#load and show an image
im = cv2.imread('faces/face_85.png', 0)
plt.imshow(im, cmap=plt.cm.gray)
plt.show()
# set up window parameters
window_size = 100
shift_size = 25
# scale the strokes
scale_factor = 8
# how many faces do you want to run?
num_faces = 10
for face in load_faces(n=num_faces):
im = cv2.imread(face, 0)
# documentation is in classification.py
# thresh is minimum confidence
# eyes, noses, mouths take the confident bounding boxes
# verbose shows each window classification and accuracy
classify(im,
window_size=window_size,
shift_size=shift_size,
scale_factor=scale_factor,
thresh=0.5,
eyes=2,
noses=1,
mouths=1,
verbose=True)
line = rdp(cluster[path], epsilon=1)
# line = cluster[path]
if show:
x, y = line.T
plt.plot(x, y)
# add line to lines
lines.append(line)
if show:
plt.show()
strokes = lines_to_strokes(lines)
# normalize strokes
if len(strokes) > 0:
strokes[:, 0:2] /= scale_factor
strokes[0] = [0, 0, 0]
return strokes
if __name__ == '__main__':
for face in load_faces(n=5):
im = cv2.imread(face, 0)
# strokes = convert_to_3_stroke(im)
# lines = get_curves(im)
lines = get_window_3_stroke(im, 0, 0)
raise
# draw_strokes(strokes)
shift_size=shift_size,
scale_factor=scale_factor,
thresh=thresh,
verbose=verbose)
# non-maximal suppression
bboxes = non_maximal_suppression(bboxes, eyes, noses, mouths)
# make plots
plot_img_with_bbox(im, bboxes)
plt.show()
if __name__ == "__main__":
# get a face image
faces = load_faces(n=10)
model = FeatureClassifier()
# for each face
for face in faces:
# zero for grayscale
im = cv2.imread(face, 0)
cv2.imshow('image', im)
cv2.waitKey(0)
classify(im)
# convert to SVG
raise NotImplementedError
# identify SVG components