Develop Reference

Pytesseract and OpenCV can't detect digits

Thanks in advance to everyone that will answer.
I am new to OpenCV, Pytesseract and overall very inexperienced about image processing and recognition.
I am trying to detect a digit from a pdf, for the sake of this code I will directly provide the image:
Initial image
My objective is to detect the number in the colored box, which in this case is number 6.
My code for preprocessing is the following:
import numpy as np
import pytesseract
from PIL import Image
from PIL import ImageFilter, ImageEnhance
pytesseract.pytesseract.tesseract_cmd = 'Tesseract-OCR\tesseract.exe'
# -----Reading the image-----------------------------------------------------
img = cv2.imread('page_image.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = cv2.resize(gray, (1028, 720))
thres_gray = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU)[1]
gray_inv = cv2.bitwise_not(thres_gray)
gray_test = cv2.bitwise_not(gray_inv)
out2 = cv2.bitwise_or(gray, gray, mask=gray_inv)
thresh_end = cv2.threshold(out2, 254, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
imageObject = Image.fromarray(thresh_end)
enhancer = ImageEnhance.Sharpness(imageObject)
sharpened1 = imageObject.filter(ImageFilter.SHARPEN)
sharpened2 = sharpened1.filter(ImageFilter.SHARPEN)
# sharpened2.show()
From this I obtain the following picture:
Preprocessed image
At this point, since I am still learning about how to detect the region of interest and crop it with OpenCV, to test the code I decided to manually crop the image to test if my script works correctly enough.
Therefore the image I pass to pytesseract is the following:
Final image to read with pytesseract
I am not really sure if the image is good enough to be read, but this is the best I could get.
From this I try image_to_string:
trial = pytesseract.image_to_string(sharpened2, config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789')
I have tried many different configurations for the tesseract but none of it worked and the final output is always an empty string.
I would be really grateful if you could help me understand whether the image is not good enough or I am doing something wrong with the tesseract configuration.
If you could also be able to help me cropping the image correctly that would be awesome, but even detecting the number is enough for me.
Sorry for the long post and thanks again.

Try this:
import cv2
import pytesseract
import numpy as np
pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
img = cv2.imread("form.jpg")
# https://stackoverflow.com/questions/10948589/choosing-the-correct-upper-and-lower-hsv-boundaries-for-color-detection-withcv
ORANGE_MIN = np.array([5, 50, 50], np.uint8)
ORANGE_MAX = np.array([15, 255, 255], np.uint8)
hsv_img = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
frame_threshed = cv2.inRange(hsv_img, ORANGE_MIN, ORANGE_MAX)
# cv2.imshow("frame_threshed", frame_threshed)
thresh = cv2.threshold(frame_threshed, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# cv2.imshow("thresh", thresh)
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
# cv2.imshow("dilate", thresh)
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
ROI = thresh[y:y + h, x:x + w]
ratio = 100.0 / ROI.shape[1]
dim = (100, int(ROI.shape[0] * ratio))
resizedCubic = cv2.resize(ROI, dim, interpolation=cv2.INTER_CUBIC)
threshGauss = cv2.adaptiveThreshold(resizedCubic, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 255, 17)
cv2.imshow("ROI", threshGauss)
text = int(pytesseract.image_to_string(threshGauss, lang='eng', config="--oem 3 --psm 13"))
print(f"Detected text: {text}")
cv2.waitKey(0)
I used HSV method to detect orange color first. Then, once the ROI was clearly visible, I applied "classic" image pre-processing steps.
Take a look at this link to understand how to select other colors than orange.
I also resized the ROI a bit.

I'm having problems recognizing text from a picture, python

I was given a school project for recognizing various kinds of CAPTCHA, and I had some difficulties with its implementation.
Images of this type will be fed into input ,,.
I handle them with the following code:
import cv2
import pytesseract
# load image
fname = 'picture.png'
im = cv2.imread(fname,cv2.COLOR_RGB2GRAY)
pytesseract.pytesseract.tesseract_cmd = r'C:\Tesseract-OCR\tesseract.exe'
im = im[0:90, 35:150]
im = cv2.blur(im,(3,3))
im = cv2.threshold(im, 223 , 250, cv2.THRESH_BINARY)
im = im[1]
cv2.imshow('',im)
cv2.waitKey(0)
After all processing, the image looks like this: And at this point, I have a problem, how can I modify the image to good readability by the computer, so that instead of the wrong TAREQ. he would display the 7TXB6Q
I am trying to display text from an image with the pytesseract library as follows
data = pytesseract.image_to_string(im, lang='eng', config='--psm 6 --oem 3 -c tessedit_char_whitelist= ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789')
print(data)
I am writing here hoping to get valuable advice (perhaps you know the most suitable way to get text from a picture or process the image pinned above). Peace for everyone)
More images

You can try finding countours and eliminating those which have small areas. This preprocessing operation should increase the success of OCR result.
Before:
import cv2 as cv
import numpy as np
# your thresholded image im
bw = cv.imread('bw.png', cv.IMREAD_GRAYSCALE)
_, cnts, _ = cv.findContours(bw, cv.RETR_TREE, cv.CHAIN_APPROX_SIMPLE)
# remove the largest contour which is background
cnts = np.array(cnts[1:], dtype=object)
areas = np.array(list(map(cv.contourArea, cnts)))
thr = 35
thr_cnts = cnts[areas > thr]
disp_img = 255 * np.ones(bw.shape, dtype=np.uint8)
disp_img = cv.drawContours(disp_img, thr_cnts, -1, (0, 0, 0), cv.FILLED)
disp_img = cv.bitwise_or(disp_img, bw)
cv.imshow('result', disp_img)
cv.waitKey()
cv.destroyAllWindows()
cv.imwrite('result.png', disp_img)
Result:
Edit: It seems that merging the two codes did not give the same result. This is the full code from the beginning to the end.
Input:
import cv2 as cv
import numpy as np
# load image
fname = 'im.png'
im = cv.imread(fname, cv.IMREAD_GRAYSCALE)
# crop
im = im[0:90, 35:150]
# blurring is essential for denoising
im = cv.blur(im, (3,3))
thr = 219
# the binary threshold value is very important
# using 220 instead of 219 causes loss of a letter
# because it touches to the bottom edge and gets involved in the background
_, im = cv.threshold(im, thr, 255, cv.THRESH_BINARY)
cv.imshow('', im)
cv.waitKey(0)
Thresholded:
# binary image
bw = np.copy(im)
# find contours and corresponding areas
_, cnts, _ = cv.findContours(bw, cv.RETR_LIST, cv.CHAIN_APPROX_NONE)
cnts = np.array(cnts, dtype=object)
areas = np.array(list(map(cv.contourArea, cnts)))
thr = 35
# eliminate contours that are smaller than threshold
# also remove the largest contour which is background
thr_cnts = cnts[np.logical_and(areas > thr, areas != np.max(areas))]
# draw the remaining contours
disp_img = 255 * np.ones(bw.shape, dtype=np.uint8)
disp_img = cv.drawContours(disp_img, thr_cnts, -1, (0, 0, 0), cv.FILLED)
disp_img = cv.bitwise_or(disp_img, bw)
cv.imshow('', disp_img)
cv.waitKey()
cv.destroyAllWindows()
Result:

Preprocess images using OpenCV for pytesseract OCR

I want to use OCR (pytesseract) to recognize the text located in images like these:
I have thousands of these arrows. Until now the procedure is as follows: I first resize the image (for another process). Then I crop the image to get rid of the most part of the arrow. Next I draw a white rectangle as a frame to remove further noise but still have distance between text and image borders for better text recognition. I resize the image again to ensure a height of capital letters to ~30 px (https://groups.google.com/forum/#!msg/tesseract-ocr/Wdh_JJwnw94/24JHDYQbBQAJ). Finally I binarize the image with a threshold of 150.
Full code:
import cv2
image_file = '001.jpg'
# load the input image and grab the image dimensions
image = cv2.imread(image_file, cv2.IMREAD_GRAYSCALE)
(h_1, w_1) = image.shape[:2]
# resize the image and grab the new image dimensions
image = cv2.resize(image, (int(w_1*320/h_1), 320))
(h_1, w_1) = image.shape
# crop image
image_2 = image[70:h_1-70, 20:w_1-20]
# get image_2 height, width
(h_2, w_2) = image_2.shape
# draw white rectangle as a frame around the number -> remove noise
cv2.rectangle(image_2, (0, 0), (w_2, h_2), (255, 255, 255), 40)
# resize image, that capital letters are ~ 30 px in height
image_2 = cv2.resize(image_2, (int(w_2*50/h_2), 50))
# image binarization
ret, image_2 = cv2.threshold(image_2, 150, 255, cv2.THRESH_BINARY)
# save image to file
cv2.imwrite('processed_' + image_file, image_2)
# tesseract part can be commented out
import pytesseract
config_7 = ("-c tessedit_char_whitelist=0123456789AB --oem 1 --psm 7")
text = pytesseract.image_to_string(image_2, config=config_7)
print("OCR TEXT: " + "{}\n".format(text))
The problem is that the text located in the arrow is never centered. Sometimes I remove part of the text with the method described above (e.g. in image 50A).
Is there a method in image processing to get rid of the arrow in a more elegant way? For instance using contour detection and deletion? I am more interested in the OpenCV part than the tesseract part to recognize the text.
Any help is appreciated.

If you look at the pictures you will see that there is a white arrow in the image which is also the biggest contour (especially if you draw a black border on the image). If you make a blank mask and draw the arrow (biggest contour on the image) then erode it a little bit you can perform a per element bitwise conjunction of the actual image and eroded mask. If it is not clear look at the bottom code and comments and you will see that it is actually pretty simple.
# imports
import cv2
import numpy as np
img = cv2.imread("number.png") # read image
# you can resize the image here if you like - it should still work for both sizes
h, w = img.shape[:2] # get the actual images height and width
img = cv2.resize(img, (int(w*320/h), 320))
h, w = img.shape[:2]
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # transform to grayscale
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1] # perform OTSU threhold
cv2.rectangle(thresh, (0, 0), (w, h), (0, 0, 0), 2)
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0] # search for contours
max_cnt = max(contours, key=cv2.contourArea) # select biggest one
mask = np.zeros((h, w), dtype=np.uint8) # create a black mask
cv2.drawContours(mask, [max_cnt], -1, (255, 255, 255), -1) # draw biggest contour on the mask
kernel = np.ones((15, 15), dtype=np.uint8) # make a kernel with appropriate values - in both cases (resized and original) 15 is ok
erosion = cv2.erode(mask, kernel, iterations=1) # erode the mask with given kernel
reverse = cv2.bitwise_not(img.copy()) # reversed image of the actual image 0 becomes 255 and 255 becomes 0
img = cv2.bitwise_and(reverse, reverse, mask=erosion) # per-element bit-wise conjunction of the actual image and eroded mask (erosion)
img = cv2.bitwise_not(img) # revers the image again
# save image to file and display
cv2.imwrite("res.png", img)
cv2.imshow("img", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:

You can try simple Python script:
import cv2
import numpy as np
img = cv2.imread('mmubS.png', cv2.IMREAD_GRAYSCALE)
thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY_INV )[1]
im_flood_fill = thresh.copy()
h, w = thresh.shape[:2]
im_flood_fill=cv2.rectangle(im_flood_fill, (0,0), (w-1,h-1), 255, 2)
mask = np.zeros((h + 2, w + 2), np.uint8)
cv2.floodFill(im_flood_fill, mask, (0, 0), 0)
im_flood_fill = cv2.bitwise_not(im_flood_fill)
cv2.imshow('clear text', im_flood_fill)
cv2.imwrite('text.png', im_flood_fill)
Result:

Get pixels location

I have a question about python and opencv. I would like to change the part of the picture which is black to some other color (no matter what). After changing, I would like to get the pixel values, ​​these 8 points marked with a red circle. How to do it?
https://imgur.com/2E1Wwqg
import cv2
import numpy as np
img = cv2.imread("image.jpg");
img[np.where((img == [0,0,0]).all(axis = 2))] = [50,150,166]
cv2.imwrite('output.png', img)
cv2.imshow("shapes", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

You can do that using OpenCV findContours() and minAreaRect() like this:
#!/usr/bin/env python3
import numpy as np
import cv2
# Load image
im = cv2.imread('start.png')
# Convert to grayscale
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
# Theshold inverse so the black comes out white because findContours() looks for white objects
ret,thresh = cv2.threshold(imgray,16,255,cv2.THRESH_BINARY_INV)
cv2.imwrite('thresh.png',thresh)
# Remove noise specks
thresh = cv2.medianBlur(thresh,5)
cv2.imwrite('thresh-m.png',thresh)
# Find contours, draw on image and save
im2, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(im, contours, -1, (0,255,0), 3)
# Show user what we found
i=0
for cnt in contours:
rect = cv2.minAreaRect(cnt)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(im,[box],0,(255,0,0),2)
print('Contour:{}\n{}'.format(i,box))
i = i+1
cv2.imwrite('result.png',im)
The thresholded image looks like this:
And the result image look like this:
The program output is the 4 corner points of the 4 minimum rectangles each one containing one of your lines.
Contour:0
[[416 776]
[410 767]
[659 607]
[664 616]]
Contour:1
[[297 780]
[ 77 599]
[ 83 592]
[303 773]]
Contour:2
[[518 695]
[507 694]
[519 176]
[530 177]]
Contour:3
[[226 688]
[224 174]
[233 173]
[235 687]]

How to count objects in image using python?

I am trying to count the number of drops in this image and the coverage percentage of the area covered by those drops.
I tried to convert this image into black and white, but the center color of those drops seems too similar to the background. So I only got something like the second picture.
Is there any way to solve this problem or any better ideas?
Thanks a lot.

You can fill the holes of your binary image using scipy.ndimage.binary_fill_holes. I also recommend using an automatic thresholding method such as Otsu's (avaible in scikit-image).
from skimage import io, filters
from scipy import ndimage
import matplotlib.pyplot as plt
im = io.imread('ba3g0.jpg', as_grey=True)
val = filters.threshold_otsu(im)
drops = ndimage.binary_fill_holes(im < val)
plt.imshow(drops, cmap='gray')
plt.show()
For the number of drops you can use another function of scikit-image
from skimage import measure
labels = measure.label(drops)
print(labels.max())
And for the coverage
print('coverage is %f' %(drops.mean()))

I used the following code to detect the number of contours in the image using OpenCV and python.
import cv2
import numpy as np
img = cv2.imread('ba3g0.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,1)
contours,h = cv2.findContours(thresh,1,2)
for cnt in contours:
cv2.drawContours(img,[cnt],0,(0,0,255),1)
For further removing the contours inside another contour, you need to iterate over the entire list and compare and remove the internal contours. After that, the size of "contours" will give you the count

The idea is to isolate the background form the inside of the drops that look like the background.
Therefore i found the connected components for the background and the inside drops took the largest connected component and change its value to be like the foreground value which left me with an image which he inside drops as a different value than the background.
Than i used this image to fill in the original threshold image.
In the end using the filled image i calculated the relevant values
import cv2
import numpy as np
from matplotlib import pyplot as plt
# Read image
I = cv2.imread('drops.jpg',0);
# Threshold
IThresh = (I>=118).astype(np.uint8)*255
# Remove from the image the biggest conneced componnet
# Find the area of each connected component
connectedComponentProps = cv2.connectedComponentsWithStats(IThresh, 8, cv2.CV_32S)
IThreshOnlyInsideDrops = np.zeros_like(connectedComponentProps[1])
IThreshOnlyInsideDrops = connectedComponentProps[1]
stat = connectedComponentProps[2]
maxArea = 0
for label in range(connectedComponentProps[0]):
cc = stat[label,:]
if cc[cv2.CC_STAT_AREA] > maxArea:
maxArea = cc[cv2.CC_STAT_AREA]
maxIndex = label
# Convert the background value to the foreground value
for label in range(connectedComponentProps[0]):
cc = stat[label,:]
if cc[cv2.CC_STAT_AREA] == maxArea:
IThreshOnlyInsideDrops[IThreshOnlyInsideDrops==label] = 0
else:
IThreshOnlyInsideDrops[IThreshOnlyInsideDrops == label] = 255
# Fill in all the IThreshOnlyInsideDrops as 0 in original IThresh
IThreshFill = IThresh
IThreshFill[IThreshOnlyInsideDrops==255] = 0
IThreshFill = np.logical_not(IThreshFill/255).astype(np.uint8)*255
plt.imshow(IThreshFill)
# Get numberof drops and cover precntage
connectedComponentPropsFinal = cv2.connectedComponentsWithStats(IThreshFill, 8, cv2.CV_32S)
NumberOfDrops = connectedComponentPropsFinal[0]
CoverPresntage = float(np.count_nonzero(IThreshFill==0)/float(IThreshFill.size))
# Print
print "Number of drops = " + str(NumberOfDrops)
print "Cover precntage = " + str(CoverPresntage)

Solution
image = cv2.imread('image path.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# (thresh, blackAndWhiteImage) = cv2.threshold(gray, 127, 255,
cv2.THRESH_BINARY)
plt.imshow(gray, cmap='gray')
blur = cv2.GaussianBlur(gray, (11, 11), 0)
plt.imshow(blur, cmap='gray')
canny = cv2.Canny(blur, 30, 40, 3)
plt.imshow(canny, cmap='gray')
dilated = cv2.dilate(canny, (1, 1), iterations=0)
plt.imshow(dilated, cmap='gray')
(cnt, hierarchy) = cv2.findContours(
dilated.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
cv2.drawContours(rgb, cnt, -1, (0, 255, 0), 2)
plt.imshow(rgb)
print("No of circles: ", len(cnt))