Embed Fast, Multi‑Language OCR Right Inside Your Application
IRIS OCR SDK (IRISOCR™) gives you AI‑enhanced OCR, PDF/A and Office conversion, and advanced compression—running locally, in your cloud, or embedded in devices.
0
Languages
Covers Latin, Cyrillic, Arabic, Asian languages and more.
0
1M Pages
Cost per 1M pages (on owned hardware)
0
Fewer Errors
With next‑gen HQOCR vs previous engine generations.
When Free OCR Isn’t Enough for Enterprise Workflows
- Open‑source OCR struggles with complex layouts, tables and reconstruction.
- OS‑embedded OCR is tied to a single platform and usually text‑only.
- Cloud OCR APIs are accurate, but add latency, per‑page costs and data residency concerns.
- LLMs can read images—but you still need standardized, searchable and compliant files.
IRIS OCR SDK keeps OCR local, predictable, and reconstruction‑ready
- Run OCR where your documents live: on‑prem, in private cloud or inside devices.
- Generate compact PDF/A, DOCX, XLSX or ALTO XML ready for DMS and archives.
- Scale economically across millions of pages with predictable TCO.
- Use the same engine that powers IRIS Powerscan and IRISXtract deployments worldwide.
Multi‑language OCR & ICR
Recognize 130+ languages, including complex scripts. Optional handwriting recognition and checkbox detection for forms and surveys.
Advanced Layout & Reconstruction
Preserve columns, tables, headings and reading order in searchable PDF/A and Office formats.
Compliance‑Ready PDF/A Output
Produce compact, standards‑compliant PDF/A‑2u and PDF/A‑3u for long‑term archiving and regulatory use cases.
Barcode & Zonal Capture
Extract 1D/2D barcodes and define zones for targeted recognition in structured workflows.
High‑Volume Performance
Optimized for multi‑threaded batch processing and server scenarios, with predictable throughput per core.
Flexible SDK Integration
C++ and .NET APIs, NuGet distribution, stream‑based processing and sample projects shorten your integration cycle.
Architecture Built for Local, Cloud and Embedded Scenarios
IRIS OCR SDK is powered by the same iDRS engine used across the IRIS product portfolio. A modular C++ core exposes OCR/ICR/OMR, barcode recognition, image preprocessing and document conversion components behind a unified API.
Developers can call the SDK via native C++ or cross‑platform .NET bindings. The .NET wrapper is distributed via NuGet, with separate asset and runtime packages for Windows, Linux and macOS, allowing you to keep deployments lean and predictable.
Internally, a rich page model captures text content, geometry and layout semantics, enabling advanced outputs like PDF/A and Office formats, as well as ALTO‑style XML for archives and downstream analytics. This same structure underpins the OCR microservices used in IRIS Pulse.
- Core engine: C++ with modular OCR, layout, conversion engines
- .NET bindings: cross‑platform, stream‑based I/O, NuGet packages
- Supported OS: Windows, Linux, macOS (server and desktop scenarios)
- Output formats: PDF, PDF/A‑2u/3u, DOCX, XLSX, PPTX, text, XML
Deploy the Engine Where You Need It
Desktop & Client Apps
Embed OCR and PDF/A creation directly into Windows or macOS applications. Offer 'Make PDF searchable', 'Scan to PDF/A', or 'Export to Word/Excel' experiences entirely offline.
On‑Prem & Private Cloud
Run the SDK on server farms or containers as a central OCR microservice. Integrate via REST, queues or custom orchestrations—ideal for BPOs, SSCs and regulated industries.
Embedded & OEM
Ship IRIS OCR technology inside scanners, MFPs or appliances. Leverage efficient local processing and flexible licensing for device‑centric products.
AI & LLM Pipelines
Standardize noisy scans into structured, searchable inputs before feeding them into LLMs or other AI services. Combine OCR outputs with domain‑specific models to automate classification, routing and content generation.Where IRIS OCR SDK Delivers the Most Value
High‑Impact Scenarios Optimized by the IRIS OCR SDK
Financial Services & Insurance
Convert legacy archives into PDF/A for compliant storage. Extract text and barcodes to power search and case routing.
Public Sector & Archives
Generate small, accessible PDF/A packages from legacy scans. Feed ALTO‑style layouts into archival and research systems.
Healthcare
Run OCR inside your infrastructure to respect privacy constraints. Provide clinicians with searchable patient documents and reports.
Manufacturing & Logistics
Extract key identifiers and content from multi‑language paperwork. Feed ERP, WMS and quality systems with standardized PDF/A outputs.
Software Vendors & OEMs
Embed IRIS OCR under your own UI and brand. Support multi‑platform deployments with a single engine.Frequently Asked Questions
Understanding the OCR SDK: Your Most Common Questions
How is IRIS OCR SDK different from open‑source OCR?
Open‑source engines are a good fit for lightweight, text‑only scenarios. IRIS OCR SDK is built for high‑volume, commercial products that need higher accuracy, multi‑language support, document reconstruction to PDF/A and Office formats, advanced compression and professional support.
Can I deploy the SDK in my own data center or private cloud?
Yes. The SDK is designed for on‑prem and private‑cloud deployments, running on your servers or containers so that documents never leave your environment.
Which programming languages and platforms are supported?
The core engine is implemented in C++, with native interfaces. A cross‑platform .NET wrapper is available via NuGet, supporting Windows, Linux and macOS deployment scenarios.
Do you offer a trial version for evaluation?
Yes. You can request a time‑limited evaluation of IRIS OCR SDK to test performance, accuracy and integration fit in your own environment.
How is licensing handled for OEMs and SaaS vendors?
Flexible licensing models are available for OEMs, ISVs and SaaS providers, including redistribution scenarios. Our sales team will help you choose a model aligned with your architecture and growth plans.
How to Get Started with IRIS OCR SDK
Ready to Build? Here’s How to Start with the IRIS OCR SDK
Discuss Your Use Case
Share your volume, platforms and target workflows so we can confirm fit and sizing.
Evaluate with a Trial SDK
Run tests in your own environment using sample code and documentation.
Integrate & Optimize
Embed the SDK into your application, fine‑tune accuracy and performance settings, and validate output formats.
Launch & Scale
Move from pilot to production with support from IRIS experts on performance tuning, deployment patterns and upgrades.
Ready to Embed OCR into Your Product?
Talk to our team about your architecture, volume and go‑live timeline. We’ll help you evaluate IRIS OCR SDK and design a deployment pattern that fits your environment.