Merge pull request #978 from serengil/feat-task-2701-return-obj-for-d…

…etectors

pretty return type for detect faces

deepface/commons/functions.py

@@ -12,6 +12,7 @@
 
 # package dependencies
 from deepface.detectors import DetectorWrapper
+from deepface.models.Detector import DetectedFace, FacialAreaRegion
 from deepface.commons.logger import Logger
 
 logger = Logger(module="commons.functions")
@@ -170,10 +171,11 @@ def extract_faces(
 
     # img might be path, base64 or numpy array. Convert it to numpy whatever it is.
     img, img_name = load_image(img)
-    img_region = [0, 0, img.shape[1], img.shape[0]]
+
+    base_region = FacialAreaRegion(x=0, y=0, w=img.shape[1], h=img.shape[0])
 
     if detector_backend == "skip":
-        face_objs = [(img, img_region, 0)]
+        face_objs = [DetectedFace(img=img, facial_area=base_region, confidence=0)]
     else:
         face_objs = DetectorWrapper.detect_faces(detector_backend, img, align)
 
@@ -192,9 +194,12 @@ def extract_faces(
             )
 
     if len(face_objs) == 0 and enforce_detection is False:
-        face_objs = [(img, img_region, 0)]
+        face_objs = [DetectedFace(img=img, facial_area=base_region, confidence=0)]
 
-    for current_img, current_region, confidence in face_objs:
+    for face_obj in face_objs:
+        current_img = face_obj.img
+        current_region = face_obj.facial_area
+        confidence = face_obj.confidence
         if current_img.shape[0] > 0 and current_img.shape[1] > 0:
             if grayscale is True:
                 current_img = cv2.cvtColor(current_img, cv2.COLOR_BGR2GRAY)
@@ -245,10 +250,10 @@ def extract_faces(
 
             # int cast is for the exception - object of type 'float32' is not JSON serializable
             region_obj = {
-                "x": int(current_region[0]),
-                "y": int(current_region[1]),
-                "w": int(current_region[2]),
-                "h": int(current_region[3]),
+                "x": current_region.x,
+                "y": current_region.y,
+                "w": current_region.w,
+                "h": current_region.h,
             }
 
             extracted_face = (img_pixels, region_obj, confidence)

deepface/detectors/DetectorWrapper.py

@@ -1,6 +1,6 @@
-from typing import Any
+from typing import Any, List
 import numpy as np
-from deepface.models.Detector import Detector
+from deepface.models.Detector import Detector, DetectedFace
 from deepface.detectors import (
     FastMtCnn,
     MediaPipe,
@@ -52,27 +52,19 @@ 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:
+def detect_faces(detector_backend: str, img: np.ndarray, align: bool = True) -> 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
     Returns:
-        results (List[Tuple[np.ndarray, List[float], float]]): A list of tuples
-            where each tuple contains:
-            - detected_face (np.ndarray): The detected face as a NumPy array.
-            - face_region (List[float]): The image region represented as
-                a list of floats e.g. [x, y, w, h]
+        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.
-
-    Example:
-        results = [
-            (array(..., dtype=uint8), [110, 60, 150, 380], 0.99),
-            (array(..., dtype=uint8), [150, 50, 299, 375], 0.98),
-            (array(..., dtype=uint8), [120, 55, 300, 371], 0.96),
-        ]
     """
     face_detector: Detector = build_model(detector_backend)
     return face_detector.detect_faces(img=img, align=align)

deepface/detectors/Dlib.py

@@ -1,10 +1,10 @@
-from typing import List, Tuple
+from typing import List
 import os
 import bz2
 import gdown
 import numpy as np
 from deepface.commons import functions
-from deepface.models.Detector import Detector
+from deepface.models.Detector import Detector, DetectedFace, FacialAreaRegion
 from deepface.commons.logger import Logger
 
 logger = Logger(module="detectors.DlibWrapper")
@@ -56,29 +56,19 @@ def build_model(self) -> dict:
         detector["sp"] = sp
         return detector
 
-    def detect_faces(
-        self, img: np.ndarray, align: bool = True
-    ) -> List[Tuple[np.ndarray, List[float], float]]:
+    def detect_faces(self, img: np.ndarray, align: bool = True) -> 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
         Returns:
-            results (List[Tuple[np.ndarray, List[float], float]]): A list of tuples
-                where each tuple contains:
-                - detected_face (np.ndarray): The detected face as a NumPy array.
-                - face_region (List[float]): The image region represented as
-                    a list of floats e.g. [x, y, w, h]
-                - confidence (float): The confidence score associated with the detected face.
-
-        Example:
-            results = [
-                (array(..., dtype=uint8), [110, 60, 150, 380], 0.99),
-                (array(..., dtype=uint8), [150, 50, 299, 375], 0.98),
-                (array(..., dtype=uint8), [120, 55, 300, 371], 0.96),
-            ]
+            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.
         """
         # this is not a must dependency. do not import it in the global level.
         try:
@@ -95,8 +85,6 @@ def detect_faces(
 
         detected_face = None
 
-        img_region = [0, 0, img.shape[1], img.shape[0]]
-
         face_detector = self.model["face_detector"]
 
         # note that, by design, dlib's fhog face detector scores are >0 but not capped at 1
@@ -115,13 +103,17 @@ def detect_faces(
                     max(0, top) : min(bottom, img.shape[0]), max(0, left) : min(right, img.shape[1])
                 ]
 
-                img_region = [left, top, right - left, bottom - top]
+                img_region = FacialAreaRegion(x=left, y=right, w=right - left, h=bottom - top)
                 confidence = scores[idx]
 
                 if align:
                     img_shape = sp(img, detections[idx])
                     detected_face = dlib.get_face_chip(img, img_shape, size=detected_face.shape[0])
 
-                resp.append((detected_face, img_region, confidence))
+                detected_face_obj = DetectedFace(
+                    img=detected_face, facial_area=img_region, confidence=confidence
+                )
+
+                resp.append(detected_face_obj)
 
         return resp

deepface/detectors/FastMtCnn.py

@@ -1,7 +1,7 @@
-from typing import Any, Union, List, Tuple
+from typing import Any, Union, List
 import cv2
 import numpy as np
-from deepface.models.Detector import Detector
+from deepface.models.Detector import Detector, DetectedFace, FacialAreaRegion
 from deepface.modules import detection
 
 # Link -> https://github.com/timesler/facenet-pytorch
@@ -12,33 +12,22 @@ class FastMtCnnClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 
-    def detect_faces(
-        self, img: np.ndarray, align: bool = True
-    ) -> List[Tuple[np.ndarray, List[float], float]]:
+    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
         """
         Detect and align face with mtcnn
         Args:
             img (np.ndarray): pre-loaded image
             align (bool): default is true
         Returns:
-            results (List[Tuple[np.ndarray, List[float], float]]): A list of tuples
-                where each tuple contains:
-                - detected_face (np.ndarray): The detected face as a NumPy array.
-                - face_region (List[float]): The image region represented as
-                    a list of floats e.g. [x, y, w, h]
-                - confidence (float): The confidence score associated with the detected face.
-
-        Example:
-            results = [
-                (array(..., dtype=uint8), [110, 60, 150, 380], 0.99),
-                (array(..., dtype=uint8), [150, 50, 299, 375], 0.98),
-                (array(..., dtype=uint8), [120, 55, 300, 371], 0.96),
-            ]
+            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.
         """
         resp = []
 
         detected_face = None
-        img_region = [0, 0, img.shape[1], img.shape[0]]
 
         img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # mtcnn expects RGB but OpenCV read BGR
         detections = self.model.detect(
@@ -49,7 +38,7 @@ def detect_faces(
             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)]
-                img_region = [x, y, w, h]
+                img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
                 confidence = current_detection[1]
 
                 if align:
@@ -59,7 +48,11 @@ def detect_faces(
                         img=detected_face, left_eye=left_eye, right_eye=right_eye
                     )
 
-                resp.append((detected_face, img_region, confidence))
+                detected_face_obj = DetectedFace(
+                    img=detected_face, facial_area=img_region, confidence=confidence
+                )
+
+                resp.append(detected_face_obj)
 
         return resp
 

deepface/detectors/MediaPipe.py

@@ -1,6 +1,6 @@
-from typing import Any, List, Tuple
+from typing import Any, List
 import numpy as np
-from deepface.models.Detector import Detector
+from deepface.models.Detector import Detector, DetectedFace, FacialAreaRegion
 from deepface.modules import detection
 
 # Link - https://google.github.io/mediapipe/solutions/face_detection
@@ -29,28 +29,18 @@ 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[Tuple[np.ndarray, List[float], float]]:
+    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
         """
         Detect and align face with mediapipe
         Args:
             img (np.ndarray): pre-loaded image
             align (bool): default is true
         Returns:
-            results (List[Tuple[np.ndarray, List[float], float]]): A list of tuples
-                where each tuple contains:
-                - detected_face (np.ndarray): The detected face as a NumPy array.
-                - face_region (List[float]): The image region represented as
-                    a list of floats e.g. [x, y, w, h]
-                - confidence (float): The confidence score associated with the detected face.
-
-        Example:
-            results = [
-                (array(..., dtype=uint8), [110, 60, 150, 380], 0.99),
-                (array(..., dtype=uint8), [150, 50, 299, 375], 0.98),
-                (array(..., dtype=uint8), [120, 55, 300, 371], 0.96),
-            ]
+            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.
         """
         resp = []
 
@@ -85,13 +75,19 @@ def detect_faces(
 
             if x > 0 and y > 0:
                 detected_face = img[y : y + h, x : x + w]
-                img_region = [x, y, w, h]
+                img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
 
                 if align:
                     detected_face = detection.align_face(
                         img=detected_face, left_eye=left_eye, right_eye=right_eye
                     )
 
-                resp.append((detected_face, img_region, confidence))
+                detected_face_obj = DetectedFace(
+                    img=detected_face,
+                    facial_area=img_region,
+                    confidence=confidence,
+                )
+
+                resp.append(detected_face_obj)
 
         return resp

deepface/detectors/MtCnn.py

@@ -1,8 +1,8 @@
-from typing import List, Tuple
+from typing import List
 import cv2
 import numpy as np
 from mtcnn import MTCNN
-from deepface.models.Detector import Detector
+from deepface.models.Detector import Detector, DetectedFace, FacialAreaRegion
 from deepface.modules import detection
 
 # pylint: disable=too-few-public-methods
@@ -14,34 +14,23 @@ class MtCnnClient(Detector):
     def __init__(self):
         self.model = MTCNN()
 
-    def detect_faces(
-        self, img: np.ndarray, align: bool = True
-    ) -> List[Tuple[np.ndarray, List[float], float]]:
+    def detect_faces(self, img: np.ndarray, align: bool = True) -> List[DetectedFace]:
         """
         Detect and align face with mtcnn
         Args:
             img (np.ndarray): pre-loaded image
             align (bool): default is true
         Returns:
-            results (List[Tuple[np.ndarray, List[float], float]]): A list of tuples
-                where each tuple contains:
-                - detected_face (np.ndarray): The detected face as a NumPy array.
-                - face_region (List[float]): The image region represented as
-                    a list of floats e.g. [x, y, w, h]
-                - confidence (float): The confidence score associated with the detected face.
-
-        Example:
-            results = [
-                (array(..., dtype=uint8), [110, 60, 150, 380], 0.99),
-                (array(..., dtype=uint8), [150, 50, 299, 375], 0.98),
-                (array(..., dtype=uint8), [120, 55, 300, 371], 0.96),
-            ]
+            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.
         """
 
         resp = []
 
         detected_face = None
-        img_region = [0, 0, img.shape[1], img.shape[0]]
 
         img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # mtcnn expects RGB but OpenCV read BGR
         detections = self.model.detect_faces(img_rgb)
@@ -51,7 +40,7 @@ def detect_faces(
             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)]
-                img_region = [x, y, w, h]
+                img_region = FacialAreaRegion(x=x, y=y, w=w, h=h)
                 confidence = current_detection["confidence"]
 
                 if align:
@@ -62,6 +51,10 @@ def detect_faces(
                         img=detected_face, left_eye=left_eye, right_eye=right_eye
                     )
 
-                resp.append((detected_face, img_region, confidence))
+                detected_face_obj = DetectedFace(
+                    img=detected_face, facial_area=img_region, confidence=confidence
+                )
+
+                resp.append(detected_face_obj)
 
         return resp