fix: enhance OCR text matching criteria for improved accuracy in predictions

mineru/backend/pipeline/batch_analyze.py

@@ -440,7 +440,7 @@ class BatchAnalyze:
                                                layout_res_item['poly'][4], layout_res_item['poly'][5]]
                             layout_res_width = layout_res_bbox[2] - layout_res_bbox[0]
                             layout_res_height = layout_res_bbox[3] - layout_res_bbox[1]
-                            if ocr_text in ['（204号', '（20', '（2', '（2号', '（20号'] and ocr_score < 0.8 and layout_res_width < layout_res_height:
+                            if ocr_text in ['（204号', '（20', '（2', '（2号', '（20号', '号', '（204'] and ocr_score < 0.8 and layout_res_width < layout_res_height:
                                 layout_res_item['category_id'] = 16
 
                     total_processed += len(img_crop_list)

mineru/model/table/rec/unet_table/main.py

@@ -219,7 +219,7 @@ class WiredTableRecognition:
                 # 处理ocr结果
                 ocr_text, ocr_score = ocr_res
                 # logger.debug(f"OCR result for box {i}: {ocr_text} with score {ocr_score}")
-                if ocr_score < 0.6 or ocr_text in ['1','口','■','（204号', '（20', '（2', '（2号', '（20号']:
+                if ocr_score < 0.6 or ocr_text in ['1','口','■','（204号', '（20', '（2', '（2号', '（20号', '号', '（204']:
                     # logger.warning(f"Low confidence OCR result for box {i}: {ocr_text} with score {ocr_score}")
                     box = sorted_polygons[i]
                     cell_box_map[i] = [[box, "", 0.1]]