Skip to content

Changelog

2.13.0

  • New endpoint GET /api/v1/config to retrieve current service configuration.
  • New endpoint POST /api/v1/config to update service configuration without restarting the service.
  • Fix: Return document images on universal output.
  • Improve error messages.
  • Update ESP ID templates.

2.12.1

  • Update document templates (Canada).

2.12.0

  • Update document-reader-sdk v2.7.1
    • Universal response output format.
    • Updated mobile interpreter.
  • Update facephi-recogntion v4.0.1

2.11.0

  • Update templates for RENTA v18.

2.10.1

  • Fix license issue to ensure compliance and smooth operation of the OCR service.

2.10.0

  • Unify configuration parameters into a single file.
  • Update facephi-recognition v3.26.0.
  • Available new IDCard interpreter with some improvements. The previous interpreter is used by default for compatibility reasons.

2.9.1

  • Set isCropped attribute of /process endpoint to true by default and mark it as deprecated.

2.9.0

  • Update facephi-recognition v3.25.0.
  • Update pipeline for Invoices v3.3.0.
  • Update pipeline for Documents v2.1.1.
  • Log improvements.

2.8.1

  • Update facephi-recognition v3.22.1.
  • Fixed templates for Mexico IDCard.

2.8.0

  • Update templates for RENTA v15.
  • Fix PDF height and width as double.
  • Update facephi-recognition v3.21.1.
  • Add Id Card Argentina version 0004. And remove version 0003.
  • Update text-interpreter and templates.

2.7.0

  • PDF: Reduce default threshold to 0.5 for better detection of text.
  • PDF: Add optional parameter pageNums. It is a list of pages numbers to be processed. The counting starts at 1. If not present all pages will be processed.
  • PDF: Ignore errors "page not parsed" on 2nd and consecutive pages.
  • PDF: Add output warnings. This field contains information about the pages which have not been processed. In the future, it may be extended to contain other information.
  • Update text-interpreter:
    • PDF: Include fields on the model although they are not detected or empty.
  • Update document-reader-sdk-templates
    • PDF: Models IVA.json and RENTA.json process correctly multi-word fields.
  • Update licensing backend v2.0.0.
    • Add high availability.
  • Update facephi-recognition v3.21.0

2.6.0

  • Parallelized the PDF processing in the OCR engine.
  • Logging improvements.
  • Bug fixes.

2.5.1

  • Added support for income taxes in El Salvador, form F-11 V17. Model name: RENTA.
  • Added support for VAT taxes in El Salvador, form F07 V14. Model name: IVA.
  • Added support for multi-page PDF in the OCR engine.
  • Improvements in logging. Propagate log level from the service configuration to the OCR engine.
  • Updated Facephi Core Recognition to version 3.20.2 and Facephi Rest Manager to version 2.12.0.
  • ForceDetection option of ProcessBody has been deprecated.

2.5.0

  • Improvements and optimizations in the OCR engine for documents and invoices.
  • Improvements in the OCR engine for raw endpoint.
  • Improvements in logging.

2.4.6

  • Improvements in the service health check.
  • Improvements in license management.

2.4.4

  • Fixed Telmex model under special cases as PUBLICO EN GENERAL as a line in the middle of the address.
  • Fixed CFE model when dates are not well-formed.
  • Fixed minor issues with the interpreter.

2.4.3

  • Added support for Mexico IDCard/ForeignCard.

2.4.2

  • Fixed dependencies, PDF engine with gcc7.

2.4.1

  • Fixed avx512 bug with openvino compilations for invoice

2.4.0

  • Facephi Rest Manager version updated to 2.5.0. Added new config parameters to json "logger_path", "logger_level", "logger_rotation", "logger_max_files".
  • Updated Facephi Core Recognition to version 2.15. Updated Invoice OCR Engine with major performance improvements.

2.3.4

  • Fixed barcode reader for some Argentina images.

2.3.3

  • Update facephi-rest-manager to v2.4.2.
  • New configuration parameter client_max_body_size to limit the maximum size of the request body.

2.3.2

  • BREAKING CHANGE: The endpoint process now receives the files parameter instead image in order to support the reading of two-sided documents.
  • Updated templates for Argentina documents: v1, v2, v3.
  • Added support for OCR, MRZ, Barcode IDCard documents.
  • Added support for IdCard documents with two sides.
  • Added support for templates based on XML files.

2.3.1

  • BREAKING CHANGE: Raw endpoint has a new parameter called type that allows to choose the document type to be processed.
  • Fixed RENTA template.
  • Fixed PDF reader.
  • Added ability to configure the OCR service.

2.3.0

  • Raw endpoint has a new type parameter.
  • Fixed CFE and TELMEX templates.
  • Added image processing improvements.
  • Bug fixes.

2.2.0

  • Support for new models.
  • Added extract text from PDF.
  • Added convert PDF to image.
  • Bug fixes.

2.1.3

  • Fixed documentation.
  • Fixed CFE and TELMEX models.
  • Modified /api/v1/process result to add more information.

2.1.2

  • Added OCR Latin 2.0
  • Added Process, Health, Version and Raw endpoints.