Er. Ramesh Neupane
Central Department of Computer Science and Information Technology
Institute of Science and Technology
March 13, 2011
Short for optical mark recognition, the technology of electronically extracting intended data from marked fields, such as checkboxes and fill-infields, on printed forms. OMR technology scans a printed form and reads predefined positions and records where marks are made on the form. This technology is useful for applications in which large numbers of hand-filled forms need to be processed quickly and with great accuracy, such as surveys, reply cards, questionnaires and ballots. A common OMR application is the use of "bubble sheets" for multiple-choice tests used by schools. The student indicates the answer on the test by filling in the corresponding bubble, and the form is fed through an optical mark reader (also abbreviated as OMR, a device that scans the document and reads the data from the marked fields. The error rate for OMR technology is less than 1%.
OMR Software is a computer software application that makes OMR possible on a desktop computer by using an Image scanner to process surveys, tests, attendance sheets, checklists, and other plain-paper forms printed on a laser printer.
1.1 Method of getting data from paper to computer
There are only three practical methods of getting data from a piece of paper into a computer. These three methods are to KEY the data, to use Optical Mark Reading (OMR) or to use Imaging combined in some way with Optical Character Reorganization (OCR). I should first like to review each of these techniques and select the best way of using each technique for census data collection.
There are two components to any keying system. The first component is human. This is the component that does most of the work. The second component is the keying hardware. In the early days, data was keyed on to
References:  D. H. Ballard. Generalizing the hough transform to detect arbitrary shapes. pages 714–725, 1987.  John Canny. A computational approach to edge detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on, PAMI-8(6):679–698, Nov. 1986.  C. Galambos, J. Kittler, and J. Matas. Progressive probabilistic hough transform for line detection. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, 1:1554, 1999.  P.V.C. Hough. Method and means for recognizing complex patterns, u.s. patent 3069654. 1962.