EMC just announced a new release of its EMC Captiva intelligent enterprise capture solution. The release offers significant breakthroughs in performance and intelligence that continues to prove its superiority when it comes to scalability, and the ability to learn document attributes while in production, allows organizations to realize the benefits of document capture faster than ever before. You can read the entire press release here.
In this release you will find several key enhancements, but probably most interesting is Captiva’s new Production Auto Learning capability that enables organizations to learn documents while in production which simplifies the initial configuration and setup of a document project, and make life easier for a project administrator when it comes to maintaining the project.
The video below provides a good introduction to what we are releasing in Captiva 6.5 and talks specifically about the benefits of Production Auto Learning.
Captiva with Production Auto Learning: Intelligent and Efficient
First off, Production Auto Learn is intelligent in that it can learn many structured and variable semi-structured documents, such as forms, applications, invoices, and other document types. Production Auto Learning is an automatic learning capability that creates new templates for each new graphic document layout entering the production flow. It uses the images processed in production and also places fields and local anchors onto the graphic templates to create the templates.
Second, it is efficient. Production Auto Learning simplifies the initial project design and maintenance by automatically or manually updating the deployed project with the new templates. Over time, Production Auto Learning reduces the human cost by progressively reducing the number of documents to be classified manually and the number of fields to be validated manually, until initial learning is complete.
Below is a demonstration I built that shows how Production Auto Learning would first learn the documents based upon the initial images collected, and then in the second time through classification and data extraction is automatic.
Enterprise Performance Highlights of Captiva 6.5
In this release, we’ve provided some enhancements to further enhance performance and scalability. To demonstrate the scalability of Captiva, internal benchmark testing was completed, and shows that a single Captiva server can now process more than 10 million images per day.
To help customers fully understand the scalability and performance of the system, EMC publishes a performance and tuning guide that details benchmark testing performed and provides guidelines to help size a Captiva capture system. There were many performance tests that were run in various hardware configurations with very specific performance metrics around key capture areas. So the performance and tuning guide provides some great metrics that can help large enterprise organizations with properly sizing an enterprise capture system.
Global support for worldwide document capture implementations
Captiva 6.5 also delivers features that provide global support for worldwide document capture implementations. Specifically it supports running multiple languages in the same configuration, and captures data in both single and double byte character languages.
At various times, I’ve highlighted Captiva customers who have true global capture operations where documents are coming in many different languages and being processed in one central location, or distributed across different processing hubs. With the Captiva 6.5 release, customers will benefit from the flexibility that Captiva 6.5 provides when it comes to processing documents and data in multiple languages.
So there you have it, a few key highlights of the latest release of the EMC Captiva intelligent enterprise capture solution. If you are at the AIIM info360 conference in Washington DC this week (March 22nd -24th), I encourage you to stop by the EMC booth and take a look at the latest release.
