Handwriting Recognition

Is ICR the same as handwriting recognition? Let's clear up some confusion. There are two interrelated terms, "handwriting recognition" and intelligent character recognition (ICR). Before ICR, there was Optical Character Recognition (OCR). It was good at reading machine printed (i.e. typed) characters, but lousy when it came to reading handwriting, or even hand printed characters. To solve this problem, developers, generally using a branch of artificial intelligence called neural network technology, developed new techniques to read handwritten characters. When they needed a name, they drew on the fact that it was based on artificial intelligence and called it Intelligent Character Recognition. Many use the term "ICR" to refer exclusively to handwriting recognition.

ICR for Machine Print?

Once the ICR engines had proven that they could effectively read hand printed characters, then developers worked to expand their usefulness by also being able to read machine printed characters. Most of today's ICR engines do an impressive job on typed materials, though usually not quite as accurately as a good-old OCR engine.

When is ICR Right for Me?

ICR works best on neat handwriting.  Recognition is best when the characters are touching each other as little as possible.  That's why form design is so important if you are considering using ICR. An ICR engine can also be a good "second pass" engine for voting on machine printed characters: use OCR for the first pass and ICR for the second.

Want to learn more about ICR?

View our webinar recording that introduces the basics of ICR. You will learn how ICR technology is working and how it can be effective to process forms and documents that are filled in by hand. This webinar also demonstrates the challenges for a succesful implementation of an ICR strategy. View the webinar

back to top | request more information | contact Datacap | site map