Switching to VGG-Face and mtcnn

Signed-off-by: James Ketrenos <james_git@ketrenos.com>

server/detect.py

@@ -1,15 +1,34 @@
 import sys
+import zlib
 import json
 import os
 import piexif
 import sqlite3
 from sqlite3 import Error
-from PIL import Image
+from PIL import Image, ImageOps
 from deepface import DeepFace
+from deepface.detectors import FaceDetector
 from retinaface import RetinaFace
 import numpy as np
 import cv2
 
+import uu
+from io import BytesIO
+
+def zlib_uuencode(databytes, name='<data>'):
+    ''' Compress databytes with zlib & uuencode the result '''
+    inbuff = BytesIO(zlib.compress(databytes, 9))
+    outbuff = BytesIO()
+    uu.encode(inbuff, outbuff, name=name)
+    return outbuff.getvalue()
+
+def zlib_uudecode(databytes):
+    ''' uudecode databytes and decompress the result with zlib '''
+    inbuff = BytesIO(databytes)
+    outbuff = BytesIO()
+    uu.decode(inbuff, outbuff)
+    return zlib.decompress(outbuff.getvalue())
+
 class NpEncoder(json.JSONEncoder):
   def default(self, obj):
     if isinstance(obj, np.integer):
@@ -21,7 +40,10 @@ class NpEncoder(json.JSONEncoder):
         
 models = ["VGG-Face", "Facenet", "Facenet512", "OpenFace", "DeepFace", "DeepID", "ArcFace", "Dlib", "SFace"]
 
-model = DeepFace.build_model('ArcFace')
+model_name = 'VGG-Face'    # 'ArcFace'
+detector_backend = 'mtcnn' # 'retinaface'
+model = DeepFace.build_model(model_name)
+face_detector = FaceDetector.build_model(detector_backend)
 input_shape = DeepFace.functions.find_input_shape(model)
 
 
@@ -52,27 +74,46 @@ def alignment_procedure(img, left_eye, right_eye):
 
   return img
 
-def extract_faces(img, threshold=0.75, model = None, allow_upscaling = True):
-  faces = RetinaFace.detect_faces(
-    img_path = img, 
-    threshold = threshold, 
-    model = model, 
-    allow_upscaling = allow_upscaling)
+def extract_faces(img, threshold=0.75, allow_upscaling = True):
+  if detector_backend == 'retinaface':
+    faces = RetinaFace.detect_faces(
+      img_path = img, 
+      threshold = threshold, 
+      model = model, 
+      allow_upscaling = allow_upscaling)
+  elif detector_backend == 'mtcnn':
+    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # mtcnn expects RGB
+    res = face_detector.detect_faces(img_rgb)
+    faces = {}
+    if type(res) == list:
+      for i, face in enumerate(res):
+        faces[f'face_{i+1}'] = { # standardize properties
+          'facial_area': [
+            face['box'][1], face['box'][1] + face['box'][3],
+            face['box'][0], face['box'][0] + face['box'][2],
+          ],
+          'landmarks': {
+            'left_eye': list(face['keypoints']['left_eye']),
+            'right_eye': list(face['keypoints']['right_eye']),
+          },
+          'score': face['confidence'],
+        }
+        print(face, faces[f'face_{i+1}'])
 
   # Re-implementation of 'extract_faces' with the addition of keeping a 
   # copy of the face image for caching on disk
   if type(faces) == dict:
-    k=1
-    for key in faces:
-      print(f'Processing face {k}/{len(faces)}')
-      k+=1
+    for k, key in enumerate(faces):
+      print(f'Processing face {k+1}/{len(faces)}')
       identity = faces[key]
       facial_area = identity["facial_area"]
       landmarks = identity["landmarks"]
       left_eye = landmarks["left_eye"]
       right_eye = landmarks["right_eye"]
 
-      if False: # Draw the face rectangle and eyes
+      markup = True
+#      markup = False
+      if markup == True: # Draw the face rectangle and eyes
         cv2.rectangle(img, 
           (int(facial_area[0]), int(facial_area[1])),
           (int(facial_area[2]), int(facial_area[3])),
@@ -116,9 +157,9 @@ def extract_faces(img, threshold=0.75, model = None, allow_upscaling = True):
         
       identity['vector'] = DeepFace.represent(
         img_path = resized,
-        model_name = 'ArcFace',
-        model = model, # pre-built
-        detector_backend = 'retinaface',
+        model_name = model_name,
+        model = model,              # pre-built
+        detector_backend = detector_backend,
         enforce_detection = False)
 
       identity["face"] = { 
@@ -217,25 +258,23 @@ with conn:
     ''')
   rows = res.fetchall()
   count = len(rows)
-  i=1
-  for row in rows:
+  for i, row in enumerate(rows):
     photoId, photoFaces, albumPath, photoFilename = row
     img_path = f'{base}{albumPath}{photoFilename}'
-    print(f'Processing {i}/{count}: {img_path}')
-    i+=1
+    print(f'Processing {i+1}/{count}: {img_path}')
     img = Image.open(img_path)
+    img = ImageOps.exif_transpose(img) # auto-rotate if needed
     img = img.convert()
     img = np.asarray(img)
     faces = extract_faces(img)
     if faces is None:
+      print(f'Image no faces: {img_path}')
       update_face_count(conn, photoId, 0)
       continue
-    j=1
-    for key in faces:
+    for j, key in enumerate(faces):
       face = faces[key]
       image = face['image']
-      print(f'Writing face {j}/{len(faces)}')
-      j+=1
+      print(f'Writing face {j+1}/{len(faces)}')
       
       #face['analysis'] = DeepFace.analyze(img_path = img, actions = ['age', 'gender', 'race', 'emotion'], enforce_detection = False)
       #face['analysis'] = DeepFace.analyze(img, actions = ['emotion'])
@@ -245,8 +284,7 @@ with conn:
       face['version'] = 1 # version 1 doesn't add much...
 
       data = {k: face[k] for k in set(list(face.keys())) - set(['image', 'facial_area', 'landmarks'])}
-      json_str = json.dumps(data, ensure_ascii=False, indent=2, cls=NpEncoder)
-
+      json_str = json.dumps(data, ensure_ascii=False, cls=NpEncoder)
       faceDescriptorId = create_face_descriptor(conn, face)
 
       faceId = create_face(conn, {
@@ -260,7 +298,7 @@ with conn:
         'descriptorId': faceDescriptorId,
       })
 
-      path = f'faces/{faceId % 10}'
+      path = f'faces/{"{:02d}".format(faceId % 10)}'
       try:
         os.mkdir(path)
       except FileExistsError:
@@ -269,13 +307,13 @@ with conn:
       with open(f'{path}/{faceId}.json', 'w', encoding = 'utf-8') as f:
         f.write(json_str)
 
+      compressed_str = zlib_uuencode(json_str.encode())
+
       # Encode this data into the JPG as Exif
-      exif_ifd = {piexif.ExifIFD.UserComment: json_str.encode()}
+      exif_ifd = {piexif.ExifIFD.UserComment: compressed_str}
       exif_dict = {"0th": {}, "Exif": exif_ifd, "1st": {},
         "thumbnail": None, "GPS": {}}
       image.save(f'{path}/{faceId}.jpg', exif = piexif.dump(exif_dict))
 
-      #df = DeepFace.find(img, db_path = '/db')
-      #print(df.head())
-
+    exit(1)
     update_face_count(conn, photoId, len(faces))

server/headers.py

@@ -0,0 +1,25 @@
+import sys
+import zlib
+import json
+import piexif
+from PIL import Image
+import uu
+from io import BytesIO
+
+def zlib_uudecode(databytes):
+    ''' uudecode databytes and decompress the result with zlib '''
+    inbuff = BytesIO(databytes)
+    outbuff = BytesIO()
+    uu.decode(inbuff, outbuff)
+    return zlib.decompress(outbuff.getvalue())
+
+faceId = int(sys.argv[1])
+path = f'faces/{"{:02d}".format(faceId % 10)}'
+
+img = Image.open(f'{path}/{faceId}.jpg')
+exif_dict = piexif.load(img.info["exif"])
+compressed_str = exif_dict["Exif"][piexif.ExifIFD.UserComment]
+
+str = zlib_uudecode(compressed_str)
+json = json.loads(str)
+print(json)