File size: 11,097 Bytes
6cf4883
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
import cv2
import requests
import os
from collections import defaultdict
from math import log, sqrt
import numpy as np
from PIL import Image, ImageDraw

GREEN = "#0F0"
BLUE = "#00F"
RED = "#F00"


def crop_image(im, settings):
  """ Intelligently crop an image to the subject matter """

  scale_by = 1
  if is_landscape(im.width, im.height):
    scale_by = settings.crop_height / im.height
  elif is_portrait(im.width, im.height):
    scale_by = settings.crop_width / im.width
  elif is_square(im.width, im.height):
    if is_square(settings.crop_width, settings.crop_height):
      scale_by = settings.crop_width / im.width
    elif is_landscape(settings.crop_width, settings.crop_height):
      scale_by = settings.crop_width / im.width
    elif is_portrait(settings.crop_width, settings.crop_height):
      scale_by = settings.crop_height / im.height

  im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
  im_debug = im.copy()

  focus = focal_point(im_debug, settings)

  # take the focal point and turn it into crop coordinates that try to center over the focal
  # point but then get adjusted back into the frame
  y_half = int(settings.crop_height / 2)
  x_half = int(settings.crop_width / 2)

  x1 = focus.x - x_half
  if x1 < 0:
      x1 = 0
  elif x1 + settings.crop_width > im.width:
      x1 = im.width - settings.crop_width

  y1 = focus.y - y_half
  if y1 < 0:
      y1 = 0
  elif y1 + settings.crop_height > im.height:
      y1 = im.height - settings.crop_height

  x2 = x1 + settings.crop_width
  y2 = y1 + settings.crop_height

  crop = [x1, y1, x2, y2]

  results = []

  results.append(im.crop(tuple(crop)))

  if settings.annotate_image:
    d = ImageDraw.Draw(im_debug)
    rect = list(crop)
    rect[2] -= 1
    rect[3] -= 1
    d.rectangle(rect, outline=GREEN)
    results.append(im_debug)
    if settings.destop_view_image:
      im_debug.show()

  return results

def focal_point(im, settings):
    corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else []
    entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else []
    face_points = image_face_points(im, settings) if settings.face_points_weight > 0 else []

    pois = []

    weight_pref_total = 0
    if len(corner_points) > 0:
      weight_pref_total += settings.corner_points_weight
    if len(entropy_points) > 0:
      weight_pref_total += settings.entropy_points_weight
    if len(face_points) > 0:
      weight_pref_total += settings.face_points_weight

    corner_centroid = None
    if len(corner_points) > 0:
      corner_centroid = centroid(corner_points)
      corner_centroid.weight = settings.corner_points_weight / weight_pref_total 
      pois.append(corner_centroid)

    entropy_centroid = None
    if len(entropy_points) > 0:
      entropy_centroid = centroid(entropy_points)
      entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
      pois.append(entropy_centroid)

    face_centroid = None
    if len(face_points) > 0:
      face_centroid = centroid(face_points)
      face_centroid.weight = settings.face_points_weight / weight_pref_total 
      pois.append(face_centroid)

    average_point = poi_average(pois, settings)

    if settings.annotate_image:
      d = ImageDraw.Draw(im)
      max_size = min(im.width, im.height) * 0.07
      if corner_centroid is not None:
        color = BLUE
        box = corner_centroid.bounding(max_size * corner_centroid.weight)
        d.text((box[0], box[1]-15), "Edge: %.02f" % corner_centroid.weight, fill=color)
        d.ellipse(box, outline=color)
        if len(corner_points) > 1:
          for f in corner_points:
            d.rectangle(f.bounding(4), outline=color)
      if entropy_centroid is not None:
        color = "#ff0"
        box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
        d.text((box[0], box[1]-15), "Entropy: %.02f" % entropy_centroid.weight, fill=color)
        d.ellipse(box, outline=color)
        if len(entropy_points) > 1:
          for f in entropy_points:
            d.rectangle(f.bounding(4), outline=color)
      if face_centroid is not None:
        color = RED
        box = face_centroid.bounding(max_size * face_centroid.weight)
        d.text((box[0], box[1]-15), "Face: %.02f" % face_centroid.weight, fill=color)
        d.ellipse(box, outline=color)
        if len(face_points) > 1:
          for f in face_points:
            d.rectangle(f.bounding(4), outline=color)

      d.ellipse(average_point.bounding(max_size), outline=GREEN)
      
    return average_point


def image_face_points(im, settings):
    if settings.dnn_model_path is not None:
      detector = cv2.FaceDetectorYN.create(
          settings.dnn_model_path,
          "",
          (im.width, im.height),
          0.9, # score threshold
          0.3, # nms threshold
          5000 # keep top k before nms
      )
      faces = detector.detect(np.array(im))
      results = []
      if faces[1] is not None:
        for face in faces[1]:
          x = face[0]
          y = face[1]
          w = face[2]
          h = face[3]
          results.append(
            PointOfInterest(
              int(x + (w * 0.5)), # face focus left/right is center
              int(y + (h * 0.33)), # face focus up/down is close to the top of the head
              size = w,
              weight = 1/len(faces[1])
            )
          )
      return results
    else:
      np_im = np.array(im)
      gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)

      tries = [
        [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ],
        [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ],
        [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ]
      ]
      for t in tries:
        classifier = cv2.CascadeClassifier(t[0])
        minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
        try:
          faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
            minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE)
        except:
          continue

        if len(faces) > 0:
          rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
          return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects]
    return []


def image_corner_points(im, settings):
    grayscale = im.convert("L")

    # naive attempt at preventing focal points from collecting at watermarks near the bottom
    gd = ImageDraw.Draw(grayscale)
    gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999")

    np_im = np.array(grayscale)

    points = cv2.goodFeaturesToTrack(
        np_im,
        maxCorners=100,
        qualityLevel=0.04,
        minDistance=min(grayscale.width, grayscale.height)*0.06,
        useHarrisDetector=False,
    )

    if points is None:
        return []

    focal_points = []
    for point in points:
      x, y = point.ravel()
      focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points)))

    return focal_points


def image_entropy_points(im, settings):
    landscape = im.height < im.width
    portrait = im.height > im.width
    if landscape:
      move_idx = [0, 2]
      move_max = im.size[0]
    elif portrait:
      move_idx = [1, 3]
      move_max = im.size[1]
    else:
      return []

    e_max = 0
    crop_current = [0, 0, settings.crop_width, settings.crop_height]
    crop_best = crop_current
    while crop_current[move_idx[1]] < move_max:
        crop = im.crop(tuple(crop_current))
        e = image_entropy(crop)

        if (e > e_max):
          e_max = e
          crop_best = list(crop_current)

        crop_current[move_idx[0]] += 4
        crop_current[move_idx[1]] += 4

    x_mid = int(crop_best[0] + settings.crop_width/2)
    y_mid = int(crop_best[1] + settings.crop_height/2)

    return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)]


def image_entropy(im):
    # greyscale image entropy
    # band = np.asarray(im.convert("L"))
    band = np.asarray(im.convert("1"), dtype=np.uint8)
    hist, _ = np.histogram(band, bins=range(0, 256))
    hist = hist[hist > 0]
    return -np.log2(hist / hist.sum()).sum()

def centroid(pois):
  x = [poi.x for poi in pois]
  y = [poi.y for poi in pois]
  return PointOfInterest(sum(x)/len(pois), sum(y)/len(pois))


def poi_average(pois, settings):
    weight = 0.0
    x = 0.0
    y = 0.0
    for poi in pois:
        weight += poi.weight
        x += poi.x * poi.weight
        y += poi.y * poi.weight
    avg_x = round(weight and x / weight)
    avg_y = round(weight and y / weight)

    return PointOfInterest(avg_x, avg_y)


def is_landscape(w, h):
  return w > h


def is_portrait(w, h):
  return h > w


def is_square(w, h):
  return w == h


def download_and_cache_models(dirname):
  download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
  model_file_name = 'face_detection_yunet.onnx'

  if not os.path.exists(dirname):
    os.makedirs(dirname)

  cache_file = os.path.join(dirname, model_file_name)
  if not os.path.exists(cache_file):
    print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
    response = requests.get(download_url)
    with open(cache_file, "wb") as f:
      f.write(response.content)

  if os.path.exists(cache_file):
    return cache_file
  return None


class PointOfInterest:
  def __init__(self, x, y, weight=1.0, size=10):
    self.x = x
    self.y = y
    self.weight = weight
    self.size = size

  def bounding(self, size):
    return [
      self.x - size//2,
      self.y - size//2,
      self.x + size//2,
      self.y + size//2
    ]


class Settings:
  def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None):
    self.crop_width = crop_width
    self.crop_height = crop_height
    self.corner_points_weight = corner_points_weight
    self.entropy_points_weight = entropy_points_weight
    self.face_points_weight = face_points_weight
    self.annotate_image = annotate_image
    self.destop_view_image = False
    self.dnn_model_path = dnn_model_path