From 8ace9df86af13cb299fe551f7dcae25f11687bee Mon Sep 17 00:00:00 2001
From: Viajero <2737079298@qq.com>
Date: Tue, 16 Sep 2025 11:15:06 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=E6=8E=A5=E5=8F=A3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 OCR_part/ocr_interface.py | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/OCR_part/ocr_interface.py b/OCR_part/ocr_interface.py
index b98c5b8..75770c0 100644
--- a/OCR_part/ocr_interface.py
+++ b/OCR_part/ocr_interface.py
@@ -5,6 +5,18 @@ import cv2
 class OCRProcessor:
     def __init__(self):
         self.model = TextRecognition(model_name="PP-OCRv5_server_rec")
+        # 定义允许的字符集合（不包含空白字符）
+        self.allowed_chars = [
+            # 中文省份简称
+            '京', '沪', '津', '渝', '冀', '晋', '蒙', '辽', '吉', '黑',
+            '苏', '浙', '皖', '闽', '赣', '鲁', '豫', '鄂', '湘', '粤',
+            '桂', '琼', '川', '贵', '云', '藏', '陕', '甘', '青', '宁', '新',
+            # 字母 A-Z
+            'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 
+            'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
+            # 数字 0-9
+            '0', '1', '2', '3', '4', '5', '6', '7', '8', '9'
+        ]
         print("OCR模型初始化完成（占位）")
 
     def predict(self, image_array):
@@ -14,6 +26,14 @@ class OCRProcessor:
         results = output[0]["rec_text"]
         placeholder_result = results.split(',')
         return placeholder_result
+    
+    def filter_allowed_chars(self, text):
+        """只保留允许的字符"""
+        filtered_text = ""
+        for char in text:
+            if char in self.allowed_chars:
+                filtered_text += char
+        return filtered_text
 
 # 保留原有函数接口
 _processor = OCRProcessor()
@@ -42,8 +62,12 @@ def LPRNmodel_predict(image_array):
     else:
         result_str = str(raw_result)
     
-    # 过滤掉'·'字符
+    # 过滤掉'·'和'-'字符
     filtered_str = result_str.replace('·', '')
+    filtered_str = filtered_str.replace('-', '')
+    
+    # 只保留允许的字符
+    filtered_str = _processor.filter_allowed_chars(filtered_str)
     
     # 转换为字符列表
     char_list = list(filtered_str)