'commit'

Apps/AiTeJiYiChong/ReadImageKit.py

@@ -7,6 +7,7 @@ import json
 import aiohttp
 import logging
 import base64
+import cv2
 from openai import AsyncOpenAI, BadRequestError
 from Config.Config import (
     ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD
@@ -15,6 +16,8 @@ from Apps.AiTeJiYiChong.Config.Setting import (
     SAFE_EXCLUDE_RATIO, FALLBACK_WIDTH, FALLBACK_HEIGHT,
     BOTTOM_SAFE_EXCLUDE_RATIO
 )
+from Util.PaddleOCRKit import get_ocr_kit
+from Apps.AiTeJiYiChong import Kit
 
 logger = logging.getLogger(__name__)
 
@@ -287,6 +290,65 @@ class ReadImageKit:
             logger.error(f"Error calling VL model for detail: {e}")
             return None
 
+    @classmethod
+    async def get_stations_hybrid(cls, image_path: str, device_info=None):
+        """
+        混合识别模式：图形学切片 + 本地 PaddleOCR 识别
+        """
+        if not os.path.exists(image_path):
+            logger.error(f"Image not found: {image_path}")
+            return []
+
+        # 1. 使用 Kit 中的图形学算法识别卡片区域
+        # Kit.crop_cards_from_image 会生成 .json, _flag.jpg, _vl.jpg
+        # 我们主要需要它返回的 json_data
+        json_data = Kit.crop_cards_from_image(image_path, save_debug=True)
+        if not json_data or not json_data.get("cards"):
+            logger.warning("No cards detected by graphical slicing.")
+            return []
+
+        img = Image.open(image_path).convert("RGB")
+        ocr_kit = get_ocr_kit()
+        
+        final_stations = []
+        
+        # 2. 对每个卡片区域进行 OCR 识别
+        # 注意：PaddleOCR 识别过程较快，且通常不涉及网络请求，可以根据需要选择并行或串行
+        # 这里使用串行以保证日志输出整齐，如果追求极致性能可改用 asyncio.to_thread 并行
+        for card in json_data["cards"]:
+            rect = card["rect"] # [x1, y1, x2, y2]
+            # 裁剪卡片
+            patch = img.crop((rect[0], rect[1], rect[2], rect[3]))
+            
+            # 转换为 ndarray 供 PaddleOCR 使用
+            patch_cv = cv2.cvtColor(np.array(patch), cv2.COLOR_RGB2BGR)
+            
+            # OCR 识别
+            logger.info(f"正在识别卡片 {card['id']}: {rect}")
+            res = ocr_kit.recognize(patch_cv)
+            
+            if res and res.get("station_name"):
+                # 注入点击坐标和原始区域信息
+                res["uia_center_x"] = card["click_point"][0]
+                res["uia_center_y"] = card["click_point"][1]
+                res["rect"] = rect
+                
+                # 转换 bounds 到 0-1000 空间（保持与 VL 模式兼容）
+                w, h = img.size
+                res["bounds"] = [
+                    int(rect[0] * 1000 / w),
+                    int(rect[1] * 1000 / h),
+                    int(rect[2] * 1000 / w),
+                    int(rect[3] * 1000 / h)
+                ]
+                
+                final_stations.append(res)
+                logger.info(f"卡片 {card['id']} 识别成功: {res['station_name']}")
+            else:
+                logger.warning(f"卡片 {card['id']} 识别失败或无名称")
+
+        return final_stations
+
     @classmethod
     async def get_stations_from_image(cls, image_path: str, device_info=None):
         """