如何清理这张图片（opencv-python）？

Question

I am really new to opencv. How can I remove the noise in the background without losing info?

I started with this: and Otsu thresholded it. I've tried erosion, dilation, bilateral filtering. My goal is to get a rectangle on the borders so I can perspective transform the thresholded picture, but it has trouble finding contours. Or maybe is there a different and better approach?

Answer 1

Here is one way to do that in Python/OpenCV.

• Read the input
• Blur it
• Convert to HSV and extract the saturation channel
• Threshold the saturation image
• Clean it up with morphology close and open and save as a mask
• Recreate your OTSU threshold image
• Write black to OTSU image where mask is black (zero)
• For comparison, write black to Input image where mask is black (zero)
• Save results

Input:

import cv2
import numpy as np

# read image
img = cv2.imread('circuit_board.jpg')

# blur
blur = cv2.GaussianBlur(img, (3,3), 0)

# convert to hsv and get saturation channel
sat = cv2.cvtColor(blur, cv2.COLOR_BGR2HSV)[:,:,1]

# threshold saturation channel
thresh = cv2.threshold(sat, 50, 255, cv2.THRESH_BINARY)[1]

# apply morphology close and open to make mask
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=1)
mask = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel, iterations=1)

# do OTSU threshold to get circuit image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
otsu = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]

# write black to otsu image where mask is black
otsu_result = otsu.copy()
otsu_result[mask==0] = 0

# write black to input image where mask is black
img_result = img.copy()
img_result[mask==0] = 0

# write result to disk
cv2.imwrite("circuit_board_mask.png", mask)
cv2.imwrite("circuit_board_otsu.png", otsu)
cv2.imwrite("circuit_board_otsu_result.png", otsu_result)
cv2.imwrite("circuit_board_img_result.png", img_result)


# display it
cv2.imshow("IMAGE", img)
cv2.imshow("SAT", sat)
cv2.imshow("MASK", mask)
cv2.imshow("OTSU", otsu)
cv2.imshow("OTSU_RESULT", otsu_result)
cv2.imshow("IMAGE_RESULT", img_result)
cv2.waitKey(0)

Mask image:

OTSU threshold image:

OTSU Result:

Image Result: