''' Set up the argument parser which will get the CSV file and location where model
is to be stored'''
argparser = argparse.ArgumentParser()
argparser.add_argument("-d", "--dataset", required = True,
help = "path to the dataset file")
argparser.add_argument("-m", "--model", required = True,
help = "path to where the model will be stored")
args = vars(argparser.parse_args())
(digits, labels) = dataset.load_data(args["dataset"])
hog = HOG(orientations = 18, pixelsPerCell = (10, 10), cellsPerBlock = (1, 1), normalise = True)
data = []
# Add histogram for each digit in a list
for digit in digits:
digit = dataset.deskew(digit)
hist = hog.describe(digit.reshape((28,28)))
data.append(hist)
# Set up and train the model
SVC_model = LinearSVC()
SVC_model.fit(data, labels)
# Save the model to file
joblib.dump(SVC_model, args["model"], compress = 3)
# Find all the bounding rectangles of the contours
rects = [cv2.boundingRect(contour) for contour in contours]
# Loop over all the rectangles
for rect in rects:
(x, y, w, h) = rect
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
# Find the region of interest, and resize it
roi = gray[y: y + h, x: x + w]
roi = cv2.resize(roi, (28, 28), interpolation = cv2.INTER_AREA)
# Threshold the region of interest
thresh = roi.copy()
_, thresh = cv2.threshold(thresh, 90, 255, cv2.THRESH_BINARY_INV)
thresh = dataset.deskew(thresh)
# Get the histogram and predict the number
hist = hog.describe(thresh)
predict = SVC_model.predict(np.array([hist], 'float64'))
cv2.putText(image, str(predict), (x-10, y-10), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 255, 0) , 2)
# Display the result
cv2.imshow("Image", image)
cv2.waitKey(0)
