-->

Tuesday, December 13, 2011

optical character recognition

If you order your cheap custom paper from our custom writing service you will receive a perfectly written assignment on optical character recognition. What we need from you is to provide us with your detailed paper instructions for our experienced writers to follow all of your specific writing requirements. Specify your order details, state the exact number of pages required and our custom writing professionals will deliver the best quality optical character recognition paper right on time.

Out staff of freelance writers includes over 120 experts proficient in optical character recognition, therefore you can rest assured that your assignment will be handled by only top rated specialists. Order your optical character recognition paper at affordable prices with cheap custom writing service!



Optical Character Recognition


From


To


Course


Order custom research paper on optical character recognition




Date


Table of Contents


Executive summary ______________________________________________


Introduction ____________________________________________________4


History ________________________________________________________6


Hardware ______________________________________________________7


Software _______________________________________________________


Conclusion ____________________________________________________11


Biography _____________________________________________________1


Executive Summary


This paper covers the history of Optical Character Recognition. Followed by that is an explanation on how the hardware component works. Software is covered then going into a conclusion of the relevance of this technology to our modern day workplace as well as possible future developments.





Introduction


Technology has advanced with great speed and stride in the last century. It has


become essential to our daily tasks and in being so, allowed us to save a great amount of


time and enhanced our productivity. Not only has technology made our lives easier, it


now open doors for us to help those of us whom we have not effectively helped in the


past, the blind. However, those days are behind us, and technology is making yet another step, with it, we are able to help those with special needs integrate into our workplaces and allowing them the freedom they demand. This is all happening thanks to OCR.


OCR stands for Optical Character Recognition. This term is typically used for general character recognition which includes the transformation of anything humanly readable to machine manipulatable representation . Simply put, OCR translates what we have on paper, to what a computer can understand.


History of OCR


The history of OCR dates back to 180 when the first patents for reading devieces to aid the blind were granted. By 11, Emmanuel Goldberg invented the first system to read printed characters and convert them to electrical code representations of the characters. His machine could translate typed characters into standard telegraph code. As well, the machine could read typed messages and convert them to paper tape, which would be used to transmit the message by the telegraphy. Two years later, the first handheld OCR scanner would be invented by Fournier D’Albe. Albe’s �optophone was a device made to aid the blind. It would emitt a �meaniful audio output” when moved across a printed page. Each tone produced had its individual unique character. Thus, the blind would be able to read by concentrating to the tones.


Through out the years, many others machines would be realized, howver, modern OCR systems originated on Friday, April 7, 151 in a home outside Washington, D,C. On that date, a 7 year old researcher working at the Deparment of Defence, created a machine capable of reading typewritten text, Morse code and musical notes. The inventor, David Shepard claimed that his machine, called GISMO, could even read back outloud letter by letter, and scanned documents. Shepard founded Intelligent Machines Reasearch Corporation(IMR) and recived a patent by 15. Around the same time, one Jacob Rabinow, founder of Rabinow Engineering, produced an OCR prototype in 15, that could identify characters at the rate of one character per minute. His company would be known for its accomplishments in OCR technologies. Up until 160, many OCR machines would be custom built and very expensive. The OCR community would also have a problem as there was no standard font for the readers. This lasted until the March of that year when the American National Standards Institute(ANSI) took on the job to find a standard font. By 166, OCR-A was pronounced the first standard font. By the mid-60’s , reader’s that could read different styles and sizes were developed. Starting from 16, font training was introduced to allow for reader’s to learn unknown fonts. One year later, the Input 80 page reader was introduced by Recognition Equipment that could read 00 large pages of text per hour, equivslent to 500 houra of manual key entry. In 17, Sear aquired a hand held OCR wand to read merchandise tags at their electronic cash registers. However, at this point in time, we haven’t even reached the real beginning to modern OCR page readers. It would be in 174 when the Kurzwell Computer Products developed a reader to scan pages of text and speak the words aloud, it was called the Reading Machine. This was for the blind. By 178 this would evolve into the first intelligent character recognition system, capable of reading typeset text and was the first with sophisticated intelligence built into the reader. In 18, Dest Corporation developed the WorkLess Station which could read up to 50 pages per hour at the price of aroun $15,000. !85 brought on new trends as the Cobra 500 was the first OCR made to work alongside a personal PC, for $000. From the mid-80’s to today, OCR development has come hand in hand with microcomputer systems. OCR are made to us the intelligence of the computer rather than stand alone. OCR of todays includes an optical scanner, interface board that plugs into an existing microcomputer and software to do the actual translations.


Hardware


Using OCR nowadays is simple enough, using a scanning device, one would scan a document and it would appear on a monitor of some sorts. Let us look more in detail the input device. OCR readers use image scanners to convert images of the characters to electrical signals that can be recognized as character by the computer. There are four types of images that can be produced by the scanner black and white bit maps, dithered halftone, grey scale image and color image. The scanner has a bright lamp that provides even light over the entire page of text. The reflected light from the page is focused using mirrors and lenses to an electrooptical sensor array, often an intergrated circuit. Each sensor of the arrayonly looks at a small portion or pixel from the array. After all pixels are read, the page opr array is moved to see a new section of the page image. This is repeated until the whole page is read.


In reading the page of text, there are three ways a scanner can accomplish this focal plane array scanning, moving mirror scanning and moving paper scanning. Focal plane scanning uses a two-dimensional array . This scanner has no moving parts, except for the automatic paper feeder. The array looks at the entire page image at once and the pixels are read out. This is limited to the resolution of the two-dimensional array. Moving mirror scanning is used in both flat and curved-platen scanners. Flate-platen scanner are used like a photocopying machine. A page is setfaced down onto the glass platen and a stepping motor moves or rotates the mirror in the optical path, moving the focal plane of the array across the page. The photosensitive array is usally one dimensional array. Due to the papper being fixed unto the platen, image distortion is reduced. However, resolution depends on the movement of the mirror and optical system. Moving paper scanning uses pinch rollers that capture the paper and guide it past the focal plane of a fixed optical system. This allows things to move faster and more smooth.But, if a roller is misaligned, problems will occur.





OCR Software


When a page of text is scanned into a PC, it is stored as an electronic file made up of tiny dots, or pixels; it is not seen by the computer as text, but rather, as a picture of text. Word processors are not capable of editing bitmap images. In order to turn the group of pixels into editable words, the image must go through OCR software.


One of the earliest OCR techniques was something called matrix, or pattern matching.. OCR programs, which use the pattern matching method, have bitmaps stored for every character of each of the different font and type sizes. By comparing a database of stored bitmaps distributed to the bitmaps of the scanned letters the program attempts to recognize the letters. This early system was only really successful using non-proportional fonts, where letters are spaced regularly and are easier to identify. This system is limited to fonts and sizes stored in its database.


Feature extraction is the next technique. This method would attempt to recognize characters by identifying their universal features. If all characters could be identified using rules defining the way that loops and lines join each other, then individual letters could be identified regardless of their typeface. However, this method would be flawed, because if the original page had extra marks on the page, or stains in the paper, it would have a dramatic effect on accuracy. Some OCR programs fix this by using spell checking on the unrecognized letters.


Predictive Optical Word Recognition (POWR) is a newer method. Instead of just trying to identify individual characters, it can identify whole words. It enables the computer to sift through the thousands or millions of different ways that dots in a word can be assembled into characters. Each possible interpretation is then assigned a probability, and the highest one is selected. POWR uses sophisticated mathematical algorithms that allow the computer to hone in on the best interpretation without examining each possible version individually. When probabilities are assigned to individual words, all kinds of contextual information and evidence is taken into account. These involve extensive use of experts algorithms set up to be specialists in various areas of character recognition. Expert knowledge about font styles, dictionary information, the degradation caused by faxes is combined into expert systems. After going through the expert system it generates an initial set of general hypotheses. The evidence for and against each hypothesis is weighed and a probability assigned to each hypothesis. The investigation continues until a clear and compelling answer emerges. At each stage in the investigation, a new set of experts is selected based on the relevance of their areas of expertise to the particular situation and their histories of success in similar situations. In the end the most probable interpretation is then selected.


Conclusion


In the modern workplace where a company can process up to a million pages of information a day, we see the importance of OCR growing each day. However, with new technology come new problems. How can a company deal with so much information and provide service in a timely manner without spending too much money?


This problem materialized itself to CIGNA, an American health insurance company, which turned to Microsystems Technologys OCR for Forms. This provided a solution similar to a conveyor belt, where analysts check each form, if fields are entered correctly then sent to the computers to process the rest. In the end, humans are still vital to any technology.


Throughout the development of OCR from the beginning till today, people have seen the potential it has to helping the blind. And it has, a blind person, as well as other jobs that need data entry can fill out any secretary job. Added to that note, OCR technology has also help children that have difficulty learning how to read. The future seems promising with OCR. Maybe it will develop into a cybernetic eye for those who are blind.





Bibliography


Books


1 Sourcebook of automatic identification and data collection


Adams, Russell E.


Van Nostrand Reinhold, 10


.Automatic Identification making it pay Sharp, Kevin R


Van Nostrand Reinhold, 10


.Automatic identification and data collection systems


Cohen, Johnathan


Mcgraw-Hill, 14


4. Optical character recognition


Mori, Shunji


J.Wiley, 1


Journals


1.Scanners OCR technology makes typing a thing of the past


Elizabeth Greenfield


The Journal (Technological Horizons In Education), Vol. 1, 11


. OCR Scanning System Saves Time and Money, Insures Good First Impression


Health Management Technology, June 1 v0 i5 p4.


Newspaper


1. Scanner-keyboard provides glimpse of better desktop


Mark Kellner


The Washington Times, July , 16





Magazines


1. Affordable Gear for the wired professional


Abhijeet Chavan, Chrus Steins


Planning, Vol. 66, July 000





Please note that this sample paper on optical character recognition is for your review only. In order to eliminate any of the plagiarism issues, it is highly recommended that you do not use it for you own writing purposes. In case you experience difficulties with writing a well structured and accurately composed paper on optical character recognition, we are here to assist you. Your cheap college papers on optical character recognition will be written from scratch, so you do not have to worry about its originality.

Order your authentic assignment from cheap custom writing service and you will be amazed at how easy it is to complete a quality custom paper within the shortest time possible!



0 comments:

Post a Comment

Note: Only a member of this blog may post a comment.