Cluster using identity merging

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

server/cluster.py

@@ -127,36 +127,120 @@ def l2_normalize(x):
 
 base = '/pictures/'
 conn = create_connection('../db/photos.db')
-faces = {}
+faces = []
 identities = []
 
+def find_nearest_face(faces, identities, face, threshold = 0.99):
+  closest = None
+  closest_distance = -1
+  for target in identities + faces:
+    if target == face:
+      continue
+    target_distance = findCosineDistance(
+      target['descriptors'], face['descriptors']
+    )
+    if target_distance > threshold:
+      continue
+    if closest_distance == -1 or target_distance < closest_distance:
+      closest = target
+      closest_distance = target_distance
+  return closest
+
+def merge_identities(identities, identity1, identity2):
+  sum1 = np.dot(
+    identity1['faces'],
+    identity1['descriptors']
+  )
+  sum2 = np.dot(
+    identity2['faces'],
+    identity2['descriptors']
+  )
+  sum = np.add(sum1, sum2)
+  faces = identity1['faces'] + identity2['faces']
+  id = 1
+  if len(identities):
+    id = identities[len(identities) - 1]['id'] + 1
+
+  return {
+    'id': id,
+    'descriptors': np.divide(sum, faces),
+    'faces': faces
+  }
+
+def delete_identity(identities, identity):
+  for i, item in enumerate(identities):
+    if item['id'] == identity['id']:
+      return identities.pop(i)
+  return None
+  
+def update_face_identity(identities, face, closest):
+  if 'identified_as' in face:
+    face_identity = face['identified_as']
+    delete_identity(identities, face_identity)
+  else:
+    face_identity = face
+  
+  if 'identified_as' in closest:
+    closest_identity = closest['identified_as']
+    delete_identity(identities, closest_identity)
+  else:
+    closest_identity = closest
+
+  identity = merge_identities(identities, face_identity, closest_identity)
+  identities.append(identity)
+  closest['identified_as'] = face['identified_as'] = identity
+  return identity
+
+def cluster_faces(face):
+  identities = []
+  for i, face in enumerate(faces):
+    print(f'Clustering {i+1}/{len(faces)}')
+    closest = find_nearest_face(faces, identities, face, threshold = 0.25)
+    if closest == None:
+      print(f'Face {i+1} does not have any matches.')
+      continue
+    identity = update_face_identity(identities, face, closest)
+#    if identity['faces'] > 2:
+#     print(f'Updated identity {identity["id"]} to hold {identity["faces"]} faces.')
+  return identities
+
+def identity_get_faces(item):
+  return item['faces']
+
 with conn:
   cur = conn.cursor()
   res = cur.execute('''
     SELECT faces.id,facedescriptors.descriptors,faces.faceConfidence,faces.photoId
     FROM faces
     JOIN facedescriptors ON (faces.descriptorId=facedescriptors.id)
-    WHERE faces.identityId IS null AND faces.faceConfidence>0.945
+    WHERE faces.identityId IS null AND faces.faceConfidence>0.99
     ''')
   for row in res.fetchall():
     id, descriptors, confidence, photoId = row
-    if id in faces:
-      face = faces[id]
-    else:
+    face = None
+    for target in faces:
+      if target['id'] == id:
+        face = target
+        break
+    if face == None:
       face = { 
         'id': id,
-        'scanned': False 
       }
-      faces[id] = face
+      faces.append(face)
+    face['faces'] = 1
     face['confidence'] = confidence
     face['photoId'] = photoId
     face['descriptors'] = np.frombuffer(descriptors)
 
-  for key1 in faces:
-    face1 = faces[key1]
-    if face1['scanned'] == True:
-      continue
-    face1['scanned'] = True
+  identities = cluster_faces(faces)
+  identities.sort(reverse = True, key = identity_get_faces)
+  for identity in identities:
+    print(f'{identity["id"]} has {identity["faces"]} faces')
+
+  print(f'{len(identities)} identities seeded.')
+
+  exit(0)
+  if False:
     for key2 in faces:
       if key1 == key2:
         continue
@@ -184,7 +268,9 @@ with conn:
       face['scoring'] = 0
 
       if model_name == 'VGG-Face':
-        thresholds = {'cosine': 0.40, 'euclidean': 0.60, 'euclidean_l2': 0.86}
+#        thresholds = {'cosine': 0.40, 'euclidean': 0.60, 'euclidean_l2': 0.86}
+#        thresholds = {'cosine': 0.31, 'euclidean': 0.47, 'euclidean_l2': 0.79}
+        thresholds = {'cosine': 0.25, 'euclidean': 0.47, 'euclidean_l2': 0.79}
       elif model_name == 'ArcFace':
         thresholds = {'cosine': 0.68, 'euclidean': 4.15, 'euclidean_l2': 1.13}