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?
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:
Related
Hi I am trying to get a mask of a T-shirt.
Here is what I am getting:
However, I would like to only receive the garment's shape without the print in the middle. How can I do that?
Thanks!
Here is the code:
import cv2
import numpy as np
# load image whose you want to create mask
img = cv2.imread('01430_00.jpg')
# convert to graky
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold input image as mask
mask = cv2.threshold(gray,220,220, cv2.THRESH_BINARY)[1]
# negate mask
mask = 255 - mask
# apply morphology to remove isolated extraneous noise
# use borderconstant of black since foreground touches the edges
kernel = np.ones((3,3), np.uint8)
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)
# anti-alias the mask -- blur then stretch
# blur alpha channel
mask = cv2.GaussianBlur(mask, (0,0), sigmaX=2, sigmaY=2, borderType =
cv2.BORDER_DEFAULT)
# linear stretch so that 127.5 goes to 0, but 255 stays 255
mask = (2*(mask.astype(np.float32))-255.0).clip(0,255).astype(np.uint8)
# Show Image in Opencv Windows
cv2.imshow("Original", img)
cv2.imshow("MASK", mask)
# Save mask Image
cv2.imwrite("Mask2.jpg",mask)
cv2.waitKey(0)
cv2.destroyAllWindows()
You already have a large contour for "garment". You can fill inside of the largest contour with the following code
contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnt = max(contours, key = cv2.contourArea)
cv2.drawContours(mask,[cnt],0,255,-1)
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Create rectangular structuring element and dilate
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dilate = cv2.dilate(thresh, kernel, iterations=4)
cv2.imshow('dilate', dilate)
cv2.waitKey()
I am trying to mask the text elements in an image and return an image with just the remaining portions. I have applied thresholding and dilating, but how can I retain the background.
Image after thresholding and dilating
Original image:
Here is a simple approach:
Using the inverted dilated image cv2.bitwise_not(dilate), create a mask over the original image.
res = cv2.bitwise_and(image, image, mask=cv2.bitwise_not(dilate))
In the above image you have all text regions and its boundaries masked out.
Now replace those masked out regions with the background of your original image. To do that, first I noted down the coordinates where of the text regoins in mask_ind. Then replaced the pixel values in those regions with the background of the original image image[0,0]
mask_ind = (dilate == 255)
res[mask_ind] = image[0,0]
cv2.imshow(res)
I'm trying to use pytesseract to convert some images into text. The images are very basic and I tried using some preprocessing:
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.bitwise_not(gray)
gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
The original image looks like this:
The resulting image looks like this:
I do this for a bunch of numbers with the same font in the same location here are the results:
It still gives no text in the output. For a few of the images, it does, but not for all and the images look nearly identical.
Here is a snippet of the code I'm using:
def checkCurrentState():
"""image = pyautogui.screenshot()
image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
cv2.imwrite("screenshot.png", image)"""
image = cv2.imread("screenshot.png")
checkNumbers(image)
def checkNumbers(image):
numbers = []
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.bitwise_not(gray)
gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
for i in storeLocations:
cropped = gray[i[1]:i[1]+storeHeight, i[0]:i[0]+storeWidth]
number = pytesseract.image_to_string(cropped)
numbers.append(number)
print(number)
cv2.imshow("Screenshot", cropped)
cv2.waitKey(0)
To perform OCR on an image, its important to preprocess the image. The idea is to obtain a processed image where the text to extract is in black with the background in white. Here's a simple approach using OpenCV and Pytesseract OCR.
To do this, we convert to grayscale, apply a slight Gaussian blur, then Otsu's threshold to obtain a binary image. From here, we can apply morphological operations to remove noise. We perform text extraction using the --psm 6 configuration option to assume a single uniform block of text. Take a look here for more options.
Here's a visualization of each step:
Input image
Convert to grayscale -> Gaussian blur
Otsu's threshold -> Morph open to remove noise
Result from Pytesseract OCR
1100
Code
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
# Grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Morph open to remove noise
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
# Perform text extraction
data = pytesseract.image_to_string(opening, lang='eng', config='--psm 6')
print(data)
cv2.imshow('blur', blur)
cv2.imshow('thresh', thresh)
cv2.imshow('opening', opening)
cv2.waitKey()
I am trying to remove text from images that has a black border with white fill. Take the image below as an example.
I have tried a few options utilizing opencv and skimage inpaint
import cv2
from skimage.restoration import inpaint
img = cv2.imread('Documents/test_image.png')
mask = cv2.threshold(img, 210, 255, cv2.THRESH_BINARY)[1][:,:,0]
dst = cv2.inpaint(img, mask, 7, cv2.INPAINT_TELEA)
image_result = inpaint.inpaint_biharmonic(img, mask,
multichannel=True)
cv2.imshow('image',img)
cv2.imshow('mask',mask)
cv2.imshow('dst',dst)
cv2.imshow('image_result',image_result)
cv2.waitKey(0)
It seems like the inpainting is just trying to fill with black as that is what it is identifying as being around the areas of interest. What I would like to do is remove the white text and black borders completely, or secondarily try to fill the white with more information from surrounding colors than just the black.
Here is the best solution I could come up with, still open to others with more experience showing me a better way if anyone has an idea.
mask = cv2.threshold(img, 245, 255, cv2.THRESH_BINARY)[1][:,:,0]
new_mask = cv2.dilate(mask, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (10,10)))
dst = cv2.inpaint(img, new_mask, 7, cv2.INPAINT_TELEA)
Here are two inpainting methods in Python/OpenCV. Note that I use the saturation channel to create the threshold, since white and black have zero saturation, in principle.
Input:
import cv2
import numpy as np
# read input
img = cv2.imread('white_black_text.png')
# convert to hsv and extract saturation
hsv = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
sat = hsv[:,:,1]
# threshold and invert
thresh = cv2.threshold(sat, 10, 255, cv2.THRESH_BINARY)[1]
thresh = 255 - thresh
# apply morphology dilate
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
thresh = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)
# do inpainting
result1 = cv2.inpaint(img,thresh,11,cv2.INPAINT_TELEA)
result2 = cv2.inpaint(img,thresh,11,cv2.INPAINT_NS)
# save results
cv2.imwrite('white_black_text_threshold.png', thresh)
cv2.imwrite('white_black_text_inpainted1.png', result1)
cv2.imwrite('white_black_text_inpainted2.png', result1)
# show results
cv2.imshow('thresh',thresh)
cv2.imshow('result1',result1)
cv2.imshow('result2',result2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold and morphology cleaned result:
Result 1 (Telea):
Result 2 (Navier Stokes):
This mathematica code removes glare from an image:
img = Import["foo.png"]
Inpaint[img, Dilation[saturated, DiskMatrix[20]]]
as shown in the most upvoted answer here:
https://dsp.stackexchange.com/questions/1215/how-to-remove-a-glare-clipped-brightness-from-an-image
I want to use opencv instead of Mathematica to get the same result. How would I write equivalent code in opencv-python?
Here is how to do that in Python/OpenCV.
But I do not think the OpenCV inpainting routines are working or at least are not working well for my Python 3.7.5 and OpenCV 3.4.8.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('apple.png')
# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold grayscale image to extract glare
mask = cv2.threshold(gray, 220, 255, cv2.THRESH_BINARY)[1]
# Optionally add some morphology close and open, if desired
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7,7))
#mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel, iterations=1)
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
#mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel, iterations=1)
# use mask with input to do inpainting
result = cv2.inpaint(img, mask, 21, cv2.INPAINT_TELEA)
# write result to disk
cv2.imwrite("apple_mask.png", mask)
cv2.imwrite("apple_inpaint.png", result)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("GRAY", gray)
cv2.imshow("MASK", mask)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Thresholded image:
Result: