Update app.py

app.py

@@ -386,26 +386,26 @@ class ImageProcessor:
 
 
     def process_image(self, image, threshold=0.5, testsize=256, 
-                     enhance_contrast=False, denoise=False, 
-                     brightness=0, contrast=0, filter_type="无",
-                     process_mode="完整分析"):
-        """增强的图像处理函数"""
-        if image is None:
-            return [None] * 9 + ["请提供有效的图像"]
-
-        # 快速模式检查
-        if process_mode == "快速模式":
-            saliency_map, time_info = self.quick_process(image, threshold, testsize)
-            return (image, saliency_map, None, None, None, None, time_info, None, None)
-
-        # 检查完整处理的缓存
-        image_hash = hash(image.tobytes())
-        cache_key = f"{image_hash}_{threshold}_{testsize}_{enhance_contrast}_{denoise}_{brightness}_{contrast}_{filter_type}_full"
-        
-        if cache_key in self.cache:
-            return self.cache[cache_key]
+                 enhance_contrast=False, denoise=False, 
+                 brightness=0, contrast=0, filter_type="无",
+                 process_mode="完整分析"):
+    """增强的图像处理函数"""
+    if image is None:
+        return [None] * 9 + ["请提供有效的图像"]
+
+    # 快速模式检查
+    if process_mode == "快速模式":
+        saliency_map, time_info = self.quick_process(image, threshold, testsize)
+        return (image, saliency_map, None, None, None, None, time_info, None, None)
+
+    # 检查完整处理的缓存
+    image_hash = hash(image.tobytes())
+    cache_key = f"{image_hash}_{threshold}_{testsize}_{enhance_contrast}_{denoise}_{brightness}_{contrast}_{filter_type}_full"
+    
+    if cache_key in self.cache:
+        return self.cache[cache_key]
 
-        # 使用线程进行图像预处理
+    # 使用线程进行图像预处理
         def preprocess_image():
             processed_image = image.copy()
             
@@ -424,11 +424,11 @@ class ImageProcessor:
                 processed_image = cv2.cvtColor(lab, cv2.COLOR_LAB2RGB)
             
             return processed_image
-
+    
         with concurrent.futures.ThreadPoolExecutor() as executor:
             future_preprocess = executor.submit(preprocess_image)
             processed_image = future_preprocess.result()
-
+    
         original_image = processed_image.copy()
         
         # 模型推理
@@ -448,7 +448,7 @@ class ImageProcessor:
         
         time_end = time.time()
         inference_time = time_end - time_start
-
+        
         # 确保转换为float32类型并保持原始显著性值
         res = res.to(torch.float32).sigmoid().cpu().numpy().squeeze()
         
@@ -480,7 +480,7 @@ class ImageProcessor:
         heatmap_rgb = cv2.cvtColor(heatmap, cv2.COLOR_BGR2RGB)
         
         # 使用原始显著性值生成分析图表
-        analysis_plot = self.generate_analysis_plots(res_resized_original)  # 使用未归一化的原始值
+        analysis_plot = self.generate_analysis_plots(res_resized_original)
         
         # 计算统计信息
         contours = cv2.findContours(binary_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
@@ -491,8 +491,8 @@ class ImageProcessor:
         stats = {
             "处理分辨率": f"{w}x{h}",
             "检测到对象数": str(len(contours)),
-            "平均置信度": f"{np.mean(res_resized_original):.2%}",  # 使用原始值
-            "最大置信度": f"{np.max(res_resized_original):.2%}",   # 使用原始值
+            "平均置信度": f"{np.mean(res_resized_original):.2%}",
+            "最大置信度": f"{np.max(res_resized_original):.2%}",
             "覆盖率": f"{coverage_ratio:.2%}",
             "处理时间": f"{inference_time:.3f}秒"
         }
@@ -502,7 +502,7 @@ class ImageProcessor:
         
         # 保存结果
         self.last_results = {
-            'saliency_map': res_resized,
+            'saliency_map': res_resized_original,  # 使用原始值
             'binary_mask': binary_mask,
             'stats': stats
         }