Offline Text-Independent Writer IdentificationBased on Scale Invariant Feature Transform

Abstract

This Project will introduce to recognize unconstrained text line. The document will illuminate the key factors in designing a text capture method. The automatic recognition of historical handwritten text—such as letters, manuscripts, or entire books.Particularly in the field of unconstrained handwriting recognition (HWR), where the writing styles of various writers must be dealt with, severe difficulties are encountered. In the present paper, novel offline text-independent writer identification method based on scale invariant feature transform (SIFT), composed of training, enrollment, and identification stages. It is derived from a neural network based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e. it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the Scale invariant feature transform (SIFT), algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperforms not only a classical state-of-the-art algorithms based approach but also a modern keyword spotting system. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting withwriter identification when compared to classic text line recognition.

Existing System

  • In existing system has not able to perform as correction of the slope and to normalize the size of the text lines images.
  • And cannot be perform a non-uniform slant correction to change the text as correct position.
  • Particularly in the field of unconstrained handwriting recognition (HWR), where the writing styles of various writers must be dealt with, severe difficulties are encountered.

Proposed System

  • To SIFT algorithm for handwritten text lines and to normalize the size of the text.
  • A novel offline text-independent writer identification method based on scale invariant feature transform (SIFT), composed of training, enrollment, and identification stages.
  • An artificial neural network based system for unconstrained handwriting recognition.
  • Our earlier work on offline handwriting recognition system is conventional.
  • The size normalization tries to make the system invariant to the character size and to reduce the empty background areas.
  • The keyword spotting as detecting Word-Based,Line-Based, Document-Based Keyword Spotting, Background Noise.

SOFTWARE REQUIREMENTS

Platform : JAVA(JDK 1.5)

  • Front End : JAVA Swing
  • Back End : MySql
  • IDE : NETBEANS 6.9
  • Operating System : Microsoft Windows XP

HARDWARE REQUIREMENTS

  • Processor : Pentium IV Processor
  • RAM : 512 MB
  • Hard Disk : 40GB
  • Monitor: 14” VGA COLOR MONITOR
  • Keyboard: 104 Keys