Update app.py

app.py

@@ -38,10 +38,6 @@ for key in models:
         models[key]["processor"] = None
         models[key]["model"] = None
 
-
-## 第二部分：模型输出处理
-
-
 def process_model_output(model_info, outputs, probabilities):
     """处理不同模型的输出，统一返回AI生成概率"""
     model_name = model_info["name"].lower()
@@ -112,10 +108,6 @@ def process_model_output(model_info, outputs, probabilities):
     
     return ai_probability
 
-
-## 第三部分：图像特征分析
-
-
 def analyze_image_features(image):
     """分析图像特征"""
     # 转换为OpenCV格式
@@ -268,6 +260,14 @@ def analyze_image_features(image):
         # 如果人脸检测失败，不添加人脸特征
         pass
     
+    # 分析衣物细节
+    clothing_features = analyze_clothing_details(img_cv)
+    features.update(clothing_features)
+    
+    # 分析手部和关节
+    extremity_features = analyze_extremities(img_cv)
+    features.update(extremity_features)
+    
     return features
 
 def analyze_face_symmetry(face):
@@ -279,9 +279,122 @@ def analyze_face_symmetry(face):
             return 1 - float(np.mean(cv2.absdiff(left_half, right_half)) / 255)
     return 0.5  # 默认值
 
+def analyze_clothing_details(image):
+    """分析衣物细节的自然度"""
+    features = {}
+    
+    try:
+        # 转换为灰度图
+        if len(image.shape) == 3:
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        else:
+            gray = image
+            
+        # 使用Canny边缘检测
+        edges = cv2.Canny(gray, 50, 150)
+        
+        # 使用霍夫变换检测直线
+        lines = cv2.HoughLinesP(edges, 1, np.pi/180, threshold=50, minLineLength=50, maxLineGap=10)
+        
+        if lines is not None:
+            # 计算直线的角度分布
+            angles = []
+            for line in lines:
+                x1, y1, x2, y2 = line[0]
+                if x2 - x1 != 0:  # 避免除以零
+                    angle = np.arctan((y2 - y1) / (x2 - x1)) * 180 / np.pi
+                    angles.append(angle)
+            
+            if angles:
+                # 计算角度的标准差 - AI生成的衣物褶皱通常角度分布不自然
+                features["clothing_angle_std"] = float(np.std(angles))
+                
+                # 计算角度的直方图 - 检查是否有过多相似角度（AI生成特征）
+                hist, _ = np.histogram(angles, bins=18, range=(-90, 90))
+                max_count = np.max(hist)
+                total_count = np.sum(hist)
+                features["clothing_angle_uniformity"] = float(max_count / max(total_count, 1))
+        
+        # 分析纹理的一致性
+        # 将图像分成小块，计算每个块的纹理特征
+        block_size = 32
+        h, w = gray.shape
+        texture_variations = []
+        
+        for i in range(0, h-block_size, block_size):
+            for j in range(0, w-block_size, block_size):
+                block = gray[i:i+block_size, j:j+block_size]
+                # 计算局部LBP特征或简单的方差
+                texture_variations.append(np.var(block))
+        
+        if texture_variations:
+            # 计算纹理变化的标准差 - 真实衣物纹理变化更自然
+            features["clothing_texture_std"] = float(np.std(texture_variations))
+            
+            # 计算纹理变化的均值 - AI生成的衣物纹理通常变化较小
+            features["clothing_texture_mean"] = float(np.mean(texture_variations))
+    except:
+        # 如果分析失败，不添加衣物特征
+        pass
+    
+    return features
 
-## 第四部分：特征检测函数
-
+def analyze_extremities(image):
+    """分析手指、脚趾等末端细节"""
+    features = {}
+    
+    try:
+        # 转换为灰度图
+        if len(image.shape) == 3:
+            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        else:
+            gray = image
+        
+        # 使用形态学操作提取可能的手部区域
+        _, thresh = cv2.threshold(gray, 120, 255, cv2.THRESH_BINARY)
+        kernel = np.ones((5,5), np.uint8)
+        opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
+        
+        # 寻找轮廓
+        contours, _ = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        
+        # 分析轮廓的复杂度
+        if contours:
+            # 计算轮廓的周长与面积比 - 手指等细节会增加这个比值
+            perimeter_area_ratios = []
+            for contour in contours:
+                area = cv2.contourArea(contour)
+                if area > 100:  # 忽略太小的轮廓
+                    perimeter = cv2.arcLength(contour, True)
+                    ratio = perimeter / max(area, 1)
+                    perimeter_area_ratios.append(ratio)
+            
+            if perimeter_area_ratios:
+                features["extremity_perimeter_area_ratio"] = float(np.mean(perimeter_area_ratios))
+                
+                # 计算凸包缺陷 - 手指之间的间隙���产生凸包缺陷
+                defect_depths = []
+                for contour in contours:
+                    if len(contour) > 5:  # 需要足够多的点来计算凸包
+                        hull = cv2.convexHull(contour, returnPoints=False)
+                        if len(hull) > 3:  # 需要至少4个点来计算凸包缺陷
+                            try:
+                                defects = cv2.convexityDefects(contour, hull)
+                                if defects is not None:
+                                    for i in range(defects.shape[0]):
+                                        _, _, _, depth = defects[i, 0]
+                                        defect_depths.append(depth)
+                            except:
+                                pass
+                
+                if defect_depths:
+                    features["extremity_defect_depth_mean"] = float(np.mean(defect_depths))
+                    features["extremity_defect_depth_std"] = float(np.std(defect_depths))
+    except:
+        # 如果分析失败，不添加末端特征
+        pass
+    
+    return features
 
 def check_ai_specific_features(image_features):
     """检查AI生成图像的典型特征"""
@@ -354,6 +467,25 @@ def check_ai_specific_features(image_features):
         ai_score += 0.3
         ai_signs.append("皮肤质感异常均匀")
     
+    # 检查衣物特征 - AI生成的衣物通常有特定问题
+    if "clothing_angle_uniformity" in image_features and image_features["clothing_angle_uniformity"] > 0.3:
+        ai_score += 0.3
+        ai_signs.append("衣物褶皱角度分布不自然")
+    
+    if "clothing_texture_std" in image_features and image_features["clothing_texture_std"] < 100:
+        ai_score += 0.2
+        ai_signs.append("衣物纹理变化异常均匀")
+    
+    # 检查手部特征 - AI生成的手部通常有特定问题
+    if "extremity_perimeter_area_ratio" in image_features:
+        if image_features["extremity_perimeter_area_ratio"] < 0.05:
+            ai_score += 0.3
+            ai_signs.append("手部/末端轮廓异常平滑")
+    
+    if "extremity_defect_depth_std" in image_features and image_features["extremity_defect_depth_std"] < 10:
+        ai_score += 0.2
+        ai_signs.append("手指间隙异常均匀")
+    
     return min(ai_score, 1.0), ai_signs
 
 def detect_beauty_filter_signs(image_features):
@@ -418,8 +550,7 @@ def detect_photoshop_signs(image_features):
         elif image_features["texture_homogeneity"] > 0.3:
             ps_score += 0.1
             ps_signs.append("皮肤质感较为均匀")
-    
-    # 检查边缘不自然
+# 检查边缘不自然
     if "edge_density" in image_features:
         if image_features["edge_density"] < 0.01:
             ps_score += 0.2
@@ -458,10 +589,6 @@ def detect_photoshop_signs(image_features):
     
     return min(ps_score, 1.0), ps_signs
 
-
-## 第五部分：结果分析与分类
-
-
 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"""
     
@@ -474,7 +601,7 @@ 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："
     
-    # 调整后的阈值判断，考虑美颜因素
+    # 调整后的阈值判断，考虑美颜因素和衣物细节
     if ai_probability > 0.7:  # 高AI概率
         category = confidence_prefix + "高概率AI生成"
         description = "图像很可能是由AI完全生成，几乎没有真人照片的特征。"
@@ -535,8 +662,6 @@ def get_detailed_analysis(ai_probability, ps_score, beauty_score, ps_signs, ai_s
     
     return category, description, ps_details, ai_details, beauty_details
 
-
-## 第六部分：主检测函数
 def detect_ai_image(image):
     """主检测函数"""
     if image is None:
@@ -608,6 +733,13 @@ def detect_ai_image(image):
     elif ai_feature_score > 0.3:
         adjusted_probability = max(adjusted_probability, 0.5)
     
+    # 如果检测到衣物或手部异常，大幅提高AI概率
+    if "clothing_angle_uniformity" in image_features and image_features["clothing_angle_uniformity"] > 0.3:
+        adjusted_probability = max(adjusted_probability, 0.7)
+    
+    if "extremity_perimeter_area_ratio" in image_features and image_features["extremity_perimeter_area_ratio"] < 0.05:
+        adjusted_probability = max(adjusted_probability, 0.7)
+    
     # 如果美颜分数高但AI特征分数不高，降低AI概率
     if beauty_score > 0.6 and ai_feature_score < 0.5:
         adjusted_probability = min(adjusted_probability, 0.5)
@@ -663,21 +795,15 @@ def detect_ai_image(image):
     
     return final_result
 
-
-## 第七部分：Gradio界面
-
-
 # 创建Gradio界面
 iface = gr.Interface(
     fn=detect_ai_image,
     inputs=gr.Image(type="pil"),
     outputs=gr.JSON(),
     title="增强型AI图像检测API",
-    description="多模型集成检测图像是否由AI生成，同时分析PS修图和美颜痕迹",
+    description="多模型集成检测图像是否由AI生成，同时分析PS修图和美颜痕迹，特别关注衣物和手部等细节问题",
     examples=None,
     allow_flagging="never"
 )
 
 iface.launch()
-
-