Sort images after ROI (Python, OpenCV) - python

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")

Related

Lines are not highlighted

I'm trying to find the outline of the lines. To further find words and symbols. But for some reason my code doesn't work and I can't figure out what it is.
I'm trying to find lines in this image Example
Here's my code
import cv2
import numpy as np
#import image
image = cv2.imread('C:\\Users\\dennn\\PycharmProjects\\untitled2\\output.jpg')
#cv2.imshow('orig',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('second',thresh)
cv2.waitKey(0)
#dilation0000
kernel = np.ones((5,100), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
cv2.imshow('dilated',img_dilation)
cv2.waitKey(0)
#find contours
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.rectangle(image,(x,y),( x + w, y + h ),(90,0,255),2)
cv2.waitKey(0)
cv2.imshow('marked areas',image)
cv2.waitKey(0)
My output image. The output image
I want to receive I want
I don't have sort contours working.
During the debugger, I get the following image, it is only this (the program freezes) show ROI
Here is the solution to this problem

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()

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)

How to improve edge detection and remove background from an image?

I am using the code below to remove the backroung of the images and highlight only my region of interest (ROI), however, the algorithm behaves in a wrong way in some images, discarding the stain (ROI) and deleting along with the background.
import numpy as np
import cv2
#Read the image and perform threshold
img = cv2.imread('photo.bmp')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.medianBlur(gray,5)
_,thresh = cv2.threshold(blur,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
#Search for contours and select the biggest one
contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
cnt = max(contours, key=cv2.contourArea)
#Create a new mask for the result image
h, w = img.shape[:2]
mask = np.zeros((h, w), np.uint8)
#Draw the contour on the new mask and perform the bitwise operation
cv2.drawContours(mask, [cnt],-1, 255, -1)
res = cv2.bitwise_and(img, img, mask=mask)
#Display the result
cv2.imwrite('photo.png', res)
#cv2.imshow('img', res)
cv2.waitKey(0)
cv2.destroyAllWindows()
I don't know if I understand correctly because when I run your code I do not get the output you posted (exit). If you would like to obtain only the mole it can't be done by simply thresholding because the mole is too near the border plus if you look at your image closley you will see that it has some sort of frame. However there is a simple way to do this for this image but it may not work in other cases. You can draw a fake border over your image and seperate the ROI from other noise area. Then make a threshold for which contour you wish to display. Cheers!
Example:
#Import all necessery libraries
import numpy as np
import cv2
#Read the image and perform threshold and get its height and weight
img = cv2.imread('moles.png')
h, w = img.shape[:2]
# Transform to gray colorspace and blur the image.
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),0)
# Make a fake rectangle arround the image that will seperate the main contour.
cv2.rectangle(blur, (0,0), (w,h), (255,255,255), 10)
# Perform Otsu threshold.
_,thresh = cv2.threshold(blur,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
# Create a mask for bitwise operation
mask = np.zeros((h, w), np.uint8)
# Search for contours and iterate over contours. Make threshold for size to
# eliminate others.
_, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
for i in contours:
cnt = cv2.contourArea(i)
if 1000000 >cnt > 100000:
cv2.drawContours(mask, [i],-1, 255, -1)
# Perform the bitwise operation.
res = cv2.bitwise_and(img, img, mask=mask)
# Display the result.
cv2.imwrite('mole_res.jpg', res)
cv2.imshow('img', res)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:

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