Python Image Processing Cookbook by Sandipan Dey

Author:Sandipan Dey [Sandipan Dey]
Language: eng
Format: epub
Tags: COM012050 - COMPUTERS / Image Processing, COM016000 - COMPUTERS / Computer Vision and Pattern Recognition, COM004000 - COMPUTERS / Intelligence (AI) and Semantics
Publisher: Packt Publishing
Published: 2020-04-17T11:40:54+00:00

Finally, compute the morphed image with increasing alpha values (from 0 to 1) to the obtained morphed images with different blending proportions and animate them to observe a smooth transition from the source to the destination image:

fig = plt.figure(figsize=(18,20))

fig.subplots_adjust(top=0.925, bottom=0, left=0, right=1, \

wspace=0.01, hspace=0.08)

i = 1

for percent in np.linspace(1, 0, 16):

points = weighted_average_points(src_points, dst_points, percent)

src_face, src_d = warp_image(src_img, src_points, points, size)

end_face, end_d = warp_image(dst_img, dst_points, points, size)

average_face = weighted_average(src_face, end_face, percent)

plt.subplot(4,4,i), plt.imshow(average_face)

plt.title('alpha=' + str(round(percent,4)), size=20), \

plt.axis('off')

i += 1

plt.suptitle('Face morphing', size=30)

plt.show()

If you run the preceding code block, you will get a screenshot like the following screenshot as output:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.