riya1405's profile - activity

Yeah it helped. Thanks a lot!

I need to superimpose another 3 channel image with this one.

I separated the HSV planes and modified the s plane.I need the merged image to look exactly like the modified s plane. How should I do that?

Modified s plane image:

Output obtained after setting other layers to 0 and merging:

Others are working too I think ;)

Thanks a lot!

Thank you! And i just wanted to ask that what is the equivalent of setTo() in python?

Yeah, I'll add the image

I dont want to remove green channel. That would give me some sort of pinkish image. I need to remove green from the entire image. The original image with green turned to black in it. The input is image containing trees and bushes. And i wish to set the regions as black.

I'll try it out. Thanks for your help! :)

I am having an image and wish to remove the green color in it i.e. to set it to value 0. How to do that? https://dditec.miraheze.org/wiki/File...

I am trying to find the area in image where there are maximum corners detected. Is there any possible way to do this?

I don't want to use contours on this one. I'm trying to detect cars in an image, so this is the basic blob test.

So what should I do to detect these blobs?

If I don't use parameters at all, then it is supposed to give me all the blobs that are detected right?

Hi, I am trying to detect simple blobs in an image but while running code, I get the image without any keypoints plotted. Why am I not able to detect the blobs?

import cv2
import numpy as np;
im = cv2.imread('blob1.jpeg', cv2.IMREAD_GRAYSCALE)

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

# Change thresholds
params.minThreshold = 50
params.maxThreshold = 150
# Filter by Area.
params.filterByArea = True
params.minArea = 150
detector = cv2.SimpleBlobDetector_create(params)

# Detect blobs.
keypoints = detector.detect(im)

# 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([]), (255,0,0), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

# Show blobs
cv2.imshow("Keypoints", im_with_keypoints)
cv2.waitKey(0)
cv2.destroyAllWindows()

Okay Thanks a lot!

I had copied the code here but there were some identation problems. I have corrected it.

yes. it works perfectly on a paint image.

I have written a basic code to detect hand drawn shapes i.e. drawn on paper and captured with a camera.[p1.png] and this is the output that i am getting.

import numpy as np
import cv2

im = cv2.imread('c:/p1.png')
cv2.imshow('original image',im)
cv2.waitKey()

imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
cv2.imshow('gray image',imgray)
cv2.waitKey()

ret,thresh = cv2.threshold(imgray,80,255,0)
cv2.imshow('thresh image',thresh)
cv2.waitKey()

image, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cv2.imshow('cont image',image)
cv2.waitKey()
ctt=0
for cnt in contours:
     approx = cv2.approxPolyDP(cnt,0.01*cv2.arcLength(cnt,True),True)
     print len(approx)
     if len(approx)==5:
         print "pentagon"
         cv2.drawContours(im,[cnt],0,255,-1)
         ctt+=1
     elif len(approx)==3:
         print "triangle"
         cv2.drawContours(im,[cnt],0,(0,255,0),-1)
         ctt+=1
     elif len(approx)==4:
         print "square"
         cv2.drawContours(im,[cnt],0,(0,0,255),-1)
         ctt+=1
     elif len(approx) == 9:
         print "half-circle"
         cv2.drawContours(im,[cnt],0,(255,255,0),-1)
         ctt+=1
     elif len(approx) > 15:
         print "circle"
         cv2.drawContours(im,[cnt],0,(0,255,255),-1)
         ctt+=1

cv2.imshow('img',im)
cv2.waitKey(0)
cv2.destroyAllWindows()
print "Total no.= ",ctt