Text line segmentation using OpenCV Python - python

I am trying to extract the text lines from the below figure and I tried the below code but I am getting only a single image without any data. While masking the images all the lines are masked perfectly. Below i attached the masked image, final output image and desired output image.
img = cv.imread('Handwritten_data/Ostu_images/H_1.jpg')
lower = (0, 0, 0)
upper = (0, 120, 150)
# threshold on border color
mask = cv.inRange(img, lower, upper)
# dilate threshold
kernel = cv.getStructuringElement(cv.MORPH_RECT, (250,10))
mask = cv.morphologyEx(mask, cv.MORPH_DILATE, kernel)
# recolor border to white
img[mask==255] = (255,255,255)
# Inverting the mask by
# performing bitwise-not operation
mask_black = cv.bitwise_not(mask)
Mask = cv.bitwise_and(img, img, mask = mask_black)
gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
# otsu threshold
thresh = cv.threshold(gray, 0, 255, cv.THRESH_OTSU )[1]
# apply morphology open
kernel = cv.getStructuringElement(cv.MORPH_RECT, (250,10))
morph = cv.morphologyEx(thresh, cv.MORPH_OPEN, kernel)
# creating a folder
try:
# creating a folder named data
if not os.path.exists('Image_0'):
os.makedirs('Image_0')
# if not created then raise error
except OSError:
print ('Error: Creating directory of data')
# find contours and bounding boxes
bboxes = []
bboxes_img = img.copy()
contours = cv.findContours(morph, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
x,y,w,h = cv.boundingRect(cntr)
cv.rectangle(bboxes_img, (x, y), (x+w, y+h), (0,0,255), 1)
bboxes.append((x,y,w,h))
for j in range(len(bboxes)):
(x,y,w,h) = bboxes[j]
crop = img[y-10:y+h+10, x-10:x+w+10]
cv.imwrite(f'Image_0/S_{j}.jpg', crop)
Any suggestions or help to solve this problem.
Below is the masking image
final image ouput
desired image output be like
Thanks in advance

The idea you presented for text line segmentation is correct. But the approach needs some tweaking.
Note:
Whenever you want to mask a portion of the image, make sure the masked region is in white. Because when finding contours the algorithm looks for white regions. Since you were looking for contours that were in black the algorithm missed it.
The following is modified with the above idea.
Solution:
img = cv2.imread(image_file)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh2 = cv2.threshold(img_gray, 150, 255, cv2.THRESH_BINARY_INV)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (150,2))
mask = cv2.morphologyEx(thresh2, cv2.MORPH_DILATE, kernel)
Below is the mask image:
bboxes = []
bboxes_img = img.copy()
contours = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
cv2.rectangle(bboxes_img, (x, y), (x+w, y+h), (0,0,255), 1)
bboxes.append((x,y,w,h))
The following is the final result with bounding boxes:
You can now add your portion of the code to save each region as a separate image file. You can try modifying the kernel parameters and exploring different morphological operations to get a better mask region.
Hope this puts you on the right track!

Related

Detect thick black lines in image with OpenCV

I have the following image of a lego board with some bricks on it
Now I am trying to detect the thick black lines (connecting the white squares) with OpenCV. I have already experimented a lot with HoughLinesP, converted the image to gray or b/w before, applied blur, ...
Nonthing led to usable results.
# Read image
img = cv2.imread('image.jpg', cv2.IMREAD_GRAYSCALE)
# Resize Image
img = cv2.resize(img, (0,0), fx=0.25, fy=0.25)
# Initialize output
out = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
# Median blurring to get rid of the noise; invert image
img = cv2.medianBlur(img, 5)
# Adaptive Treshold
bw = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,\
cv2.THRESH_BINARY,15,8)
# HoughLinesP
linesP = cv2.HoughLinesP(bw, 500, np.pi / 180, 50, None, 50, 10)
# Draw Lines
if linesP is not None:
for i in range(0, len(linesP)):
l = linesP[i][0]
cv2.line(out, (l[0], l[1]), (l[2], l[3]), (0,0,255), 3, cv2.LINE_AA)
The adaptive treshold lets you see edges quite well, but with HoughLinesP you don't get anything usable out of it
What am I doing wrong?
Thanks, both #fmw42 and #jeru-luke for your great solutions to this problem! I liked isolating / masking the green board, so I combined both:
import cv2
import numpy as np
img = cv2.imread("image.jpg")
scale_percent = 50 # percent of original size
width = int(img.shape[1] * scale_percent / 100)
height = int(img.shape[0] * scale_percent / 100)
dim = (width, height)
# resize image
img = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)
lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
a_component = lab[:,:,1]
# binary threshold the a-channel
th = cv2.threshold(a_component,127,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)[1]
# numpy black
black = np.zeros((img.shape[0],img.shape[1]),np.uint8)
# function to obtain the largest contour in given image after filling it
def get_region(image):
contours, hierarchy = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
c = max(contours, key = cv2.contourArea)
mask = cv2.drawContours(black,[c],0,255, -1)
return mask
mask = get_region(th)
# turning the region outside the green block white
green_block = cv2.bitwise_and(img, img, mask = mask)
green_block[black==0]=(255,255,255)
# median blur
median = cv2.medianBlur(green_block, 5)
# threshold on black
lower = (0,0,0)
upper = (15,15,15)
thresh = cv2.inRange(median, lower, upper)
# apply morphology open and close
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (29,29))
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# filter contours on area
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result = green_block.copy()
for c in contours:
area = cv2.contourArea(c)
if area > 1000:
cv2.drawContours(result, [c], -1, (0, 0, 255), 2)
# view result
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Here I am presenting a repeated segmentation approach using color.
This answer is based on the usage of LAB color space
1. Isolating the green lego block
img = cv2.imread(image_path)
lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
a_component = lab[:,:,1]
# binary threshold the a-channel
th = cv2.threshold(a_component,127,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)[1]
th
# function to obtain the largest contour in given image after filling it
def get_region(image):
contours, hierarchy = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
c = max(contours, key = cv2.contourArea)
black = np.zeros((image.shape[0], image.shape[1]), np.uint8)
mask = cv2.drawContours(black,[c],0,255, -1)
return mask
mask = get_region(th)
mask
# turning the region outside the green block white
green_block = cv2.bitwise_and(img, img, mask = mask)
green_block[black==0]=(255,255,255)
green_block
2. Segmenting the road
To get an approximate region of the road, I subtracted the mask and th.
cv2.subtract() performs arithmetic subtraction, where cv2 will take care of negative values.
road = cv2.subtract(mask,th)
# `road` contains some unwanted spots/contours which are removed using the function "get_region"
only_road = get_region(road)
only_road
Masking only the road segment with the original image gives
road_colored = cv2.bitwise_and(img, img, mask = only_road)
road_colored[only_road==0]=(255,255,255)
road_colored
From the above image only the black regions (road) are present, which is easy to segment:
# converting to grayscale and applying threshold
th2 = cv2.threshold(road_colored[:,:,1],127,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)[1]
# using portion of the code from fmw42's answer, to get contours above certain area
contours = cv2.findContours(th2, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result = img.copy()
for c in contours:
area = cv2.contourArea(c)
if area > 1000:
cv2.drawContours(result, [c], -1, (0, 0, 255), 4)
result
Note:
To clean up the end result, you can apply morphological operations on th2 before drawing contours.
Here is one way to do that in Python/OpenCV.
Read the image
Apply median blur
Threshold on black color using cv2.inRange()
Apply morphology to clean it up
Get contours and filter on area
Draw contours on input
Save the result
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('black_lines.jpg')
# median blur
median = cv2.medianBlur(img, 5)
# threshold on black
lower = (0,0,0)
upper = (15,15,15)
thresh = cv2.inRange(median, lower, upper)
# apply morphology open and close
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (29,29))
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# filter contours on area
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result = img.copy()
for c in contours:
area = cv2.contourArea(c)
if area > 1000:
cv2.drawContours(result, [c], -1, (0, 0, 255), 2)
# save result
cv2.imwrite("black_lines_threshold.jpg", thresh)
cv2.imwrite("black_lines_morphology.jpg", morph)
cv2.imwrite("black_lines_result.jpg", result)
# view result
cv2.imshow("threshold", thresh)
cv2.imshow("morphology", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold image:
Morphology image:
Result:

Detect squares (paintings) in images and draw contour around them using python

I'm trying to detect and draw a rectangular contour on every painting on for example this image:
I followed some guides and did the following:
Grayscale conversion
Applied median blur
Sharpen image
Applied adaptive Threshold
Applied Morphological Gradient
Find contours
Draw contours
And got the following result:
I know it's messy but is there a way to somehow detect and draw a contour around the paintings better?
Here is the code I used:
path = '<PATH TO THE PICTURE>'
#reading in and showing original image
image = cv2.imread(path)
image = cv2.resize(image,(880,600)) # resize was nessecary because of the large images
cv2.imshow("original", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
# grayscale conversion
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow("painting_gray", gray)
cv2.waitKey(0)
cv2.destroyAllWindows()
# we need to find a way to detect the edges better so we implement a couple of things
# A little help was found on stackoverflow: https://stackoverflow.com/questions/55169645/square-detection-in-image
median = cv2.medianBlur(gray,5)
cv2.imshow("painting_median_blur", median) #we use median blur to smooth the image
cv2.waitKey(0)
cv2.destroyAllWindows()
# now we sharpen the image with help of following URL: https://www.analyticsvidhya.com/blog/2021/08/sharpening-an-image-using-opencv-library-in-python/
kernel = np.array([[0, -1, 0],
[-1, 5,-1],
[0, -1, 0]])
image_sharp = cv2.filter2D(src=median, ddepth=-1, kernel=kernel)
cv2.imshow('painting_sharpend', image_sharp)
cv2.waitKey(0)
cv2.destroyAllWindows()
# now we apply adapptive thresholding
# thresholding: https://opencv24-python-tutorials.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_thresholding/py_thresholding.html#adaptive-thresholding
thresh = cv2.adaptiveThreshold(src=image_sharp,maxValue=255,adaptiveMethod=cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
thresholdType=cv2.THRESH_BINARY,blockSize=61,C=20)
cv2.imshow('thresholded image', thresh)
cv2.waitKey(0)
cv2.destroyAllWindows()
# lets apply a morphological transformation
kernel = np.ones((7,7),np.uint8)
gradient = cv2.morphologyEx(thresh, cv2.MORPH_GRADIENT, kernel)
cv2.imshow('dilated image', gradient)
cv2.waitKey(0)
cv2.destroyAllWindows()
# # lets now find the contours of the image
# # find contours: https://docs.opencv.org/4.x/dd/d49/tutorial_py_contour_features.html
contours, hierarchy = cv2.findContours(gradient, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print("contours: ", len(contours))
print("hierachy: ", len(hierarchy))
print(hierarchy)
cv2.drawContours(image, contours, -1, (0,255,0), 3)
cv2.imshow("contour image", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
Tips, help or code is appreciated!
Here's a simple approach:
Obtain binary image. We load the image, grayscale, Gaussian blur, then Otsu's threshold to obtain a binary image.
Two pass dilation to merge contours. At this point, we have a binary image but individual separated contours. Since we can assume that a painting is a single large square contour, we can merge small individual adjacent contours together to form a single contour. To do this, we create a vertical and horizontal kernel using cv2.getStructuringElement then dilate to merge them together. Depending on the image, you may need to adjust the kernel sizes or number of dilation iterations.
Detect paintings. Now we find contours and filter using contour area using a minimum threshold area to filter out small contours. Finally we obtain the bounding rectangle coordinates and draw the rectangle with cv2.rectangle.
Code
import cv2
# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.jpeg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (13,13), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Two pass dilate with horizontal and vertical kernel
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,5))
dilate = cv2.dilate(thresh, horizontal_kernel, iterations=2)
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,9))
dilate = cv2.dilate(dilate, vertical_kernel, iterations=2)
# Find contours, filter using contour threshold area, 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:
area = cv2.contourArea(c)
if area > 20000:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36, 255, 12), 3)
cv2.imshow('thresh', thresh)
cv2.imshow('dilate', dilate)
cv2.imshow('image', image)
cv2.waitKey()
So here is the actual size of the portrait frame.
So here is small code.
#!/usr/bin/python 37
#OpenCV 4.3.0, Raspberry Pi 3/B/4B-w/4/8GB RAM, Buster,v10.
#Date: 3rd, June, 2020
import cv2
# Load the image
img = cv2.imread('portrait.jpeg')
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(img, 120,890)
# Apply adaptive threshold
thresh = cv2.adaptiveThreshold(edged, 255, 1, 1, 11, 2)
thresh_color = cv2.cvtColor(thresh, cv2.COLOR_GRAY2BGR)
# apply some dilation and erosion to join the gaps - change iteration to detect more or less area's
thresh = cv2.dilate(thresh,None,iterations = 50)
thresh = cv2.erode(thresh,None,iterations = 50)
# Find the contours
contours,hierarchy = cv2.findContours(thresh,
cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
# For each contour, find the bounding rectangle and draw it
for cnt in contours:
area = cv2.contourArea(cnt)
if area > 20000:
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(img,
(x,y),(x+w,y+h),
(0,255,0),
2)
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Here is output:

Image cropping on white boundaries from a Complex Image using python

Problem Summary: I have got many complex histopathology images with different dimensions. Complex means a single image having multiple images in it as shown in below input image examples. I need to separate out or crop each single image only and not the text/label/caption of it from that input complex image and further save each of them individually. For the bounding boxes I have gone through the white boundaries (separation) along the single images.
Complex Input Image Example 1:
Complex Input Image Example 2:
Complex Input Image Example 3:
Code I have tried:
import cv2
import numpy as np
# reading the input image
img = cv2.imread('cmp.jpg')
cv2.imshow("histology image", img)
# defining border color
lower = (0, 80, 110)
upper = (0, 120, 150)
# applying thresholding on border color
mask = cv2.inRange(img, lower, upper)
cv2.imshow("masked", mask)
# Using dilate threshold
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15, 15))
mask = cv2.morphologyEx(mask, cv2.MORPH_DILATE, kernel)
# coloring border to white for other images
img[mask==255] = (255,255,255)
cv2.imshow("white_border", img)
# converting image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# applying otsu threshold
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU )[1]
cv2.imshow("thresholded", thresh)
# applying 'Open' morphological operation
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (17,17))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
morph = 255 - morph
cv2.imshow("morphed", morph)
# finding contours and bounding boxes
bboxes = []
bboxes_img = img.copy()
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
cv2.rectangle(bboxes_img, (x, y), (x+w, y+h), (0, 0, 255), 1)
bboxes.append((x,y,w,h))
cv2.imshow("boundingboxes", bboxes_img)
cv2.waitKey(0)
cv2.destroyAllWindows()
I am not getting exact bounding boxes for each of single images present in the input complex image and further I need to save each cropped image individually. Any kind of help will be much appreciated.

OpenCV: How to remove text from background

Right now I am trying to create one program, which remove text from background but I am facing a lot of problem going through it
My approach is to use pytesseract to get text boxes and once I get boxes, I use cv2.inpaint to paint it and remove text from there. In short:
d = pytesseract.image_to_data(img, output_type=Output.DICT) # Get text
n_boxes = len(d['level']) # get boxes
for i in range(n_boxes): # Looping through boxes
# Get coordinates
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
crop_img = img[y:y+h, x:x+w] # Crop image
gray = cv2.cvtColor(crop_img, cv2.COLOR_BGR2GRAY)
gray = inverte(gray) # Inverse it
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU)[1]
dst = cv2.inpaint(crop_img, thresh, 10, cv2.INPAINT_TELEA) # Then Inpaint
img[y:y+h, x:x+w] = dst # Place back cropped image back to the source image
Now the problem is that I am not able to remove text completely
Image:
Now I am not sure what other method I can use to remove text from image, I am new to this that's why I am facing problem. Any help is much appreciated
Note: Image looks stretched because I resized it to show it in screen size
Original Image:
Here's an approach using morphological operations + contour filtering
Convert image to grayscale
Otsu's threshold to obtain a binary image
Perform morph close to connect words into a single contour
Dilate to ensure that all bits of text are contained in the contour
Find contours and filter using contour area
Remove text by "filling" in the contour rectangle with the background color
I used chrome developer tools to determine the background color of the image which was (222,228,251). If you want to dynamically determine the background color, you could try finding the dominant color using k-means. Here's the result
import cv2
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,3))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, close_kernel, iterations=1)
dilate_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,3))
dilate = cv2.dilate(close, dilate_kernel, iterations=1)
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:
area = cv2.contourArea(c)
if area > 800 and area < 15000:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (222,228,251), -1)
cv2.imshow('image', image)
cv2.waitKey()

How to extract white region in an image

I have a sample image like this
I'm looking for a way to black out the noise from the image such that I end up with an image that just has black text on white background so that I may send it to tesseract.
I've tried morphing with
kernel = np.ones((4,4),np.uint8)
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
cv2.imshow("opening", opening)
but it doesn't seem to work.
I've also tried to find contours
img = cv2.cvtColor(rotated, cv2.COLOR_BGR2GRAY)
(cnts, _) = cv2.findContours(img, cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:1]
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
roi=rotated[y:y+h,x:x+w].copy()
cv2.imwrite("roi.png", roi)
With the above code, I get the following contours:
which leads to this image when cropped:
which is still not good enough. I want black text on white background, so that I can send it to tesseract OCR and have good success rate.
Is there anything else I can try?
Update
Here is an additional similar image. This one is a bit easier because it has a smooth rectangle in it
The following works for your given example, although it might need tweaking for a wider range of images.
import numpy as np
import cv2
image_src = cv2.imread("input.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
ret, gray = cv2.threshold(gray, 250,255,0)
image, contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
largest_area = sorted(contours, key=cv2.contourArea)[-1]
mask = np.zeros(image_src.shape, np.uint8)
cv2.drawContours(mask, [largest_area], 0, (255,255,255,255), -1)
dst = cv2.bitwise_and(image_src, mask)
mask = 255 - mask
roi = cv2.add(dst, mask)
roi_gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
ret, gray = cv2.threshold(roi_gray, 250,255,0)
image, contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
max_x = 0
max_y = 0
min_x = image_src.shape[1]
min_y = image_src.shape[0]
for c in contours:
if 150 < cv2.contourArea(c) < 100000:
x, y, w, h = cv2.boundingRect(c)
min_x = min(x, min_x)
min_y = min(y, min_y)
max_x = max(x+w, max_x)
max_y = max(y+h, max_y)
roi = roi[min_y:max_y, min_x:max_x]
cv2.imwrite("roi.png", roi)
Giving you the following type of output images:
And...
The code works by first locating the largest contour area. From this a mask is created which is used to first select only the area inside, i.e. the text. The inverse of the mask is then added to the image to convert the area outside the mask to white.
Lastly contours are found again for this new image. Any contour areas outside a suitable size range are discarded (this is used to ignore any small noise areas), and a bounding rect is found for each. With each of these rectangles, an outer bounding rect is calculated for all of the remaining contours, and a crop is made using these values to give the final image.
Update - To get the remainder of the image, i.e. with the above area removed, the following could be used:
image_src = cv2.imread("input.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
ret, gray = cv2.threshold(gray, 10, 255,0)
image, contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
largest_area = sorted(contours, key=cv2.contourArea)[-1]
mask = np.zeros(image_src.shape, np.uint8)
cv2.drawContours(mask, [largest_area], 0, (255,255,255,255), -1)
image_remainder = cv2.bitwise_and(image_src, 255 - mask)
cv2.imwrite("remainder.png", image_remainder)
I get this:
Result
Source Code:
if __name__ == '__main__':
SrcImg = cv2.imread('./Yahi9.png', cv2.CV_LOAD_IMAGE_GRAYSCALE)
_, BinImg = cv2.threshold(SrcImg, 80, 255, cv2.THRESH_OTSU)
Contours, Hierarchy = cv2.findContours(image=copy.deepcopy(SrcImg),
mode=cv2.cv.CV_RETR_EXTERNAL,
method=cv2.cv.CV_CHAIN_APPROX_NONE)
MaxContour, _ = getMaxContour(Contours)
Canvas = np.ones(SrcImg.shape, np.uint8)
cv2.drawContours(image=Canvas, contours=[MaxContour], contourIdx=0, color=(255), thickness=-1)
mask = (Canvas != 255)
RoiImg = copy.deepcopy(BinImg)
RoiImg[mask] = 255
RoiImg = cv2.morphologyEx(src=RoiImg, op=cv2.MORPH_CLOSE, kernel=np.ones((3,3)), iterations=4)
cv2.imshow('RoiImg', RoiImg)
cv2.waitKey(0)
Function:
def getMaxContour(contours):
MaxArea = 0
Location = 0
for idx in range(0, len(contours)):
Area = cv2.contourArea(contours[idx])
if Area > MaxArea:
MaxArea = Area
Location = idx
MaxContour = np.array(contours[Location])
return MaxContour, MaxArea
Ehh, it's python code.
It only works when the white region is the max contour.
Basic idea of this answer is to use border around text.
1) Erode horizontally with a very large kernel, say size of 100 px or 8 times size of single expected character, something like that. It should be done row-wise. The extreme ordinate will give y-location of boundaries around text.
2) Process vertically same way to get x-location of boundaries around text. Then use these locations to crop out image you want.
-- One benefit of this method is you will get every sentence/word segmented separately which, I presume, is good for an OCR.
Happy Coding :)
Edited in by Mark Setchell
Here is a demo of 1)
Here is a demo of 2)

Categories