From 5e55fafdb56b43185befffb23f8b7bad5335b7d0 Mon Sep 17 00:00:00 2001
From: "Anthr@X" <anthrax1@users.noreply.github.com>
Date: Sat, 8 Jul 2023 23:17:50 +1000
Subject: [PATCH] Add Yunet detector

---
 deepface/detectors/FaceDetector.py |  3 ++
 deepface/detectors/YunetWrapper.py | 64 ++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 deepface/detectors/YunetWrapper.py

diff --git a/deepface/detectors/FaceDetector.py b/deepface/detectors/FaceDetector.py
index 6e7f258..522592d 100644
--- a/deepface/detectors/FaceDetector.py
+++ b/deepface/detectors/FaceDetector.py
@@ -10,6 +10,7 @@ from deepface.detectors import (
     RetinaFaceWrapper,
     MediapipeWrapper,
     YoloWrapper,
+    YunetWrapper,
 )
 
 
@@ -24,6 +25,7 @@ def build_model(detector_backend):
         "retinaface": RetinaFaceWrapper.build_model,
         "mediapipe": MediapipeWrapper.build_model,
         "yolov8": YoloWrapper.build_model,
+        "yunet": YunetWrapper.build_model,
     }
 
     if not "face_detector_obj" in globals():
@@ -67,6 +69,7 @@ def detect_faces(face_detector, detector_backend, img, align=True):
         "retinaface": RetinaFaceWrapper.detect_face,
         "mediapipe": MediapipeWrapper.detect_face,
         "yolov8": YoloWrapper.detect_face,
+        "yunet": YunetWrapper.detect_face,
     }
 
     detect_face_fn = backends.get(detector_backend)
diff --git a/deepface/detectors/YunetWrapper.py b/deepface/detectors/YunetWrapper.py
new file mode 100644
index 0000000..9d184df
--- /dev/null
+++ b/deepface/detectors/YunetWrapper.py
@@ -0,0 +1,64 @@
+import numpy as np
+import cv2
+import os
+import gdown
+from deepface.detectors import FaceDetector
+from deepface.commons import functions
+
+
+def build_model():
+    url = "https://github.com/opencv/opencv_zoo/raw/main/models/face_detection_yunet/face_detection_yunet_2023mar.onnx"
+    file_name = "face_detection_yunet_2023mar.onnx"
+    home = functions.get_deepface_home()
+    if os.path.isfile(home + f"/.deepface/weights/{file_name}") is False:
+        print("yunet_n_dynamic.onnx will be downloaded...")
+        output = home + f"/.deepface/weights/{file_name}"
+        gdown.download(url, output, quiet=False)
+    face_detector = cv2.FaceDetectorYN_create(
+        home + f"/.deepface/weights/{file_name}", "", (0, 0)
+    )
+    return face_detector
+
+
+def detect_face(detector, image, align=True, score_threshold=0.8):
+    # FaceDetector.detect_faces does not support score_threshold parameter.
+    # We can set it via environment variable.
+    score_threshold = os.environ.get("yunet_score_threshold", score_threshold)
+    resp = []
+    detected_face = None
+    img_region = [0, 0, image.shape[1], image.shape[0]]
+    faces = []
+    height, width = image.shape[0], image.shape[1]
+    # resize image if it is too large (Yunet fails to detect faces on large input sometimes)
+    # I picked 640 as a threshold because it is the default value of max_size in Yunet.
+    if height > 640 or width > 640:
+        r = 640.0 / max(height, width)
+        image = cv2.resize(image, (int(width * r), int(height * r)))
+        height, width = image.shape[0], image.shape[1]
+    detector.setInputSize((width, height))
+    detector.setScoreThreshold(score_threshold)
+    _, faces = detector.detect(image)
+    for face in faces:
+        """
+        The detection output faces is a two-dimension array of type CV_32F,
+        whose rows are the detected face instances, columns are the location of a face and 5 facial landmarks.
+        The format of each row is as follows:
+        x1, y1, w, h, x_re, y_re, x_le, y_le, x_nt, y_nt, x_rcm, y_rcm, x_lcm, y_lcm,
+        where x1, y1, w, h are the top-left coordinates, width and height of the face bounding box,
+        {x, y}_{re, le, nt, rcm, lcm} stands for the coordinates of right eye, left eye, nose tip, the right corner and left corner of the mouth respectively.
+        """
+        (x, y, w, h, x_re, y_re, x_le, y_le) = list(map(int, face[:8]))
+        confidence = face[-1]
+        confidence = "{:.2f}".format(confidence)
+        detected_face = image[int(y) : int(y + h), int(x) : int(x + w)]
+        img_region = [x, y, w, h]
+        if align:
+            detected_face = yunet_align_face(detected_face, x_re, y_re, x_le, y_le)
+        resp.append((detected_face, img_region, confidence))
+    return resp
+
+
+# x_re, y_re, x_le, y_le stands for the coordinates of right eye, left eye
+def yunet_align_face(img, x_re, y_re, x_le, y_le):
+    img = FaceDetector.alignment_procedure(img, (x_le, y_le), (x_re, y_re))
+    return img