QuickStudy: Optical Character Recognition

Rapid application development, rapid results HP StorageWorks Virtualization Outlasting the Competition: Why High Availability is Critical to Midsize Businesses Sign up to receive Security Resource Alerts

July 29, 2002 (Computerworld) -- Suppose you wanted to digitize the novel Moby Dick overnight. You could stay up all night typing and still not finish. Or you could use a high-end scanner and in minutes scan all of author Herman Melville's works into a computer using optical character recognition (OCR) technology.

This is the technology long used by libraries and government agencies to make lengthy documents quickly available electronically. Advances in OCR technology have spurred its increasing use by enterprises.

For many document-input tasks, OCR is the most cost-effective and speedy method available. And each year, the technology frees acres of storage space once given over to file cabinets and boxes full of paper documents.

Before OCR can be used, the source material must be scanned using an optical scanner (and sometimes a specialized circuit board in the PC) to read in the page as a bitmap (a pattern of dots). Software to recognize the images is also required.

The OCR software then processes these scans to differentiate between images and text and determine what letters are represented in the light and dark areas.

Older OCR systems match these images against stored bitmaps based on specific fonts. The hit-or-miss results of such pattern-recognition systems helped establish OCR's reputation for inaccuracy.

Today's OCR engines add the multiple algorithms of neural network technology to analyze the stroke edge, the line of discontinuity between the text characters, and the background. Allowing for irregularities of printed ink on paper, each algorithm averages the light and dark along the side of a stroke, matches it to known characters and makes a best guess as to which character it is. The OCR software then averages or polls the results from all the algorithms to obtain a single reading.

Print this Story

Send Us Feedback

E-mail this Story

Digg this Story

Slashdot this Story

Optical Character Recognition After the Scan Is Over

"Apple fans have made much of the fact that the newest figures from Net Applications show that Apple's share of..." Read more... "It's IT Blogwatch: in which Mozilla's Firefox Web browser continues to gain market share, smashing records as it does so...." Read more... Read more Desktop Applications posts or See all Blogs

Microsoft promises four patches next week Google gives away home-cooked Web application security scanner Storm botnet stages Fourth of July attacks More top stories...

Microsoft trumpets security additions in upcoming IE8 Apple cuts price of high-end SSD MacBook Air by $500 Ultrathin showdown: Apple MacBook Air vs. Lenovo ThinkPad X300 vs. Toshiba Portege R500

This old laptop: Revitalizing an aging notebook on the cheap All it takes is a couple hours and about $125 to breathe new life into an old laptop. Here's how. Bill Gates moves on Is Microsoft's Golden Age over? What are Gates' most memorable quotes? Find out in Computerworld's complete coverage of the end of the Bill Gates era at Microsoft. Five things you should never tell your boss There are some things your CIO definitely doesn't want to hear. Also don't miss the flipside, Five things you should always tell your boss. Hands-On: Firefox 3 fixes what's broke and keeps what's right With its latest version, Mozilla's browser continues to raise the bar for what Web browsers should be. Windows Vista A to Z Reviews, analyses, how-tos, visual tours, hot issues and predictions about Microsoft's new OS. More Continuing Coverage After 9/11: Homeland SecurityAsk a Premier 100 IT LeaderBlackBerry Legal BattleData Security BreachesElectronic VotingFirefoxH-1B VisasHP's Boardroom ScandalHandheld DevicesHurricane Katrina AftermathMicrosoft Legal IssuesMicrosoft's VistaOpen SourceRFID TechnologySCO's Linux FightSarbanes-Oxley ActSpamVoice Over IPWi-FiWindows Meta File VulnerabilityWindows XP Service Pack 3 IT Careers 2010 Four years from now, the IT field will be a vastly different place. Will you be ready? More Special Reports Premier 100 IT Leaders 2007 Best in Class2006 Computerworld Horizon Awards2006 Premier 100 IT Leaders2006 Salary Survey2007 Best Places to Work in IT2007 IT Forecast2007 Premier 100 IT Leaders40 Years of ComputerworldASPs, Take TwoBest Places to Work in IT 2003Best Places to Work in IT 2004Best Places to Work in IT 2005Best Places to Work in IT 2006Business Intelligence Home RunsBusiness Intelligence: Smarter BIBusiness Intelligence: The Future of BICRM Goes VerticalCRM: Sober CRMCareer Planning Guide 2005Careers: IT Profession 2010Computerworld Horizon Awards 2005Data Management: Mining for GemsData Management: Taming Data ChaosDevelopment: Hard-Workin' Web SitesDevelopment: New Tools New ChoicesDevelopment: The New World of Application DevelopmentDevelopment: The Web Services TsunamiDevelopment: Web Services HurdlesDisaster Recovery: Preparing for the WorstE-commerce Grows UpE-mail/Groupware: Big DecisionsFaces of Mobile ITForecast 2006Global MobileHardware: Multiple Cores, Multiple ChallengesHardware: On-Demand Un-HypedHardware: The Shape of Things to ComeHorizon Awards: 10 Cool Cutting Edge TechnologiesIT Management: Guide to Managing VendorsIT Management: Navigating Global ITIT Management: Recovery AheadIT Management: The Future of ITIT Management: The Resourceful Project ManagerInnovative Technology Awards 2004Management: Reinventing ITMicrosoft in TransitionMobile/Wireless Leaders and LaggardsMobile/Wireless: The Untethered WorkerMobile/Wireless: Tiny Gadgets, Huge CostsNetwork Management: Taking ControlNetworking: Turbulence Ahead!Networking: VoIP Goes MainstreamOperating Systems: In the Slow LaneOperating Systems: Linux Goes GlobalOperating Systems: Should You Nix Unix?Outsourcing: Offshore Buyer's GuideOutsourcing: Outsourcing DangersPremier 100 IT Leaders 2004 Best in ClassPremier 100 IT Leaders 2005 Best in ClassROI: Do the Math!Salary Survey 2003Salary Survey 2004Salary Survey 2005Security Action PlanSecurity: Compliance HeadachesSecurity: Proactive SecuritySecurity: Risk and RewardSecurity: Tips From Security ProsSouped-up SecurityStorage: Battling ComplexityStorage: Cheap & Secure Data StoresStorage: Stretching Your Storage DollarsStorage: The Lean Storage MachineStorage: The New Rules of StorageStorage: The Ultimate Backup GuideSupply Chain: Missing LinksSupply Chain: RFID Reality CheckThe Business of SecurityWeb 2.0 SecurityWireless: Wireless At Work All Zones Application Performance Zone Business Continuity Zone Data Center Management Zone Enterprise-Class Security Zone The File Data Management Zone Grid Computing on Windows Zone Security Management Zone ITIL Best Practices Zone The SAS Zone Storage Virtualization Zone Business Intelligence and Analytics Zone See your link here

Computerworld Technology Briefing: An open-source path to optimal virtualization Download this Technology Briefing now! (Source: Novell/IBM/Intel) Virtualization is about a lot more than just lowering total cost of ownership. In fact users that have taken an open source path to virtualization have realized the additional, mission-critical benefit of markedly reduced IT complexity, as well as a more flexible infrastructure that is easier to change to meet shifting, often unpredictable business requirements. Download this executive briefing  Advance your BlackBerry(R) solution management know-how this July Advance your BlackBerry(R) solution management know-how this July BlackBerry Technical Seminar, register today! Go to the webcast  Adventist Health Improves Document Access with Single Supplier Solution Download this white paper, free, compliments of Kodak! (Source: Kodak) Until 2003, Adventist Health System- headquartered in Orlando, FL-relied on a paper-based filing system to manage medical records. The not-for-profit healthcare system, with over 45,000 employees, wanted to improve access to patient records at all of its 40 hospitals in 10 states. And when they transitioned to an electronic medical records system, the organization wanted to work with the best one-vendor solution for scanners. Download this white paper  White Papers Read up on the latest ideas and technologies from companies that sell hardware, software and services. Deploying Virtualized NetWare on Linux Whitepaper Toward More Flexible, Next-Generation Collaboration Solutions Driving Business Success Through Workgroup Choice and Flexibility View more whitepapers

• Optical Character Recognition
• After the Scan Is Over

• Microsoft promises four patches next week
• Google gives away home-cooked Web application security scanner
• Storm botnet stages Fourth of July attacks
• More top stories 

Computerworld Technology Briefing: Meetings @ the Speed of Business For large organizations, Web conferencing gives a major boost to collaboration among far-flung offices. For smaller companies, experts say Web conferencing is no longer a luxury but a necessity for everything from webinars to customer presentations. But the real value lies in saving soft costs and in increases in productivity. Download this briefing

In Depth: Apple's Leopard leaps to new heights A refined look, revamped apps and new options build on an already solid OS foundation. Read more...

Accelerate your pursuit of perfection For almost 80 years, Kodak has been helping banks, insurance companies, healthcare providers, government agencies and other businesses produce billions of document images. So Kodak is uniquely positioned to know and deliver–what customers want: easy-to-use scanners that output the best possible image quality. Download this white paper now!

This podcast delivers summaries of key technologies and concepts every week. Listen to the short program on your iPod or in your Web browser. This Week: Darwin Information Typing Architecture,  List of Episodes Subscribe