adding expand percentage argument for detection

Author: serengil

deepface/DeepFace.py

@@ -58,6 +58,7 @@ def verify(
     distance_metric: str = "cosine",
     enforce_detection: bool = True,
     align: bool = True,
+    expand_percentage: int = 0,
     normalization: str = "base",
 ) -> Dict[str, Any]:
     """
@@ -83,6 +84,8 @@ def verify(
 
         align (bool): Flag to enable face alignment (default is True).
 
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
         normalization (string): Normalize the input image before feeding it to the model.
             Options: base, raw, Facenet, Facenet2018, VGGFace, VGGFace2, ArcFace (default is base)
 
@@ -119,6 +122,7 @@ def verify(
         distance_metric=distance_metric,
         enforce_detection=enforce_detection,
         align=align,
+        expand_percentage=expand_percentage,
         normalization=normalization,
     )
 
@@ -129,6 +133,7 @@ def analyze(
     enforce_detection: bool = True,
     detector_backend: str = "opencv",
     align: bool = True,
+    expand_percentage: int = 0,
     silent: bool = False,
 ) -> List[Dict[str, Any]]:
     """
@@ -152,6 +157,8 @@ def analyze(
 
         align (boolean): Perform alignment based on the eye positions (default is True).
 
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
         silent (boolean): Suppress or allow some log messages for a quieter analysis process
             (default is False).
 
@@ -209,6 +216,7 @@ def analyze(
         enforce_detection=enforce_detection,
         detector_backend=detector_backend,
         align=align,
+        expand_percentage=expand_percentage,
         silent=silent,
     )
 
@@ -221,6 +229,7 @@ def find(
     enforce_detection: bool = True,
     detector_backend: str = "opencv",
     align: bool = True,
+    expand_percentage: int = 0,
     threshold: Optional[float] = None,
     normalization: str = "base",
     silent: bool = False,
@@ -249,6 +258,8 @@ def find(
 
         align (boolean): Perform alignment based on the eye positions (default is True).
 
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
         threshold (float): Specify a threshold to determine whether a pair represents the same
             person or different individuals. This threshold is used for comparing distances.
             If left unset, default pre-tuned threshold values will be applied based on the specified
@@ -286,6 +297,7 @@ def find(
         enforce_detection=enforce_detection,
         detector_backend=detector_backend,
         align=align,
+        expand_percentage=expand_percentage,
         threshold=threshold,
         normalization=normalization,
         silent=silent,
@@ -298,6 +310,7 @@ def represent(
     enforce_detection: bool = True,
     detector_backend: str = "opencv",
     align: bool = True,
+    expand_percentage: int = 0,
     normalization: str = "base",
 ) -> List[Dict[str, Any]]:
     """
@@ -320,6 +333,8 @@ def represent(
 
         align (boolean): Perform alignment based on the eye positions (default is True).
 
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
         normalization (string): Normalize the input image before feeding it to the model.
             Default is base. Options: base, raw, Facenet, Facenet2018, VGGFace, VGGFace2, ArcFace
             (default is base).
@@ -346,6 +361,7 @@ def represent(
         enforce_detection=enforce_detection,
         detector_backend=detector_backend,
         align=align,
+        expand_percentage=expand_percentage,
         normalization=normalization,
     )
 
@@ -409,6 +425,7 @@ def extract_faces(
     detector_backend: str = "opencv",
     enforce_detection: bool = True,
     align: bool = True,
+    expand_percentage: int = 0,
     grayscale: bool = False,
 ) -> List[Dict[str, Any]]:
     """
@@ -429,6 +446,8 @@ def extract_faces(
 
         align (bool): Flag to enable face alignment (default is True).
 
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
         grayscale (boolean): Flag to convert the image to grayscale before
             processing (default is False).
 
@@ -448,6 +467,7 @@ def extract_faces(
         detector_backend=detector_backend,
         enforce_detection=enforce_detection,
         align=align,
+        expand_percentage=expand_percentage,
         grayscale=grayscale,
         human_readable=True,
     )

deepface/detectors/DetectorWrapper.py

@@ -12,6 +12,9 @@
     Yolo,
     YuNet,
 )
+from deepface.commons.logger import Logger
+
+logger = Logger(module="deepface/detectors/DetectorWrapper.py")
 
 
 def build_model(detector_backend: str) -> Any:
@@ -52,19 +55,35 @@ def build_model(detector_backend: str) -> Any:
     return face_detector_obj[detector_backend]
 
 
-def detect_faces(detector_backend: str, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
+def detect_faces(
+    detector_backend: str, img: np.ndarray, align: bool = True, expand_percentage: int = 0
+) -> List[DetectedFace]:
     """
     Detect face(s) from a given image
     Args:
         detector_backend (str): detector name
+
         img (np.ndarray): pre-loaded image
-        alig (bool): enable or disable alignment after detection
+
+        align (bool): enable or disable alignment after detection
+
+        expand_percentage (int): expand detected facial area with a percentage (default is 0).
+
     Returns:
         results (List[DetectedFace]): A list of DetectedFace objects
             where each object contains:
-            - img (np.ndarray): The detected face as a NumPy array.
-            - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
-            - confidence (float): The confidence score associated with the detected face.
+
+        - img (np.ndarray): The detected face as a NumPy array.
+
+        - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
+
+        - confidence (float): The confidence score associated with the detected face.
     """
     face_detector: Detector = build_model(detector_backend)
-    return face_detector.detect_faces(img=img, align=align)
+    if expand_percentage < 0:
+        logger.warn(
+            f"Expand percentage cannot be negative but you set it to {expand_percentage}."
+            "Overwritten it to 0."
+        )
+        expand_percentage = 0
+    return face_detector.detect_faces(img=img, align=align, expand_percentage=expand_percentage)

deepface/detectors/Dlib.py

@@ -56,18 +56,27 @@ def build_model(self) -> dict:
         detector["sp"] = sp
         return detector
 
-    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
+    def detect_faces(
+        self, img: np.ndarray, align: bool = True, expand_percentage: int = 0
+    ) -> List[DetectedFace]:
         """
         Detect and align face with dlib
+
         Args:
-            face_detector (Any): dlib face detector object
-            img (np.ndarray): pre-loaded image
-            align (bool): default is true
+            img (np.ndarray): pre-loaded image as numpy array
+
+            align (bool): flag to enable or disable alignment after detection (default is True)
+
+            expand_percentage (int): expand detected facial area with a percentage
+
         Returns:
-            results (List[DetectedFace]): A list of DetectedFace objects
+            results (List[Tuple[DetectedFace]): A list of DetectedFace objects
                 where each object contains:
+
             - img (np.ndarray): The detected face as a NumPy array.
+
             - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
+
             - confidence (float): The confidence score associated with the detected face.
         """
         # this is not a must dependency. do not import it in the global level.
@@ -79,6 +88,12 @@ def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace
                 "Please install using 'pip install dlib' "
             ) from e
 
+        if expand_percentage != 0:
+            logger.warn(
+                f"You set expand_percentage argument to {expand_percentage},"
+                "but dlib hog handles detection by itself"
+            )
+
         resp = []
 
         sp = self.model["sp"]

deepface/detectors/FastMtCnn.py

@@ -12,17 +12,27 @@ class FastMtCnnClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 
-    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
+    def detect_faces(
+        self, img: np.ndarray, align: bool = True, expand_percentage: int = 0
+    ) -> List[DetectedFace]:
         """
         Detect and align face with mtcnn
+
         Args:
-            img (np.ndarray): pre-loaded image
-            align (bool): default is true
+            img (np.ndarray): pre-loaded image as numpy array
+
+            align (bool): flag to enable or disable alignment after detection (default is True)
+
+            expand_percentage (int): expand detected facial area with a percentage
+
         Returns:
-            results (List[DetectedFace]): A list of DetectedFace objects
+            results (List[Tuple[DetectedFace]): A list of DetectedFace objects
                 where each object contains:
+
             - img (np.ndarray): The detected face as a NumPy array.
+
             - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
+
             - confidence (float): The confidence score associated with the detected face.
         """
         resp = []
@@ -37,7 +47,16 @@ def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace
 
             for current_detection in zip(*detections):
                 x, y, w, h = xyxy_to_xywh(current_detection[0])
-                detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
+
+                # expand the facial area to be extracted and stay within img.shape limits
+                x2 = max(0, x - int((w * expand_percentage) / 100))  # expand left
+                y2 = max(0, y - int((h * expand_percentage) / 100))  # expand top
+                w2 = min(img.shape[1], w + int((w * expand_percentage) / 100))  # expand right
+                h2 = min(img.shape[0], h + int((h * expand_percentage) / 100))  # expand bottom
+
+                # detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
+                detected_face = img[int(y2) : int(y2 + h2), int(x2) : int(x2 + w2)]
+
                 img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
                 confidence = current_detection[1]
 

deepface/detectors/MediaPipe.py

@@ -29,17 +29,27 @@ def build_model(self) -> Any:
         face_detection = mp_face_detection.FaceDetection(min_detection_confidence=0.7)
         return face_detection
 
-    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
+    def detect_faces(
+        self, img: np.ndarray, align: bool = True, expand_percentage: int = 0
+    ) -> List[DetectedFace]:
         """
         Detect and align face with mediapipe
+
         Args:
-            img (np.ndarray): pre-loaded image
-            align (bool): default is true
+            img (np.ndarray): pre-loaded image as numpy array
+
+            align (bool): flag to enable or disable alignment after detection (default is True)
+
+            expand_percentage (int): expand detected facial area with a percentage
+
         Returns:
-            results (List[DetectedFace): A list of DetectedFace objects
+            results (List[Tuple[DetectedFace]): A list of DetectedFace objects
                 where each object contains:
+
             - img (np.ndarray): The detected face as a NumPy array.
+
             - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
+
             - confidence (float): The confidence score associated with the detected face.
         """
         resp = []
@@ -74,7 +84,16 @@ def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace
             # left_ear = (int(landmarks[5].x * img_width), int(landmarks[5].y * img_height))
 
             if x > 0 and y > 0:
-                detected_face = img[y : y + h, x : x + w]
+
+                # expand the facial area to be extracted and stay within img.shape limits
+                x2 = max(0, x - int((w * expand_percentage) / 100))  # expand left
+                y2 = max(0, y - int((h * expand_percentage) / 100))  # expand top
+                w2 = min(img.shape[1], w + int((w * expand_percentage) / 100))  # expand right
+                h2 = min(img.shape[0], h + int((h * expand_percentage) / 100))  # expand bottom
+
+                # detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
+                detected_face = img[int(y2) : int(y2 + h2), int(x2) : int(x2 + w2)]
+
                 img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
 
                 if align:

deepface/detectors/MtCnn.py

@@ -13,17 +13,27 @@ class MtCnnClient(Detector):
     def __init__(self):
         self.model = MTCNN()
 
-    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
+    def detect_faces(
+        self, img: np.ndarray, align: bool = True, expand_percentage: int = 0
+    ) -> List[DetectedFace]:
         """
         Detect and align face with mtcnn
+
         Args:
-            img (np.ndarray): pre-loaded image
-            align (bool): default is true
+            img (np.ndarray): pre-loaded image as numpy array
+
+            align (bool): flag to enable or disable alignment after detection (default is True)
+
+            expand_percentage (int): expand detected facial area with a percentage
+
         Returns:
-            results (List[DetectedFace]): A list of DetectedFace objects
+            results (List[Tuple[DetectedFace]): A list of DetectedFace objects
                 where each object contains:
+
             - img (np.ndarray): The detected face as a NumPy array.
+
             - facial_area (FacialAreaRegion): The facial area region represented as x, y, w, h
+
             - confidence (float): The confidence score associated with the detected face.
         """
 
@@ -40,7 +50,16 @@ def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace
 
             for current_detection in detections:
                 x, y, w, h = current_detection["box"]
-                detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
+
+                # expand the facial area to be extracted and stay within img.shape limits
+                x2 = max(0, x - int((w * expand_percentage) / 100))  # expand left
+                y2 = max(0, y - int((h * expand_percentage) / 100))  # expand top
+                w2 = min(img.shape[1], w + int((w * expand_percentage) / 100))  # expand right
+                h2 = min(img.shape[0], h + int((h * expand_percentage) / 100))  # expand bottom
+
+                # detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
+                detected_face = img[int(y2) : int(y2 + h2), int(x2) : int(x2 + w2)]
+
                 img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
                 confidence = current_detection["confidence"]