Advice for face alignment about mtcnn

[kizilkanat]

This worked fine:

import numpy as np
import cv2

imgSize = (112, 96)

x_ = [30.2946, 65.5318, 48.0252, 33.5493, 62.7299]
y_ = [51.6963, 51.5014, 71.7366, 92.3655, 92.2041]

src = np.array( zip(x_, y_) ).astype(np.float32).reshape(1,5,2)

alignedFaces = []

# there might be more than one faces, hence
# multiple sets of points
for pset in points:
    img2 = img.copy()

    pset_x = pset[0:5]
    pset_y = pset[5:10]

    dst = np.array( zip(pset_x, pset_y) ).astype(np.float32).reshape(1,5,2)
    
    transmat = cv2.estimateRigidTransform( dst, src, False )

    out = cv2.warpAffine(img2, transmat, (imgSize[1], imgSize[0]))

    alignedFaces.append(out)

[nttstar]

you can refer to my article: here

[DuinoDu]

Good for you.

[xizi]

Hi @DuinoDu ,
I found transmat = cv2.estimateRigidTransform( dst, src, False ) sometimes return None when the face is side face. But transf = cp2tform(coord5point_ori, coord5point_fixed, 'similarity') can work well. Could you give some help?

[DuinoDu]

Hi, @xizi. Where do you find "transmat = cv2.estimateRigidTransform( dst, src, False ) "?
Can you provide url?

[xizi]

It is kizilkanat provide it from above and i have solved this problem by use "transmat = cv2.estimateRigidTransform( dst, src, True ) ". Thanks for your reply.

[DuinoDu]

Good for you.

[DL-85]

It's very helpful! Thanks, nttstar.

[cannguyen275]

Hey guys, I just saw @nttstar have 25% better results with skimage SimilarityTransform than OpenCV estimateRigidTransform.

That's insane! The aligned images from 2 methods totally looks the same.
Does skimage do any difference things with its function, compare with Opencv?

I do want to use skimage SimilarityTransform in C++, Java also but skimage doesn't support. Do you guys know any which can use in C++, Java but strong liked skimage?