File size: 6,562 Bytes
a6028c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
import cv2

"""
brief: face alignment with FFHQ method (https://github.com/NVlabs/ffhq-dataset)
author: lzhbrian (https://lzhbrian.me)
date: 2020.1.5
note: code is heavily borrowed from 
    https://github.com/NVlabs/ffhq-dataset
    http://dlib.net/face_landmark_detection.py.html
requirements:
    apt install cmake
    conda install Pillow numpy scipy
    pip install dlib
    # download face landmark model from: 
    # http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
"""

import numpy as np
from PIL import Image
import dlib


class Croper:
    def __init__(self, path_of_lm):
        # download model from: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
        self.predictor = dlib.shape_predictor(path_of_lm)

    def get_landmark(self, img_np):
        """get landmark with dlib
        :return: np.array shape=(68, 2)
        """
        detector = dlib.get_frontal_face_detector()
        dets = detector(img_np, 1)
        #     print("Number of faces detected: {}".format(len(dets)))
        #     for k, d in enumerate(dets):
        if len(dets) == 0:
            return None
        d = dets[0]
        # Get the landmarks/parts for the face in box d.
        shape = self.predictor(img_np, d)
        #         print("Part 0: {}, Part 1: {} ...".format(shape.part(0), shape.part(1)))
        t = list(shape.parts())
        a = []
        for tt in t:
            a.append([tt.x, tt.y])
        lm = np.array(a)
        # lm is a shape=(68,2) np.array
        return lm

    def align_face(self, img, lm, output_size=1024):
        """
        :param filepath: str
        :return: PIL Image
        """
        lm_chin = lm[0: 17]  # left-right
        lm_eyebrow_left = lm[17: 22]  # left-right
        lm_eyebrow_right = lm[22: 27]  # left-right
        lm_nose = lm[27: 31]  # top-down
        lm_nostrils = lm[31: 36]  # top-down
        lm_eye_left = lm[36: 42]  # left-clockwise
        lm_eye_right = lm[42: 48]  # left-clockwise
        lm_mouth_outer = lm[48: 60]  # left-clockwise
        lm_mouth_inner = lm[60: 68]  # left-clockwise

        # Calculate auxiliary vectors.
        eye_left = np.mean(lm_eye_left, axis=0)
        eye_right = np.mean(lm_eye_right, axis=0)
        eye_avg = (eye_left + eye_right) * 0.5
        eye_to_eye = eye_right - eye_left
        mouth_left = lm_mouth_outer[0]
        mouth_right = lm_mouth_outer[6]
        mouth_avg = (mouth_left + mouth_right) * 0.5
        eye_to_mouth = mouth_avg - eye_avg

        # Choose oriented crop rectangle.
        x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]  # Addition of binocular difference and double mouth difference
        x /= np.hypot(*x)
        x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
        y = np.flipud(x) * [-1, 1]
        c = eye_avg + eye_to_mouth * 0.1
        quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
        qsize = np.hypot(*x) * 2

        # Shrink.
        shrink = int(np.floor(qsize / output_size * 0.5))
        if shrink > 1:
            rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
            img = img.resize(rsize, Image.ANTIALIAS)
            quad /= shrink
            qsize /= shrink
        else:
            rsize = (int(np.rint(float(img.size[0]))), int(np.rint(float(img.size[1]))))

        # Crop.
        border = max(int(np.rint(qsize * 0.1)), 3)
        crop = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
                int(np.ceil(max(quad[:, 1]))))
        crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]),
                min(crop[3] + border, img.size[1]))
        if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
            # img = img.crop(crop)
            quad -= crop[0:2]

        # Pad.
        pad = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
               int(np.ceil(max(quad[:, 1]))))
        pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0),
               max(pad[3] - img.size[1] + border, 0))
        # if enable_padding and max(pad) > border - 4:
        #     pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
        #     img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
        #     h, w, _ = img.shape
        #     y, x, _ = np.ogrid[:h, :w, :1]
        #     mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w - 1 - x) / pad[2]),
        #                       1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h - 1 - y) / pad[3]))
        #     blur = qsize * 0.02
        #     img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
        #     img += (np.median(img, axis=(0, 1)) - img) * np.clip(mask, 0.0, 1.0)
        #     img = Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        #     quad += pad[:2]

        # Transform.
        quad = (quad + 0.5).flatten()
        lx = max(min(quad[0], quad[2]), 0)
        ly = max(min(quad[1], quad[7]), 0)
        rx = min(max(quad[4], quad[6]), img.size[0])
        ry = min(max(quad[3], quad[5]), img.size[0])
        # img = img.transform((transform_size, transform_size), Image.QUAD, (quad + 0.5).flatten(),
        #                     Image.BILINEAR)
        # if output_size < transform_size:
        #     img = img.resize((output_size, output_size), Image.ANTIALIAS)

        # Save aligned image.
        return rsize, crop, [lx, ly, rx, ry]
    
    def crop(self, img_np_list, still=False, xsize=512):    # first frame for all video
        img_np = img_np_list[0]
        lm = self.get_landmark(img_np)
        if lm is None:
            raise 'can not detect the landmark from source image'
        rsize, crop, quad = self.align_face(img=Image.fromarray(img_np), lm=lm, output_size=xsize)
        clx, cly, crx, cry = crop
        lx, ly, rx, ry = quad
        lx, ly, rx, ry = int(lx), int(ly), int(rx), int(ry)
        for _i in range(len(img_np_list)):
            _inp = img_np_list[_i]
            _inp = cv2.resize(_inp, (rsize[0], rsize[1]))
            _inp = _inp[cly:cry, clx:crx]
            # cv2.imwrite('test1.jpg', _inp)
            if not still:
                _inp = _inp[ly:ry, lx:rx]
            # cv2.imwrite('test2.jpg', _inp)
            img_np_list[_i] = _inp
        return img_np_list, crop, quad