Optical Character Recognition with Python Tesseract on a series of symbols - ocr

Question

Hello, i am looking for guidance. I have been using pytesseract to do OCR but it seems like i can't get the OCR to recognise a series of equal signs put together in an image. any guidance on how to address this issue ? i tested the image with AWS Rekognition, Google Vision and same results. I tried to select ROI with Open CV and focus the OCR on that, and yet it still came out empty, i.e. no character recognised. appreciate for any guidance.
thank you

Answer 1

Your text seems to be dificult to extract. Try to work on a full image when extracting text with tesseract.
I made one aproach to your solution but as you can see the bounding box for characters is not the expected.
This is the code:
import cv2
import numpy as np
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
originalImage = cv2.imread('a.png')
grayImage = cv2.cvtColor(originalImage, cv2.COLOR_BGR2GRAY)
(thresh, blackAndWhiteImageOriginal) = cv2.threshold(grayImage, 127, 255, cv2.THRESH_BINARY_INV)
blackAndWhiteImage = cv2.dilate(blackAndWhiteImageOriginal, np.ones((3,3), np.uint8))
ocr_output_details = pytesseract.image_to_data(blackAndWhiteImage, output_type=pytesseract.Output.DICT, config="--psm 7 -c tessedit_char_whitelist==")
rgbImage = cv2.cvtColor(blackAndWhiteImage,cv2.COLOR_GRAY2RGB)
for i in range(len(ocr_output_details['level'])):
(x, y, w, h) = (ocr_output_details['left'][i], ocr_output_details['top'][i], ocr_output_details['width'][i], ocr_output_details['height'][i])
cv2.rectangle(rgbImage, (x, y), (x + w, y + h), (0,0,255), 2)
print('Text: ', ocr_output_details['text'])
cv2.imshow('Boxes', rgbImage)
cv2.waitKey(0)
cv2.destroyAllWindows()
And the result:
Result 1
Using another apropiate full image with expected caracthers size i can extract equal symbols perfectly with tesseract.
This is the code:
import cv2
import numpy as np
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
originalImage = cv2.imread('b.jpg')
grayImage = cv2.cvtColor(originalImage, cv2.COLOR_BGR2GRAY)
(thresh, blackAndWhiteImageOriginal) = cv2.threshold(grayImage, 127, 255, cv2.THRESH_BINARY)
blackAndWhiteImage = cv2.erode(blackAndWhiteImageOriginal, np.ones((3,3), np.uint8))
img = originalImage
img_copy = img.copy()
gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY)
results = pytesseract.image_to_data(thresh, config="-c tessedit_char_whitelist== --psm 6")
text = []
for b in map(str.split, results.splitlines()[1:]):
if len(b) == 12:
x, y, w, h = map(int, b[6: 10])
cv2.rectangle(originalImage, (x, y), (x + w, y + h), (255,0,0), 2)
cv2.putText(originalImage, b[11], (x, y + h + 15), cv2.FONT_HERSHEY_COMPLEX, 0.6, 0)
text.append(b[11])
print('Text: ', text)
cv2.imshow("Result", originalImage)
cv2.waitKey(0)
And the result:
Result 2
You can try to improve results using Tesseract documentation. Tesseract -Improving the quality of the output
Important things to do are:
Use white for the background and black for characters font color
Select desired tesseractpsm mode. In the previous cases i was using 6 and 7 psm modes to treat image as a single uniform block of text and treat the image as a single text line respectively
Try to use tessedit_char_whitelist config to specify only the characters that you are sarching for.