GUI front end _amp; User Interactions for OCR by ert554898


									                 14th July 2011

GUI front end & User
Interactions for OCR
                            A Brief Overview of OCR and Braille
Optical       character         recognition,    usually    abbreviated         to      OCR,       is
the mechanical or electronic translation of scanned images of handwritten, typewritten or
printed text into machine-encoded text. It is widely used to convert books and documents into
electronic files, to computerize a record-keeping system in an office, or to publish the text on a
website. OCR makes it possible to edit the text, search for a word or phrase, store it more
compactly, display or print a copy free of scanning artifacts, and apply techniques such
as machine translation, text-to-speech and text mining to it. OCR is a field of research in pattern
recognition, artificial intelligence and computer vision.

The Braille system is a method that is widely used by blind people to read and write, and was
the first digital form of writing. Each Braille character, or cell, is made up of six dot positions,
arranged in a rectangle containing two columns of three dots each. A dot may be raised at any
of the six positions to form sixty-four (26) possible subsets, including the arrangement in which
no dots are raised. For reference purposes, a particular permutation may be described by
naming the positions where dots are raised, the positions being universally numbered 1 to 3,
from top to bottom, on the left, and 4 to 6, from top to bottom, on the right. For example,
dots 1-3-4 would describe a cell with three dots raised, at the top and bottom in the left
column and on top of the right column, i.e., the letter m. The lines of horizontal Braille text are
separated by a space, much like visible printed text, so that the dots of one line can be
differentiated from the Braille text above and below. Punctuation is represented by its own
unique set of characters.
 Initial preview of the GUI showing different options provided for the user .
 On the Menu Bar whenever cursor is clicked on the File tab , a window
consisting of 3 alternatives one for opening a new scanned file , one for closing
the current file and the other for exiting from the software is provided .
 When “Open” option is selected from File tab , the usual dialog box is opened as
shown. Now the desired scanned file is selected .
 File  Open  Choose the scanned file.
 The scanned image file is opened on the left hand side as shown ( provided
vertical split is selected . The horizontal split is shown later ) .
 Once after the scanned text gets loaded , from the Language tab on the Menu bar ,
desired language is chosen .
 Now when the button provided at the bottom “Perform OCR” ( Highlighted in the picture )
is pressed , a dialog box showing the progress of OCR is opened as shown.
 The process can be paused as well as stopped in between .
 To enhance the speed of proof reading , “Spell Check” option is provided at the
bottom of the window .
 By right clicking on the word which contains the error will show the suggestions to rectify
the word.
 On the blank space of the OCR output if a right click is made, the window providing
the option for demarking the beginning ,ending of the chapter and also to skip a
specific image is opened . This facilitates Braille formatting process.
 After final proof reading , the OCR output can be either saved in Daisy or Braille
format . Also the OCR output can be retained as it is (.RTF format ) .
 This can be done by selecting appropriate option in “Save as” tab ( Highlighted in
the picture ) , provided at the bottom of the window.
 The help tab on the menu bar is provided to guide the users. It is provided
with two options - “Help topics” & “About” .
 After performing the OCR , clicking on the Spell check button (provided
at the bottom) ,a new window gets opened .
 It contains the suggestion to rectify the word . We can edit the word too.
The word which contain the error is highlighted in both the sides.
The dotted green box is used to select text in the image file.
Similarly the Red dotted box is used to delete the text/symbols in the OCR text.
     The Image file and OCR text can also be represented as horizontal split by
    clicking the toggle button


To top