Try the demo
Try the demo
Open-Capture technology platform

Open-Source Software
Full-Web Access and AI-Powered

Open-Capture is a document capture and automated processing software solution combining OCR and AI, machine learning, to extract data and export it to third-party management software. A free and open-source solution distributed under the GNU General Public License v3.

Published by Edissyum, expert in ECM, document management and BPM

Capture and process all types of
documents from all your sources

Separation, sorting, bundling and unbundling of documents
Automated document capture

Open-Capture automates the acquisition of paper and digital documents to simplify their processing. The platform handles content capture, data extraction and file conversion.

Open-Capture Verifier module interface showing the batch view with filters, search and several invoice documents ready for verification.
Advanced processing technologies

The solution relies on technologies such as OCR, machine learning, regular expressions and open APIs to improve document reading, analysis and use.

Multi-channel collection

Files can be captured automatically from scanners, multifunction copiers, emails, attachments or web forms, then injected into a processing workflow.

Flexible and configurable workflows

Workflow settings, capture rules and scripts make it possible to create processing scenarios tailored to each organization’s needs.

Document workflow diagram showing the steps capture, extraction, OCR, validation and export in an automated processing flow.
Export and integration

Processed documents and data can be sent to network folders, ECM systems such as Alfresco or SharePoint, or exported as PDF, PDF/A, XML or plain text.

Document export diagram showing multiple possible output formats and destinations, XML, COOC, SharePoint, OpenCRM, TXT, Alfresco, PDF and PDF with Factur-X metadata.
Performance and time savings

Open-Capture can process large document volumes quickly thanks to simple administration, fast deployment and automation of recurring tasks.

1 %
OCR Success
1 h
Time saved
1 %
Deadlines respected
Acquisition
Extraction
Verification
Exportation

Document acquisition

Capture, acquisition and sorting of documents from multiple sources, including separation, sorting, bundling and unbundling operations.

  • Scanners
  • Multifunction copiers
  • File drop
  • Emails and attachments
  • Upload interface
  • Web services

Data extraction and classification

Automated extraction of information using OCR, pre-trained models and document classification mechanisms.

  • Tesseract OCR
  • Pre-trained models
  • Key-value extraction
  • Matching through reference data
  • Data dictionaries
  • Barcode and QR code reading

Verification and validation

The platform checks the consistency and validity of extracted fields using simple or advanced rules.

  • Compliance with extraction rules
  • Format validation
  • Validation against reference data
  • Advanced business rules through scripts

Export and distribution

Documents and data are distributed to ECM, workflow or archiving tools according to your needs.

  • Native MEM Courrier connector
  • CMIS connector
  • OpenADS / Oxalis
  • OpenCRM
  • PDF, XML, CSV
  • Web services
An open-source technology designed for document capture

Open-Capture is a full-web IDR software solution developed by our teams in React and Python. It integrates several open-source building blocks for reading, analysis, classification and document distribution.

 

Tesseract OCR

Supervised AI and pre-trained models

Machine learning classification

100% web application

Native Linux operation

Open and extensible technology

No limit on the number of users

Additional modules available