Update app.py

app.py

@@ -1,20 +1,31 @@
-import computervision
+import cv2
+import numpy as np
+from PIL import Image
+import gradio as gr
 
-# Load the cascade classifier for face detection
-face_cascade = computervision.CascadeClassifier('haarcascade_frontalface_alt.xml')
+def detect_faces(image):
+    # OpenCV를 사용하여 이미지를 배열로 변환
+    open_cv_image = np.array(image)
+    # OpenCV에서 사용하는 색상 순서는 RGB가 아닌 BGR이므로 변환
+    open_cv_image = open_cv_image[:, :, ::-1].copy()
 
-# Load the input image
-img = computervision.Image('input_image.jpg')
+    # 사전 훈련된 얼굴 인식 분류기 로드
+    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
 
-# Convert the image to grayscale
-gray = img.convert_to_grayscale()
+    # 이미지를 회색조로 변환
+    gray = cv2.cvtColor(open_cv_image, cv2.COLOR_BGR2GRAY)
 
-# Detect faces in the grayscale image using the Haar cascade
-faces = face_cascade.detect_multi_scale(gray, scale_factor=1.1, min_neighbors=5, min_size=(30, 30))
+    # 얼굴 감지
+    faces = face_cascade.detectMultiScale(gray, 1.1, 4)
 
-# Draw rectangles around the detected faces
-for (x, y, w, h) in faces:
-    img.draw_rectangle((x, y), (x+w, y+h), fill=(0, 255, 0))
+    # 감지된 얼굴 주위에 사각형 그리기
+    for (x, y, w, h) in faces:
+        cv2.rectangle(open_cv_image, (x, y), (x+w, y+h), (255, 0, 0), 2)
 
-# Display the output image with the detected faces
-img.show()
+    # OpenCV에서 사용한 BGR 이미지를 PIL 이미지로 변환
+    return Image.fromarray(open_cv_image[:, :, ::-1])
+
+iface = gr.Interface(fn=detect_faces, inputs=gr.inputs.Image(), outputs="image", title="얼굴 감지", description="이미지를 업로드하면 얼굴에 사각형을 그립니다.")
+
+if __name__ == "__main__":
+    iface.launch()