How Does Incoming Mail Processing Software Work?

State-of-the-art incoming mail processing software is able to locate the correct destination address block on the image of an envelope, flat-size mail piece, or parcel. The software automatically parses and recognizes the fields within this address block. It is designed to deal with different address block structures and automatically reads the variety of fields and […]

Read More

3 Thoughts from Harvey Spencer’s 2013 Capture Conference

Every year in early September, leading document capture analyst Harvey Spencer hosts an annual industry vendor conference at the Glen Cove Mansion in Glen Cove, NY. Here, Harvey provides a synopsis of the document capture market, and IT trends as they relate to capture (think process-oriented applications, information security and governance, etc). Here’s a few […]

Read More

Over $1,000 Billion Bill Payments by Mail in 2013

According to a recent report from Aite Research, $1.062 billion of consumer payments will be done by mail in 2013 in the U.S. That’s compared to $1.769 billion done online. Payments with checks are declining, but as we can see here, they are still part of the second most used payment channel. Even if the […]

Read More

New Aite Research Highlights Remittance Processing Pains of the B2B Middle Market

Back in March and April, Parascript commissioned research with the Aite Group to better understand the current state of receivables processing automation at mid-market companies ($50m – $500m). Most specifically, we were interested in the more complex, business-to-business (B2B) market. We learned a great deal. A few of the highlights: The average mid-size B2B company […]

Read More

The 2 Most Common Misconceptions about Recognition Technology

When it comes to automated recognition technology, there are 2 common misconceptions about expected results that can be easily solved with tuning. Misconception #1: All items in a stream are equally hard to read, both automatically and manually The items that cause the most errors and rejects are not random. In fact, the items that […]

Read More

The Truth about Trainable Forms Processing

There are many capture systems that market the ability to automatically “learn” document formats and layouts or to allow the system to be “trained”. In either case, the objective is twofold: Minimize the effort required to define document rules specific to each document variant and Improve overall recognition rates and lower error rates. The Problem […]

Read More

Understanding Recognition: Reject Mechanism

Let’s explore the mathematical model for optimizing the tradeoff between errors and rejects. The reject mechanism helps to guarantee the specified error level required by an application. Recognition engines usually return an answer accompanied by a value parameter called confidence value. The confidence value ranges from 0 to 100 and indicates how confident the engine is that […]

Read More

Understanding Recognition: Errors and Rejects

There are 3 possible outcomes when recognition engines attempt to read any data: the correct answer, error, or reject. This post will focus on understanding errors and rejects and how to find the right balance between them. Errors refer to the instances when a recognition engine gives an incorrect result. The problem with errors is […]

Read More