Clustering worked well enough; need to add face column indicating manual (expert) assignment

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

client/src/App.css

@@ -58,7 +58,7 @@ div {
 
 .Image .FaceBox {
   border: 1px solid red;
-  border-radius: 0.25rem;
+/*  border-radius: 0.25rem;*/
   position: absolute;
 }
 

client/src/App.tsx

@@ -37,55 +37,31 @@ const makeFaceBoxes = (photo: any, dimensions: any): any => {
   ));
 };
 
-/*
-function debounce(fn: any, ms: number) {
-  let timer: any;
-  return () => {
-    if (timer) clearTimeout(timer);
-    timer = setTimeout(() => {
-      timer = null
-      fn.apply(this as typeof Photo, arguments)
-    }, ms)
-  };
-};
-*/
-
 const Photo = ({ photoId }: any) => {
   const [image, setImage] = useState<any>(undefined);
   const ref = useRef(null);
-  const [dimensions, setDimensions] = React.useState({
-    height: window.innerHeight,
-    width: window.innerWidth
-  })
+  const [dimensions, setDimensions] = React.useState({width: 0, height: 0});
 
   const faces = useMemo(() => {
-    if (image === undefined) {
+    if (image === undefined || dimensions.height === 0) {
       return <></>;
     }
     return makeFaceBoxes(image, dimensions);
   }, [image, dimensions]);
 
-  useEffect(() : any => {
-    if (!ref || !ref.current) {
+  useEffect(() => {
+    if (!ref.current) {
       return;
     }
-
     const el: Element = ref.current as Element;
-
-    const handleResize = () => {
+    if (dimensions.height !== el.clientHeight
+      || dimensions.width !== el.clientWidth) {
       setDimensions({
         height: el.clientHeight,
         width: el.clientWidth
       })
-    };
-    
-    const debouncedHandleResize = handleResize;//debounce(handleResize, 250);
-    debouncedHandleResize();
-    window.addEventListener('resize', debouncedHandleResize);
-    return () => {
-      window.removeEventListener('resize', debouncedHandleResize)
-    };
-  });
+    }
+  }/*, [dimensions.height, dimensions.width]*/);
 
   useEffect(() => {
     if (photoId === 0) {
@@ -108,7 +84,7 @@ const Photo = ({ photoId }: any) => {
   return (<div className="Image"
     ref={ref}
     style={{
-      background: `url(../${image.path}thumbs/scaled/${image.filename})`
+      background: `url(../${image.path}thumbs/scaled/${image.filename})`.replace(/ /g, '%20')
     }}>{ faces }</div>
   );
 };

ketrface/cluster.py

@@ -24,6 +24,9 @@ html_base = config['basePath']
 if html_base == "/":
   html_base = "."
 
+MAX_CLUSTER_DISTANCE = 0.14       # Used to merge clusters
+MAX_DISTANCE_FROM_CENTROID = 0.14 # Used to prune outliers
+
 # TODO
 # Switch to using DBSCAN
 #
@@ -86,8 +89,10 @@ def load_faces(db_path = db_path):
     res = cur.execute('''
       SELECT faces.id,facedescriptors.descriptors,faces.faceConfidence,faces.photoId,faces.focus
       FROM faces
+      INNER JOIN photos ON (photos.duplicate == 0 OR photos.duplicate IS NULL)
       JOIN facedescriptors ON (faces.descriptorId=facedescriptors.id)
       WHERE faces.identityId IS null AND faces.faceConfidence>0.99
+        AND faces.photoId=photos.id
       ''')
     for row in res.fetchall():
       id, descriptors, confidence, photoId, focus = row
@@ -109,21 +114,27 @@ def load_faces(db_path = db_path):
       faces.append(face)
   return faces
 
-def update_distances(identities, prune = False):
+def update_distances(identities, 
+    prune = False, 
+    maxDistance = MAX_DISTANCE_FROM_CENTROID):
   removed = 0
   for identity in identities:
     for face in identity['faces']:
       average = identity['descriptors']
-      distance = findCosineDistance(average, face['descriptors'])
-      if prune and distance > MAX_EPOCH_DISTANCE:
+      distance = findCosineDistanceBaked(identity, face)
+      if prune and distance > maxDistance:
         average = np.dot(average, len(identity['faces']))
         average = np.subtract(average, face['descriptors'])
-  
+
         face['cluster'] = Undefined
         face['distance'] = 0
         identity['faces'].remove(face)
 
-        identity['descriptors'] = np.divide(average, len(identity['faces']))
+        average = np.divide(average, len(identity['faces']))
+        identity['descriptors'] = average
+        identity['sqrtsummul'] = np.sqrt(np.sum(np.multiply(
+          average, average)))
+  
         removed += 1
       else:
         face['distance'] = distance
@@ -159,19 +170,19 @@ def build_straglers(faces):
 
 print('Loading faces from database')
 faces = load_faces()
-minPts = len(faces) / 100
-eps = 0.2
+
+minPts = max(len(faces) / 500, 5)
+eps = 0.185
 print(f'Scanning {len(faces)} faces for clusters (minPts: {minPts}, eps: {eps})')
 identities = DBSCAN(faces, minPts = minPts, eps = eps)
 print(f'{len(identities)} clusters grouped')
 
-MAX_CLUSTER_DISTANCE = 0.15  # Used to merge clusters
-MAX_EPOCH_DISTANCE = 0.14    # Used to prune outliers
-
 # Compute average center for all clusters
 identities = update_cluster_averages(identities)
+epoch_prune = True
+merge_identities = True
 
-if False:
+if epoch_prune:
   removed = -1
   epoch = 1
   # Filter each cluster removing any face that is > cluster_max_distance
@@ -179,14 +190,17 @@ if False:
   while removed != 0:
     print(f'Epoch {epoch}...')
     epoch += 1
-    removed = update_distances(identities, prune = True)
+    removed = update_distances(
+      identities, 
+      prune = True, 
+      maxDistance = MAX_DISTANCE_FROM_CENTROID)
     if removed > 0:
       print(f'Excluded {removed} faces this epoch')
 
 print(f'{len(identities)} identities seeded.')
 reduced = identities
 
-if False:
+if merge_identities:
   # Cluster the clusters...
   print('Reducing clusters via DBSCAN')
   reduced = DBSCAN(identities, eps = MAX_CLUSTER_DISTANCE, minPts = 3)
@@ -229,9 +243,7 @@ for id, identity in enumerate(reduced):
     face['cluster'] = identity
 
 reduced = update_cluster_averages(reduced)
-
 update_distances(reduced)
-
 sort_identities(reduced)
 
 if False:
@@ -294,6 +306,7 @@ print(f'Connecting to database: {db_path}')
 conn = create_connection(db_path)
 with conn:
   for identity in reduced:
+    print(f'Writing identity {identity["id"]} to DB')
     id = create_identity(conn, identity)
     for face in identity['faces']:
       update_face_identity(conn, face['id'], id)

ketrface/detect.py

@@ -197,9 +197,10 @@ conn = create_connection('../db/photos.db')
 with conn:
   cur = conn.cursor()
   res = cur.execute('''
-    SELECT photos.id,photos.faces,albums.path,photos.filename FROM photos
+    SELECT photos.id,photos.faces,albums.path,photos.filename 
+    FROM photos
     LEFT JOIN albums ON (albums.id=photos.albumId) 
-    WHERE photos.faces=-1
+    WHERE photos.faces=-1 AND photos.duplicate=0
     ''')
   rows = res.fetchall()
   count = len(rows)

ketrface/ketrface/dbscan.py

@@ -11,13 +11,8 @@ Noise = -2
 # Union of two lists of dicts, adding unique elements of B to
 # end of A
 def Union(A, B):
-# 5.012 of 100s sample
   return A + [x for x in B if x not in A]
-# 5.039 of 100s sample
-#  for key in B:
-#    if key not in A:
-#      A.append(key)
-#  return A
+
 
 # https://en.wikipedia.org/wiki/DBSCAN
 #
@@ -91,7 +86,7 @@ def RangeQuery(points, Q, eps):
   for P in points:                    # Scan all points in the database
     if P == Q:
       continue
-    distance = findCoseinDistanceBaked(# Compute distance
+    distance = findCosineDistanceBaked(# Compute distance
       Q, P) 
     if distance <= eps:               # Check epsilon
       neighbors.append(P)             # Add to result  

ketrface/ketrface/util.py

@@ -23,7 +23,6 @@ def redirect_off():
     sys.stdout = original
     original = None
 
-
 def zlib_uuencode(databytes, name='<data>'):
   ''' Compress databytes with zlib & uuencode the result '''
   inbuff = BytesIO(zlib.compress(databytes, 9))
@@ -47,15 +46,11 @@ class NpEncoder(json.JSONEncoder):
     if isinstance(obj, np.ndarray):
       return obj.tolist()
 
-def findCoseinDistanceBaked(src, dst):
+def findCosineDistanceBaked(src, dst):
   a = np.matmul(np.transpose(src['descriptors']), dst['descriptors'])
   return 1 - (a / (src['sqrtsummul'] * dst['sqrtsummul']))
 
 def findCosineDistance(source_representation, test_representation):
-#  if type(source_representation) == list:
-#    source_representation = np.array(source_representation)
-#  if type(test_representation) == list:
-#    test_representation = np.array(test_representation)
   a = np.matmul(np.transpose(source_representation), test_representation)
   b = np.sum(np.multiply(source_representation, source_representation))
   c = np.sum(np.multiply(test_representation, test_representation))