print(f'Area: {area}, Perimeter:{perimeter}')
return objects
if __name__ == '__main__':
try:
edge_filter_dict = {
'sobel': apply_sobel,
'prewitt': apply_prewitt,
'canny': apply_canny,
}
filter_func = edge_filter_dict.get(sys.argv[1])
if len(sys.argv) < 3 and filter_func:
start_cv_video(img_filter=filter_func)
elif len(sys.argv) < 4 and filter_func:
img_path = sys.argv[2]
img = cv2.imread(img_path, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
new_img = filter_func(img)
plt_show_img(new_img)
else:
raise Exception('Method not implemented')
except Exception as error:
print(error)
print(
'Usage: python3 edge_detection[canny | sobel | prewitt] [file_path]'
for (x, y, r) in circles:
# draw the circle in the output image, then draw a rectangle
# corresponding to the center of the circle
cv2.circle(output, (x, y), r, RGB_GREEN, 4)
cv2.rectangle(output, (x - 5, y - 5), (x + 5, y + 5), RGB_GREEN, -1)
return output
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser(description='Emoji segmentation')
parser.add_argument('-i', '--image', type=str, action='store', dest='src_img', help='The image to apply the filter')
parser.add_argument('-ks', '--kernel_size', type=int, default=5, action='store', dest='kernel_size', help='The size of the kernel when applying dilatation or erotion')
parser.add_argument('-d', '--dilate', type=int, default=0, action='store', dest='dilate_iter', help='Number of times to apply the Dilate operation')
parser.add_argument('-e', '--erode', type=int, default=0, action='store', dest='erode_iter', help='Number of times to apply the Erode operation')
args = parser.parse_args()
if args.src_img:
try:
img = cv2.imread(args.src_img, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
rgb_img = filter(img)
plt_show_img(rgb_img)
except Exception as error:
print(error)
else:
start_cv_video(0, filter)
def increase_sat(img):
img = cv2.cvtColor(img, cv2.COLOR_RGB2HSV).astype('float32')
h, s, v = cv2.split(img)
s = s + 200
s = np.clip(s, 0, 255)
imghsv = cv2.merge((h, s, v))
imghsv = cv2.cvtColor(imghsv.astype('uint8'), cv2.COLOR_HSV2RGB)
return imghsv
if __name__ == '__main__':
try:
alpha = float(input('* Enter the contrast value [1.0 to 3.0]: '))
beta = int(input('* Enter the brightness value [-255 to 255]: '))
if len(sys.argv) < 2:
start_cv_video(0, apply_contrast_brightness, alpha, beta)
else:
img_path = sys.argv[1]
img = cv2.imread(img_path, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
new_img = apply_contrast_brightness(img, alpha, beta)
plt_show_img(new_img)
except Exception as error:
print(error)
erode_iter = int(params[2]) if len(params) > 2 else 0
kernel = np.ones((kernel_size,kernel_size), np.uint8)
mask = cv2.dilate(mask, kernel, iterations=dilate_iter)
mask = cv2.erode(mask, kernel, iterations=erode_iter)
return img * mask
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser(description='RGB filter')
parser.add_argument('-i', '--image', type=str, action='store', dest='src_img', help='The image to apply the filter')
parser.add_argument('-ks', '--kernel_size', type=int, default=5, action='store', dest='kernel_size', help='The size of the kernel when applying dilatation or erotion')
parser.add_argument('-d', '--dilate', type=int, default=0, action='store', dest='dilate_iter', help='Number of times to apply the Dilate operation')
parser.add_argument('-e', '--erode', type=int, default=0, action='store', dest='erode_iter', help='Number of times to apply the Erode operation')
args = parser.parse_args()
if args.src_img:
try:
img = cv2.imread(args.src_img, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
rgb_img = rgb_filter(img, args.kernel_size, args.dilate_iter, args.erode_iter)
plt_show_img(rgb_img)
except Exception as error:
print(error)
else:
start_cv_video(0, rgb_filter, args.kernel_size, args.dilate_iter, args.erode_iter)
def slow_binarization(img, threshold=127):
img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
height, width = img.shape
binary = np.zeros([height, width, 1], 'uint8')
for row in range(0, height):
for col in range(0, width):
if img[row][col] > threshold:
binary[row][col] = 255
return binary
if __name__ == '__main__':
if len(sys.argv) < 2:
start_cv_video(img_filter=otsu_binarization)
else:
try:
img_path = sys.argv[1]
img = cv2.imread(img_path, cv2.IMREAD_COLOR)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
binarized_img = otsu_binarization(img)
plt_show_img(binarized_img)
if (sys.argv[2] == '-h'):
plt_hist(img.ravel(), 'Color Histogram')
except Exception as error:
print(error)
type=str,
action='store',
dest='train_img',
required=True,
help='The image to apply the filter')
parser.add_argument('-test',
type=str,
action='store',
dest='test_img',
help='The image to test')
args = parser.parse_args()
if args.test_img:
try:
img1 = cv2.imread(args.train_img, cv2.IMREAD_COLOR)
img2 = cv2.imread(args.test_img, cv2.IMREAD_COLOR)
new_img = feature_match(img1, img2)
new_img = cv2.cvtColor(new_img, cv2.COLOR_RGB2BGR)
plt_show_img(new_img)
except Exception as error:
print(error)
else:
img = cv2.imread(args.train_img, cv2.IMREAD_GRAYSCALE)
img = process_train_image(img)
points, desc = ORB_descriptor(img)
start_cv_video(0, feature_track, points, desc, img)