| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303 |
- # OCR验证工具配置文件
- # 样式配置
- styles:
- font_size: 8
-
- colors:
- primary: "#0288d1"
- secondary: "#ff9800"
- success: "#4caf50"
- error: "#f44336"
- warning: "#ff9800"
- background: "#fafafa"
- text: "#333333"
-
- layout:
- default_zoom: 1.0
- default_height: 800
- sidebar_width: 1
- content_width: 0.65
- # 界面配置
- ui:
- page_title: "OCR可视化校验工具"
- page_icon: "🔍"
- layout: "wide"
- sidebar_state: "expanded"
-
- # OCR数据配置
- ocr:
- min_text_length: 2
- default_confidence: 1.0
- exclude_texts: ["Picture", ""]
-
- # 图片方向检测配置
- orientation_detection:
- enabled: true
- confidence_threshold: 0.3 # 置信度阈值
- methods: ["opencv_analysis"] # 检测方法
- cache_results: true # 缓存检测结果
-
- # OCR工具类型配置
- tools:
- dots_ocr:
- name: "Dots OCR"
- description: "专业VLM OCR"
- json_structure: "array" # JSON为数组格式
- text_field: "text"
- bbox_field: "bbox"
- category_field: "category"
- confidence_field: "confidence"
- # 旋转处理配置
- rotation:
- coordinates_are_pre_rotated: false # 坐标不是预旋转的
-
- ppstructv3:
- name: "PPStructV3"
- description: "PaddleOCR PP-StructureV3"
- json_structure: "object" # JSON为对象格式
- parsing_results_field: "parsing_res_list"
- text_field: "block_content"
- bbox_field: "block_bbox"
- rec_texts_field: "overall_ocr_res.rec_texts" # 针对表格中的文字块
- rec_boxes_field: "overall_ocr_res.rec_boxes" # 针对表格中的文字块
- category_field: "block_label"
- confidence_field: "confidence"
- # 旋转处理配置
- rotation:
- coordinates_are_pre_rotated: true # 坐标已经是预旋转的
-
- table_recognition_v2:
- name: "TableRecognitionV2"
- description: "PaddleOCR Table Recognition V2"
- json_structure: "object"
- parsing_results_field: "table_res_list"
- text_field: "pred_html"
- bbox_field: "cell_box_list" # 原先的 cell_box_listox 为笔误
- rec_texts_field: "table_ocr_pred.rec_texts" # 针对表格中的文字块
- rec_boxes_field: "table_ocr_pred.rec_boxes" # 针对表格中的文字块
- category_field: "type"
- confidence_field: "confidence"
- rotation:
- coordinates_are_pre_rotated: true
-
- mineru:
- name: "MinerU"
- description: "MinerU OCR"
- json_structure: "array" # JSON为数组格式
- text_field: "text"
- bbox_field: "bbox"
- category_field: "type"
- confidence_field: "confidence"
- # 表格相关字段
- table_body_field: "table_body"
- table_cells_field: "table_cells"
- img_path_field: "img_path"
- # 旋转处理配置
- rotation:
- coordinates_are_pre_rotated: false
-
- # 自动检测工具类型的规则(按优先级从高到低)
- auto_detection:
- enabled: true
- rules:
- # Table Recognition V2 - 最高优先级
- - tool_type: "table_recognition_v2"
- conditions:
- - type: "field_exists"
- field: "table_res_list"
- - type: "field_not_exists"
- field: "parsing_res_list"
- priority: 4
-
- # PPStructV3 - 第二优先级
- - tool_type: "ppstructv3"
- conditions:
- - type: "field_exists"
- field: "parsing_res_list"
- - type: "field_exists"
- field: "doc_preprocessor_res"
- priority: 2
-
- # MinerU - 第三优先级
- - tool_type: "mineru"
- conditions:
- - type: "field_exists"
- field: "page_idx"
- - type: "field_exists"
- field: "type"
- - type: "json_structure"
- structure: "array"
- priority: 1
-
- # Dots OCR - 最低优先级(默认)
- - tool_type: "dots_ocr"
- conditions:
- - type: "json_structure"
- structure: "array"
- - type: "field_exists"
- field: "category"
- priority: 3
- data_sources:
- - name: "德_内蒙古银行照"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/data_PPStructureV3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/data_PPStructureV3_Results/德_内蒙古银行照"
- description: "德_内蒙古银行照使用PPStructV3的图片合成结果"
- - name: "德_内蒙古银行照_PaddleOCR_VL_cell_bbox"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/PaddleOCR_VL_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/PaddleOCR_VL_Results/德_内蒙古银行照"
- description: "德_内蒙古银行照使用PaddleOCR VLM的图片合成结果"
- - name: "德_内蒙古银行照"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/mineru-vlm-2.5.3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/mineru-vlm-2.5.3_Results/德_内蒙古银行照"
- description: "德_内蒙古银行照使用Mineru的图片合成结果"
- - name: "德_内蒙古银行照_mineru_cell_bbox"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/mineru-vlm-2.5.3_Results_cell_bbox"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/mineru-vlm-2.5.3_Results/德_内蒙古银行照"
- description: "德_内蒙古银行照使用Mineru的图片合成结果, 整合PaddleOCR坐标"
- - name: "德_内蒙古银行照"
- ocr_tool: "dots_ocr"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/data_DotsOCR_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/德_内蒙古银行照/data_DotsOCR_Results/德_内蒙古银行照"
- description: "德_内蒙古银行照使用Dots OCR的图片合成结果"
- - name: "对公_招商银行图"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/data_PPStructureV3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/data_PPStructureV3_Results/对公_招商银行图"
- description: "对公_招商银行图使用PPStructV3的图片合成结果"
- - name: "对公_招商银行图_PaddleOCR_VL_cell_bbox"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/PaddleOCR_VL_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/PaddleOCR_VL_Results/对公_招商银行图"
- description: "对公_招商银行图使用PaddleOCR VLM的图片合成结果"
- - name: "对公_招商银行图"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/mineru-vlm-2.5.3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/mineru-vlm-2.5.3_Results/对公_招商银行图"
- description: "对公_招商银行图使用Mineru的图片合成结果"
- - name: "对公_招商银行图_mineru_cell_bbox"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/mineru-vlm-2.5.3_Results_cell_bbox"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/mineru-vlm-2.5.3_Results/对公_招商银行图"
- description: "对公_招商银行图使用Mineru的图片合成结果, 整合PaddleOCR坐标"
- - name: "对公_招商银行图"
- ocr_tool: "dots_ocr"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/data_DotsOCR_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/对公_招商银行图/data_DotsOCR_Results/对公_招商银行图"
- description: "对公_招商银行图使用Dots OCR的图片合成结果"
- - name: "A用户_单元格扫描流水"
- ocr_tool: "dots_ocr"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/data_DotsOCR_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/data_DotsOCR_Results/A用户_单元格扫描流水"
- description: "A用户使用Dots OCR的单元格扫描结果"
-
- - name: "A用户_单元格扫描流水_PaddleOCR_VL_cell_bbox"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/data_PPStructureV3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/data_PPStructureV3_Results/A用户_单元格扫描流水"
- description: "A用户使用PPStructV3的单元格扫描结果"
- - name: "A用户_单元格扫描流水"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/PaddleOCR_VL_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/PaddleOCR_VL_Results/A用户_单元格扫描流水"
- description: "A用户使用PaddleOCR VLM的单元格扫描结果"
- - name: "A用户_单元格扫描流水"
- ocr_tool: "table_recognition_v2"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/table_recognition_v2_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/data_PPStructureV3_Results/A用户_单元格扫描流水"
- description: "A用户使用Table Recognition V2的单元格扫描结果"
-
- - name: "A用户_单元格扫描流水"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/mineru-vlm-2.5.3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水.img"
- description: "A用户使用Mineru的识别结果"
- - name: "A用户_单元格扫描流水_mineru_cell_bbox"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水/mineru-vlm-2.5.3_Results_cell_bbox"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/A用户_单元格扫描流水.img"
- description: "A用户使用Mineru VLM识别结果, 整合PaddleOCR坐标"
- - name: "B用户_扫描流水"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/data_PPStructureV3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/data_PPStructureV3_Results/B用户_扫描流水"
- description: "B用户使用PPStructV3的扫描结果"
- - name: "B用户_扫描流水_PaddleOCR_VL_cell_bbox"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/PaddleOCR_VL_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/PaddleOCR_VL_Results/B用户_扫描流水"
- description: "B用户使用PaddleOCR VLM的扫描结果"
- - name: "B用户_扫描流水"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/mineru-vlm-2.5.3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水.img"
- description: "B用户使用Mineru的扫描结果"
- - name: "B用户_扫描流水_mineru_cell_bbox"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/mineru-vlm-2.5.3_Results_cell_bbox"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水.img"
- description: "B用户使用Mineru的扫描结果, 整合PaddleOCR坐标"
- - name: "B用户_扫描流水"
- ocr_tool: "dots_ocr"
- ocr_out_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/data_DotsOCR_Results"
- src_img_dir: "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/data_DotsOCR_Results/B用户_扫描流水"
- description: "B用户使用Dots OCR的扫描结果"
- - name: "至远彩色_2023年报"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/data_PPStructureV3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/data_PPStructureV3_Results/2023年度报告母公司"
- description: "至远彩色使用PPStructV3的2023年报"
- - name: "至远彩色_2023年报_PaddleOCR_VL_cell_bbox"
- ocr_tool: "ppstructv3"
- ocr_out_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/PaddleOCR_VL_Results"
- src_img_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/PaddleOCR_VL_Results/2023年度报告母公司"
- description: "至远彩色使用PaddleOCR VLM的2023年报"
- - name: "至远彩色_2023年报"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/mineru-vlm-2.5.3_Results"
- src_img_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/mineru-vlm-2.5.3_Results/2023年度报告母公司"
- description: "至远彩色使用mineru的2023年报"
- - name: "至远彩色_2023年报_mineru_cell_bbox"
- ocr_tool: "mineru"
- ocr_out_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/mineru-vlm-2.5.3_Results_cell_bbox"
- src_img_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/mineru-vlm-2.5.3_Results/2023年度报告母公司"
- description: "至远彩色使用mineru的2023年报, 整合PaddleOCR坐标"
- - name: "至远彩色_2023年报"
- ocr_tool: "dots_ocr"
- ocr_out_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/data_DotsOCR_Results"
- src_img_dir: "/Users/zhch158/workspace/data/至远彩色印刷工业有限公司/data_DotsOCR_Results/2023年度报告母公司"
- description: "至远彩色使用Dots OCR的2023年报"
- # 预校验结果文件路径
- pre_validation:
- out_dir: "./output/pre_validation/"
|