OCR (Optical Character Recognition)

Optical Character Recognition (OCR) is one of the oldest data-entry techniques, letting machines read printed characters directly and, in certain controlled applications, outperform barcodes for information density.

Next to keypunching, Optical Character Recognition is the oldest data entry technique in existence. Long before the first key-to-disk or CRT-based systems were used, optical character readers were entering data in commercial and government EDP installations.

The popularity of OCR has increased each year with the advent of fast microprocessors, which enabled vastly improved recognition techniques. This is evident in OCR wands that now read print that, over 10 years ago, large batch readers would have rejected. There have also been tremendous improvements in both effective read rates and accuracy. Data entry through OCR is faster, more accurate, and generally more efficient than keystroke data entry. Desktop OCR scanners can read typewritten data into a computer at rates of up to 2400 words per minute!

There are two basic methods used for OCR: matrix matching and feature extraction. Of the two, matrix matching is the simpler and more common.

Matrix matching compares what the OCR scanner sees as a character with a library of character matrices or templates. When an image matches one of these prescribed matrices of dots within a given level of similarity, the computer labels that image as the corresponding ASCII character.

Feature extraction is OCR without strict matching to prescribed templates. Also known as Intelligent Character Recognition (ICR), or topological feature analysis, this method varies according to how much "computer intelligence" the manufacturer applies. The computer looks for general features such as open areas, closed shapes, diagonal lines, line intersections, etc. This method is much more versatile than matrix matching. Matrix matching works best when the OCR encounters a limited repertoire of type styles with little or no variation within each style. Where characters are less predictable, feature or topographical analysis is superior.

What is a font? A font is the term given to a set of characters, usually 0-9, A through Z, and a few special characters. Each character within a font has a defined, reproducible size and shape. For OCR, these are defined by ANSI, the American National Standards Institute.

OCR fonts, or characters, readable by the lower-speed, lower-cost systems discussed here require well-defined character shapes that are very reproducible and designed to be both machine- and human-readable. These unique, well-defined character sets allow for greater accuracy.

OCR reading devices fall fundamentally into two categories: text input and data capture.

Text input devices are page readers or document scanners that scan entire documents or large portions of documents. The source data is entered with the expectation that someone will edit it during or after scanning. Text input devices have varying degrees of automation, from hand-fed to fully automatic feeding, reading, sorting, and stacking.

Data capture devices are designed to capture repetitive data and perform formatting functions on it as it is entered. The data delivered from the scanner to the computer must be very accurate, because it is entered without the intention of being edited later, so accuracy must be higher than for text input.

Elements of a Successful OCR Application

The elements of a successful OCR installation include:

• Proper media
• Forms design
• Data integrity and output processing
• OCR reader

Reasons for Using OCR

There are a number of reasons for choosing OCR scanning over other methods of data entry. Some of the more significant include:

• Reducing data entry errors
• Consolidating data entry
• Handling peak loads
• Human readability
• Compatibility with many printing techniques
• Scanning corrections

When Is OCR Preferred over Barcodes?

OCR is better suited to data entry in a controlled environment, for any number of characters. For example, remittance processing, where data on utility bills or other turnaround documents needs to be entered into a system.

Some OCR scan lines may contain more than 40 characters and a variety of valuable information, such as the date the bill is due, account number, amount owed, type of service, etc.

Barcodes are best suited where the primary function is to identify parts or items in harsh environments, or where the media is reused repeatedly and consists of relatively few characters. For example, identifying and tracking passenger luggage in the airline industry. Barcodes are very tolerant of rough handling and harsh environments, but require much more space on a label or document than OCR. Inch for inch, OCR can hold six times more information than a standard barcode.