Intelligent document and data capture technologies and why they matter


Working with Acolad, I am able to understand and assist organizations where Enterprise Content systems (ECS) are paired with Enterprise Capture platforms. However, I notice that in almost all organizations the Enterprise capture platform is not regarded with the same business relevance as the ECS.


Many people, even those working with data day in and day out aren't aware of how relevant data capture is in all business operations. It is especially essential when the amount of data that needs to be processed keeps growing – customer or prospect contact requests, contracts, invoices, expense reports, and so on. From gathering all incoming communications in all document and data formats from different areas of business (mail correspondence, fax, paper or digital) to sending it to the right person/department or archiving it in the correct ECS repository folder, handling data inflow accurately and efficiently is crucial.

One of the leading platforms for intelligent document and data capture is OpenText Captiva. Captiva is completely customizable to your organization's communication and content streams, from the number of users and document types, to the different workflows and systems it needs to connect.

We'll go through some examples of how to take full advantage of data capture and intelligent document recognition technologies to improve processes and reduce costs.

Automated content categorization through advanced recognition takes away tasks from the ECS and the end-users, resulting in better performance of both

One of the basic features of an Enterprise Capture system is to scan and deliver content to a desired platform. But if you limit it to deliver non-processed (raw) content to another platform, you're just making a digital copy of the document.

A data capture system can transform your content into usable information, using intelligent recognition technologies such as optical character recognition (OCR), intelligent character recognition (ICR), optical mark recognition (OMR) and barcode recognition. It identifies and classifies the document type and extracts all relevant information, generating huge time savings to end-users on the otherwise manual tasks.  

Think about an emailed form requesting a loading station for an electric car. The form layout, questions, answers and information about the applicant is always located in the same position in the form fields. This structured layout enables its automatic processing with Captiva - it can read the mailbox where the forms gather, search the document for information and read the answers from the email form, thus liberating the staff from all the manual tasks up to approval/rejection of the request made.

Another typical example is that of a business who receives huge number of invoices per day which would benefit from an advanced capture process that automatically recognizes the document type (I.e. an invoice) and extracts the data related to the sender, purchasing order, taxes and prices to forward the necessary details to the originating department for validation or accounting for payment.

Processing multiple input sources into one output format with Captiva creates one advanced capture process that shouts efficiency

Input can come from different places (mail, fax, email, electronic files or ECS platforms) and in different formats (paper, images, pdf, xml, etc.). Creating one processing standard can be the key to meeting your efficiency, service and compliance goals.

Transforming multiple input sources into one output format helps to structure information before it goes into your ECS. By extracting data, classifying and validating it against your existing databases, you make sure that data is always correct, avoid duplications, and guarantee that accurate information gets to those who need it as quickly as possible.

Limiting Captiva to basic scanning and storing documents will guide the content to the correct location, but it will not help you manage an increasing influx of data, resulting in higher maintenance, more complex processing steps and reduced end-user efficiency.

Having an advanced capture process prevents "garbage in"

Creating an advanced capture process enables to transform the so called "garbage" into useable information. While creating a process, you should always aim to keep Poka Yoke (foolproof) in mind and deliver content as complete and accurate as possible, not because all end-users are fools, but because human error is the most common error in manual handling of documents.

Returning to my previous example, recognizing invoices and automatically filling financial values in a form achieves greater accuracy and is far more efficient than having the end-users type them manually. An advanced capture process facilitates "garbage in", information out.

Captiva refunds itself over time

Yes, creating the most advanced capture process takes time, nevertheless, Captiva refunds time spent. Most organizations report a return on investment within 12 months by implementing automated classification alone.

For companies just starting out with enterprise capture, Captiva refunds itself by reducing the analog way of working and automating basic tasks. When taken to its full potential, Captiva can help phase out the analog way of working (if the business processes allow it) to achieve higher quality, accurate content.

And don't be thrown out by the misconception that if your organization has many content types it will take ages to implement an advanced recognition system. Working with a wide range of clients, we find that, many times, only a few content types can take up 80% of the process flow. So if you set up a system to automatically recognize those few most commonly used content types, you'll see immediate gains.


Advances in data capture and document recognition technologies are leading more and more organizations to integrate them into their content management solutions. Driving these automations into your business processes will reduce time, costs and risks of errors associated with manual intervention in document-centric workflows, which will ultimately impact your service delivery in a positive way.

However, due to the diversity of platforms, documents and user profiles, intelligent document and data capture technologies can be challenging to implement and customize. Consulting with the right partner will ensure you balance your data capture needs with your existing IT infrastructure to get you the functionalities you need to maximize business outcomes.