-
-
Save softwarevamp/061cabe71d784c2e018dd8ac6c5bfc81 to your computer and use it in GitHub Desktop.
Bypass Captcha using 10 lines of code with Python, OpenCV & Tesseract OCR engine
This file contains hidden or 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.cv as cv | |
import tesseract | |
gray = cv.LoadImage('captcha.jpeg', cv.CV_LOAD_IMAGE_GRAYSCALE) | |
cv.Threshold(gray, gray, 231, 255, cv.CV_THRESH_BINARY) | |
api = tesseract.TessBaseAPI() | |
api.Init(".","eng",tesseract.OEM_DEFAULT) | |
api.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyz") | |
api.SetPageSegMode(tesseract.PSM_SINGLE_WORD) | |
tesseract.SetCvImage(gray,api) | |
print api.GetUTF8Text() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment