diff --git a/README.md b/README.md
index 822f298..f351c20 100644
--- a/README.md
+++ b/README.md
@@ -16,6 +16,9 @@
[](https://github.com/sponsors/serengil)
[](https://buymeacoffee.com/serengil)
+[](https://news.ycombinator.com/item?id=42584896)
+[](https://www.producthunt.com/posts/deepface?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-deepface)
+
@@ -392,7 +395,7 @@ Before creating a PR, you should run the unit tests and linting locally by runni
There are many ways to support a project - starring⭐️ the GitHub repo is just one 🙏
-If you do like this work, then you can support it financially on [Patreon](https://www.patreon.com/serengil?repo=deepface), [GitHub Sponsors](https://github.com/sponsors/serengil) or [Buy Me a Coffee](https://buymeacoffee.com/serengil).
+If you do like this work, then you can support it financially on [Patreon](https://www.patreon.com/serengil?repo=deepface), [GitHub Sponsors](https://github.com/sponsors/serengil) or [Buy Me a Coffee](https://buymeacoffee.com/serengil). Also, your company's logo will be shown on README on GitHub and PyPI if you become a sponsor in gold, silver or bronze tiers.
@@ -402,7 +405,19 @@ If you do like this work, then you can support it financially on [Patreon](https
-Also, your company's logo will be shown on README on GitHub and PyPI if you become a sponsor in gold, silver or bronze tiers.
+Additionally, you can help us reach a wider audience by upvoting our posts on Hacker News and Product Hunt.
+
+
## Citation
diff --git a/deepface/DeepFace.py b/deepface/DeepFace.py
index 6eb31ac..f8930e5 100644
--- a/deepface/DeepFace.py
+++ b/deepface/DeepFace.py
@@ -68,18 +68,18 @@ def build_model(model_name: str, task: str = "facial_recognition") -> Any:
def verify(
- img1_path: Union[str, np.ndarray, List[float]],
- img2_path: Union[str, np.ndarray, List[float]],
- model_name: str = "VGG-Face",
- detector_backend: str = "opencv",
- distance_metric: str = "cosine",
- enforce_detection: bool = True,
- align: bool = True,
- expand_percentage: int = 0,
- normalization: str = "base",
- silent: bool = False,
- threshold: Optional[float] = None,
- anti_spoofing: bool = False,
+ img1_path: Union[str, np.ndarray, List[float]],
+ img2_path: Union[str, np.ndarray, List[float]],
+ model_name: str = "VGG-Face",
+ detector_backend: str = "opencv",
+ distance_metric: str = "cosine",
+ enforce_detection: bool = True,
+ align: bool = True,
+ expand_percentage: int = 0,
+ normalization: str = "base",
+ silent: bool = False,
+ threshold: Optional[float] = None,
+ anti_spoofing: bool = False,
) -> Dict[str, Any]:
"""
Verify if an image pair represents the same person or different persons.
@@ -164,14 +164,14 @@ def verify(
def analyze(
- img_path: Union[str, np.ndarray],
- actions: Union[tuple, list] = ("emotion", "age", "gender", "race"),
- enforce_detection: bool = True,
- detector_backend: str = "opencv",
- align: bool = True,
- expand_percentage: int = 0,
- silent: bool = False,
- anti_spoofing: bool = False,
+ img_path: Union[str, np.ndarray],
+ actions: Union[tuple, list] = ("emotion", "age", "gender", "race"),
+ enforce_detection: bool = True,
+ detector_backend: str = "opencv",
+ align: bool = True,
+ expand_percentage: int = 0,
+ silent: bool = False,
+ anti_spoofing: bool = False,
) -> List[Dict[str, Any]]:
"""
Analyze facial attributes such as age, gender, emotion, and race in the provided image.
@@ -263,20 +263,20 @@ def analyze(
def find(
- img_path: Union[str, np.ndarray],
- db_path: str,
- model_name: str = "VGG-Face",
- distance_metric: str = "cosine",
- 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,
- refresh_database: bool = True,
- anti_spoofing: bool = False,
- batched: bool = False,
+ img_path: Union[str, np.ndarray],
+ db_path: str,
+ model_name: str = "VGG-Face",
+ distance_metric: str = "cosine",
+ 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,
+ refresh_database: bool = True,
+ anti_spoofing: bool = False,
+ batched: bool = False,
) -> Union[List[pd.DataFrame], List[List[Dict[str, Any]]]]:
"""
Identify individuals in a database
@@ -369,15 +369,15 @@ def find(
def represent(
- img_path: Union[str, np.ndarray],
- model_name: str = "VGG-Face",
- enforce_detection: bool = True,
- detector_backend: str = "opencv",
- align: bool = True,
- expand_percentage: int = 0,
- normalization: str = "base",
- anti_spoofing: bool = False,
- max_faces: Optional[int] = None,
+ img_path: Union[str, np.ndarray],
+ model_name: str = "VGG-Face",
+ enforce_detection: bool = True,
+ detector_backend: str = "opencv",
+ align: bool = True,
+ expand_percentage: int = 0,
+ normalization: str = "base",
+ anti_spoofing: bool = False,
+ max_faces: Optional[int] = None,
) -> List[Dict[str, Any]]:
"""
Represent facial images as multi-dimensional vector embeddings.
@@ -441,15 +441,16 @@ def represent(
def stream(
- db_path: str = "",
- model_name: str = "VGG-Face",
- detector_backend: str = "opencv",
- distance_metric: str = "cosine",
- enable_face_analysis: bool = True,
- source: Any = 0,
- time_threshold: int = 5,
- frame_threshold: int = 5,
- anti_spoofing: bool = False,
+ db_path: str = "",
+ model_name: str = "VGG-Face",
+ detector_backend: str = "opencv",
+ distance_metric: str = "cosine",
+ enable_face_analysis: bool = True,
+ source: Any = 0,
+ time_threshold: int = 5,
+ frame_threshold: int = 5,
+ anti_spoofing: bool = False,
+ output_path: Optional[str] = None,
) -> None:
"""
Run real time face recognition and facial attribute analysis
@@ -478,6 +479,10 @@ def stream(
frame_threshold (int): The frame threshold for face recognition (default is 5).
anti_spoofing (boolean): Flag to enable anti spoofing (default is False).
+
+ output_path (str): Path to save the output video. (default is None
+ If None, no video is saved).
+
Returns:
None
"""
@@ -495,19 +500,20 @@ def stream(
time_threshold=time_threshold,
frame_threshold=frame_threshold,
anti_spoofing=anti_spoofing,
+ output_path=output_path,
)
def extract_faces(
- img_path: Union[str, np.ndarray],
- detector_backend: str = "opencv",
- enforce_detection: bool = True,
- align: bool = True,
- expand_percentage: int = 0,
- grayscale: bool = False,
- color_face: str = "rgb",
- normalize_face: bool = True,
- anti_spoofing: bool = False,
+ img_path: Union[str, np.ndarray],
+ detector_backend: str = "opencv",
+ enforce_detection: bool = True,
+ align: bool = True,
+ expand_percentage: int = 0,
+ grayscale: bool = False,
+ color_face: str = "rgb",
+ normalize_face: bool = True,
+ anti_spoofing: bool = False,
) -> List[Dict[str, Any]]:
"""
Extract faces from a given image
@@ -584,11 +590,11 @@ def cli() -> None:
def detectFace(
- img_path: Union[str, np.ndarray],
- target_size: tuple = (224, 224),
- detector_backend: str = "opencv",
- enforce_detection: bool = True,
- align: bool = True,
+ img_path: Union[str, np.ndarray],
+ target_size: tuple = (224, 224),
+ detector_backend: str = "opencv",
+ enforce_detection: bool = True,
+ align: bool = True,
) -> Union[np.ndarray, None]:
"""
Deprecated face detection function. Use extract_faces for same functionality.
diff --git a/deepface/modules/recognition.py b/deepface/modules/recognition.py
index 1edb430..f153132 100644
--- a/deepface/modules/recognition.py
+++ b/deepface/modules/recognition.py
@@ -149,7 +149,7 @@ def find(
# Ensure the proper pickle file exists
if not os.path.exists(datastore_path):
with open(datastore_path, "wb") as f:
- pickle.dump([], f)
+ pickle.dump([], f, pickle.HIGHEST_PROTOCOL)
# Load the representations from the pickle file
with open(datastore_path, "rb") as f:
@@ -232,7 +232,7 @@ def find(
if must_save_pickle:
with open(datastore_path, "wb") as f:
- pickle.dump(representations, f)
+ pickle.dump(representations, f, pickle.HIGHEST_PROTOCOL)
if not silent:
logger.info(f"There are now {len(representations)} representations in {file_name}")
diff --git a/deepface/modules/streaming.py b/deepface/modules/streaming.py
index cc44783..e461e56 100644
--- a/deepface/modules/streaming.py
+++ b/deepface/modules/streaming.py
@@ -22,6 +22,7 @@ os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
IDENTIFIED_IMG_SIZE = 112
TEXT_COLOR = (255, 255, 255)
+
# pylint: disable=unused-variable
def analysis(
db_path: str,
@@ -33,6 +34,7 @@ def analysis(
time_threshold=5,
frame_threshold=5,
anti_spoofing: bool = False,
+ output_path: Optional[str] = None,
):
"""
Run real time face recognition and facial attribute analysis
@@ -62,6 +64,8 @@ def analysis(
anti_spoofing (boolean): Flag to enable anti spoofing (default is False).
+ output_path (str): Path to save the output video. (default is None
+ If None, no video is saved).
Returns:
None
"""
@@ -77,12 +81,31 @@ def analysis(
model_name=model_name,
)
+ cap = cv2.VideoCapture(source if isinstance(source, str) else int(source))
+ if not cap.isOpened():
+ logger.error(f"Cannot open video source: {source}")
+ return
+
+ # Get video properties
+ width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+ height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+ fps = cap.get(cv2.CAP_PROP_FPS)
+ fourcc = cv2.VideoWriter_fourcc(*"mp4v") # Codec for output file
+ # Ensure the output directory exists if output_path is provided
+ if output_path:
+ os.makedirs(os.path.dirname(output_path), exist_ok=True)
+ # Initialize video writer if output_path is provided
+ video_writer = (
+ cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
+ if output_path
+ else None
+ )
+
freezed_img = None
freeze = False
num_frames_with_faces = 0
tic = time.time()
- cap = cv2.VideoCapture(source) # webcam
while True:
has_frame, img = cap.read()
if not has_frame:
@@ -91,9 +114,9 @@ def analysis(
# we are adding some figures into img such as identified facial image, age, gender
# that is why, we need raw image itself to make analysis
raw_img = img.copy()
-
faces_coordinates = []
- if freeze is False:
+
+ if not freeze:
faces_coordinates = grab_facial_areas(
img=img, detector_backend=detector_backend, anti_spoofing=anti_spoofing
)
@@ -101,7 +124,6 @@ def analysis(
# we will pass img to analyze modules (identity, demography) and add some illustrations
# that is why, we will not be able to extract detected face from img clearly
detected_faces = extract_facial_areas(img=img, faces_coordinates=faces_coordinates)
-
img = highlight_facial_areas(img=img, faces_coordinates=faces_coordinates)
img = countdown_to_freeze(
img=img,
@@ -111,8 +133,8 @@ def analysis(
)
num_frames_with_faces = num_frames_with_faces + 1 if len(faces_coordinates) else 0
-
freeze = num_frames_with_faces > 0 and num_frames_with_faces % frame_threshold == 0
+
if freeze:
# add analyze results into img - derive from raw_img
img = highlight_facial_areas(
@@ -144,22 +166,28 @@ def analysis(
tic = time.time()
logger.info("freezed")
- elif freeze is True and time.time() - tic > time_threshold:
+ elif freeze and time.time() - tic > time_threshold:
freeze = False
freezed_img = None
# reset counter for freezing
tic = time.time()
- logger.info("freeze released")
+ logger.info("Freeze released")
freezed_img = countdown_to_release(img=freezed_img, tic=tic, time_threshold=time_threshold)
+ display_img = img if freezed_img is None else freezed_img
- cv2.imshow("img", img if freezed_img is None else freezed_img)
+ # Save the frame to output video if writer is initialized
+ if video_writer:
+ video_writer.write(display_img)
- if cv2.waitKey(1) & 0xFF == ord("q"): # press q to quit
+ cv2.imshow("img", display_img)
+ if cv2.waitKey(1) & 0xFF == ord("q"):
break
- # kill open cv things
+ # Release resources
cap.release()
+ if video_writer:
+ video_writer.release()
cv2.destroyAllWindows()
+