change bbox to norm, refine face extractor

1 files changed, 19 insertions, 12 deletions

diff --git a/megapixels/app/processors/face_landmarks.py b/megapixels/app/processors/face_landmarks.py
index 171fc666..231e378f 100644
--- a/megapixels/app/processors/face_landmarks.py
+++ b/megapixels/app/processors/face_landmarks.py
@@ -30,6 +30,9 @@ class Landmarks2D:
     self.log.warn('Define landmarks() function')
     pass
 
+  def to_str(self, vec):
+    return ','.join([','.join(list(map(str,[x,y]))) for x,y in vec])
+
   def flatten(self, points):
     '''Converts list of point-tupes into a flattened list for CSV
     :param points: (list) of x,y points
@@ -69,9 +72,9 @@ class FaceAlignment2D_68(Landmarks2D):
     # predict landmarks
     points = self.fa.get_landmarks(im)  # returns array of arrays of 68 2D pts/face
     # convert to data type
-    points = [list(map(int, p)) for p in points[0]]
-    return points
-
+    w,h = im.shape[:2][::-1]
+    points = [tuple(x/w, y/h) for x,y in points[0]]
+    return points  # normalized
 
 class Dlib2D(Landmarks2D):
   
@@ -82,15 +85,16 @@ class Dlib2D(Landmarks2D):
     self.predictor = dlib.shape_predictor(model)
     self.log.info(f'loaded predictor model: {model}')
 
-  def landmarks(self, im, bbox):
+  def landmarks(self, im, bbox_norm):
     '''Generates 68-pt landmarks using dlib predictor
     :param im: (numpy.ndarray) BGR image
     :param bbox: (app.models.BBox) dimensioned
-    :returns (list) of (int, int) for x,y values
+    :returns (list) of (float, float) for normalized x,y values
     '''
-    bbox = bbox.to_dlib()
+    dim = im.shape[:2][::-1]
+    roi_dlib = bbox_norm.to_dim(dim).to_dlib()
     im_gray = cv.cvtColor(im, cv.COLOR_BGR2GRAY)
-    points = [[p.x, p.y] for p in self.predictor(im_gray, bbox).parts()]
+    points = [[p.x/dim[0], p.y/dim[1]] for p in self.predictor(im_gray, roi_dlib).parts()]
     return points
 
 
@@ -121,13 +125,13 @@ class MTCNN2D_5(Landmarks2D):
     from mtcnn.mtcnn import MTCNN
     self.detector = MTCNN()
 
-  def landmarks(self, im, bbox):
+  def landmarks(self, im, bbox_norm):
     '''Detects face using MTCNN and returns (list) of BBox
     :param im: (numpy.ndarray) image
     :returns list of BBox
     '''
     results = []
-    dim_wh = im.shape[:2][::-1]  # (w, h)
+    dim = im.shape[:2][::-1]  # (w, h)
     
     # run MTCNN to get bbox and landmarks
     dets = self.detector.detect_faces(im)
@@ -138,7 +142,7 @@ class MTCNN2D_5(Landmarks2D):
       #rect = det['box']
       points = det['keypoints']
       # convert to normalized for contain-comparison
-      points_norm = [np.array(pt)/dim_wh for pname, pt in points.items()]
+      points_norm = [np.array(pt)/dim for pname, pt in points.items()]
       contains = False not in [bbox.contains(pn) for pn in points_norm]
       if contains:
         results.append(points)  # append original points
@@ -185,14 +189,17 @@ class FaceAlignment3D_68(Landmarks3D):
     device = f'cuda:{gpu}' if gpu > -1 else 'cpu'
     self.fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._3D, device=device, flip_input=flip_input)
 
-  def landmarks(self, im, rect):
+  def landmarks(self, im, bbox_norm):
     '''Calculates the 3D facial landmarks
     :param im: (numpy.ndarray) BGR image
-    :param rect: (list) of face (x1, y1, x2, y2)
+    :param bbox_norm: (BBox) of face roi
     :returns (list) of 68 (int) (tuples) as (x,y, z) 
     '''
     # predict landmarks
+    dim = im.shape[:2][::-1]
+    rect = bbox_norm.to_dim(dim).to_xyxy()
     points = self.fa.get_landmarks(im, [rect])  # returns array of arrays of 68 3D pts/face
     # convert to data type
+    # TODO normalize this, but how to norm 3D?
     points = [list(map(int, p)) for p in points[0]]
     return points
\ No newline at end of file