remove small whits dots from binary image using opencv python

Question

i have a binary image and I want to remove small white dots from the image using opencv python.You can refer to my problem here enter link description here

My original image is

i want the output image as:

Wigwam

What code have you tried? Please read this forum's help section for how to ask a good question. – Floranceflore

@Floranceflore I have shared the link of the code which i tried .please refer it – Wigwam

Sorry, I missed it. But why did you not just modify the one post? – Floranceflore

the function connectedcomponentswithstats is working but i am unable to display in in form of image – Wigwam

See #42799159 – Floranceflore

See also pyimagesearch.com/2016/10/31/… – Floranceflore

Answer 1

This seems to work using connected components in Python Opencv.

#!/bin/python3.7

import cv2
import numpy as np

src = cv2.imread('img.png', cv2.IMREAD_GRAYSCALE)

# convert to binary by thresholding
ret, binary_map = cv2.threshold(src,127,255,0)

# do connected components processing
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binary_map, None, None, None, 8, cv2.CV_32S)

#get CC_STAT_AREA component as stats[label, COLUMN] 
areas = stats[1:,cv2.CC_STAT_AREA]

result = np.zeros((labels.shape), np.uint8)

for i in range(0, nlabels - 1):
    if areas[i] >= 100:   #keep
        result[labels == i + 1] = 255

cv2.imshow("Binary", binary_map)
cv2.imshow("Result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

cv2.imwrite("Filterd_result.png, result)

See here

Floranceflore

Can you help me to apply this to multiple jpg images and save it with the same name but extension png? – Wigwam

Answer 2

You can simply use image smoothing techniques like gaussian blur, etc. to remove noise from the image, followed by binary thresholding like below:

img = cv2.imread("your-image.png",0)
blur = cv2.GaussianBlur(img,(13,13),0)
thresh = cv2.threshold(blur, 100, 255, cv2.THRESH_BINARY)[1]

cv2.imshow('original', img)
cv2.imshow('output', thresh)
cv2.waitKey(0)
cv2.destroyAllWinsdows()

output:

Read about different image smoothing/blurring techniques from here.

Phonsa

Thank you for the suggestion but using gaussian blur the edges would be affected so I want connectedcompoments function to work – Wigwam

But there are also image blurring techniques which preserves the edges while removing noises like median blur, etc. So, why not you try those. – Phonsa

Answer 3

You can use the closing function - erosion followed by dilation. It don't need the blurring function.

import cv2 as cv
import numpy as np

img = cv.imread('original',0)
kernel = np.ones((5,5),np.uint8)

opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)

cv2.imshow('original', img)
cv2.imshow('output', opening)
cv2.waitKey(0)
cv2.destroyAllWindows()

Harumscarum

You mean opening. (I would edit, but the queue is full...) – Pignus