Return brown percentage in image

Question

Return brown percentage in image

Asked 5 years, 2 months ago

Viewed 86 times

0

I have a code where I take a video and save an image every 20 frames and I take a slice of that image, until then I was able to do it, but I need to analyze if they have pixels with the same or darker shade of brown than this: RGB 194, 187, 138 and I have no idea how to do this, how to detect percentage of brown color with this specific RGB?

That’s my code so far

import cv2 
import os
import numpy as np

# Read the video from specified path 
cam = cv2.VideoCapture("D:/outpy.avi") 

currentframe = 0
x = 20
while(True): 

    # reading from frame 
    ret,frame = cam.read() 

    if ret: 
        # if video is still left continue creating images 
        name = 'D:/' + str(currentframe) + '.png'
        print ('Creating...' + name) 

        # writing the extracted images
        if currentframe == x:
            cv2.imwrite(name, frame)
            imagem = cv2.imread("D:/{}.png".format(x))
            fatia = imagem[0:150, 150:300]


            x = x + 20
        if cv2.waitKey(25) & 0xFF == ord('q'):
            break

        # increasing counter so that it will 
        # show how many frames are created 
        currentframe += 1
    else: 
        break

# Release all space and windows once done 
cam.release() 
cv2.destroyAllWindows()

See if the following answers help: Calculate percentage of certain colors in an image and Color detection and tell which color is appearing. But note the fact that the Opencv library works in the BGR color space as default, so if the RGB color space is used, perform the conversion with cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

– danieltakeshi

2019/09/13 at 11:03
I had already seen the two links, but I could not solve by the tip they pass on

– Simone

2019/09/13 at 11:55
You first need to set a range in some type of color space, for example RGB, or the most recommended HSV. By setting the range of what you consider brown, it’s easy to check... An interval split is the of Soen’s reply

– danieltakeshi

2019/09/16 at 19:41

1 answer

Browser other questions tagged python opencv

You are not signed in. Login or sign up in order to post.

by Jasar Orion • **1,052** points · Answer 1 · 2020-04-04T14:06:59+00:00

when I want to detect % of a certain color in my image you do so:

import numpy as np
import cv2

img = cv2.imread('J9MbW.jpg')

brown = [194, 187, 138]  # RGB
diff = 20
boundaries = [([brown[2]-diff, brown[1]-diff, brown[0]-diff],
               [brown[2]+diff, brown[1]+diff, brown[0]+diff])]
# in order BGR as opencv represents images as numpy arrays in reverse order

for (lower, upper) in boundaries:
    lower = np.array(lower, dtype=np.uint8)
    upper = np.array(upper, dtype=np.uint8)
    mask = cv2.inRange(img, lower, upper)
    output = cv2.bitwise_and(img, img, mask=mask)

    ratio_brown = cv2.countNonZero(mask)/(img.size/3)
    print('brown pixel percentage:', np.round(ratio_brown*100, 2))

    cv2.imshow("images", np.hstack([img, output]))
    cv2.waitKey(0)