We Keep Coding

Find contours based on edges

I want to detect the contours of an equipment label. Although the code runs correctly, it never quite detects the contours of the label.
Original Image
Using this code:
import numpy as np
import cv2
import imutils #resizeimage
import pytesseract # convert img to string
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
# Read the image file
image = cv2.imread('Car Images/5.JPG')
# Resize the image - change width to 500
image = imutils.resize(image, width=500)
# Display the original image
cv2.imshow("Original Image", image)
cv2.waitKey(0)
# RGB to Gray scale conversion
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow("1 - Grayscale Conversion", gray)
cv2.waitKey(0)
# Noise removal with iterative bilateral filter(removes noise while preserving edges)
gray = cv2.bilateralFilter(gray, 11, 17, 17)
cv2.imshow("2 - Bilateral Filter", gray)
cv2.waitKey(0)
# Find Edges of the grayscale image
edged = cv2.Canny(gray, 170, 200)
cv2.imshow("3 - Canny Edges", edged)
cv2.waitKey(0)
# Find contours based on Edges
cnts, new = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# Create copy of original image to draw all contours
img1 = image.copy()
cv2.drawContours(img1, cnts, -1, (0,255,0), 3)
cv2.imshow("4- All Contours", img1)
cv2.waitKey(0)
#sort contours based on their area keeping minimum required area as '30' (anything smaller than this will not be considered)
cnts=sorted(cnts, key = cv2.contourArea, reverse = True)[:30]
NumberPlateCnt = None #we currently have no Number plate contour
# Top 30 Contours
img2 = image.copy()
cv2.drawContours(img2, cnts, -1, (0,255,0), 3)
cv2.imshow("5- Top 30 Contours", img2)
cv2.waitKey(0)
# loop over our contours to find the best possible approximate contour of number plate
count = 0
idx =7
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
# print ("approx = ",approx)
if len(approx) == 4: # Select the contour with 4 corners
NumberPlateCnt = approx #This is our approx Number Plate Contour
# Crop those contours and store it in Cropped Images folder
x, y, w, h = cv2.boundingRect(c) #This will find out co-ord for plate
new_img = gray[y:y + h, x:x + w] #Create new image
cv2.imwrite('Cropped Images-Text/' + str(idx) + '.png', new_img) #Store new image
idx+=1
break
# Drawing the selected contour on the original image
#print(NumberPlateCnt)
cv2.drawContours(image, [NumberPlateCnt], -1, (0,255,0), 3)
cv2.imshow("Final Image With Number Plate Detected", image)
cv2.waitKey(0)
Cropped_img_loc = 'Cropped Images-Text/7.png'
cv2.imshow("Cropped Image ", cv2.imread(Cropped_img_loc))
# Use tesseract to covert image into string
text = pytesseract.image_to_string(Cropped_img_loc, lang='eng')
print("Equipment Number is :", text)
cv2.waitKey(0) #Wait for user input before closing the images displayed
Displayed output
Is there a better way to narrow down the contour to the equipment label?
Here is the code for your reference on github:
https://github.com/AjayAndData/Licence-plate-detection-and-recognition---using-openCV-only/blob/master/Car%20Number%20Plate%20Detection.py

I think this code may help you
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('C:/Users/DELL/Desktop/download (5).png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
corners = cv2.goodFeaturesToTrack(gray,60,0.001,10)
corners = np.int0(corners)
for i in corners:
x,y = i.ravel()
cv2.circle(img,(x,y),0,255,-1)
coord = np.where(np.all(img == (255, 0, 0),axis=-1))
plt.imshow(img)
plt.show()

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 remove all portrait pictures from a document

I am working on OCRing a document image. I want to detect all pictures and remove from the document image. I want to retain tables in the document image. Once I detect pictures I will remove and then want to OCR. I tried to find contour tried to detect all the bigger areas. unfortunately it detects tables also. Also how to remove the objects keeping other data in the doc image. I am using opencv and python
Here's my code
import os
from PIL import Image
import pytesseract
img = cv2.imread('block2.jpg' , 0)
mask = np.ones(img.shape[:2], dtype="uint8") * 255
ret,thresh1 = cv2.threshold(img,127,255,0)
contours, sd = cv2.findContours(thresh1,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
areacontainer = []
for cnt in contours:
area = cv2.contourArea(cnt)
areacontainer.append(area)
avgArea = sum(areacontainer)/len(areacontainer)
[enter code here][1]
for c in contours:# average area heuristics
if cv2.contourArea(c)>6*avgArea:
cv2.drawContours(mask, [c], -1, 0, -1)
binary = cv2.bitwise_and(img, img, mask=mask) # subtracting
cv2.imwrite("bin.jpg" , binary)
cv2.imwrite("mask.jpg" , mask)

Here's an approach:
Convert image to grayscale and Gaussian blur
Perform canny edge detection
Perform morphological operations to smooth image
Find contours and filter using a minimum/maximum threshold area
Remove portrait images
Here's the detected portraits highlighted in green
Now that we have the bounding box ROIs, we can effectively remove the pictures by filling them in with white. Here's the result
import cv2
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
canny = cv2.Canny(blur, 120, 255, 1)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
close = cv2.morphologyEx(canny, cv2.MORPH_CLOSE, kernel, iterations=2)
cnts = cv2.findContours(close, 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 > 15000 and area < 35000:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (255,255,255), -1)
cv2.imshow('image', image)
cv2.waitKey()

Split handwritten number touching each other with openCV in Python for MNIST preprocessing

I'm looking to split number on image. My main problem is that the number may touch each other. so all technique with OpenCV contour found online doesn't work.
Here the steps i've done so far. It's working well with image that have number well separated, but not with number touching each other. One of the image i try to solve:
I'm trying to do that as part of the preprocessing step so i can after that use the number in my MNIST model.
My actual code:
import cv2
import numpy as np
# 3 - detect and extract ROI's
#image = cv2.imread('imgs/01.jpg')
#image = cv2.imread('imgs/03.jpg')
image = cv2.imread('imgs/01_tresh_210.jpg')
#cv2.imshow('i', image)
#cv2.waitKey(0)
# grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow('gray', gray)
cv2.waitKey(0)
# binary
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV)
cv2.imshow('thresh', thresh)
cv2.waitKey(0)
# dilation
kernel = np.ones((10, 1), np.uint8) # values set for this image only - need to change for different images
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
cv2.imshow('dilated', img_dilation)
cv2.waitKey(0)
# find contours
im2, ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# sort contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
# Get bounding box
x, y, w, h = cv2.boundingRect(ctr)
# Getting ROI
roi = image[y:y + h, x:x + w]
# show ROI
#cv2.imshow('segment no:'+str(i),roi)
cv2.imwrite('imgs\\roi\\{}.png'.format(i), roi)
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 0, 0), 1)
#cv2.waitKey(0)
# save only the ROI's which contain a valid information
if h > 20 and w > 75:
cv2.imwrite('roi\\{}.png'.format(i), roi)
cv2.imshow('marked areas', image)
cv2.waitKey(0)

Sort images after ROI (Python, OpenCV)

I am near new to OpenCV world. I am working on a project which need (for now) to detect numbers in an image, select them and save.
This is the code I used:
# Importing modules
import cv2
import numpy as np
# Read the input image
im = cv2.imread('C:\\Users\\User\\Desktop\\test.png')
# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)
# Threshold the image
ret, im_th = cv2.threshold(im_gray, 90, 255, cv2.THRESH_BINARY_INV)
# Find contours in the image
image, ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Bounding rectangle for a set of points
i = 0
#rects = [cv2.boundingRect(ctr) for ctr in ctrs]
#rects.sort()
for ctr in ctrs:
x, y, w, h = cv2.boundingRect(ctrs[i])
# Getting ROI
roi = im[y:y+h, x:x+w]
#cv2.imshow('roi',roi)
#cv2.waitKey()
i += 1
cv2.imwrite('C:\\Users\\User\\Desktop\\crop\\' + str(i) + '.jpg', roi)
#print(rects)
print("OK - NO ERRORS")
It works a half. The problem is the output numbers (in image format, it need to be that way) aren't ordered by the original image (below).
This is the output:
What is wrong in the code ?
Also, you can note the rects variable. I used it to do some debug and I noted an interesting thing: if I sort it's content, in console the array of images order is right.
Is there a way to sort the images in the original order ?
I also saw this very similar post but I can't understand the solution.
Thank you very much.

There is no natural order given that the ROIs could be spread out in two dimensional space.
If you want to order them by x coordinate you could do:
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
and then loop over sorted_ctrs instead of ctrs.
Edit: More precisely:
import cv2
import numpy as np
# Read the input image
im = cv2.imread('JnUpW.png')
# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)
# Threshold the image
ret, im_th = cv2.threshold(im_gray, 90, 255, cv2.THRESH_BINARY_INV)
# Find contours in the image
image, ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Sort the bounding boxes
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
# Get bounding box
x, y, w, h = cv2.boundingRect(ctr)
# Getting ROI
roi = im[y:y+h, x:x+w]
# Write to disk
cv2.imwrite(str(i) + '.jpg', roi)
#print(rects)
print("OK - NO ERRORS")