cnts = cnts[1] if imutils.is_cv3() else cnts[0]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:4]
cnts = contours.sort_contours(cnts)[0]
# Initialize the output image as a "grayscale" image with 3 channels along with the output predictions
output = cv2.merge([gray] * 3)
predictions = []
# Loop over the contours
for c in cnts:
# Compute the bounding box for the contour then extract the digit
(x, y, w, h) = cv2.boundingRect(c)
roi = gray[y - 5:y + h + 5, x - 5:x + w + 5]
# Pre-process the ROI and classify it
roi = preprocess(roi, 28, 28)
roi = np.expand_dims(img_to_array(roi), axis=0)
pred = model.predict(roi).argmax(axis=1)[0] + 1
predictions.append(str(pred))
# Draw the prediction on the output image
cv2.rectangle(output, (x - 2, y - 2), (x + w + 4, y + h + 4),
(0, 255, 0), 1)
cv2.putText(output, str(pred), (x - 5, y - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 255, 0), 2)
# Show the output image
print("[INFO]: Captcha: {}".format("".join(predictions)))
cv2.imshow("Output", output)
cv2.waitKey()
ap.add_argument("-d", "--dataset", required=True,
help="path to input dataset")
ap.add_argument("-m", "--model", required=True,
help="path to output model")
args = vars(ap.parse_args())
# Initialize the data and labels
data = []
labels = []
# Loop over the input images
for image_path in paths.list_images(args["dataset"]):
# load the image, pre-process it, and store it in the data list
image = cv2.imread(image_path)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = preprocess(image, 28, 28)
image = img_to_array(image)
data.append(image)
# Extract the class label from the image path and update the labels list
label = image_path.split(os.path.sep)[-2]
labels.append(label)
# Scale the raw pixel intensities to the range [0, 1]
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
# Partition the data into training data (75%) and testing data (25%)
(train_x, test_x, train_y, test_y) = train_test_split(data, labels, test_size=0.25, random_state=42)
# Convert the labels from integers to vectors