Scribd Logo
Upload

Welcome to Scribd!

  • 19 views

    Sinhala OCR To Produce Rich Text: Punchihewa D.H.T. Nishshanka N.M.J.W. Samaranayake M.M.U.C

    Uploaded by

    Priyantha Wijesinghe
    The document outlines a plan by Punchihewa D.H.T., Nishshanka N.M.J.W., and Samaranayake M.M.U.C. to develop a Sinhala optical character recognition (OCR) system that can produce rich text by recognizing layout features such as tables, bullets, columns and colors from scanned documents. The system will be integrated with a Java text editor and also delivered as a web service to facilitate conversion of images to formatted text files.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd

    Sinhala OCR To Produce Rich Text: Punchihewa D.H.T. Nishshanka N.M.J.W. Samaranayake M.M.U.C

    Uploaded by

    Priyantha Wijesinghe
    19 views13 pages
    The document outlines a plan by Punchihewa D.H.T., Nishshanka N.M.J.W., and Samaranayake M.M.U.C. to develop a Sinhala optical character recognition (OCR) system that can produce rich text by recognizing layout features such as tables, bullets, columns and colors from scanned documents. The system will be integrated with a Java text editor and also delivered as a web service to facilitate conversion of images to formatted text files.

    Original Title

    Report

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document outlines a plan by Punchihewa D.H.T., Nishshanka N.M.J.W., and Samaranayake M.M.U.C. to develop a Sinhala optical character recognition (OCR) system that can produce rich text by recognizing layout features such as tables, bullets, columns and colors from scanned documents. The system will be integrated with a Java text editor and also delivered as a web service to facilitate conversion of images to formatted text files.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    19 views13 pages

    Sinhala OCR To Produce Rich Text: Punchihewa D.H.T. Nishshanka N.M.J.W. Samaranayake M.M.U.C

    Uploaded by

    Priyantha Wijesinghe
    The document outlines a plan by Punchihewa D.H.T., Nishshanka N.M.J.W., and Samaranayake M.M.U.C. to develop a Sinhala optical character recognition (OCR) system that can produce rich text by recognizing layout features such as tables, bullets, columns and colors from scanned documents. The system will be integrated with a Java text editor and also delivered as a web service to facilitate conversion of images to formatted text files.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 13

    Sinhala OCR

    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    Sinhala OCR to produce Rich Text
    M.M.U.C.

    Outline

    Introduction Punchihewa D.H.T.


    Present status Nishshanka N.M.J.W.
    of OCR
    Samaranayake M.M.U.C.
    Our Target

    Our Plan

    Finally...
    Supervisor: Dr.Roshan G. Ragel
    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T. 1 Introduction
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C. 2 Present status of OCR
    Outline

    Introduction
    3 Our Target
    Present status
    of OCR

    Our Target
    4 Our Plan
    Our Plan

    Finally...
    5 Finally...
    What is an OCR System ?

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C. Optical Character Recognition, usually abbreviated to OCR, is
    Outline the mechanical or electronic translation of scanned images of
    Introduction handwritten, typewritten or printed text into machine-encoded
    Present status text.
    of OCR
    −Wikipedia
    Our Target

    Our Plan

    Finally...
    Sinhala OCR to produce Rich Text

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C.
    This is a software solution for
    Outline Recognizing Sinhala characters and encode it into
    Introduction
    Unicode.
    Present status
    of OCR Detect layout of the document and preserve it.
    Our Target

    Our Plan

    Finally...
    Why is this important ?

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka To convert books and documents into electronic files.
    N.M.J.W.
    Samaranayake
    M.M.U.C.
    To computerize a record-keeping system in an office.
    To publish the text on a website.
    Outline

    Introduction OCR makes it possible to


    Present status
    of OCR Edit the text
    Our Target Search for a word or phrase
    Our Plan
    Text-to-speech
    Finally...
    Text mining
    Current work on the field

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa Best softwares


    D.H.T.
    Nishshanka Microsoft OneNote 2007
    N.M.J.W.
    Samaranayake
    M.M.U.C.
    SimpleOCR
    Outline
    TopOCR
    Introduction freeOCR
    Present status
    of OCR
    Many of these
    Our Target Produces normal text.
    Our Plan
    Do not have font styling.
    Finally...
    Do not have Table detection.
    Only supported for two or three image file types.
    Avalable Sinhala OCR

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    Sinhala OCR
    M.M.U.C.
    A tool from UCSC
    Outline
    Only output a text file without formating
    Introduction

    Present status
    TerpWord
    of OCR
    A tool from UOP
    Our Target

    Our Plan Only contains certain levels of formatting


    Finally...
    What we are going to about it

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W. Support lots of image types
    Samaranayake
    M.M.U.C.
    Detect format not by line but as words
    Outline Detect tables
    Introduction
    Detect bullets
    Present status
    of OCR
    Detect columns
    Our Target

    Our Plan
    Detect colors
    Finally... Provide all these facilities as a WEB Service
    Task distribution

    Sinhala OCR
    to produce
    Rich Text
    Reviewing the current TerpWord code base
    Punchihewa
    D.H.T.
    Nishshanka
    Related knowledge gathering
    N.M.J.W.
    Samaranayake Devising a way to recognize words and its format
    M.M.U.C.
    Implementing those features in phase one
    Outline

    Introduction
    Debugging the whole application
    Present status Developing a way to detect tables
    of OCR

    Our Target
    Developing way to detect colors
    Our Plan Including punctuation marks in the image to the rich text
    Finally...
    Recognizing english characters in text
    Integrate it with a JAVA text editor
    Developing a web service as web version of this application
    Technologies and needed resources

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C.
    Image processing using matlab
    Outline
    Text editor integration using java
    Introduction

    Present status
    Version controlling using Mercural
    of OCR
    Eclipse for code editing
    Our Target

    Our Plan

    Finally...
    Final outcome

    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C.
    A text editor which has capability convert images of
    Outline
    sinhala documents preserving all page formats and
    Introduction
    styles.And deliver a *.rtf file.
    Present status
    of OCR A web service that can facilitate all these features.
    Our Target

    Our Plan

    Finally...
    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C.

    Outline

    Introduction

    Present status
    of OCR
    Q&A
    Our Target

    Our Plan

    Finally...
    Sinhala OCR
    to produce
    Rich Text

    Punchihewa
    D.H.T.
    Nishshanka
    N.M.J.W.
    Samaranayake
    M.M.U.C.

    Outline

    Introduction

    Present status
    of OCR
    Thank You !
    Our Target

    Our Plan

    Finally...

    You might also like