We Keep Coding

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:

Complete missing lines in table opencv

I am trying to detect cells in bill image:
I have this image
Removed the stamp with this code:
import cv2
import numpy as np
# read image
img = cv2.imread('dummy1.PNG')
# threshold on yellow
lower = (0, 200, 200)
upper = (100, 255, 255)
thresh = cv2.inRange(img, lower, upper)
# apply dilate morphology
kernel = np.ones((9, 9), np.uint8)
mask = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)
# get largest contour
contours = cv2.findContours(mask, 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 white contour on input
result = img.copy()
cv2.drawContours(result, [big_contour], 0, (255, 255, 255), -1)
cv2.imwrite('removed.png', result)
# show the images
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
And obtained this image:
Then applied grayscale, inverted, detected vertical and horizontal kernel and merged through this main.py :
# Imports
import cv2
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import csv
try:
from PIL import Image
except ImportError:
import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
#################################################################################################
# Read your file
file = 'removed.png'
img = cv2.imread(file, 0)
img.shape
# thresholding the image to a binary image
thresh, img_bin = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# inverting the image
img_bin = 255 - img_bin
cv2.imwrite(r'C:\Users\marou\Desktop\cv_inverted.png', img_bin)
# Plotting the image to see the output
plotting = plt.imshow(img_bin, cmap='gray')
plt.show()
# Define a kernel to detect rectangular boxes
# Length(width) of kernel as 100th of total width
kernel_len = np.array(img).shape[1] // 100
# Defining a vertical kernel to detect all vertical lines of image
ver_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, kernel_len))
# Defining a horizontal kernel to detect all horizontal lines of image
hor_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_len, 1))
# A kernel of 2x2
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
#### Vertical LINES ####
# Use vertical kernel to detect and save the vertical lines in a jpg
image_1 = cv2.erode(img_bin, ver_kernel, iterations=5)
vertical_lines = cv2.dilate(image_1, ver_kernel, iterations=5)
cv2.imwrite(r'C:\Users\marou\Desktop\vertical.jpg', vertical_lines)
# Plot the generated image
plotting = plt.imshow(image_1, cmap='gray')
plt.show()
#### HORTIZONAL LINES ####
# Use horizontal kernel to detect and save the horizontal lines in a jpg
image_2 = cv2.erode(img_bin, hor_kernel, iterations=5)
horizontal_lines = cv2.dilate(image_2, hor_kernel, iterations=5)
cv2.imwrite(r'C:\Users\marou\Desktop\horizontal.jpg', horizontal_lines)
# Plot the generated image
plotting = plt.imshow(image_2, cmap='gray')
plt.show()
# Combining both H and V
# Combine horizontal and vertical lines in a new third image, with both having same weight.
img_vh = cv2.addWeighted(vertical_lines, 0.5, horizontal_lines, 0.5, 0.0)
# Eroding and thesholding the image
img_vh = cv2.erode(~img_vh, kernel, iterations=2)
thresh, img_vh = cv2.threshold(img_vh, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
cv2.imwrite(r'C:\Users\marou\Desktop\img_vh.jpg', img_vh)
plotting = plt.imshow(img_vh, cmap='gray')
plt.show()
To get this :
Now I am trying to fill the voids in my lines that happened due to the watermark removal, to be able to apply correct OCR.
I tried following the steps in this thread but I can't seem to get it right.
When I try to fill the grid holes :
# Fill individual grid holes
cnts = cv2.findContours(result, 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(result, (x, y), (x + w, y + h), 255, -1)
cv2.imshow('result', result)
cv2.waitKey()
I get blank image:

I have outlined an approach to fill the missing lines in the table using the second image as input.
image = cv2.imread(image_path)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Now to create a separate mask for the horizontal lines:
h_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
# contains only the horizontal lines
h_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, h_kernel, iterations=1)
# performing repeated iterations to join lines
h_mask = cv2.dilate(h_mask, h_kernel, iterations=7)
And a separate mask for the vertical lines:
v_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,50))
v_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, v_kernel, iterations=1)
Upon combining the above results we get the following:
joined_lines = cv2.bitwise_or(v_mask, h_mask)
The result above is not what you expected, the lines have extended beyond the boundaries of the table. In order to avoid this, I created a separate mask bounding the table region.
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
dilate = cv2.dilate(thresh, kernel, iterations=1)
Now find the largest contour in the above image and draw it on another binary image to create the mask.
contours, hierarchy = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
c = max(contours, key = cv2.contourArea) # contour with largest area
black = np.zeros((image.shape[0], image.shape[1]), np.uint8)
mask = cv2.drawContours(black, [c], 0, 255, -1) # --> -1 to fill the contour
Using the above image as mask over the joined_lines created further above
fin = cv2.bitwise_and(joined_lines, joined_lines, mask = mask)
Note:
You can perform more iterations over the morphological operations to better join the discontinuous lines

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.

detect an initial/a sketch drawing on a text page

I would like to get the coordinates of the box around the initial ("H") on the following page (and similar ones with other initials, so opencv template matching is not an option):
Following this tutorial, I tried to solve the problem with opencv contours:
import cv2
import matplotlib.pyplot as plt
page = "image.jpg"
# read the image
image = cv2.imread(page)
# convert to RGB
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# create a binary thresholded image
_, binary = cv2.threshold(gray, 0,150,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# find the contours from the thresholded image
contours, hierarchy = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# draw all contours
image = cv2.drawContours(image, contours, 3, (0, 255, 0), 2)
plt.savefig("result.png")
The result is of course not exactly what I wanted:
Does anyone know of an viable algorithm (and possibly an implementation thereof) that could provide an easy solution to my task?

You can find the target area by filtering your contours. Now, there's at least two filtering criteria that you can use. One is filter by area - that is, discard too small and too large contours until you get the contour you are looking for. The other one is by computing the extent of every contour. The extent is the ratio of the contour's area to its bounding rectangle area. You are looking for a square-like contour, so its extent should be close to 1.0.
Let's see the code:
# imports:
import cv2
import numpy as np
# Reading an image in default mode:
inputImage = cv2.imread(path + fileName)
# Deep copy for results:
inputImageCopy = inputImage.copy()
# Convert RGB to grayscale:
grayscaleImage = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Get binary image via Otsu:
_, binaryImage = cv2.threshold(grayscaleImage, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
The first portion of the code gets you a binary image that you can use as a mask to compute contours:
Now, let's filter contours. Let's use the area approach first. You need to define a range of minimum area and maximum area to filter everything that does not fall in this range. I've heuristically determined a range of areas from 30000 px to 150000 px:
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(binaryImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get blob area:
currentArea = cv2.contourArea(c)
print("Contour Area: "+str(currentArea))
# Set an area range:
minArea = 30000
maxArea = 150000
if minArea < currentArea < maxArea:
# Get the contour's bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rect:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Set bounding rect:
color = (0, 0, 255)
cv2.rectangle( inputImageCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 2 )
cv2.imshow("Rectangles", inputImageCopy)
cv2.waitKey(0)
Once you successfully filter the area, you can then compute the bounding rectangle of the contour with cv2.boundingRect. You can retrieve the bounding rectangle's x, y (top left) coordinates as well as its width and height. After that just draw the rectangle on a deep copy of the original input.
Now, let's see the second option, using the contour's extent. The for loop gets modified as follows:
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get blob area:
currentArea = cv2.contourArea(c)
# Get the contour's bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rect:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Calculate extent:
extent = float(currentArea)/(rectWidth *rectHeight)
print("Extent: " + str(extent))
# Set the extent filter, look for an extent close to 1.0:
delta = abs(1.0 - extent)
epsilon = 0.1
if delta < epsilon:
# Set bounding rect:
color = (0, 0, 255)
cv2.rectangle( inputImageCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 2 )
cv2.imshow("Rectangles", inputImageCopy)
cv2.waitKey(0)
Both approaches yield this result:

You almost have it. You just need to filter contours on area and aspect ratio. Here is my approach in Python/OpenCV.
Input:
import cv2
import numpy as np
# read image as grayscale
img = cv2.imread('syriados.jpg')
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold to binary
#thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# invert threshold
thresh = 255 - thresh
# apply morphology to remove small white regions and to close the rectangle boundary
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# find contours
result = img.copy()
cntrs = cv2.findContours(morph, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
# filter on area and aspect ratio
for c in cntrs:
area = cv2.contourArea(c)
x,y,w,h = cv2.boundingRect(c)
if area > 10000 and abs(w-h) < 100:
cv2.drawContours(result, [c], 0, (0,0,255), 2)
# write results
cv2.imwrite("syriados_thresh.jpg", thresh)
cv2.imwrite("syriados_morph.jpg", morph)
cv2.imwrite("syriados_box.jpg", result)
# show results
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
Threshold image:
Morphology image:
Resulting contour image:

To get a result like this:
You'll need to detect the contour in the image with the second to the greatest area, as the one possessing the greatest area would be the border of the image.
So with the list of contours, we can get the one with the second greatest area via the built-in sorted method, using the cv2.contourArea method as the custom key:
import cv2
import numpy as np
def process(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (7, 7), 2)
img_canny = cv2.Canny(img_blur, 50, 50)
kernel = np.ones((6, 6))
img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
img_erode = cv2.erode(img_dilate, kernel, iterations=2)
return img_erode
def get_contours(img):
contours, _ = cv2.findContours(process(img), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnt = sorted(contours, key=cv2.contourArea)[-2]
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.02 * peri, True)
cv2.drawContours(img, [approx], -1, (0, 255, 0), 2)
page = "image.jpg"
image = cv2.imread(page)
get_contours(image)
cv2.imshow("Image", image)
cv2.waitKey(0)
The above only puts the area of the contours into consideration; if you want more reliable results, you can make it so that it will only detect contours that are 4-sided.