Ocr abstract


Published on

This abstract is for Optical character recognition.

Published in: Education, Technology, Business
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Ocr abstract

  1. 1. Multilingual OCR Introduction ABSTRACT The aim of the project ‘Multilingual OCR’ is to develop OCR software foronline/offline handwriting recognition. OCR is an Optical character recognition and is themechanical or electronic translation of images of handwritten or typewritten text (usuallycaptured by a scanner) into machine-editable text. OCR is a field of research in patternrecognition, artificial intelligence and machine vision. Handwritten recognition is used most often to describe the ability of a computer totranslate human writing into text. This may take in one of the two ways, either by scanning ofwritten text or by writing directly on peripheral input devices.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 1
  2. 2. Multilingual OCR IntroductionAim: To develop an OCR for online/offline handwriting recognition.Description: We are going to implement the software which will recognize the characters fromonline or offline document (in image format) and use it as individual user profile. Here we are developing OCR which will recognize handwritten English characters.OCR is an Optical character recognition and is the mechanical or electronic translation ofimages of handwritten or typewritten text (usually captured by a scanner) into machine-editable text. OCR is a field of research in pattern recognition, artificial intelligence andmachine vision.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 2
  3. 3. Multilingual OCR IntroductionScope of the project: This system can be used by multiple users. We can do this by improving our software forrecognizing the handwriting of more than one user. Also if we can take the stroke information andgive it to our system, then it will be possible to recognize even cursive script also.The recognized characters are stored in the text file. We can add words to the sound files and invokethem through the program, so that the recognized words can be read aloud. Thus we can make thecomputer read the handwritten document.Block Diagram: Stored Characters Grayscale Conversion Touch Pad FilteringOn Line / Real Time Input PC Thinning Feature Scanned Document Extraction Off Line Input Pattern Recognition Recognition Output Software Domain Fig. Block Diagram for OCRPES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 3
  4. 4. Multilingual OCR Introduction1. Introduction1.1 Problem Statement: To develop an OCR for online/offline handwriting recognition.1.2 Project Scope: This system can be used by multiple users. We can do this by improving our softwarefor recognizing the handwriting of more than one user. Also if we can take the strokeinformation and give it to our system, then it will be possible to recognize even cursive scriptalso. The recognized characters are stored in the text file. We can add words to the soundfiles and invoke them through the program, so that the recognized words can be read aloud.Thus we can make the computer read the handwritten document.1.3 Project Objectives: This software is for recognizing handwritten characters and creating profile for eachparticular user. This software supports various languages (except Marathi and Hindi). Thesoftware can be used for security purposes and for creating font of user’s handwriting.1.4 Assumptions and dependencies: 1. “Multilingual OCR” requires input image with a black background and white fore color. For this purpose, the software has Invert Image option, which will convert the image in proper format. 2. System is designed only for Windows OS. It may not work for other operating system. 3. System will recognize any set of characters provided that they are written in legible manner. 4. The characters must be properly separated for greater accuracy. 5. The input given to the system must be in a Bitmap, png, jpeg, jpg file. 6. There should be constant distance between characters and rows to ensure accuracy.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 4
  5. 5. Multilingual OCR Introduction1.5 Applications of OCR:• Practical Applications: In recent years, OCR (Optical Character Recognition) technology has been appliedthroughout the entire spectrum of industries, revolutionizing the document managementprocess. OCR has enabled scanned documents to become more than just image files, turninginto fully searchable documents with text content that is recognized by computers. With thehelp of OCR, people no longer need to manually retype important documents when enteringthem into electronic databases. Instead, OCR extracts relevant information and enters itautomatically. The result is accurate, efficient information processing in less time.• Banking: The uses of OCR vary across different fields. One widely known application is inbanking, where OCR is used to process checks without human involvement. A check can beinserted into a machine, the writing on it is scanned instantly, and the correct amount ofmoney is transferred. This technology has nearly been perfected for printed checks, and isfairly accurate for handwritten checks as well, though it occasionally requires manualconfirmation. Overall, this reduces wait times in many banks.• Legal: In the legal industry, there has also been a significant movement to digitize paperdocuments. In order to save space and eliminate the need to sift through boxes of paper files,documents are being scanned and entered into computer databases. OCR further simplifiesthe process by making documents text-searchable, so that they are easier to locate and workwith once in the database. Legal professionals now have fast, easy access to a huge library ofdocuments in electronic format, which they can find simply by typing in a few keywords.• Healthcare: Healthcare has also seen an increase in the use of OCR technology to processpaperwork. Healthcare professionals always have to deal with large volumes of forms foreach patient, including insurance forms as well as general health forms. To keep up with allof this information, it is useful to input relevant data into an electronic database that can bePES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 5
  6. 6. Multilingual OCR Introductionaccessed as necessary. Form processing tools, powered by OCR, are able to extractinformation from forms and put it into databases, so that every patients data is promptlyrecorded. As a result, healthcare providers can focus on delivering the best possible service toevery patient.• OCR in Other Industries: OCR is widely used in many other fields, including education, finance, and governmentagencies. OCR has made countless texts available online, saving money for students andallowing knowledge to be shared. Invoice imaging applications are used in many businessesto keep track of financial records and prevent a backlog of payments from piling up. Ingovernment agencies and independent organizations, OCR simplifies data collection andanalysis, among other processes. As the technology continues to develop, more and moreapplications are found for OCR technology, including increased use of handwritingrecognition. Furthermore, other technologies related to OCR, such as barcode recognition, areused daily in retail and other industries. To learn more about OCR solutions for your office,you can download a free trial of Maestro Recognition Server, CVISIONs OCR toolkit, orTrapeze, our automated form-processing solution.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 6
  7. 7. Multilingual OCR Introduction1.6 Literature Survey: Now a days, there are software’s for recognizing only the English characters. Itrecognizes and stores the characters in ASCII format. Optical character recognition, usually abbreviated to OCR, is the mechanical orelectronic translation of images of handwritten, typewritten or printed text (usually capturedby a scanner) into machine-editable text. OCR is a field of research in pattern recognition, artificial intelligence and machinevision. Though academic research in the field continues, the focus on OCR has shifted toimplementation of proven techniques. Optical character recognition (using optical techniquessuch as mirrors and lenses) and digital character recognition (using scanners and computeralgorithms) were originally considered separate fields. Because very few applications survivethat use true optical techniques, the OCR term has now been broadened to include digitalimage processing as well. Early systems required training (the provision of known samples of each character) toread a specific font. "Intelligent" systems with a high degree of recognition accuracy for mostfonts are now common. Some systems are even capable of reproducing formatted output thatclosely approximates the original scanned page including images, columns and other non-textual components. In about 1965, Readers Digest and RCA collaborated to build an OCR Documentreader designed to digitize the serial numbers on Readers Digest coupons returned fromadvertisements. The fonts used on the documents were printed by an RCA Drum printerusing the OCR-A font. The reader was connected directly to an RCA 301 computer (one ofthe first solid state computers). This reader was followed by a specialised document readerinstalled at TWA where the reader processed Airline Ticket stock. The readers processeddocuments at a rate of 1,500 documents per minute, and checked each document, rejectingthose it was not able to process correctly. The product became part of the RCA product lineas a reader designed to process "Turn around Documents" such as those utility and insurancebills returned with payments. The United States Postal Service has been using OCR machines to sort mail since1965 based on technology devised primarily by the prolific inventor Jacob Rabinow. The firstPES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 7
  8. 8. Multilingual OCR Introductionuse of OCR in Europe was by the British General Post Office (GPO). In 1965 it beganplanning an entire banking system, the National Giro, using OCR technology, a process thatrevolutionized bill payment systems in the UK. Canada Post has been using OCR systemssince 1971. In 1974 Ray Kurzweil started the company Kurzweil Computer Products, Inc. and leddevelopment of the first omni-font optical character recognition system — a computerprogram capable of recognizing text printed in any normal font. He decided that the bestapplication of this technology would be to create a reading machine for the blind, whichwould allow blind people to have a computer read text to them out loud. This device requiredthe invention of two enabling technologies — the CCD flatbed scanner and the text-to-speechsynthesizer. In 1978 Kurzweil Computer Products began selling a commercial version of theoptical character recognition computer program. LexisNexis was one of the first customers,and bought the program to upload paper legal and news documents onto its nascent onlinedatabases. 1992-1996 Commissioned by the U.S. Department of Energy (DOE), InformationScience Research Institute (ISRI) conducted the most authoritative of the Annual Test ofOCR Accuracy for 5 consecutive years in the mid-90s. Information Science ResearchInstitute (ISRI) is a research and development unit of University of Nevada, Las Vegas. ISRIwas established in 1990 with funding from the U.S. Department of Energy. Its mission is tofoster the improvement of automated technologies for understanding machine printeddocuments. One study based on recognition of 19th and early 20th century newspaper pagesconcluded that character-by-character OCR accuracy for commercial OCR software variedfrom 71% to 98%; total accuracy can only be achieved by human review. Other areas—including recognition of hand printing, cursive handwriting, and printed text in other scripts(especially those East Asian language characters which have many strokes for a singlecharacter)—are still the subject of active research.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 8
  9. 9. Multilingual OCR Introduction3.5 User Characteristics: • User should be provided proper training to operate whole system • User must have the basic knowledge of computers. • User must know the handling of different instruments e.g. scanner, mouse etc.3.6 Specific Requirement:3.6.1 User Interfaces The user will interact with system • Depending on type of user required output will be generated • By writing directly on the text area provided on the GUI. • By first writing in an image file and then giving as input to the system. • The user will be asked to save the text generated in a .TXT file.3.6.2 Hardware Requirements • Intel Pentium 2 Processor • CPU minimum 500MHZ • Minimum 64 MB of RAM • Mouse • Keyboard • Scanner • MonitorPES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 9
  10. 10. Multilingual OCR Introduction3.6.3 Software Requirements • Microsoft Windows 98/NT/XP/2000 • MINIMUM JDK 1.4 • JAVA 2D API • JAVA Advanced Imaging API • JAVA Image I/O API • JAVA Media Frameworks3.6.4 Performance Requirements: • Accuracy: The extent to which a program satisfies its specification and fulfils the customer mission objective. • Reliability: The extent to which a program can be expected to perform its intended function with require precision. • Speed: The time require for a program to perform the given task. • Maintainability: The efforts required to locate and fix an error in the program. • Portability: The efforts required to transform a program from one hardware and/or software system environment to another. • Availability: The system is expected to be available around the clock as it will be further used to analyze blood slides at the installed site.3.6.5 Functional Requirements: 1. For static OCR, software should provide a way to load scanned document for recognition purpose. 2. If scanned image is not having black background and white foreground, facility for image inversion should be provided by software. 3. Software should process the image and extract characters. 4. User should have facility to save extracted data in format of his interest. 5. For dynamic OCR, the software should recognize characters drawn by user simultaneously.PES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 10
  11. 11. Multilingual OCR Introduction 6. If software is not giving proper output, there should be a way for training the database of software.3.6.6 Other Requirements: • The input image is to be in the bitmap file format • In case of scanned image, a high quality scanner as well as good paper quality is required. The resolution of the scanner should be set to a minimum of 300 dots per inch (dpi). • During scanning a maximum tilt of up to 20º can be corrected. • In case of discontinuities in the hand written characters a maximum gap of up to 3 pixel wide thickness is tolerable. • A first order median filter is used.3.7 Position Statement: Optical Handwriting recognition is used most often used to describethe ability of a computer to translate human writing into text. This system canbe used for: -  Railway Reservation Forms  Libraries  Government Agencies  School/College Admission Forms  Make other Lengthy Documents available ElectronicallyPES’s Modern College of Engineering, Shivajinagar, Pune-5 Page 11