J'ai trouvé le code suivant sur ce site Web :
import os
import os.path
import cv2
import glob
import imutils
CAPTCHA_IMAGE_FOLDER = "generated_captcha_images"
OUTPUT_FOLDER = "extracted_letter_images"
# Get a list of all the captcha images we need to process
captcha_image_files = glob.glob(os.path.join(CAPTCHA_IMAGE_FOLDER, "*"))
counts = {}
# loop over the image paths
for (i, captcha_image_file) in enumerate(captcha_image_files):
print("[INFO] processing image {}/{}".format(i + 1, len(captcha_image_files)))
# Since the filename contains the captcha text (i.e. "2A2X.png" has the text "2A2X"),
# grab the base filename as the text
filename = os.path.basename(captcha_image_file)
captcha_correct_text = os.path.splitext(filename)[0]
# Load the image and convert it to grayscale
image = cv2.imread(captcha_image_file)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Add some extra padding around the image
gray = cv2.copyMakeBorder(gray, 8, 8, 8, 8, cv2.BORDER_REPLICATE)
# threshold the image (convert it to pure black and white)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
# find the contours (continuous blobs of pixels) the image
contours = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Hack for compatibility with different OpenCV versions
contours = contours[0] if imutils.is_cv2() else contours[1]
letter_image_regions = []
# Now we can loop through each of the four contours and extract the letter
# inside of each one
for contour in contours:
# Get the rectangle that contains the contour
(x, y, w, h) = cv2.boundingRect(contour)
# Compare the width and height of the contour to detect letters that
# are conjoined into one chunk
if w / h > 1.25:
# This contour is too wide to be a single letter!
# Split it in half into two letter regions!
half_width = int(w / 2)
letter_image_regions.append((x, y, half_width, h))
letter_image_regions.append((x + half_width, y, half_width, h))
else:
# This is a normal letter by itself
letter_image_regions.append((x, y, w, h))
# If we found more or less than 4 letters in the captcha, our letter extraction
# didn't work correcly. Skip the image instead of saving bad training data!
if len(letter_image_regions) != 4:
continue
# Sort the detected letter images based on the x coordinate to make sure
# we are processing them from left-to-right so we match the right image
# with the right letter
letter_image_regions = sorted(letter_image_regions, key=lambda x: x[0])
# Save out each letter as a single image
for letter_bounding_box, letter_text in Zip(letter_image_regions, captcha_correct_text):
# Grab the coordinates of the letter in the image
x, y, w, h = letter_bounding_box
# Extract the letter from the original image with a 2-pixel margin around the Edge
letter_image = gray[y - 2:y + h + 2, x - 2:x + w + 2]
# Get the folder to save the image in
save_path = os.path.join(OUTPUT_FOLDER, letter_text)
# if the output directory does not exist, create it
if not os.path.exists(save_path):
os.makedirs(save_path)
# write the letter image to a file
count = counts.get(letter_text, 1)
p = os.path.join(save_path, "{}.png".format(str(count).zfill(6)))
cv2.imwrite(p, letter_image)
# increment the count for the current key
counts[letter_text] = count + 1
Lorsque j'essaie d'exécuter le code, j'obtiens l'erreur suivante:
[INFO] processing image 1/9955
Traceback (most recent call last):
File "extract_single_letters_from_captchas.py", line 47, in <module>
(x, y, w, h) = cv2.boundingRect(contour)
cv2.error: OpenCV(4.0.0) /Users/travis/build/skvark/opencv-python/opencv/modules/imgproc/src/shapedescr.cpp:741: error: (-215:Assertion failed) npoints >= 0 && (depth == CV_32F || depth == CV_32S) in function 'pointSetBoundingRect'
J'ai essayé de chercher une solution sur StackOverflow, mais je n'ai rien trouvé de semblable à distance.
EDIT (voir commentaires):
type(contour[0])
= <class 'numpy.ndarray'>
len(contour)
= 4
C'est à cause de opencv-python version 4.0.0. Si vous souhaitez résoudre ce problème sans modifier votre code, rétrogradez opencv-python vers la version 3.4.9.31
Désinstaller opencv-python
pip désinstaller opencv-python
Installez opencv-python == 3.4.9.31
pip install opencv-python == 3.4.9.31
Si vous rencontrez un problème avec la fonction 'pointSetBoundingRect', vous devez installer 'opencv-python-headless'
pip install opencv-python-headless==3.4.9.31