Adding face detection to opencv space

README.md

@@ -7,6 +7,11 @@ sdk: gradio
 sdk_version: 5.34.1
 app_file: app.py
 pinned: false
+short_description: Face detection using OpenCV YuNet ONNX model with Gradio UI
+tags:
+  - opencv
+  - face-detection
+  - yunet
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,62 @@
+import cv2 as cv
+import numpy as np
+import gradio as gr
+from yunet import YuNet
+from huggingface_hub import hf_hub_download
+
+# Download ONNX model from Hugging Face
+model_path = hf_hub_download(repo_id="opencv/face_detection_yunet", filename="face_detection_yunet_2023mar.onnx")
+
+# Initialize YuNet model
+model = YuNet(
+    modelPath=model_path,
+    inputSize=[320, 320],
+    confThreshold=0.9,
+    nmsThreshold=0.3,
+    topK=5000,
+    backendId=cv.dnn.DNN_BACKEND_OPENCV,
+    targetId=cv.dnn.DNN_TARGET_CPU
+)
+
+def visualize(image, results, box_color=(0, 255, 0), text_color=(0, 0, 255)):
+    output = image.copy()
+    landmark_color = [
+        (255,   0,   0), # right eye
+        (  0,   0, 255), # left eye
+        (  0, 255,   0), # nose tip
+        (255,   0, 255), # right mouth corner
+        (  0, 255, 255)  # left mouth corner
+    ]
+
+    for det in results:
+        bbox = det[0:4].astype(np.int32)
+        cv.rectangle(output, (bbox[0], bbox[1]), (bbox[0]+bbox[2], bbox[1]+bbox[3]), box_color, 2)
+        conf = det[-1]
+        cv.putText(output, '{:.2f}'.format(conf), (bbox[0], bbox[1] + 12), cv.FONT_HERSHEY_SIMPLEX, 0.5, text_color)
+
+        landmarks = det[4:14].astype(np.int32).reshape((5, 2))
+        for idx, landmark in enumerate(landmarks):
+            cv.circle(output, tuple(landmark), 2, landmark_color[idx], 2)
+
+    return output
+
+def detect_faces(input_image):
+    h, w, _ = input_image.shape
+    model.setInputSize([w, h])
+    results = model.infer(input_image)
+    if results is None or len(results) == 0:
+        return input_image
+    return visualize(input_image, results)
+
+# Gradio Interface
+demo = gr.Interface(
+    fn=detect_faces,
+    inputs=gr.Image(type="numpy", label="Upload Image"),
+    outputs=gr.Image(type="numpy", label="Detected Faces"),
+    title="Face Detection YuNet (OpenCV DNN)",
+    allow_flagging="never",
+    description="Upload an image to detect faces using OpenCV's ONNX-based YuNet face detector."
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+opencv-python
+gradio
+numpy
+huggingface_hub

yunet.py

@@ -0,0 +1,55 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+from itertools import product
+
+import numpy as np
+import cv2 as cv
+
+class YuNet:
+    def __init__(self, modelPath, inputSize=[320, 320], confThreshold=0.6, nmsThreshold=0.3, topK=5000, backendId=0, targetId=0):
+        self._modelPath = modelPath
+        self._inputSize = tuple(inputSize) # [w, h]
+        self._confThreshold = confThreshold
+        self._nmsThreshold = nmsThreshold
+        self._topK = topK
+        self._backendId = backendId
+        self._targetId = targetId
+
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackendAndTarget(self, backendId, targetId):
+        self._backendId = backendId
+        self._targetId = targetId
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    def setInputSize(self, input_size):
+        self._model.setInputSize(tuple(input_size))
+
+    def infer(self, image):
+        # Forward
+        faces = self._model.detect(image)
+        return np.empty(shape=(0, 5)) if faces[1] is None else faces[1]