Update app.py

app.py

@@ -182,33 +182,33 @@ transform = transforms.Compose([
 
 def predict_image(image):
     """
-    处理上传的图片并返回预测结果
+    Process uploaded image and return prediction result
     """
     if image is None:
-        return "请上传图片"
+        return "Please upload an image"
     
-    # 转换图片格式
+    # Convert image format
     if isinstance(image, np.ndarray):
         image = Image.fromarray(image)
     
-    # 应用转换
+    # Apply transformations
     image_tensor = transform(image).unsqueeze(0)
     
-    # 准备特征提取用的图像
+    # Prepare image for feature extraction
     np_image = image_tensor.cpu().numpy().squeeze(0).transpose(1, 2, 0)
     np_image = np.clip(np_image, 0, 1)
     
-    # 转换为灰度图
+    # Convert to grayscale
     gray_image = cv2.cvtColor((np_image * 255).astype(np.uint8), cv2.COLOR_RGB2GRAY)
     gray_image = gray_image.astype(np.float32) / 255.0
     
-    # 提取特征
+    # Extract features
     glcm_features = extract_glcm_features(gray_image)
     spectrum_features = analyze_spectrum(gray_image)
     edge_features = extract_edge_features(gray_image)
     lbp_features = extract_lbp_features(gray_image)
     
-    # 转换为张量并移到设备
+    # Convert to tensors and move to device
     with torch.no_grad():
         image_tensor = image_tensor.to(device)
         glcm_features = torch.from_numpy(glcm_features).unsqueeze(0).to(device)
@@ -216,27 +216,32 @@ def predict_image(image):
         edge_features = torch.from_numpy(edge_features).unsqueeze(0).to(device)
         lbp_features = torch.from_numpy(lbp_features).unsqueeze(0).to(device)
         
-        # 模型预测
+        # Model prediction
         outputs = model(image_tensor, glcm_features, spectrum_features, edge_features, lbp_features)
         prediction = torch.sigmoid(outputs).item()
         
-        # 返回预测结果
-        if prediction > 0.5:
-            return "真实人脸图片"
+        # Return prediction result (corrected logic)
+        if prediction < 0.5:  # Changed from > to <
+            return "Real Face"
         else:
-            return "虚假人脸图片"
+            return "AI-Generated Face"
 
-# 创建Gradio界面
+# Create Gradio interface
 iface = gr.Interface(
     fn=predict_image,
     inputs=gr.Image(type="pil"),
-    outputs=gr.Text(label="预测结果"),
-    title="人脸真伪检测",
-    description="上传一张人脸图片，模型将判断是真实人脸还是虚假人脸。",
+    outputs=gr.Text(label="Prediction Result"),
+    title="Face Authentication System",
+    description="Upload a face image to determine if it's a real face or an AI-generated face.",
     examples=[
-        # 这里可以添加示例图片路径
-    ]
+        # Add example image paths here
+    ],
+    article="""
+    This system uses advanced deep learning techniques to detect whether a face image is real or AI-generated.
+    The model analyzes various image features including texture patterns, frequency spectrum, and local binary patterns
+    to make its determination.
+    """
 )
 
-# 启动应用
+# Launch the application
 iface.launch()