OCR is an acronym for “Optical Character Recognition.” Many people are surprised to learn that a scanned image in its native state cannot be searched. OCR technology is what makes the image searchable. How does OCR do this? We get into the details below, but for now consider this analogy: the OCR software reads the images and creates a layer of “hidden text” behind the image, so that your computer can read this additional layer, recognize it and search it. See Wikipedia info here
Because OCR today is embedded in many applications, websites and content management systems, the modern office worker often takes for granted the process of making a scanned file searchable. In the early days of the new millennium, OCR was a very expensive type of software reserved for imaging service bureaus and Fortune 500 companies. Service bureaus often charged as much as $0.05 per page for OCR, because the server infrastructure and software is expensive to own.
The benefits of being able to search for text in large PDF or TIF files can be priceless. For example, in the legal industry it is a significant time and cost saver. A $250 per hour attorney can find a critical portion of text in several boxes of files, in a matter of seconds. Compare this to the potential cost if the attorney and support staff had to read through thousands of pages the old fashion way.
Over the past 20 or so years, OCR technology has rapidly proved its worth in a variety of other industries and processes such as medical, accounting, accounts payable and the like.
What's In it For You?
If you have ever spent hours searching for content, words or other information in a collection of documents, OCR may be your new best friend. The ability to use a PDF reader, or other content management tool can be a significant time saver. For most of us in business, we are constantly looking for ways to streamline processes and increase productivity. OCR can be a significant enabler in this pursuit.
OCR can make your life easier by:
Making paper-based information searchable in seconds, rather than hours.
Reduce or eliminate costly data entry by automatically grabbing information you need from paper and putting it where it needs to go.
Enabling entirely new ways to process documents that can eliminate “human touches”, thereby reducing costs and dramatically reducing processing times.
For example, many companies use Forms Recognition software (a type of OCR) to extract data from documents and then use that data to kick-off some number of process steps a document must go through. Examples that are common are eliminating the data entry associated with processing medical claims forms and accounts payable invoices. A favorite of ours is using a combination of OCR and AI to automatically compare an invoice to its PO, confirming that pricing and quantities are as originally quoted. The system can then flag items with discrepancies and route the document to the appropriate party for review.
In the coming months we will delve deeper into ways that automation can benefit organizations with document intensive applications. We have yet to hear any industry scuttlebutt involving Zombies, but two hot topics we will be writing about are the impact of Artificial Intelligence (AI) and the coming of the Bots. Stay tuned!
For those of you who want to get a bit technical . . .
As early as the 1960’s, engineers were trying to develop a way for machines to recognize text. Unlike humans with visual capability, computers don’t have eyes, nor can they differentiate between font types to be able to form a character or word. There was early capability to read a singular font type called OCR-A, but there was no way to assure that everyone used this one typeface, so its usefulness was limited.
After a spell back at the proverbial drawing board, a new way of performing OCR was developed. This new method relied on pattern recognition, whereby the computer didn’t have to recognize the whole letter “R” to know it was an “R.” Instead, the computer would look for common points, patterns and combinations of lines and shapes to determine which letter it was reading. This image, found on the website “explainthatstuff.com” demonstrates this phenomenon.
Utilizing points, patterns and lines helped speed the OCR process and enabled the flexibility to read hundreds of fonts. This technology has expanded to handwriting as well, though it works best on structured forms rather than free form handwriting.
Over the last 15 years, OCR technology has gotten faster and more accurate. Modern OCR software will have multiple language packs and the ability to ready scientific symbols and other less common font types.