Removing White Text with Black Borders From Image - python

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):

Related

Detect scratches on the white Images

I have a data set that contains washing machine images with light and big deep scratches. I have tried the following two images with the the below-listed code.
Side cropped and rotated image:
Side cropped image but not rotated:
I have tried the following code from How to improve the detection of the defect on the surface? but it is not working for white images which show black screens in the output. I have a huge data set of such images but am not able to detect the scratches. How could I do this using the following code? If it's not possible then what would be the right approach?
import cv2
import numpy as np
# load image
img = cv2.imread('./detect-01.jpg')
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# adaptive threshold
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, -35)
# apply morphology
kernel = np.ones((3,30),np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
kernel = np.ones((3,35),np.uint8)
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# get hough line segments
threshold = 25
minLineLength = 10
maxLineGap = 20
lines = cv2.HoughLinesP(morph, 1, 30*np.pi/360, threshold, minLineLength, maxLineGap)
# draw lines
linear1 = np.zeros_like(thresh)
linear2 = img.copy()
for [line] in lines:
x1 = line[0]
y1 = line[1]
x2 = line[2]
y2 = line[3]
cv2.line(linear1, (x1,y1), (x2,y2), 255, 1)
cv2.line(linear2, (x1,y1), (x2,y2), (0,0,255), 1)
print('number of lines:',len(lines))
# save resulting masked image
cv2.imwrite('scratches_thresh.jpg', thresh)
cv2.imwrite('scratches_morph.jpg', morph)
cv2.imwrite('scratches_lines1.jpg', linear1)
cv2.imwrite('scratches_lines2.jpg', linear2)
# display result
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("lines1", linear1)
cv2.imshow("lines2", linear2)
cv2.waitKey(0)
cv2.destroyAllWindows()
I will provide you few suggestions based on my experience.
Get the Canny of the gray scale image.
Canny thresholds for the lighter background images should be less. For example threshold1: 20, threshold2: 35 etc.
For dark background images canny thresholds can be 150, 220 etc.
Apply the houghline on the canny output image.
Try to use Houghlines first instead of HoughlinesP.
Draw the detected lines on image and adjust the threshold values.

How can I retain background after dilating text in image

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)

how to change the text layout color to white and text to black using python?

I have this image.
I want to make all the colored headings to white and the text in it to black.
I try below to make the image full black and white.
img_grey = cv2.imread('img.jpg', cv2.IMREAD_GRAYSCALE)
thresh = 170
img_binary = cv2.threshold(img_grey, thresh, 250, cv2.THRESH_BINARY)[1]
cv2.imwrite('bw_img.jpg',img_binary)
Now those headings are black and text within those is white. But i want to make text black and heading layout white. So, can anyone helps me with that?
You may convert the image to HSV, apply threshold to find colored regions, and copy the result of cv2.threshold with cv2.THRESH_BINARY_INV only to the colored regions.
Main stages of the suggested solution:
Convert from BGR to HSV color space, and get the saturation color channel.
all black and white are zero, and colored pixels are above zero.
Apply threshold to the saturation channel.
Find contours on the binarized saturation channel.
Draw the contours as white (255 values) on black background to form a mask.
Apply morphological closing for closing some black gaps.
Get only the area inside the mask from img_binary_inv (result of your code using cv2.THRESH_BINARY_INV).
Copy masked img_binary_inv to img_grey only in pixels that mask is white.
Complete code sample:
import numpy as np
import cv2
img_bgr = cv2.imread('img.jpg') # Read image as BGR
img_grey = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY) # Convert from BGR to grayscale.
thresh = 170
img_binary_inv = cv2.threshold(img_grey, thresh, 255, cv2.THRESH_BINARY_INV)[1] # Apply threshold and invert black/white
# Convert from BGR to HSV color space.
hsv = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2HSV)
# Get the saturation color channel - all black and white are zero, and colored pixels are above zero.
s = hsv[:, :, 1]
thresh = 100
s_binary = cv2.threshold(s, thresh, 255, cv2.THRESH_BINARY)[1] # Apply threshold to the saturation channel.
# Find contours on s_binary
cnts = cv2.findContours(s_binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[-2] # Use index [-2] to be compatible to OpenCV 3 and 4
# Draw the contours as white (255 values) on black background.
mask = np.zeros_like(s_binary)
cv2.drawContours(mask, cnts, -1, 255, -1)
# Apply morphological closing for closing some black gaps.
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, np.ones((3, 3)))
# Get only the area inside the mask from img_binary_inv
masked_binary_inv = cv2.bitwise_or(img_binary_inv, img_binary_inv, mask=mask)
# Copy masked_binary_inv to img_grey only in pixels that mask is white.
cv2.copyTo(masked_binary_inv, mask, img_grey)
cv2.imwrite('img_grey.png', img_grey) # Save result (as PNG and not JPEG for better quality).
# Show images
cv2.imshow('img_bgr', img_bgr)
cv2.imshow('s_binary', s_binary)
cv2.imshow('mask', mask)
cv2.imshow('masked_binary_inv', masked_binary_inv)
cv2.imshow('img_grey', img_grey)
cv2.waitKey()
cv2.destroyAllWindows()
Result (img_grey):
The result doesn't look so good, due to the relatively low quality of the input image.
Intermediate results:
s_binary:
mask:
masked_binary_inv:

How can I clean this picture up (opencv-python)?

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:

How to detect blurry blobs?

I would like to detect all the bright spots in this image (https://i.imgur.com/UnTWWHz.png)
The code I've tried is via thresholding, but it only detects the very bright ones. As you can see in the image below.
But some of the spots are out of focus which I need to also detect them.
Could you suggest a method? The picture below shows the blurred spots that I'd like to detect in yellow circles
I tried with the following code
import os
import cv2
import numpy as np
path="C:/Slides/Fluoroscent/E_03_G_O_subpics"
imgname="sub_2_4.png"
image = cv2.imread(os.path.join(path,imgname))
# constants
BINARY_THRESHOLD = 10
CONNECTIVITY = 4
DRAW_CIRCLE_RADIUS = 18
thr=50
# convert to gray
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# threshold the black/ non-black areas
_, thresh = cv2.threshold(gray_image, BINARY_THRESHOLD, thr, cv2.THRESH_BINARY)
# find connected components
components = cv2.connectedComponentsWithStats(thresh, CONNECTIVITY, cv2.CV_32S)
# draw circles around center of components
#see connectedComponentsWithStats function for attributes of components variable
centers = components[3]
for center in centers:
cv2.circle(image, (int(center[0]), int(center[1])), DRAW_CIRCLE_RADIUS, (0,0,255), thickness=1)
cv2.imwrite(os.path.join(path,"result_thresh_"+str(thr)+".png"), image)
cv2.imshow("result", image)
cv2.waitKey(0)
As mentioned in the comments you will get better results by changing the threshold values. I changed the values to 20 and 255 respectively and added erosion to get rid of some noise. You can play around with morphological transformations to get the exact desired result. Read more here .
Code:
import cv2
import numpy as np
kernel = np.ones((5,5),np.uint8)
CONNECTIVITY = 4
DRAW_CIRCLE_RADIUS = 18
img = cv2.imread('blobs.png')
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray_img, 20, 255, cv2.THRESH_BINARY)
erosion = cv2.erode(thresh,kernel,iterations = 1)
components = cv2.connectedComponentsWithStats(erosion, CONNECTIVITY, cv2.CV_32S)
centers = components[3]
for center in centers:
cv2.circle(img, (int(center[0]), int(center[1])), DRAW_CIRCLE_RADIUS, (0,0,255), thickness=1)
cv2.imshow('Original', img)
cv2.imshow('Thresh', thresh)
cv2.imshow('Erosion', erosion)
cv2.waitKey(0)
Results:
Threshold
Erosion
Original with circles

Categories

Resources