Unable to read image text with python tesseract and OpenCV - python

I am trying read text from this
using Python with OpenCV. However, it is not able to read it.
import cv2 as cv
import numpy as np
from matplotlib import pyplot as plt
img=cv.imread(file_path,0)
img = cv.medianBlur(img,5)
ret,th1 = cv.threshold(img,127,255,cv.THRESH_BINARY)
th2 =cv.adaptiveThreshold(img,255,cv.ADAPTIVE_THRESH_MEAN_C,\
cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(img,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,\
cv.THRESH_BINARY,11,2)
titles = ['Original Image', 'Global Thresholding (v = 127)',
'Adaptive Mean Thresholding', 'Adaptive Gaussian Thresholding']
images = [img, th1, th2, th3]
for i in range(4):
plt.subplot(2,2,i+1),plt.imshow(images[i],'gray')
plt.title(titles[i])
plt.xticks([]),plt.yticks([])
plt.show()
anyway to do this?

Instead of working on the grayscale image, working on saturation channel of the HSV color space makes the subsequent steps easier.
img = cv2.imread(image_path_to_captcha)
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
s_component = hsv[:,:,1]
s_component
Next, apply a Gaussian blur of appropriate kernel size and sigma value, and later threshold.
blur = cv2.GaussianBlur(s_component,(7,7), 7)
ret,th3 = cv2.threshold(blur,127,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
th3
Next, finding contours in the image above and preserving those above a certain area threshold in the black image variable which will be used as mask later on.
contours, hierarchy = cv2.findContours(th3, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
black = np.zeros((img.shape[0], img.shape[1]), np.uint8)
for contour in contours:
if cv2.contourArea(contour) >600 :
cv2.drawContours(black, [contour], 0, 255, -1)
black
Using the black image variable as mask over the threshold image
res = cv2.bitwise_and(th3, th3, mask = black)
res
Finally, applying morphological thinning to the above result
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
erode = cv2.erode(res, kernel, iterations=1)
erode
The end result is not what you expect. You can try experimenting different morphology operations prior to drawing contours as well.
EDIT
You can perform distance transform on the above image and use the result:
dist = cv2.distanceTransform(res, cv2.DIST_L2, 3)
dst = cv2.normalize(dist, dst=None, alpha=0, beta=255,norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)
dst

Related

Masked out large irregular shape from image with Python

The objective is to remove large irregular area and maintained only character in the image.
For example, given the following
and the expected masked output
I have the impression this can be achieved as below
import cv2
import numpy as np
from matplotlib import pyplot as plt
dpath='remove_bg1.jpg'
img = cv2.imread(dpath)
img_fh=img.copy()
cv2.bitwise_not(img_fh,img_fh)
ksize=10
kernel = np.ones((ksize,ksize),np.uint8)
erosion = cv2.erode(img_fh,kernel,iterations = 3)
invertx = cv2.bitwise_not(erosion)
masked = cv2.bitwise_not(cv2.bitwise_and(img_fh,invertx))
all_image=[img,invertx,masked]
ncol=len(all_image)
for idx, i in enumerate(all_image):
plt.subplot(int(f'1{ncol}{idx+1}')),plt.imshow(i)
plt.show()
which produce
Clearly, the code above did not produced the expected result.
May I know how to address this issue properly?
To remove the unwanted blob, we must create a mask such that it encloses it completely.
Flow:
Inversely binarize the image (such that you have a white foreground against dark background)
Dilate the image (since the blob makes contact with letter 'A', it has to be isolated )
Find contour with the largest area
Draw the contour on an another 1-channel image and thicken it (dilation)
Pixel Assignment: Pixels containing the dilated blob are made white on the original image
Code:
im = cv2.imread('stained_text.jpg')
im2 = im.copy()
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
# inverse binaraization
th = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Notice the blob region touching the letter 'A'. Hence to isolate it we perform erosion using an elliptical kernel
# erosion
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
erode = cv2.erode(th, kernel, iterations=2)
# find contours
contours, hierarchy = cv2.findContours(erode, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Contour of maximum area
c = max(contours, key = cv2.contourArea)
# create 1-channel image in black
black = np.zeros((im.shape[0], im.shape[1]), np.uint8)
# draw the contour on it
black = cv2.drawContours(black, [c], 0, 255, -1)
# perform dilation to have clean border
# we are using the same kernel
dilate = cv2.dilate(black, kernel, iterations = 3)
# assign the dilated area in white over the original image
im2[dilate == 255] = (255,255,255)
This was just one of the many possible ways on how to proceed. The key thing to note is how to isolate the blob.

How can I retain background after dilating text in image

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)
cv2.imshow('dilate', dilate)
cv2.waitKey()
I am trying to mask the text elements in an image and return an image with just the remaining portions. I have applied thresholding and dilating, but how can I retain the background.
Image after thresholding and dilating
Original image:
Here is a simple approach:
Using the inverted dilated image cv2.bitwise_not(dilate), create a mask over the original image.
res = cv2.bitwise_and(image, image, mask=cv2.bitwise_not(dilate))
In the above image you have all text regions and its boundaries masked out.
Now replace those masked out regions with the background of your original image. To do that, first I noted down the coordinates where of the text regoins in mask_ind. Then replaced the pixel values in those regions with the background of the original image image[0,0]
mask_ind = (dilate == 255)
res[mask_ind] = image[0,0]
cv2.imshow(res)

Identify and count objects different from background

I try to use python, NumPy, and OpenCV to analyze the image below and just draw a circle on each object found. The idea here is not to identify the bug only identify any object that is different from the background.
Original Image:
Here is the code that I'm using.
import cv2
import numpy as np
img = cv2.imread('per.jpeg', cv2.IMREAD_GRAYSCALE)
if cv2.__version__.startswith('2.'):
detector = cv2.SimpleBlobDetector()
else:
detector = cv2.SimpleBlobDetector_create()
keypoints = detector.detect(img)
print(len(keypoints))
imgKeyPoints = cv2.drawKeypoints(img, keypoints, np.array([]), (0,0,255), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
status = cv2.imwrite('teste.jpeg',imgKeyPoints)
print("Image written to file-system : ",status)
But the problem is that I'm getting only a greyscale image as result without any counting or red circle, as shown below:
Since I'm new to OpenCV and object recognition world I'm not able to identify what is wrong, and any help will be very appreciated.
Here is one way in Python/OpenCV.
Threshold on the bugs color in HSV colorspace. Then use morphology to clean up the threshold. Then get contours. Then find the minimum enclosing circle around each contour. Then bias the radius to make a bit larger and draw the circle around each bug.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('bugs.jpg')
# convert image to hsv colorspace
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# threshold on bugs color
lower=(0,90,10)
upper=(100,250,170)
thresh = cv2.inRange(hsv, lower, upper)
# apply morphology to clean up
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (6,6))
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
result = img.copy()
bias = 10
for cntr in contours:
center, radius = cv2.minEnclosingCircle(cntr)
cx = int(round(center[0]))
cy = int(round(center[1]))
rr = int(round(radius)) + bias
cv2.circle(result, (cx,cy), rr, (0, 0, 255), 2)
# save results
cv2.imwrite('bugs_threshold.jpg', thresh)
cv2.imwrite('bugs_cleaned.jpg', morph)
cv2.imwrite('bugs_circled.jpg', result)
# display results
cv2.imshow('thresh', thresh)
cv2.imshow('morph', morph)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold Image:
Morphology Cleaned Image:
Resulting Circles:

Retinal blood vessel segmentation using Python

I have the following retina image and I'm trying to trace the vessels (the darker lines coming out of the circle). Here is the original image:
I have tried thresholding the image using division normalization followed by filtering on contour area (as per a different stackoverflow solution):
import cv2
import numpy as np
# read the image
img = cv2.imread('retina_eye.jpg')
# convert to gray
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_RECT , (5,5))
morph = cv2.morphologyEx(gray, cv2.MORPH_DILATE, kernel)
# divide gray by morphology image
division = cv2.divide(gray, morph, scale=255)
# threshold
thresh = cv2.threshold(division, 0, 255, cv2.THRESH_OTSU )[1]
# invert
thresh = 255 - thresh
# find contours and discard contours with small areas
mask = np.zeros_like(thresh)
contours = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
area_thresh = 10000
for cntr in contours:
area = cv2.contourArea(cntr)
if area > area_thresh:
cv2.drawContours(mask, [cntr], -1, 255, 2)
# apply mask to thresh
result1 = cv2.bitwise_and(thresh, mask)
mask = cv2.merge([mask,mask,mask])
result2 = cv2.bitwise_and(img, mask)
# save results
cv2.imwrite('retina_eye_division.jpg',division)
cv2.imwrite('retina_eye_thresh.jpg',thresh)
cv2.imwrite('retina_eye_mask.jpg',mask)
cv2.imwrite('retina_eye_result1.jpg',result1)
cv2.imwrite('retina_eye_result2.jpg',result2)
# show results
cv2.imshow('morph', morph)
cv2.imshow('division', division)
cv2.imshow('thresh', thresh)
cv2.imshow('mask', mask)
cv2.imshow('result1', result1)
cv2.imshow('result2', result2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Here is the final output I got:
It ended up tracing the vessels, but it also had some background noise.
Ideally I am looking for this output:
Any suggestions for achieving this result?
I have been researching the topic of retinal blood-vessel segmentation using deep learning and the question you asked is basically the same.
I would like to share my research with you.
In the cases where the part of images we want to segment has very low intensity or contrast, we have to apply CLAHE (Contrast Limited Adaptive Histogram Equalization). It is very powerful technique to get the very good results. I would like you to try it. Let me provide you some code for this also:
import cv2
bgr = cv2.imread(retinal_image)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
equalized = clahe.apply(gray)
More over you can also use Non Local Mean for denoising the image.
If you want to know about the full process how it is done, I would recommend you to go through this easy paper which covers the whole process.

find rectangle in image and extract text inside of it to save it as new image

I am new to OpenCV so I really need your help. I have a bunch of images like this one:
I need to detect the rectangle on the image, extract the text part from it and save it as a new image.
Can you please help me with this?
Thank you!
Just to add to Danyals answer I have added an example code with steps written in comments. For this image you don't even need to perform morphological opening on the image. But usually for this kind of noise in the image it is recomended. Cheers!
import cv2
import numpy as np
# Read the image and create a blank mask
img = cv2.imread('napis.jpg')
h,w = img.shape[:2]
mask = np.zeros((h,w), np.uint8)
# Transform to gray colorspace and invert Otsu threshold the image
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
# ***OPTIONAL FOR THIS IMAGE
### Perform opening (erosion followed by dilation)
#kernel = np.ones((2,2),np.uint8)
#opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
# ***
# Search for contours, select the biggest and draw it on the mask
_, contours, hierarchy = cv2.findContours(thresh, # if you use opening then change "thresh" to "opening"
cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
cnt = max(contours, key=cv2.contourArea)
cv2.drawContours(mask, [cnt], 0, 255, -1)
# Perform a bitwise operation
res = cv2.bitwise_and(img, img, mask=mask)
########### The result is a ROI with some noise
########### Clearing the noise
# Create a new mask
mask = np.zeros((h,w), np.uint8)
# Transform the resulting image to gray colorspace and Otsu threshold the image
gray = cv2.cvtColor(res,cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# Search for contours and select the biggest one again
_, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
cnt = max(contours, key=cv2.contourArea)
# Draw it on the new mask and perform a bitwise operation again
cv2.drawContours(mask, [cnt], 0, 255, -1)
res = cv2.bitwise_and(img, img, mask=mask)
# If you will use pytesseract it is wise to make an aditional white border
# so that the letters arent on the borders
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(res,(x,y),(x+w,y+h),(255,255,255),1)
# Crop the result
final_image = res[y:y+h+1, x:x+w+1]
# Display the result
cv2.imshow('img', final_image)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:
One way to do this (if the rectangle sizes are somewhat predictable) is:
Convert the image to black and white
Invert the image
Perform morphological opening on the image from (2) with a horizontal line / rectangle (I tried with 2x30).
Perform morphological opening on the image from (2) with a vertical line (I tried it with 15x2).
Add the images from (3) and (4). You should only have a white rectangle now. Now can remove all corresponding rows and columns in the original image that are entirely zero in this image.

Categories

Resources