diff --git a/README.md b/README.md index 106bdc0..2bbeeda 100644 --- a/README.md +++ b/README.md @@ -194,7 +194,7 @@ Age model got ± 4.65 MAE; gender model got 97.44% accuracy, 96.29% precision an **Face Detectors** - [`Demo`](https://youtu.be/GZ2p2hj2H5k) -Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/), [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/), [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/) and [`YOLOv8 Face`](https://github.com/derronqi/yolov8-face) detectors are wrapped in deepface. +Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/), [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/), [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/), [`YOLOv8 Face`](https://github.com/derronqi/yolov8-face) and [`YuNet`](https://github.com/ShiqiYu/libfacedetection) detectors are wrapped in deepface.

@@ -209,6 +209,7 @@ backends = [ 'retinaface', 'mediapipe', 'yolov8', + 'yunet', ] #face verification 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..dc7b1b2 --- /dev/null +++ b/deepface/detectors/YunetWrapper.py @@ -0,0 +1,77 @@ +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(f"{file_name} 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=0.9): + # 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. + resized = False + if height > 640 or width > 640: + r = 640.0 / max(height, width) + original_image = image.copy() + image = cv2.resize(image, (int(width * r), int(height * r))) + height, width = image.shape[0], image.shape[1] + resized = True + detector.setInputSize((width, height)) + detector.setScoreThreshold(score_threshold) + _, faces = detector.detect(image) + if faces is None: + return resp + 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])) + if resized: + image = original_image + x, y, w, h = int(x / r), int(y / r), int(w / r), int(h / r) + x_re, y_re, x_le, y_le = ( + int(x_re / r), + int(y_re / r), + int(x_le / r), + int(y_le / r), + ) + 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