Created
January 26, 2019 15:34
-
-
Save mkorkmaz/3b19d706729e00b0e7e40d81ee67987b to your computer and use it in GitHub Desktop.
Solves simple captchas has only digits
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import cv2 | |
| import pytesseract | |
| from os import walk | |
| pytesseract.pytesseract.tesseract_cmd = r'/usr/local/bin/tesseract' | |
| config = u" -c tessedit_char_whitelist=0123456789 --oem 3 --psm 7 -l digits" | |
| def solve(file): | |
| image_file_name = './data/' + file | |
| im = cv2.imread(image_file_name) | |
| ret,thresh1 = cv2.threshold(im, 150, 255, cv2.THRESH_BINARY_INV) | |
| cv2.imwrite('/tmp/temp.jpg', thresh1) | |
| ocr = pytesseract.image_to_string('/tmp/temp.jpg', config=config).replace(' ', '').replace('/', '7').replace('?', '7') | |
| expected = image_file_name.replace('.jpg', '').replace('./data/', '') | |
| if ocr == expected: | |
| print('\33[2;32m') | |
| print('-----------------------------------') | |
| print('OCR\t:' + ocr) | |
| print('EXPT\t:' + expected) | |
| else: | |
| print('\33[1;31m') | |
| print('-----------------------------------') | |
| print('OCR\t:' + ocr) | |
| print('EXPT\t:' + expected) | |
| print('\33[m') | |
| files = [] | |
| for (dirpath, dirnames, filenames) in walk('./data'): | |
| files.extend(filenames) | |
| break | |
| for file in files: | |
| solve(file) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment