face_align.py

import cv2
import dlib
import numpy
import time
import os
import sys
import glob

PREDICTOR_PATH = "landmarks/shape_predictor_68_face_landmarks.dat"
FOLDER_PATH = sys.argv[1]
IMAGE_FORMAT = sys.argv[2]
REFERENCE_PATH = sys.argv[3]
SCALE_FACTOR = 1
FEATHER_AMOUNT = 11

FACE_POINTS = list(range(17, 68))
MOUTH_POINTS = list(range(48, 61))
RIGHT_BROW_POINTS = list(range(17, 22))
LEFT_BROW_POINTS = list(range(22, 27))
RIGHT_EYE_POINTS = list(range(36, 42))
LEFT_EYE_POINTS = list(range(42, 48))
NOSE_POINTS = list(range(27, 35))
JAW_POINTS = list(range(0, 17))

# Points used to line up the images.
ALIGN_POINTS = (LEFT_BROW_POINTS + RIGHT_EYE_POINTS + LEFT_EYE_POINTS +
                               RIGHT_BROW_POINTS + NOSE_POINTS + MOUTH_POINTS)

# Points from the second image to overlay on the first. The convex hull of each
# element will be overlaid.
OVERLAY_POINTS = [
    LEFT_EYE_POINTS + RIGHT_EYE_POINTS + LEFT_BROW_POINTS + RIGHT_BROW_POINTS,
    NOSE_POINTS + MOUTH_POINTS,
]

detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(PREDICTOR_PATH)

class TooManyFaces(Exception):
    pass

class NoFaces(Exception):
    pass

def get_landmarks(im):
    rects = detector(im, 1)

    if len(rects) > 1:
        raise TooManyFaces
    if len(rects) == 0:
        raise NoFaces

    return numpy.matrix([[p.x, p.y] for p in predictor(im, rects[0]).parts()])

def transformation_from_points(points1, points2):
    """
    Return an affine transformation [s * R | T] such that:
        sum ||s*R*p1,i + T - p2,i||^2
    is minimized.
    """
    # Solve the procrustes problem by subtracting centroids, scaling by the
    # standard deviation, and then using the SVD to calculate the rotation. See
    # the following for more details:
    #   https://en.wikipedia.org/wiki/Orthogonal_Procrustes_problem

    points1 = points1.astype(numpy.float64)
    points2 = points2.astype(numpy.float64)

    c1 = numpy.mean(points1, axis=0)
    c2 = numpy.mean(points2, axis=0)
    points1 -= c1
    points2 -= c2

    s1 = numpy.std(points1)
    s2 = numpy.std(points2)
    points1 /= s1
    points2 /= s2

    U, S, Vt = numpy.linalg.svd(points1.T * points2)

    # The R we seek is in fact the transpose of the one given by U * Vt. This
    # is because the above formulation assumes the matrix goes on the right
    # (with row vectors) where as our solution requires the matrix to be on the
    # left (with column vectors).
    R = (U * Vt).T

    return numpy.vstack([numpy.hstack(((s2 / s1) * R,
                                       c2.T - (s2 / s1) * R * c1.T)),
                         numpy.matrix([0., 0., 1.])])

def read_im_and_landmarks(fname):
    im = cv2.imread(fname, cv2.IMREAD_COLOR)
    im = cv2.resize(im, (im.shape[1] * SCALE_FACTOR,
                         im.shape[0] * SCALE_FACTOR))
    s = get_landmarks(im)

    return im, s

def warp_im(im, M, dshape):
    output_im = numpy.zeros(dshape, dtype=im.dtype)
    cv2.warpAffine(im,
                   M[:2],
                   (dshape[1], dshape[0]),
                   dst=output_im,
                   borderMode=cv2.BORDER_TRANSPARENT,
                   flags=cv2.WARP_INVERSE_MAP)
    return output_im

img_ref, landmark_ref = read_im_and_landmarks(REFERENCE_PATH)
img_index = 0
start = time.time()
for f in glob.glob(os.path.join(FOLDER_PATH, "*." + IMAGE_FORMAT)):
    print("Processing file: {}".format(f))
    f1 = list(f)
    f1=f1[2:len(f1)]
    f1=f1[0:len(f1)-4]
    n = "Image%05d" % img_index
    try:
        img, landmark = read_im_and_landmarks(f)
        M = transformation_from_points(landmark_ref[ALIGN_POINTS],
                                   landmark[ALIGN_POINTS])
        warped_im2 = warp_im(img, M, img_ref.shape)
        cv2.imwrite('result_align/' + n + '.jpg', warped_im2)
        img_index = img_index + 1
    except:
        print('Face not found in ', f)

##    cv2.imwrite('result_align/' + str(img_index) + '.jpg', warped_im2)
end = time.time()
## print(end - start)