at 17:27

Jeru Luke

21.4k13 gold badges85 silver badges91 bronze badges

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

4 Comments

StupidGuy Over a year ago

Point Noted. BTW instead of using loop to calculate the no. of blob you could have simply used len(keypoints). Thanks again.

StupidGuy Over a year ago

Just a simple question,how exactly did the statement inverted_img = cv2.bitwise_not(blur) made the code run. And one more thing I'm unable to obtain circles of same radius as the blob(In my case the circles are smaller than the blob)

Jeru Luke Over a year ago

Try cv2.imshow() of the inverted image and see for yourself. You will understand. To get better radius, try performing Gaussian blur before blob detection. That is what I did

StupidGuy Over a year ago

Hey, is there a way I could contact you incase I get any doubts. I'm a noob to image processing maybe you can help me.

Collectives™ on Stack Overflow

Blob detection not working

1 Answer 1

What do I do?

4 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

What do I do?

4 Comments

Your Answer

Sign up or log in

Post as a guest

Related