Unstructured Documents

What if the OCR misses a field or value?

What if the OCR misses a field or value?

You have a software package that relies on optical character recognition (OCR) to classify, pick up words, numbers or phrases from a document.  As long as the quality of the document is mostly clean, everything works well.  However, what happens when the document arrives and the quality is simply, not good?  Does the software give up and run away with its tail between its legs? Are there any options to classify or capture anything on these documents?  

Top 3 Optical Character Recognition (OCR) Misconceptions

Top 3 Optical Character Recognition (OCR) Misconceptions

Optical Character Recognition can be an extremely powerful tool, but there are many things that an OCR engine can’t actually handle, that often times get overlooked. Below I have listed out the top 3 most common misconceptions of an OCR engine.

NCSC Highlights Redaction Technology Advancements

NCSC Highlights Redaction Technology Advancements

Last month the National Center for State Courts (NCSC) coordinated an Automated Redaction Proof of Concept (PoC) with several vendors. 

The PoC was made possible thanks to funding from the State Justice Institute (SJI).  The purpose was to provide accuracy benchmarks to courts considering implementing automated redaction technology. NCSC is planning to issue results prior to CTC, publish on their website, and present to various target groups and at conferences.

Princeton Hosts Second Court Summit – Brings courts and technology together

Princeton Hosts Second Court Summit – Brings courts and technology together

Never in my wildest dreams did I ever think I would attend Princeton. Boasting two former presidents, several supreme court justices, the founder of Amazon, and chairman of Google as some of the famous alumni. Several weeks ago, I had the opportunity to go to “Princeton, NJ” for the second Industry Summit coordinated by the National Center for State courts (NCSC). The goal of the summit was to bring NCSC staff, court representatives and their system providers together in a non-tradeshow environment to talk about the current and future state of technology in the courts. 

5 Signs You Need a Document Handling Solution

5 Signs You Need a Document Handling Solution

Even if you have a current system to store your documents, and your employees use the world’s best labeling system, they may not put everything back in the same place. Nor will they necessarily place paperwork back in the same order within the label. The most up-to-date or accurate version could be found out of order...

What do Document Handling & Peanut Butter Jelly Sandwiches Have in Common?

What do Document Handling & Peanut Butter Jelly Sandwiches Have in Common?

Every good process has a starting point. In the instance of making the perfect peanut butter and jelly sandwich, “first you take the peanuts and you crush ‘em, you crush ‘em" view entire peanut butter and jelly sandwich process here. Whereas, the first step of a government data entry process, is document handling. First you take the paper documents, and you sort ‘em, you sort ‘em. Then you take the documents and you scan ‘em, you scan em...

What do Thanksgiving and the Courts have in Common?

What do Thanksgiving and the Courts have in Common?

If you answered George Washington, you are correct.  President Washington signed the Judiciary Act of 1789 establishing the federal court system, and only days later proclaimed November 26, 1789 as a “day of public thanksgiving and prayer.”  The actual holiday we celebrate today was proclaimed by Abraham Lincoln during the Civil War in 1863. A lot has changed since the Pilgrims and Wampanoag Indians first Thanksgiving more than 400 years ago.  There was no turkey, potatoes, or pumpkin pie on the original menu, no NFL football or holiday shopping.

Automated Document Classification: Saving Time and Money

Automated Document Classification: Saving Time and Money

Automated Document Classification is defined based on your business requirements and documents. Documents may be classified according to subjects or based on other attributes such as; document type, author, printing year, etc. 

Once these classifications are defined, documents stored in an assigned repository or arriving by fax, e-mail or via an upstream workflow, are sent to an Automated Document Classification application.