Update app.py

app.py

@@ -534,6 +534,7 @@ def analyze_clothing_details(image):
             
             # 计算纹理变化的熵 - 真实衣物纹理变化的熵更高
             features["clothing_texture_entropy"] = float(stats.entropy(texture_variations + 1e-10))
+        
  # 褶皱分析 - 使用形态学操作提取可能的褶皱
         _, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
         kernel = np.ones((3,3), np.uint8)
@@ -661,19 +662,19 @@ def check_ai_specific_features(image_features):
     # 增加对微观纹理的分析权重
     if "lbp_entropy" in image_features:
         if image_features["lbp_entropy"] < 2.0:
-            ai_score += 0.3  # 提高权重
+            ai_score += 0.4  # 提高权重
             ai_signs.append("微观纹理熵极低，典型AI生成特征")
         elif image_features["lbp_entropy"] < 3.0:
-            ai_score += 0.2
+            ai_score += 0.3
             ai_signs.append("微观纹理熵异常低")
     
     # 增加对频率分布各向异性的分析权重
     if "freq_anisotropy" in image_features:
         if image_features["freq_anisotropy"] < 0.05:
-            ai_score += 0.3  # 提高权重
+            ai_score += 0.4  # 提高权重
             ai_signs.append("频率分布各向异性极低，典型AI生成特征")
         elif image_features["freq_anisotropy"] < 0.5:
-            ai_score += 0.2
+            ai_score += 0.3
             ai_signs.append("频率分布各向异性异常低")
     
     # 增加对细节一致性的分析
@@ -960,8 +961,8 @@ def detect_photoshop_signs(image_features):
     
     return min(ps_score, 1.0), ps_signs
 
-def get_detailed_analysis(ai_probability, ps_score, beauty_score, ps_signs, ai_signs, beauty_signs, valid_models_count):
-    """提供更详细的分析结果，使用二级分类框架"""
+def get_detailed_analysis(ai_probability, ps_score, beauty_score, ps_signs, ai_signs, beauty_signs, valid_models_count, ai_feature_score):
+    """提供更详细的分析结果，使用二级分类框架，优先考虑AI特征分析"""
     
     # 根据有效模型数量调整置信度描述
     confidence_prefix = ""
@@ -972,6 +973,25 @@ def get_detailed_analysis(ai_probability, ps_score, beauty_score, ps_signs, ai_s
     elif valid_models_count == 1:
         confidence_prefix = "中等置信度："
     
+    # 特征与模型判断严重不一致时的处理
+    if ai_feature_score > 0.8 and ai_probability < 0.6:
+        ai_probability = max(0.8, ai_probability)  # 当AI特征分数非常高时，覆盖模型判断
+        category = confidence_prefix + "AI生成图像（基于特征分析）"
+        description = "基于多种典型AI特征分析，该图像很可能是AI生成的，尽管模型判断结果不确定。"
+        main_category = "AI生成"
+    elif ai_feature_score > 0.6 and ai_probability < 0.5:
+        ai_probability = max(0.7, ai_probability)  # 当AI特征分数高时，提高AI概率
+    
+    # 特定关键特征的硬性覆盖
+    if "lbp_entropy" in image_features and image_features["lbp_entropy"] < 2.0:
+        if "freq_anisotropy" in image_features and image_features["freq_anisotropy"] < 0.05:
+            # 当微观纹理熵极低且频率分布各向异性极低时，几乎可以确定是AI生成
+            ai_probability = 0.95
+            category = confidence_prefix + "AI生成图像（确定）"
+            description = "检测到多个决定性AI生成特征，该图像几乎可以确定是AI生成的。"
+            main_category = "AI生成"
+            return category, description, ps_details, ai_details, beauty_details, main_category
+    
     # 第一级分类：AI生成 vs 真人照片
     if ai_probability > 0.6:  # 降低AI判定阈值，提高AI检出率
         category = confidence_prefix + "AI生成图像"
@@ -1026,7 +1046,7 @@ def detect_ai_image(image):
     valid_models = 0
     weighted_ai_probability = 0
     
-    # 使用每个模型进行预测
+# 使用每个模型进行预测
     for key, model_info in models.items():
         if model_info["processor"] is not None and model_info["model"] is not None:
             try:
@@ -1064,7 +1084,8 @@ def detect_ai_image(image):
         final_ai_probability = weighted_ai_probability / sum(m["weight"] for k, m in models.items() if m["processor"] is not None and m["model"] is not None)
     else:
         return {"error": "所有模型加载失败"}
- # 分析图像特征
+    
+    # 分析图像特征
     image_features = analyze_image_features(image)
     
     # 检查AI特定特征
@@ -1125,19 +1146,11 @@ def detect_ai_image(image):
     # 确保概率在0-1范围内
     adjusted_probability = min(1.0, max(0.0, adjusted_probability))
     
-    # 如果umm-maybe/AI-image-detector模型的预测与其他模型不一致，增加其权重
-    if "model1" in results and "ai_probability" in results["model1"]:
-        ai_detector_prob = results["model1"]["ai_probability"]
-        # 如果专用AI检测器给出的概率与调整后概率差异大，增加其权重
-        if abs(ai_detector_prob - adjusted_probability) > 0.3:
-            adjusted_probability = (adjusted_probability + ai_detector_prob * 2) / 3
-    
     # 获取详细分析
     category, description, ps_details, ai_details, beauty_details, main_category = get_detailed_analysis(
-        adjusted_probability, ps_score, beauty_score, ps_signs, ai_signs, beauty_signs, valid_models
+        adjusted_probability, ps_score, beauty_score, ps_signs, ai_signs, beauty_signs, valid_models, ai_feature_score
     )
     
-    # 构建最终结果
     # 构建最终结果
     final_result = {
         "ai_probability": adjusted_probability,
@@ -1155,10 +1168,8 @@ def detect_ai_image(image):
         "features": image_features
     }
     
-    # 为Label组件准备数据
-    label_data = {main_category: 1.0}
-    
     # 返回两个值：JSON结果和Label数据
+    label_data = {main_category: 1.0}
     return final_result, label_data
 
 # 创建Gradio界面