Removing background color from image opencv python - python

I have many images of specimen which have uncontrollable background color. Some of them have black background. Some of them have white background. Some of them have green background, etc.
I would like to remove these background color of a given image where the object in the image is just only one specimen. I try this code but it does not work as i expect.
def get_holes(image, thresh):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
im_bw = cv2.threshold(gray, thresh, 255, cv2.THRESH_BINARY)[1]
im_bw_inv = cv2.bitwise_not(im_bw)
_, contour, _ = cv2.findContours(im_bw_inv, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contour:
cv2.drawContours(im_bw_inv, [cnt], 0, 255, -1)
nt = cv2.bitwise_not(im_bw)
im_bw_inv = cv2.bitwise_or(im_bw_inv, nt)
return im_bw_inv
def remove_background(image, thresh, scale_factor=.25, kernel_range=range(1, 15), border=None):
border = border or kernel_range[-1]
holes = get_holes(image, thresh)
small = cv2.resize(holes, None, fx=scale_factor, fy=scale_factor)
bordered = cv2.copyMakeBorder(small, border, border, border, border, cv2.BORDER_CONSTANT)
for i in kernel_range:
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2*i+1, 2*i+1))
bordered = cv2.morphologyEx(bordered, cv2.MORPH_CLOSE, kernel)
unbordered = bordered[border: -border, border: -border]
mask = cv2.resize(unbordered, (image.shape[1], image.shape[0]))
fg = cv2.bitwise_and(image, image, mask=mask)
return fg
file = your_file_location
img = cv2.imread(file)
nb_img = dm.remove_background(img, 255)
These are some example images
May i have your suggestions?

Here's a simple approach with the assumption that there is only one specimen per image.
Kmeans color quantization. We load the image then perform Kmeans color quantization to segment the image into a specified cluster of colors. For instance with clusters=4, the image will be labeled into four colors.
Obtain binary image. Convert to grayscale, Gaussian blur, adaptive threshold.
Draw largest enclosing circle onto mask. Find contours, sort for largest contour using contour area filtering then draw the largest enclosing circle onto a mask using cv2.minEnclosingCircle.
Bitwise-and. Since we have isolated the desired sections to extract, we simply bitwise-and the mask and input image
Input image -> Kmeans -> Binary image
Detected largest enclosing circle -> Mask -> Result
Here's the output for the second image
Input image -> Kmeans -> Binary image
Detected largest enclosing circle -> Mask -> Result
Code
import cv2
import numpy as np
# Kmeans color segmentation
def kmeans_color_quantization(image, clusters=8, rounds=1):
h, w = image.shape[:2]
samples = np.zeros([h*w,3], dtype=np.float32)
count = 0
for x in range(h):
for y in range(w):
samples[count] = image[x][y]
count += 1
compactness, labels, centers = cv2.kmeans(samples,
clusters,
None,
(cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10000, 0.0001),
rounds,
cv2.KMEANS_RANDOM_CENTERS)
centers = np.uint8(centers)
res = centers[labels.flatten()]
return res.reshape((image.shape))
# Load image and perform kmeans
image = cv2.imread('2.jpg')
original = image.copy()
kmeans = kmeans_color_quantization(image, clusters=4)
# Convert to grayscale, Gaussian blur, adaptive threshold
gray = cv2.cvtColor(kmeans, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,21,2)
# Draw largest enclosing circle onto a mask
mask = np.zeros(original.shape[:2], dtype=np.uint8)
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
for c in cnts:
((x, y), r) = cv2.minEnclosingCircle(c)
cv2.circle(image, (int(x), int(y)), int(r), (36, 255, 12), 2)
cv2.circle(mask, (int(x), int(y)), int(r), 255, -1)
break
# Bitwise-and for result
result = cv2.bitwise_and(original, original, mask=mask)
result[mask==0] = (255,255,255)
cv2.imshow('thresh', thresh)
cv2.imshow('result', result)
cv2.imshow('mask', mask)
cv2.imshow('kmeans', kmeans)
cv2.imshow('image', image)
cv2.waitKey()

Related

How to fill a contour plot mask and retain data inside the contour and blackout the rest

I have an image like so,
By using the following code,
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg", 1)
#color boundaries [B, G, R]
lower = [0, 3, 30]
upper = [30, 117, 253]
# create NumPy arrays from the boundaries
lower = np.array(lower, dtype="uint8")
upper = np.array(upper, dtype="uint8")
# find the colors within the specified boundaries and apply
# the mask
mask = cv2.inRange(image, lower, upper)
output = cv2.bitwise_and(image, image, mask=mask)
ret,thresh = cv2.threshold(mask, 50, 255, 0)
if (int(cv2.__version__[0]) > 3):
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
else:
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
if len(contours) != 0:
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imshow('ROI',ROI)
cv2.imwrite('ROI.png',ROI)
cv2.waitKey(0)
I get the following cropped image,
I would like to retain all data within the orange hand-drawn boundary including the boundary itself and blackout the rest.
In the image above the data outside the orange boundary is still there. I do not want that. How do i fill the mask which is like this now so that i can retain data inside the orange boundary,
I would still like to retain other properties like the rectangular bounding box. I don't want anything else to change. How do I go about this?
Thanks.
As you desire (in your comments to my previous answer) to have the outer region to be black rather than transparent, you can do that as follows in Python/OpenCV with a couple of lines changed to multiply the mask by the input rather than put the mask into the alpha channel.
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# apply mask to input image
new_image = cv2.bitwise_and(image, mask)
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image2.jpg',new_image)
cv2.imwrite('frame50_roi2.jpg',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
new_image after applying the mask:
cropped roi image:
Here is one way to do that in Python/OpenCV.
Read the input
Threshold on the orange color
Find the (largest) contour and get its bounding box
Draw a white filled contour on a black background as a mask
Create a copy of the input with an alpha channel
Copy the mask into the alpha channel
Crop the ROI
Save the results
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# put mask into alpha channel of input
new_image = cv2.cvtColor(image, cv2.COLOR_BGR2BGRA)
new_image[:,:,3] = mask[:,:,0]
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image.jpg',new_image)
cv2.imwrite('frame50_roi.png',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
Threshold image:
Mask Image:
New image with mask in alpha channel:
Cropped ROI

How to separate images using watershed algorithm in Python

How to separate indiviual images among multiple images after image segmentaion using watershed algorithm in Python
The attached image is consists of 4 images , from which we need to apply image segmentation and separate individual image from those 4 images
We will flood fill it first
import cv2;
import numpy as np;
# Read image
im_in = cv2.imread("2SNAT.jpg", cv2.IMREAD_GRAYSCALE);
# Threshold.
# Set values equal to or above 220 to 0.
# Set values below 220 to 255.
th, im_th = cv2.threshold(im_in, 220, 255, cv2.THRESH_BINARY_INV);
# Copy the thresholded image.
im_floodfill = im_th.copy()
# Mask used to flood filling.
# Notice the size needs to be 2 pixels than the image.
h, w = im_th.shape[:2]
mask = np.zeros((h+2, w+2), np.uint8)
# Floodfill from point (0, 0)
cv2.floodFill(im_floodfill, mask, (0,0), 255);
# Invert floodfilled image
im_floodfill_inv = cv2.bitwise_not(im_floodfill)
# Combine the two images to get the foreground.
im_out = im_th | im_floodfill_inv
Then find contour and crop out
im, contours, hierarchy = cv2.findContours(im_out.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
final_contours = []
for contour in contours:
area = cv2.contourArea(contour)
if area > 1000:
final_contours.append(contour)
Crop out step, also drawing rectangle on original image
counter = 0
for c in final_contours:
counter = counter + 1
# for c in [final_contours[0]]:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.01 * peri, True)
x,y,w,h = cv2.boundingRect(approx)
print(x, y, w, h)
aspect_ratio = w / float(h)
if (aspect_ratio >= 0.8 and aspect_ratio <= 4):
cv2.rectangle(im_in,(x,y),(x+w,y+h),(0,255,0),2)
cv2.imwrite('splitted_{}.jpg'.format(counter), im_in[y:y+h, x:x+w])
cv2.imwrite('rectangled_split.jpg', im_in)
Instead of using watershed, here's a simple approach using thresholding + morphological operations. The idea is to obtain a binary image then perform morph close to combine each object as a single contour. We then find contours and extract/save each ROI using Numpy slicing.
Here's each individual object highlighted in green
Individual saved object
Code
import cv2
# Load image, grayscale, Otsu's threshold
image = cv2.imread('1.jpg')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Morph close
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=3)
# Find contours and extract ROI
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
num = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
ROI = original[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(num), ROI)
num += 1
cv2.imshow('image', image)
cv2.waitKey()

How to detect paragraphs in a text document image for a non-consistent text structure in Python OpenCV

I am trying to identify paragraphs of text in a .pdf document by first converting it into an image then using OpenCV. But I am getting bounding boxes on lines of text instead of paragraphs. How can I set some threshold or some other limit to get paragraphs instead of lines?
Here is the sample input image:
Here is the output I am getting for the above sample:
I am trying to get a single bounding box on the paragraph in the middle. I am using this code.
import cv2
import numpy as np
large = cv2.imread('sample image.png')
rgb = cv2.pyrDown(large)
small = cv2.cvtColor(rgb, cv2.COLOR_BGR2GRAY)
# kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
kernel = np.ones((5, 5), np.uint8)
grad = cv2.morphologyEx(small, cv2.MORPH_GRADIENT, kernel)
_, bw = cv2.threshold(grad, 0.0, 255.0, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 1))
connected = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)
# using RETR_EXTERNAL instead of RETR_CCOMP
contours, hierarchy = cv2.findContours(connected.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
#For opencv 3+ comment the previous line and uncomment the following line
#_, contours, hierarchy = cv2.findContours(connected.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
mask = np.zeros(bw.shape, dtype=np.uint8)
for idx in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[idx])
mask[y:y+h, x:x+w] = 0
cv2.drawContours(mask, contours, idx, (255, 255, 255), -1)
r = float(cv2.countNonZero(mask[y:y+h, x:x+w])) / (w * h)
if r > 0.45 and w > 8 and h > 8:
cv2.rectangle(rgb, (x, y), (x+w-1, y+h-1), (0, 255, 0), 2)
cv2.imshow('rects', rgb)
cv2.waitKey(0)
This is a classic situation for dilate. Whenever you want to connect multiple items together, you can dilate them to join adjacent contours into a single contour. Here's a simple approach:
Obtain binary image. Load the image, convert to grayscale, Gaussian blur, then Otsu's threshold to obtain a binary image.
Connect adjacent words together. We create a rectangular kernel and dilate to merge individual contours together.
Detect paragraphs. From here we find contours, obtain the rectangular bounding rectangle coordinates and highlight the rectangular contours.
Otsu's threshold to obtain a binary image
Here's where the magic happens. We can assume that a paragraph is a section of words that are close together, to achieve this we dilate to connect adjacent words
Result
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)
# Find contours and draw rectangle
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
cv2.imshow('thresh', thresh)
cv2.imshow('dilate', dilate)
cv2.imshow('image', image)
cv2.waitKey()

How to extract multiple objects from an image using Python OpenCV?

I am trying to extract object from an image using the color using OpenCV, I have tried by inverse thresholding and grayscale combined with cv2.findContours() but I am unable to use it recursively. Furthermore I can't figure out how to "cut out" the match from the original image and save it to a single file.
EDIT
~
import cv2
import numpy as np
# load the images
empty = cv2.imread("empty.jpg")
full = cv2.imread("test.jpg")
# save color copy for visualization
full_c = full.copy()
# convert to grayscale
empty_g = cv2.cvtColor(empty, cv2.COLOR_BGR2GRAY)
full_g = cv2.cvtColor(full, cv2.COLOR_BGR2GRAY)
empty_g = cv2.GaussianBlur(empty_g, (51, 51), 0)
full_g = cv2.GaussianBlur(full_g, (51, 51), 0)
diff = full_g - empty_g
# thresholding
diff_th =
cv2.adaptiveThreshold(full_g,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY,11,2)
# combine the difference image and the inverse threshold
zone = cv2.bitwise_and(diff, diff_th, None)
# threshold to get the mask instead of gray pixels
_, zone = cv2.threshold(bag, 100, 255, 0)
# dilate to account for the blurring in the beginning
kernel = np.ones((15, 15), np.uint8)
bag = cv2.dilate(bag, kernel, iterations=1)
# find contours, sort and draw the biggest one
contours, _ = cv2.findContours(bag, cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
contours = sorted(contours, key=cv2.contourArea, reverse=True)[:3]
i = 0
while i < len(contours):
x, y, width, height = cv2.boundingRect(contours[i])
roi = full_c[y:y+height, x:x+width]
cv2.imwrite("piece"+str(i)+".png", roi)
i += 1
Where empty is just a white image size 1500 * 1000 as the one above and test is the one above.
This is what I came up with, only downside, I have a third image instead of only the 2 expected showing a shadow zone now...
Here's a simple approach:
Obtain binary image. Load the image, grayscale, Gaussian blur, Otsu's threshold, then dilate to obtain a binary black/white image.
Extract ROI. Find contours, obtain bounding boxes, extract ROI using Numpy slicing, and save each ROI
Binary image (Otsu's thresholding + dilation)
Detected ROIs highlighted in green
To extract each ROI, you can find the bounding box coordinates using cv2.boundingRect(), crop the desired region, then save the image
x,y,w,h = cv2.boundingRect(c)
ROI = original[y:y+h, x:x+w]
First object
Second object
import cv2
# Load image, grayscale, Gaussian blur, Otsu's threshold, dilate
image = cv2.imread('1.jpg')
original = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
dilate = cv2.dilate(thresh, kernel, iterations=1)
# Find contours, obtain bounding box coordinates, and extract ROI
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
image_number = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
ROI = original[y:y+h, x:x+w]
cv2.imwrite("ROI_{}.png".format(image_number), ROI)
image_number += 1
cv2.imshow('image', image)
cv2.imshow('thresh', thresh)
cv2.imshow('dilate', dilate)
cv2.waitKey()

Detecting vertical lines using Hough transforms in opencv

I'm trying to remove the square boxes(vertical and horizontal lines) using Hough transform in opencv (Python). The problem is none of the vertical lines are being detected. I've tried looking through contours and hierarchy but there are too many contours in this image and I'm confused how to use them.
After looking through related posts, I've played with the threshold and rho parameters but that didn't help.
I've attached the code for more details. Why does Hough transform not find the vertical lines in the image?. Any suggestions in solving this task are welcome. Thanks.
Input Image :
Hough transformed Image:
Drawing contours:
import cv2
import numpy as np
import pdb
img = cv2.imread('/home/user/Downloads/cropped/robust_blaze_cpp-300-0000046A-02-HW.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 140, 255, 0)
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, contours, -1, (0,0,255), 2)
edges = cv2.Canny(gray,50,150,apertureSize = 3)
minLineLength = 5
maxLineGap = 100
lines = cv2.HoughLinesP(edges,rho=1,theta=np.pi/180,threshold=100,minLineLength=minLineLength,maxLineGap=maxLineGap)
for x1,y1,x2,y2 in lines[0]:
cv2.line(img,(x1,y1),(x2,y2),(0,255,0),2)
cv2.imwrite('probHough.jpg',img)
To be honest, rather than looking for the lines, I'd instead look for the white boxes.
Preparation
import cv2
import numpy as np
Load the image
img = cv2.imread("digitbox.jpg", 0)
Binarize it, so that both the boxes and the digits are black, rest is white
_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
cv2.imwrite('digitbox_step1.png', thresh)
Find contours. In this example image, it's fine to just look for external contours.
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
Process the contours, filtering out any with too small an area. Find convex hull of each contour, create a mask of all areas outside the contour. Store the bounding boxes of each found contour, sorted by x coordinate.
mask = np.ones_like(img) * 255
boxes = []
for contour in contours:
if cv2.contourArea(contour) > 100:
hull = cv2.convexHull(contour)
cv2.drawContours(mask, [hull], -1, 0, -1)
x,y,w,h = cv2.boundingRect(contour)
boxes.append((x,y,w,h))
boxes = sorted(boxes, key=lambda box: box[0])
cv2.imwrite('digitbox_step2.png', mask)
Dilate the mask (to shrink the black parts), to clip off any remains the the gray frames.
mask = cv2.dilate(mask, np.ones((5,5),np.uint8))
cv2.imwrite('digitbox_step3.png', mask)
Fill all the masked pixels with white, to erase the frames.
img[mask != 0] = 255
cv2.imwrite('digitbox_step4.png', img)
Process the digits as you desire -- i'll just draw the bounding boxes.
result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
for n,box in enumerate(boxes):
x,y,w,h = box
cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)
cv2.imwrite('digitbox_step5.png', result)
The whole script in one piece:
import cv2
import numpy as np
img = cv2.imread("digitbox.jpg", 0)
_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
mask = np.ones_like(img) * 255
boxes = []
for contour in contours:
if cv2.contourArea(contour) > 100:
hull = cv2.convexHull(contour)
cv2.drawContours(mask, [hull], -1, 0, -1)
x,y,w,h = cv2.boundingRect(contour)
boxes.append((x,y,w,h))
boxes = sorted(boxes, key=lambda box: box[0])
mask = cv2.dilate(mask, np.ones((5,5),np.uint8))
img[mask != 0] = 255
result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
for n,box in enumerate(boxes):
x,y,w,h = box
cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)
cv2.imwrite('digitbox_result.png', result)

Categories

Resources