提交历史

作者 SHA1 备注 提交日期
  zhch158_admin 05f77c04db feat: add comprehensive documentation for `unclip_ratio` parameter in OCR text detection, detailing its function, effects, and configuration recommendations for optimal performance 6 天之前
  zhch158_admin 6043464fee feat: implement streaming processing mode in document parser, allowing memory-efficient handling of large documents with enhanced output summary and configuration options 6 天之前
  zhch158_admin 4bc0837069 feat: introduce detailed documentation for converting large text blocks to tables, including configuration options, rules, and best practices for effective layout post-processing 6 天之前
  zhch158_admin ad10e0509b feat: add post-processing section for converting large text blocks to tables, including configuration examples and rules for improved layout handling 6 天之前
  zhch158_admin dc939addb8 feat: add documentation for streaming processing mode, detailing memory optimization, usage instructions, and performance comparisons with batch processing 6 天之前
  zhch158_admin 7b21a7774a feat: expand utility module by adding new formatters and normalization functions for enhanced document processing capabilities 6 天之前
  zhch158_admin f42b493c9e feat: implement conversion of large text blocks to tables in post-processing, improving layout organization and enhancing document structure recognition 6 天之前
  zhch158_admin 5af14a8cd9 feat: implement streaming document processing pipeline for efficient page-by-page handling, optimizing memory usage and ensuring consistent output formatting 6 天之前
  zhch158_admin a11d9c639c feat: add functionality to convert large text blocks into tables during post-processing, enhancing layout organization and improving document structure recognition 6 天之前
  zhch158_admin 927beae129 feat: update table bounding box calculation in enhance_table_html_with_bbox method to use relative coordinates for improved accuracy in cell matching 6 天之前
  zhch158_admin 7c121fdadd feat: enhance bank statement configuration by adding layout post-processing options and adjusting OCR parameters for improved text detection accuracy 6 天之前
  zhch158_admin 9c7c0c78f7 feat: add comprehensive analysis and improvement strategies for OCR performance, detailing parameter adjustments and recommendations for enhanced text recognition accuracy across various document types 6 天之前
  zhch158_admin 4fb6cf4eb9 feat: add page range argument to process_single_input for selective document processing, enhancing user control over which pages to process 6 天之前
  zhch158_admin aeea003eaf feat: implement page-level OCR and Span-Block matching strategy to enhance text extraction accuracy, allowing for improved processing of various document types and better handling of overlapping spans 6 天之前
  zhch158_admin 0449712ccc feat: enhance document processing by adding page range support and integrating SpanMatcher for improved OCR span matching, allowing for more accurate text extraction and processing across specified pages 6 天之前
  zhch158_admin e0bd11a14e feat: add page range parsing and filtering to PDFUtils for enhanced document processing, allowing users to specify which pages to load and process 6 天之前
  zhch158_admin f4fd5eb3de feat: refactor layout utilities to delegate coordinate calculations to CoordinateUtils, and introduce SpanMatcher for OCR span and layout block matching, enhancing text extraction accuracy 6 天之前
  zhch158_admin 3d0698d9e9 feat: enhance element processing with pre-matched spans for OCR, improving text extraction priority and accuracy across various document types 6 天之前
  zhch158_admin fdc80948b0 feat: add coordinate calculation methods including IoU and overlap ratio, and implement polygon to bbox conversion utilities for enhanced spatial analysis 6 天之前
  zhch158_admin bf2448d3a8 feat: enhance OCR model initialization with detailed configuration parameters for improved detection accuracy and flexibility 6 天之前
  zhch158_admin ccbbc36fa9 feat: add comprehensive configuration for bank statement processing v2, including input, preprocessing, layout detection, VL recognition, OCR, and output settings to enhance document handling and accuracy 6 天之前
  zhch158_admin 01920d7a82 feat: update input and output configurations for bank statement processing, adding support for new document types and adjusting configuration file references for improved processing accuracy 1 周之前
  zhch158_admin 6653c2cb9f feat: enhance financial document processing framework with improved model selection, layout detection options, and detailed processing flow, including support for various document types and output formats 1 周之前
  zhch158_admin b6a4b45c91 feat: implement financial number normalization across output formats, enhancing data consistency and accuracy in JSON, Markdown, and HTML exports 1 周之前
  zhch158_admin db78f28b68 feat: integrate DoclingLayoutDetector into the adapter module, expanding layout detection capabilities and updating the export list for improved accessibility 1 周之前
  zhch158_admin e14a1607c7 refactor: update category mapping and color definitions in PaddleLayoutDetector for improved clarity and consistency with EnhancedDocPipeline 1 周之前
  zhch158_admin f98e8cc99f feat: implement DoclingLayoutDetector adapter for layout detection using HuggingFace models, supporting batch processing and visualization, while ensuring compatibility with existing MinerU categories 1 周之前
  zhch158_admin 22f3d967cf feat: add support for Docling layout detector in ModelFactory, enhancing layout detection options and improving error handling during initialization 1 周之前
  zhch158_admin edd2eea7ce feat: add enhanced bank statement configuration files for MinerU and PaddleOCR-VL, supporting improved processing workflows and output options, while removing the outdated financial report configuration 1 周之前
  zhch158_admin c813baaef7 refactor: remove main_enhanced.py to streamline document processing scripts, consolidating functionality into main_v2.py for improved maintainability and clarity 1 周之前