DOCSLIB.ORG

HISTORIA DE OCR Reconocimiento Óptico De Caracteres

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
HISTORIA DE OCR Reconocimiento Óptico De Caracteres RECONOCIMIENTO ÓPTICO DE CARACTERES (OCR) CON REDES NEURONALES ESTADO DEL ARTE OPTICAL CHARACTER RECOGNITION (OCR) WITH NEURAL NETWORKS STATE OF THE ART Juan Pablo Ordóñez L. Loja 086244139 [email protected] RESUMEN conversion of written text on paper to text Los sistemas que, a partir de un texto stored in an ASCII file. escrito o impreso en papel o similar, WORKS KEY: Ocr, network neuronal, crean un fichero de texto en un soporte de Recognition of manuscripts. almacenamiento informático, se denominan Sistemas de OCR (Optical Character Recognition), o de HISTORIA DE OCR Reconocimiento óptico de Caracteres. Un sistema OCR cuenta con las siguientes características: de poder "aprender", En 1929, Gustav Tauschek obtuvo una mediante una red neuronal, patrones de patente sobre OCR en Alemania, luego, caracteres que representen las posibles Handel en 1933 obtiene la patente de variaciones (tamaño) de la forma de los diferentes caracteres impresos que pueden OCR en EEUU. En 1935, a Tauschek aparecer en los documentos, para en el también se le concedió una patente en futuro y con la misma red, poder EEUU por su método. "reconocerlos" y realizar la conversión del texto escrito en papel a texto La máquina de Tauschek era un almacenado en un fichero ASCII. dispositivo mecánico que utilizaba PALABRAS CLAVE: Ocr, Redes plantillas. Un foto-detector era colocado neuronales, Reconocimiento de de modo que cuando la plantilla y el manuscritos. carácter que se reconocería estuvieran ABSTRACT alineados, una luz era dirigida hacia ellos. Systems that, from a written or printed on paper or similar, creating a text file on a En 1950, David Shepard, criptoanalista en storage medium for computer systems are la agencia de seguridad de las fuerzas called OCR (Optical Character Recognition). An OCR system has the armadas de los Estados Unidos, fue following characteristics: can "learn" consultado por Rowlett Franco para through a neural network, patterns of trabajar con el Dr. Louis Tordella, para characters representing the possible recomendar los procedimientos de la variations (size) as the different automatización de los datos de la agencia. characters that can appear in documents, Esto incluía el problema de convertir so in the future and with the same mensajes impresos en lenguajes para network, able to "recognize" and the almacenarlos en un computador. Shepard decide que es posible construir una máquina. IBM y otras empresas fueron máquina para realizar ese proceso, y, con licenciadas más adelante sobre las la ayuda del cocinero de Harvey, un patentes del OCR de Shepard. amigo, construyeron Gismo durante las tardes y fines de semana. Este suceso fue El servicio postal de Estados Unidos ha divulgado en los periódicos Washington estado utilizando las máquinas de OCR Daily News y el New York Times en el para clasificar el correo desde que 1965, año 1953, después de que su patente fuera basados en la tecnología ideada sobre concedida. En este momento, Shepard todo por el inventor prolífico Jacob fundó Intelligent Machines Research Rabinow. El primer uso del OCR en Corporation (IMR), comenzando a Europa sucedió en la oficina de Gran fabricar el primero de varios sistemas del Bretaña. En 1965 se comenzó a planear OCR usados para operaciones un sistema de actividades bancarias comerciales. Mientras que Gismo y los completo, Nacional Giro, usando la últimos sistemas de IMR, utilizaron tecnología del OCR, ideó un proceso que análisis de imagen, en comparación con el revolucionó los sistemas del pago de carácter que emparejaba, pudiendo cuentas en el Reino Unido. El correo aceptar una cierta variación de la fuente. postal de Canadá ha estado utilizando Gismo estaba limitado a los registros sistemas OCR desde 1971. Los sistemas verticales, mientras que los reconocedores OCR leen el nombre y la dirección del posteriores de la compañía IMR, destinatario, e imprimen un código de analizaban caracteres en cualquier parte barras en el sobre basados en el código del campo de exploración, una necesidad postal del mismo. Después, las cartas práctica en documentos del mundo real. necesitan solamente ser clasificadas por los compaginadores, menos costosos que necesitan leer solamente el código de El primer sistema comercial fue instalado barras. Para evitar interferencia con el en Readers Digest en 1955, que, muchos campo de dirección escrita a mano, que se años más tarde, fue donado por al museo puede situar en cualquier parte de la carta, Smithsonian, donde fue puesto en la se usa una tinta especial leída bajo una exhibición. El segundo sistema fue ultravioleta. Esta tinta parece anaranjada vendido a los Standard Oil Company de en condiciones normales de la California para leer impresiones en iluminación. Los sobres marcados con el tarjetas de crédito para propósitos de código de barras que son leídos por la facturación, además se vendieron muchos máquina pueden ser posteriormente más sistemas a compañías petroleras. procesados. [1] Otros sistemas vendieron por el IMR durante los últimos años 50 incluyeron un ESTADO ACTUAL DE LA escáner de páginas para la fuerza aérea de TECNOLOGÍA OCR los Estados Unidos para la lectura y transmisión de mensajes escritos a El reconocimiento exacto de la escritura el Reconocimiento Inteligente de latina, ahora se considera en gran parte un Caracteres. problema solucionado. La exactitud excede el 99%, aunque hay veces en que El reconocimiento del texto cursivo es un se exige incluso una exactitud más alta, campo de investigación activo, con requiriendo la revisión humana para los medidas de reconocimiento incluso mas errores. Actualmente está en desarrollo el baja que el del reconocimiento de texto reconocimiento de la mano que escribe, al impreso a mano. Índices más altos del igual que el reconocimiento del texto reconocimiento de la escritura cursiva impreso en otras lenguas (especialmente general no serán probablemente posibles en los que tienen un número muy grande sin el uso de la información del contexto de caracteres). o gramatical. Por ejemplo, el reconocimiento de palabras enteras de un Los sistemas reconocedores el texto diccionario es más fácil que intentando impreso a mano han gozado de éxito analizar caracteres individuales de la comercial estos últimos años. Entre éstos escritura. La lectura de la línea de la están dispositivos de asistencia personales monto de un cheque, es un ejemplo donde digitales (PDA) tales como los Palm OS. usar un diccionario más pequeño Apple es pionero en esta tecnología. Los especializado en escritura de números, algoritmos usados en estos dispositivos puede aumentar tarifas del toman ventaja del orden, velocidad y reconocimiento enormemente. El dirección de las líneas o segmentos conocimiento de la gramática de la lengua individuales en su entrada son conocidos. que es explorada puede también ayudar a También, el usuario puede aprendido determinar si una palabra es probable ser habilidades nuevas para utilizar un verbo o un sustantivo, por ejemplo, solamente formas específicas de la letra permitiendo mayor exactitud. (por ejemplo, un triangulo sin su base correspondería a la letra A). Estos Para problemas más complejos del métodos no se pueden utilizar en software reconocimiento, se usan los sistemas de escanean documentos en papel, por lo que reconocimiento inteligente de caracteres, el reconocimiento exacto de documentos pues las redes neuronales artificiales que impresos a mano sigue siendo en gran los componen, trabajan indiferentes a las parte un problema abierto al desarrollo. transformaciones lineales y no lineales Índices de exactitud del 80 al 90% en del proceso de reconocimiento. caracteres impresos a mano, pueden ser alcanzados, pero esta exactitud todavía se Una variante del OCR es el OMR (optical traduce en docenas de errores por cada mark recognition) que se utiliza para página, haciendo la tecnología útil reconocimiento de marcas. Una solamente en contextos muy limitados. aplicación sería la corrección automática Esta variedad de OCR ahora se conoce de exámenes de tipo test, en los que la comúnmente en la industria como ICR, o respuesta correcta se rodea con un círculo, tipo PSU. [2] [3] Software OCR. Aquí se lista algunas aplicaciones que hacen uso de la tecnología ocr. [4] Nombre Licencia Sistemas Notas Operativos ExperVision Commercial Windows,Mac OS ExperVision Inc. was founded TypeReader & X,Unix,Linux,OS/2 in 1987, its OCR technology OpenRTK and product won the highest marks in the independent testing performed by UNLV for the consecutive years that ExperVision participated. ABBYY Commercial Windows For working with localized FineReader OCR interfaces, corresponding language support is required. OmniPage Commercial Windows, Mac OS Product of Nuance (Nuance Communications EULA) Readiris Commercial Windows, Mac OS Product of I.R.I.S. Group of Belgium. Asian and Middle Eastern editions. SmartZone Commercial Windows Zonal OCR is the process by (formerly known which Optical Character as Zonal OCR) Recognition (OCR) applications "read" specifically zoned text from a scanned image. Computhink's Commercial Windows Document Management ViewWise system CuneiForm BSD variant Windows, Linux, Enterprise-class system, multi BSD, MacOSX. language, can save text formatting and recognizes complicated tables of any structure GOCR GPL Many (open source) Early development Microsoft Office Commercial Windows, Mac OS Document X Imaging Microsoft Office Commercial Windows OneNote 2007 NovoDynamics Commercial? ? Specializes in languages of the VERUS Middle East Ocrad GPL Unix-like, OS/2
Load more

Recommended publications
  • OCR Pwds and Assistive Qatari Using OCR Issue No
    Arabic Optical State of the Smart Character Art in Arabic Apps for Recognition OCR PWDs and Assistive Qatari using OCR Issue no. 15 Technology Research Nafath Efforts Page 04 Page 07 Page 27 Machine Learning, Deep Learning and OCR Revitalizing Technology Arabic Optical Character Recognition (OCR) Technology at Qatar National Library Overview of Arabic OCR and Related Applications www.mada.org.qa Nafath About AboutIssue 15 Content Mada Nafath3 Page Nafath aims to be a key information 04 Arabic Optical Character resource for disseminating the facts about Recognition and Assistive Mada Center is a private institution for public benefit, which latest trends and innovation in the field of Technology was founded in 2010 as an initiative that aims at promoting ICT Accessibility. It is published in English digital inclusion and building a technology-based community and Arabic languages on a quarterly basis 07 State of the Art in Arabic OCR that meets the needs of persons with functional limitations and intends to be a window of information Qatari Research Efforts (PFLs) – persons with disabilities (PWDs) and the elderly in to the world, highlighting the pioneering Qatar. Mada today is the world’s Center of Excellence in digital work done in our field to meet the growing access in Arabic. Overview of Arabic demands of ICT Accessibility and Assistive 11 OCR and Related Through strategic partnerships, the center works to Technology products and services in Qatar Applications enable the education, culture and community sectors and the Arab region. through ICT to achieve an inclusive community and educational system. The Center achieves its goals 14 Examples of Optical by building partners’ capabilities and supporting the Character Recognition Tools development and accreditation of digital platforms in accordance with international standards of digital access.
    [Show full text]
  • Reconocimiento De Escritura Lecture 4/5 --- Layout Analysis
    Reconocimiento de Escritura Lecture 4/5 | Layout Analysis Daniel Keysers Jan/Feb-2008 Keysers: RES-08 1 Jan/Feb-2008 Outline Detection of Geometric Primitives The Hough-Transform RAST Document Layout Analysis Introduction Algorithms for Layout Analysis A `New' Algorithm: Whitespace Cuts Evaluation of Layout Analyis Statistical Layout Analysis OCR OCR - Introduction OCR fonts Tesseract Sources of OCR Errors Keysers: RES-08 2 Jan/Feb-2008 Outline Detection of Geometric Primitives The Hough-Transform RAST Document Layout Analysis Introduction Algorithms for Layout Analysis A `New' Algorithm: Whitespace Cuts Evaluation of Layout Analyis Statistical Layout Analysis OCR OCR - Introduction OCR fonts Tesseract Sources of OCR Errors Keysers: RES-08 3 Jan/Feb-2008 Detection of Geometric Primitives some geometric entities important for DIA: I text lines I whitespace rectangles (background in documents) Keysers: RES-08 4 Jan/Feb-2008 Outline Detection of Geometric Primitives The Hough-Transform RAST Document Layout Analysis Introduction Algorithms for Layout Analysis A `New' Algorithm: Whitespace Cuts Evaluation of Layout Analyis Statistical Layout Analysis OCR OCR - Introduction OCR fonts Tesseract Sources of OCR Errors Keysers: RES-08 5 Jan/Feb-2008 Hough-Transform for Line Detection Assume we are given a set of points (xn; yn) in the image plane. For all points on a line we must have yn = a0 + a1xn If we want to determine the line, each point implies a constraint yn 1 a1 = − a0 xn xn Keysers: RES-08 6 Jan/Feb-2008 Hough-Transform for Line Detection The space spanned by the model parameters a0 and a1 is called model space, parameter space, or Hough space.
    [Show full text]
  • An Accuracy Examination of OCR Tools
    International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8, Issue-9S4, July 2019 An Accuracy Examination of OCR Tools Jayesh Majumdar, Richa Gupta texts, pen computing, developing technologies for assisting Abstract—In this research paper, the authors have aimed to do a the visually impaired, making electronic images searchable comparative study of optical character recognition using of hard copies, defeating or evaluating the robustness of different open source OCR tools. Optical character recognition CAPTCHA. (OCR) method has been used in extracting the text from images. OCR has various applications which include extracting text from any document or image or involves just for reading and processing the text available in digital form. The accuracy of OCR can be dependent on text segmentation and pre-processing algorithms. Sometimes it is difficult to retrieve text from the image because of different size, style, orientation, a complex background of image etc. From vehicle number plate the authors tried to extract vehicle number by using various OCR tools like Tesseract, GOCR, Ocrad and Tensor flow. The authors in this research paper have tried to diagnose the best possible method for optical character recognition and have provided with a comparative analysis of their accuracy. Keywords— OCR tools; Orcad; GOCR; Tensorflow; Tesseract; I. INTRODUCTION Optical character recognition is a method with which text in images of handwritten documents, scripts, passport documents, invoices, vehicle number plate, bank statements, Fig.1: Functioning of OCR [2] computerized receipts, business cards, mail, printouts of static-data, any appropriate documentation or any II. OCR PROCDURE AND PROCESSING computerized receipts, business cards, mail, printouts of To improve the probability of successful processing of an static-data, any appropriate documentation or any picture image, the input image is often ‘pre-processed’; it may be with text in it gets processed and the text in the picture is de-skewed or despeckled.
    [Show full text]
  • Integral Estimation in Quantum Physics
    INTEGRAL ESTIMATION IN QUANTUM PHYSICS by Jane Doe A dissertation submitted to the faculty of The University of Utah in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Mathematical Physics Department of Mathematics The University of Utah May 2016 Copyright c Jane Doe 2016 All Rights Reserved The University of Utah Graduate School STATEMENT OF DISSERTATION APPROVAL The dissertation of Jane Doe has been approved by the following supervisory committee members: Cornelius L´anczos , Chair(s) 17 Feb 2016 Date Approved Hans Bethe , Member 17 Feb 2016 Date Approved Niels Bohr , Member 17 Feb 2016 Date Approved Max Born , Member 17 Feb 2016 Date Approved Paul A. M. Dirac , Member 17 Feb 2016 Date Approved by Petrus Marcus Aurelius Featherstone-Hough , Chair/Dean of the Department/College/School of Mathematics and by Alice B. Toklas , Dean of The Graduate School. ABSTRACT Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah. Blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah.
    [Show full text]
  • JETIR Research Journal
    © 2019 JETIR June 2019, Volume 6, Issue 6 www.jetir.org (ISSN-2349-5162) IMAGE TEXT CONVERSION FROM REGIONAL LANGUAGE TO SPEECH/TEXT IN LOCAL LANGUAGE 1Sayee Tale,2Manali Umbarkar,3Vishwajit Singh Javriya,4Mamta Wanjre 1Student,2Student,3Student,4Assistant Professor 1Electronics and Telecommunication, 1AISSMS, Institute of Information Technology, Pune, India. Abstract: The drivers who drive in other states are unable to recognize the languages on the sign board. So this project helps them to understand the signs in different language and also they will be able to listen it through speaker. This paper describes the working of two module image processing module and voice processing module. This is done majorly using Raspberry Pi using the technology OCR (optical character recognition) technique. This system is constituted by raspberry Pi, camera, speaker, audio playback module. So the system will help in decreasing the accidents causes due to wrong sign recognition. Keywords: Raspberry pi model B+, Tesseract OCR, camera module, recording and playback module,switch. 1. Introduction: In today’s world life is too important and one cannot loose it simply in accidents. The accident rates in today’s world are increasing day by day. The last data says that 78% accidents were because of driver’s fault. There are many faults of drivers and one of them is that they are unable to read the signs and instructions written on boards when they drove into other states. Though the instruction are for them only but they are not able to make it. So keeping this thing in mind we have proposed a system which will help them to understand the sign boards written in regional language.
    [Show full text]
  • Representation of Web Based Graphics and Equations for the Visually Impaired
    TH NATIONAL ENGINEERING CONFERENCE 2012, 18 ERU SYMPOSIUM, FACULTY OF ENGINEERING, UNIVERSITY OF MORATUWA, SRI LANKA Representation of Web based Graphics and Equations for the Visually Impaired C.L.R. Gunawardhana, H.M.M. Hasanthika, T.D.G.Piyasena,S.P.D.P.Pathirana, S. Fernando, A.S. Perera, U. Kohomban Abstract With the extensive growth of technology, it is becoming prominent in making learning more interactive and effective. Due to the use of Internet based resources in the learning process, the visually impaired community faces difficulties. In this research we are focusing on developing an e-Learning solution that can be accessible by both normal and visually impaired users. Accessibility to tactile graphics is an important requirement for visually impaired people. Recurrent expenditure of the printers which support graphic printing such as thermal embossers is beyond the budget for most developing countries which cannot afford such a cost for printing images. Currently most of the books printed using normal text Braille printers ignore images in documents and convert only the textual part. Printing images and equations using normal text Braille printers is a main research area in the project. Mathematical content in a forum and simple images such as maps in a course page need to be made affordable using the normal text Braille printer, as these functionalities are not available in current Braille converters. The authors came up with an effective solution for the above problems and the solution is presented in this paper. 1 1. Introduction In order to images accessible to visually impaired people the images should be converted into a tactile In this research our main focus is to make e-Learning format.
    [Show full text]
  • OCR with Printed Text Author: Gerry Kennedy © ICT Consultancy
    Fact Sheet: Universal Access using OCR with Printed Text Author: Gerry Kennedy © ICT Consultancy Title: Universal Access using OCR with Printed Text Author: Gerry Kennedy © February 2009 Software: OCR (Optical Character Recognition) programs Category: Scanning devices OCR applications and access to text 1. Introduction Optical Character Recognition (usually referred to simply as OCR) software has been used for many years in education, research and business. It provides access to text in all manner of printed materials. OCR software makes it easy to re-use and access existing printed or online documents with perfect formatting. Converted documents can look exactly like the original – complete with colour, columns, tables, bullets and graphics. Optical character recognition „is the mechanical or electronic translation of images of handwritten, typewritten or printed text (usually captured by a scanner) into machine-editable text.‟ [http://en.wikipedia.org/wiki/Optical_character_recognition] Any scanning device can benefit from the power of unlocking and sharing information stored on paper as accurately reproduced digital documents. They can be reversioned as PDF, MS Word, HTML documents or purely as text. Various OCR programs provide the speed, accuracy, quality and features to maximise the benefits of current scanning or all-in-one devices. Note: The device needs to be OCR capable or can save/convert a file in a format that can be used by scanning software. With most flatbed scanners, photocopiers or printer-scanner models, converting information that was formerly „locked‟ on paper or in digital files into a preferred format, is made simpler and easier than previously imagined. Just load the print material, convert it and students are ready to re-use it.
    [Show full text]
  • Manual Archivista 2009/I
    Manual Archivista 2009/I c 18th January 2009 by Archivista GmbH, CH-8118 Pfaffhausen Web pages: www.archivista.ch Contents I Introduction 8 4.4 Accessing the manual . 26 4.5 Login WebClient . 26 1 Introduction 9 4.6 Scanning and entering keywords . 26 1.1 Welcome to Archivista . 9 4.7 Rotating pages . 26 1.2 Notes on the manual . 9 4.8 Title search . 27 1.3 Our address . 9 4.9 Full text search . 27 1.4 Previous versions . 9 4.10 Login WebAdmin . 27 1.5 Licensing . 12 4.11 Adding users . 27 4.12 Adding/deleting fields . 27 2 First Steps 18 4.13 Editing the input/search mask . 27 2.1 Introduction . 18 4.14 Activating SSH . 27 2.2 The digital archive . 18 4.15 Activating VNC . 27 2.3 Database, server and client . 18 4.16 Enabling print server (CUPS) . 28 2.4 Tables, records and fields . 19 4.17 Password, Unlock & Restart OCR . 28 2.5 Archivista and working method . 19 4.18 Activating HTTPS . 28 2.6 Tips for archiving . 20 2.7 Archive, pages and documents . 20 5 Tutorial RichClient 29 2.8 The Archivista document . 20 5.1 Archivista in 90 Seconds . 29 5.2 Adding Documents . 29 3 Installation 22 5.3 Search . 29 3.1 ArchivistaBox . 22 5.4 Extended Functions . 30 3.2 Virtual (Box) . 22 5.5 Users & Fields . 31 3.3 OpenSource (Box) . 22 5.6 Databases, fields and barcodes . 31 3.4 OpenSource (Windows) . 22 III ArchivistaBox 33 II Tutorials 25 6 Introduction 34 4 Introduction 26 6.1 Advantages .
    [Show full text]
  • Design and Implementation of a System for Recording and Remote Monitoring of a Parking Using Computer Vision and Ip Surveillance Systems
    VOL. 11, NO. 24, DECEMBER 2016 ISSN 1819-6608 ARPN Journal of Engineering and Applied Sciences ©2006-2016 Asian Research Publishing Network (ARPN). All rights reserved. www.arpnjournals.com DESIGN AND IMPLEMENTATION OF A SYSTEM FOR RECORDING AND REMOTE MONITORING OF A PARKING USING COMPUTER VISION AND IP SURVEILLANCE SYSTEMS Albeiro Cortés Cabezas, Rafael Charry Andrade and Harrinson Cárdenas Almario Department of Electronic Engineering, Surcolombiana University Grupo de Tratamiento de Señales y Telecomunicaciones, Pastrana Av. Neiva Colombia, Huila E-Mail: [email protected] ABSTRACT This article presents the design and implementation of a system for detection of license plates for a public parking located at the municipality of Altamira at the state of Huila in Colombia. The system includes also, a module of surveillance cameras for remote monitoring. The detection system consists of three steps: the first step consists in locating and cutting the vehicle license plate from an image taken by an IP camera. The second step is an optical character recognition (OCR), responsible for identifying alphanumeric characters included in the license plate obtained in the first step. And the third step consists in the date and time register operation for the vehicles entry and exit. This data base stores also the license plate number, information about the contract between parking and vehicle owner and billing. Keywords: image processing, vision, monitoring, surveillance, OCR. 1. INTRODUCTION vehicles in a parking and store them in digital way to gain In recent years the automatic recognition plates control of the activity in the parking, minimizing errors numbers technology -ANPR- (Automatic Number Plate that entail manual registration and storage of information Recognition) has had a great development in congestion in books accounting and papers.
    [Show full text]
  • Optical Character Recognition Using Android
    International Journal of Computer Networking, Wireless and Mobile Communications (IJCNWMC) ISSN 2250-1568 Vol. 3, Issue 3, Aug 2013, 57-62 © TJPRC Pvt. Ltd. OPTICAL CHARACTER RECOGNITION USING ANDROID BHAKTI KARANI1, PARITA SANGHAVI2, HARSHITA BHALAKIYA3 & VINAYA SAWANT4 1,2,3B.E.,Information Technology, D. J. Sanghvi College of Engineering, Mumbai, Maharashtra, India 4Assistant Professor, Information Technology, D. J. Sanghvi College of Engineering, Mumbai, Maharashtra, India ABSTRACT The paper deals with the development of a mobile application based on Android platform for capturing digital photography and its subsequent processing by OCR (Optical Character Recognition) technologies. The developed solution provides capability of calculating equations and getting synonyms of difficult words. KEYWORDS: ABBYY’s Engine, Android OS, Optical Character Recognition (OCR) INTRODUCTION In today's world of automation, time is equivalent to money. Doing the work on the go is the need of the hour. The major problem these days arises in the organization is, for performing even the small task the user has to input the data manually into the corresponding software on the computer. This becomes very time consuming and tedious task for the user. Results for strategic decisions are required every now and then, but, on the other hand, it takes a long time for the user to obtain the results. Archaic aims on solving all the above problems on the go by just using their mobile phones. The project aims at using scanning and comparing techniques intended to identify printed text and equations into a digital format, in other words, getting answer of equation and meaning of words. In comparison with other calculation software’s that are available for PCs and mobiles, Archaic has the potential to give the output just by scanning the data taken as input in the form of equations or words from a mobile camera rather than making the user input the data manually.
    [Show full text]
  • The Common OCR Service Interface Rev 4 (2 Apr 2016) – © Sylvain Giroudon, 2007-2016
    COSI – The Common OCR Service Interface Rev 4 (2 apr 2016) – © Sylvain Giroudon, 2007-2016 What is COSI COSI stands for « Common OCR Service Interface ». COSI is an open standard targeted at using different OCR (Optical Character Recognition) programs as external agents in a unified manner. COSI allows to integrate an OCR tool into various top-level applications using a client-server approach. COSI has been successfully implemented and experimented on well-known open source OCR applications: – GOCR (http://jocr.sourceforge.net); – Tesseract-OCR (http://code.google.com/p/tesseract-ocr). – GNU Ocrad (http://www.gnu.org/software/ocrad). COSI implementations are available from the GitHub repository, at github.com/testfarm/cosi. Where does COSI come from ? The primary goal of COSI is to implement OCR capability for the “TestFarm Virtual User” software platform, a test automation tool that detects and tracks graphical objects displayed by an application. Please refer to the web site http://www.testfarm.org for further details about this tool. COSI Overview The main principles that characterize COSI are: – We use use existing OCR tools as local services to extract text from a graphical frame buffer, rather than from a static image file. An OCR tool that supports COSI is then called the “OCR server”. – The OCR server takes its graphical input from a frame buffer mapped in a shared memory segment. This shared frame buffer is written by the client and read by the OCR server. – The OCR server accepts requests from the client through its standard input. A request is a simple command line, which may include some options such as the coordinates of the graphical window from which the text is extracted (a.k.a Region of Interest).
    [Show full text]
  • Comparison of Optical Character Recognition (OCR) Software
    Angelica Gabasio May 2013 Comparison of optical character recognition (OCR) software Master's thesis work carried out at Sweco Position. Supervisors Bj¨ornHarrtell, Sweco Tobias Lennartsson, Sweco Examiner Jacek Malec, Lund University The purpose of the thesis was to test some different optical char- acter recognition (OCR) software to find out which one gives the best output. Different kinds of images have been OCR scanned to test the software. The output from the OCR tools has been automatically compared to the correct text and the error percentage has been cal- culated. Introduction Optical character recognition (OCR) is used to extract plain text from images containing text. This is useful when information in paper form is going to be digitized. OCR is applied to the images to make the text editable or searchable. Another way of using OCR scanning is to process forms automatically.[1] If the output from the OCR tool contains many errors, it would require a lot of manual work to fix them. This is why it is important to get a correct or almost correct output when using OCR. The output from different OCR tools may differ a lot, and the purpose of this comparison is to find out which OCR software to use for OCR scanning. OCR steps As seen in Figure 1, the OCR software takes an image, applies OCR on it and outputs plain text. Figure 1 also shows the basic steps of the OCR algorithm, which are explained below[1, 2]: Preprocessing Preprocessing can be done either manually before the image is given to the OCR tool, or it can be done internally in the software.
    [Show full text]