From Wikipedia, the free encyclopedia.
Optical Mark Recognition is a method of computerized input from (usually) paper forms. It is generally distinguished from OCR by the fact that a recognition engine is not required. That is, the marks are constructed in such a way that there is little chance of not reading the marks correctly.
In OMR, there is no image kept after acquisition. That is, the image is immediately interpreted, and the original image is thrown away. The high accuracy of OMR (typically 99.9%+) reduces the need for keeping any record other than the scanned value. Think of it as being similar to not keeping a copy of the sound when a record is played on a phonograph.
One of the most familiar applications of OMR is the #2 Pencil bubble test. The bubbles are filled in by aspiring students, and afterwards the test is automatically graded by a scanning machine. An image of the bubble test is not maintained, but the score is often put into a database.
Another example would be the MICR recognition of the numbers on the bottom of checks. Another would be the recognition of bar codes.
Recent improvements in OMR have lead to various kinds of two dimensional bar codes called matrix codes. For example, UPS now prints a two dimensional bar code on every package. It looks something like a black and white checkerboard painted by Salvador Dali. Of course it is printed by a computer. These images have a lot of redundancy, allowing for extremely accurate scanning. Despite this, UPS still occasionally misplaces packages.
Most of today's OMR applications work from mechanically generated images like bar codes. A smaller but still significant number of applications involve people filling in specialized forms. These forms are optimized for computer scanning, with careful registration in the printing, and careful design so that ambiguity is reduced to the minimum possible. Nevertheless, there are always ambiguous cases in converting an analog document into a digital signal, as anyone who can remember what a dangling chad is can remind you.
