python opencv clear noise and remove boxes - python

I would like to clear noise from the upper part of the image as it is corrupt and in text recognition produce wrong results
I would like to make letter/characters clear and also remove the box surround letter
i used this code :
def remove_boxes(image,flag=False):
# threshold the gray image to binarize, and negate it
_,binary = cv2.threshold(image, 150, 255, cv2.THRESH_BINARY)
if flag :
binary = cv2.bitwise_not(binary)
# find external contours of all shapes
_,contours,_ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# create a mask for floodfill function, see documentation
h,w,_= cropped_top.shape
mask = np.zeros((h+2,w+2), np.uint8)
# determine which contour belongs to a square or rectangle
for cnt in contours:
poly = cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt,True),True)
if len(poly) == 4:
# if the contour has 4 vertices then floodfill that contour with black color
cnt = np.vstack(cnt).squeeze()
_,binary,_,_ = cv2.floodFill(binary, mask, tuple(cnt[0]), 0)
# convert image back to original color
if flag:
binary = cv2.bitwise_not(binary)
return binary
but it failed in removing the box arround letter D

Related

Get the location of all contours present in image using opencv, but skipping text

I want to retrieve all contours of the image below, but ignore text.
Image:
When I try to find the contours of the current image I get the following:
I have no idea how to go about this as I am new to using OpenCV and image processing. I want to get ignore the text, how can I achieve this? If ignoring is not possible but making a single bounding box surrounding the text is, than that would be good too.
Edit:
Criteria that I need to match:
The contours may very in size and shape.
The colors from the image may differ.
The colors and size of the text inside the image may differ.
Here is one way to do that in Python/OpenCV.
Read the input
Convert to grayscale
Get Canny edges
Apply morphology close to ensure they are closed
Get all contour hierarchy
Filter contours to keep only those above threshold in perimeter
Draw contours on input
Draw each contour on a black background
Save results
Input:
import numpy as np
import cv2
# read input
img = cv2.imread('short_title.png')
# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# get canny edges
edges = cv2.Canny(gray, 1, 50)
# apply morphology close to ensure they are closed
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
edges = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
# get contours
contours = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
contours = contours[0] if len(contours) == 2 else contours[1]
# filter contours to keep only large ones
result = img.copy()
i = 1
for c in contours:
perimeter = cv2.arcLength(c, True)
if perimeter > 500:
cv2.drawContours(result, c, -1, (0,0,255), 1)
contour_img = np.zeros_like(img, dtype=np.uint8)
cv2.drawContours(contour_img, c, -1, (0,0,255), 1)
cv2.imwrite("short_title_contour_{0}.jpg".format(i),contour_img)
i = i + 1
# save results
cv2.imwrite("short_title_gray.jpg", gray)
cv2.imwrite("short_title_edges.jpg", edges)
cv2.imwrite("short_title_contours.jpg", result)
# show images
cv2.imshow("gray", gray)
cv2.imshow("edges", edges)
cv2.imshow("result", result)
cv2.waitKey(0)
Grayscale:
Edges:
All contours on input:
Contour 1:
Contour 2:
Contour 3:
Contour 4:
Here are two options for erasing the text:
Using pytesseract OCR.
Finding white (and small) connected components.
Both solution build a mask, dilate the mask and use cv2.inpaint for erasing the text.
Using pytesseract:
Find text boxes using pytesseract.image_to_boxes.
Fill the boxes in the mask with 255.
Code sample:
import cv2
import numpy as np
from pytesseract import pytesseract, Output
# Tesseract path
pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"
img = cv2.imread('ShortAndInteresting.png')
# https://stackoverflow.com/questions/20831612/getting-the-bounding-box-of-the-recognized-words-using-python-tesseract
boxes = pytesseract.image_to_boxes(img, lang='eng', config=' --psm 6') # Run tesseract, returning the bounding boxes
h, w, _ = img.shape # assumes color image
mask = np.zeros((h, w), np.uint8)
# Fill the bounding boxes on the image
for b in boxes.splitlines():
b = b.split(' ')
mask = cv2.rectangle(mask, (int(b[1]), h - int(b[2])), (int(b[3]), h - int(b[4])), 255, -1)
mask = cv2.dilate(mask, np.ones((5, 5), np.uint8)) # Dilate the boxes in the mask
clean_img = cv2.inpaint(img, mask, 2, cv2.INPAINT_NS) # Remove the text using inpaint (replace the masked pixels with the neighbor pixels).
# Show mask and clean_img for testing
cv2.imshow('mask', mask)
cv2.imshow('clean_img', clean_img)
cv2.waitKey()
cv2.destroyAllWindows()
Mask:
Finding white (and small) connected components:
Use mask = cv2.inRange(img, (230, 230, 230), (255, 255, 255)) for finding the text (assume the text is white).
Finding connected components in the mask using cv2.connectedComponentsWithStats(mask, 4)
Remove large components from the mask - fill components with large area with zeros.
Code sample:
import cv2
import numpy as np
img = cv2.imread('ShortAndInteresting.png')
mask = cv2.inRange(img, (230, 230, 230), (255, 255, 255))
nlabel, labels, stats, centroids = cv2.connectedComponentsWithStats(mask, 4) # Finding connected components with statistics
# Remove large components from the mask (fill components with large area with zeros).
for i in range(1, nlabel):
area = stats[i, cv2.CC_STAT_AREA] # Get area
if area > 1000:
mask[labels == i] = 0 # Remove large connected components from the mask (fill with zero)
mask = cv2.dilate(mask, np.ones((5, 5), np.uint8)) # Dilate the text in the maks
cv2.imwrite('mask2.png', mask)
clean_img = cv2.inpaint(img, mask, 2, cv2.INPAINT_NS) # Remove the text using inpaint (replace the masked pixels with the neighbor pixels).
# Show mask and clean_img for testing
cv2.imshow('mask', mask)
cv2.imshow('clean_img', clean_img)
cv2.waitKey()
cv2.destroyAllWindows()
Mask:
Clean image:
Note:
My assumption is that you know how to split the image into contours, and the only issue is the present of the text.
I would recommend using flood fill, find the seed point for each color region, flood fill it to ignore the text values within. Hope that helps!
Refer to example of using floodfill here: https://www.programcreek.com/python/example/89425/cv2.floodFill
Example below copied from link above
def fillhole(input_image):
'''
input gray binary image get the filled image by floodfill method
Note: only holes surrounded in the connected regions will be filled.
:param input_image:
:return:
'''
im_flood_fill = input_image.copy()
h, w = input_image.shape[:2]
mask = np.zeros((h + 2, w + 2), np.uint8)
im_flood_fill = im_flood_fill.astype("uint8")
cv.floodFill(im_flood_fill, mask, (0, 0), 255)
im_flood_fill_inv = cv.bitwise_not(im_flood_fill)
img_out = input_image | im_flood_fill_inv
return img_out

detect checkboxes from a form using opencv python

given a dental form as input, need to find all the checkboxes present in the form using image processing. I have answered my current approach below. Is there any better approach to find the checkboxes for low-quality docs as well?
sample input:
This is one approach in which we can solve the issue,
import cv2
import numpy as np
image=cv2.imread('path/to/image.jpg')
### binarising image
gray_scale=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
th1,img_bin = cv2.threshold(gray_scale,150,225,cv2.THRESH_BINARY)
Defining vertical and horizontal kernels
lineWidth = 7
lineMinWidth = 55
kernal1 = np.ones((lineWidth,lineWidth), np.uint8)
kernal1h = np.ones((1,lineWidth), np.uint8)
kernal1v = np.ones((lineWidth,1), np.uint8)
kernal6 = np.ones((lineMinWidth,lineMinWidth), np.uint8)
kernal6h = np.ones((1,lineMinWidth), np.uint8)
kernal6v = np.ones((lineMinWidth,1), np.uint8)
Detect horizontal lines
img_bin_h = cv2.morphologyEx(~img_bin, cv2.MORPH_CLOSE, kernal1h) # bridge small gap in horizonntal lines
img_bin_h = cv2.morphologyEx(img_bin_h, cv2.MORPH_OPEN, kernal6h) # kep ony horiz lines by eroding everything else in hor direction
finding vertical lines
## detect vert lines
img_bin_v = cv2.morphologyEx(~img_bin, cv2.MORPH_CLOSE, kernal1v) # bridge small gap in vert lines
img_bin_v = cv2.morphologyEx(img_bin_v, cv2.MORPH_OPEN, kernal6v)# kep ony vert lines by eroding everything else in vert direction
merging vertical and horizontal lines to get blocks. Adding a layer of dilation to remove small gaps
### function to fix image as binary
def fix(img):
img[img>127]=255
img[img<127]=0
return img
img_bin_final = fix(fix(img_bin_h)|fix(img_bin_v))
finalKernel = np.ones((5,5), np.uint8)
img_bin_final=cv2.dilate(img_bin_final,finalKernel,iterations=1)
Apply Connected component analysis on the binary image to get the blocks required.
ret, labels, stats,centroids = cv2.connectedComponentsWithStats(~img_bin_final, connectivity=8, ltype=cv2.CV_32S)
### skipping first two stats as background
for x,y,w,h,area in stats[2:]:
cv2.rectangle(image,(x,y),(x+w,y+h),(0,255,0),2)
You can also use contours for this problem.
# Reading the image in grayscale and thresholding it
Image = cv2.imread("findBox.jpg", 0)
ret, Thresh = cv2.threshold(Image, 100, 255, cv2.THRESH_BINARY)
Now perform dilation and erosion twice to join the dotted lines present inside the boxes.
kernel = np.ones((3, 3), dtype=np.uint8)
Thresh = cv2.dilate(Thresh, kernel, iterations=2)
Thresh = cv2.erode(Thresh, kernel, iterations=2)
Find contours in the image with cv2.RETR_TREE flag to get all contours with parent-child relations. For more info on this.
Contours, Hierarchy = cv2.findContours(Thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
Now all the boxes along with all the alphabets in the image are detected. We have to eliminate the alphabets detected, very small contours(due to noise), and also those boxes which contain smaller boxes inside them.
For this, I am running a for loop iterating over all the contours detected, and using this loop I am saving 3 values for each contour in 3 different lists.
1st value: Area of contour(Number of pixels a contour encloses)
2nd value: Contour's bounding rectangle info.
3rd value: Ratio of area of contour to the area of its bounding rectangle.
Areas = []
Rects = []
Ratios = []
for Contour in Contours:
# Getting bounding rectangle
Rect = cv2.boundingRect(Contour)
# Drawing contour on new image and finding number of white pixels for contour area
C_Image = np.zeros(Thresh.shape, dtype=np.uint8)
cv2.drawContours(C_Image, [Contour], -1, 255, -1)
ContourArea = np.sum(C_Image == 255)
# Area of the bounding rectangle
Rect_Area = Rect[2]*Rect[3]
# Calculating ratio as explained above
Ratio = ContourArea / Rect_Area
# Storing data
Areas.append(ContourArea)
Rects.append(Rect)
Ratios.append(Ratio)
Filtering out undesired contours:
Getting indices of those contours which have an area less than 3600(threshold value for this image) and which have Ratio >= 0.99.
The ratio defines the extent of overlap of contour to its bounding rectangle. As in this case, the desired contours are rectangle in shape, this ratio for them is expected to be "1.0" (0.99 for keeping a threshold of small noise).
BoxesIndices = [i for i in range(len(Contours)) if Ratios[i] >= 0.99 and Areas[i] > 3600]
Now final contours are those among contours at indices "BoxesIndices" which do not have a child contour(this will extract innermost contours) and if they have a child contour, then this child contour should not be one of the contours at indices "BoxesIndices".
FinalBoxes = [Rects[i] for i in BoxesIndices if Hierarchy[0][i][2] == -1 or BoxesIndices.count(Hierarchy[0][i][2]) == 0]
Final output image

How to use OpenCV to crop an image based on a certain criteria?

I would like to crop the images like the one below using python's OpenCV library. The area of interest is inside the squiggly lines on the top and bottom, and the lines on the side. The problem is that every image is slightly different. This means that I need some automated way of cropping for the area of interest. I guess the top and the sides would be easy since you could just crop it by 10 pixels or so. But how can I crop out the bottom half of the image where the line is not straight? I have included this example image. The image that follows highlights in pink the area of the image that I am interested in keeping.
Here is one way using Python/OpenCV.
Read input
Get center point (assume it is inside the desired region)
Convert image to grayscale
Floodfill the gray image and set background to black
Get the largest contour and its bounding box
Draw the largest contour as filled on black background as mask
Apply the mask to the input image
Crop the masked input image
Input:
import cv2
import numpy as np
# load image and get dimensions
img = cv2.imread("odd_region.png")
hh, ww, cc = img.shape
# compute center of image (as integer)
wc = ww//2
hc = hh//2
# create grayscale copy of input as basis of mask
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# create zeros mask 2 pixels larger in each dimension
zeros = np.zeros([hh + 2, ww + 2], np.uint8)
# do floodfill at center of image as seed point
ffimg = cv2.floodFill(gray, zeros, (wc,hc), (255), (0), (0), flags=8)[1]
# set rest of ffimg to black
ffimg[ffimg!=255] = 0
# get contours, find largest and its bounding box
contours = cv2.findContours(ffimg, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
area_thresh = 0
for cntr in contours:
area = cv2.contourArea(cntr)
if area > area_thresh:
area = area_thresh
outer_contour = cntr
x,y,w,h = cv2.boundingRect(outer_contour)
# draw the filled contour on a black image
mask = np.full([hh,ww,cc], (0,0,0), np.uint8)
cv2.drawContours(mask,[outer_contour],0,(255,255,255),thickness=cv2.FILLED)
# mask the input
masked_img = img.copy()
masked_img[mask == 0] = 0
#masked_img[mask != 0] = img[mask != 0]
# crop the bounding box region of the masked img
result = masked_img[y:y+h, x:x+w]
# draw the contour outline on a copy of result
result_outline = result.copy()
cv2.drawContours(result_outline,[outer_contour],0,(0,0,255),thickness=1,offset=(-x,-y))
# display it
cv2.imshow("img", img)
cv2.imshow("ffimg", ffimg)
cv2.imshow("mask", mask)
cv2.imshow("masked_img", masked_img)
cv2.imshow("result", result)
cv2.imshow("result_outline", result_outline)
cv2.waitKey(0)
cv2.destroyAllWindows()
# write result to disk
cv2.imwrite("odd_region_cropped.png", result)
cv2.imwrite("odd_region_cropped_outline.png", result_outline)
Result:
Result With Contour Drawn:

Remove remains in a letter image with Python

I have a set of images that represent letters extracted from an image of a word. In some images there are remains of the adjacent letters and I want to eliminate them but I do not know how.
Some samples
I'm working with openCV and I've tried two ways and none works.
With findContours:
def is_contour_bad(c):
return len(c) < 50
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(gray, 50, 100)
contours = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if imutils.is_cv2() else contours[1]
mask = np.ones(image.shape[:2], dtype="uint8") * 255
for c in contours:
# if the c ontour is bad, draw it on the mask
if is_contour_bad(c):
cv2.drawContours(mask, [c], -1, 0, -1)
# remove the contours from the image and show the resulting images
image = cv2.bitwise_and(image, image, mask=mask)
cv2.imshow("After", image)
cv2.waitKey(0)
I think it does not work because the image is on the edge cv2.drawContours can not calculate the area correctly and does not eliminate the interior points
With connectedComponentsWithStats:
cv2.imshow("Image", img)
cv2.waitKey(0)
nb_components, output, stats, centroids = cv2.connectedComponentsWithStats(img)
sizes = stats[1:, -1];
nb_components = nb_components - 1
min_size = 150
img2 = np.zeros((output.shape))
for i in range(0, nb_components):
if sizes[i] >= min_size:
img2[output == i + 1] = 255
cv2.imshow("After", img2)
cv2.waitKey(0)
In this case I do not know why the small elements on the sides do not recognize them as connected components
Well..I would greatly appreciate any help!
In the very beginning of the question you have mentioned that letters have been extracted from an image of a word.
So as I think, You could have done the extraction correctly. Then you wouldn't have faced a problem like this. I can give you a solution which is applicable to either extracting letters from original image or extract and separate letters from the image you have given.
Solution:
You can use convex hull coordinates to separate characters like this.
code:
import cv2
import numpy as np
img = cv2.imread('test.png', 0)
cv2.bitwise_not(img,img)
img2 = img.copy()
ret, threshed_img = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
image, contours, hier = cv2.findContours(threshed_img, cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
#--- Black image to be used to draw individual convex hull ---
black = np.zeros_like(img)
contours = sorted(contours, key=lambda ctr: cv2.boundingRect(ctr)[0])
for cnt in contours:
hull = cv2.convexHull(cnt)
img3 = img.copy()
black2 = black.copy()
#--- Here is where I am filling the contour after finding the convex hull ---
cv2.drawContours(black2, [hull], -1, (255, 255, 255), -1)
r, t2 = cv2.threshold(black2, 127, 255, cv2.THRESH_BINARY)
masked = cv2.bitwise_and(img2, img2, mask = t2)
cv2.imshow("masked.jpg", masked)
cv2.waitKey(0)
cv2.destroyAllWindows()
outputs:
So as I suggest, the better thing is to use this solution when you extract characters from original image rather than removing noises after extraction.
I would try the following:
Sum along the columns so that every image gets projected into a vector
Assuming that white=0 and black=1, find the first index value in that vector that = 0.
Remove the image columns to the left of the index value from step 2.
Reverse the summed vector from step 1
Find the first index value that =0 in the reversed vector from step four.
Remove the image columns to the right of the reversed index value from step 5.
This would work nicely for a binary image where white = 0 and black = 1 but if not, there are several methods around this including image threshholding or setting tolerance levels (e.g. for step 2. find first index value in vector that > tolerance...)

python opencv crop using contour hierarchy

I was looking to remove the borders from the below image
what I have tried till now is using OpenCV to get edges
code:
def autocrop(image, threshold=0):
"""Crops any edges below or equal to threshold
Crops blank image to 1x1.
Returns cropped image.
"""
if len(image.shape) == 3:
flatImage = np.max(image, 2)
else:
flatImage = image
assert len(flatImage.shape) == 2
rows = np.where(np.max(flatImage, 0) > threshold)[0]
if rows.size:
cols = np.where(np.max(flatImage, 1) > threshold)[0]
image = image[cols[0]: cols[-1] + 1, rows[0]: rows[-1] + 1]
else:
image = image[:1, :1]
return image
no_border = autocrop(new_image)
cv2.imwrite('no_border.png',no_border)
the result is this image , next how to remove those boxes
Update :
I have found that the solution works for a white background but when I change the background color border are not removed
Edited
I have tried the solution on this image
But the result was like this
How I can achieve a complete removal of the boundary boxes .
For this we use floodFill function.
import cv2
import numpy as np
if __name__ == '__main__':
# read image and convert to gray
img = cv2.imread('image.png',cv2.IMREAD_UNCHANGED)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold the gray image to binarize, and negate it
_,binary = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)
binary = cv2.bitwise_not(binary)
# find external contours of all shapes
_,contours,_ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# create a mask for floodfill function, see documentation
h,w,_ = img.shape
mask = np.zeros((h+2,w+2), np.uint8)
# determine which contour belongs to a square or rectangle
for cnt in contours:
poly = cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt,True),True)
if len(poly) == 4:
# if the contour has 4 vertices then floodfill that contour with black color
cnt = np.vstack(cnt).squeeze()
_,binary,_,_ = cv2.floodFill(binary, mask, tuple(cnt[0]), 0)
# convert image back to original color
binary = cv2.bitwise_not(binary)
cv2.imshow('Image', binary)
cv2.waitKey(0)
cv2.destroyAllWindows()
There is another to find the characters within the image. This using the concept of hierarchy in contours.
The implementation is in python:
path = r'C:\Desktop\Stack'
filename = '2.png'
img = cv2.imread(os.path.join(path, filename), 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY|cv2.THRESH_OTSU)
_, contours2, hierarchy2 = cv2.findContours(binary, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)
Notice that in the cv2.findContours() function is passed in the RETR_CCOMP parameter to store contours according to their different levels of hierarchy. Hierarchy is useful when one contour lies inside another contour, thus enabling and parent-child relationship. RETR_CCOMP helps identify this relationship.
img2 = img.copy()
l = []
for h in hierarchy2[0]:
if h[0] > -1 and h[2] > -1:
l.append(h[2])
In the snippet above I am passing all contours that have a child into the list l. Using l I am drawing those contours in the snippet below.
for cnt in l:
if cnt > 0:
cv2.drawContours(img2, [contours2[cnt]], 0, (0,255,0), 2)
cv2.imshow('img2', img2)
Have a look at the DOCUMENTATION HERE to learn more about hierarchy in contours.

Categories

Resources