An evaluation of feature extraction algorithms for automatic language transcription system for ancient handwriting Javanese manuscripts

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

An evaluation of feature extraction algorithms for automatic language transcription system for ancient handwriting Javanese manuscripts

Rumondor, Brian Charles - Personal Name; Nugroho, Anto Satriyo - Personal Name;

In order to preserve and extract the implicit knowledge of ancient Javanese manuscript, a system is required to scan and translate these manuscripts. The problem faced is the fact that most of these manuscripts are written over a very brittle medium. The best way to solve the problem is by digitalizing them to digital images, then being processed to extract the content. Optical Character Recognition is an effort to extract the content of such invaluable documents that will be followed by language translation process. Optical Character Recognition System consists of preprocessing, feature extraction, character recognition and post processing. Feature extraction works to extract distinctive features of the character that will be fed to the next step: character recognition. In this study, we evaluated several feature extraction algorithms including Local Line Direction, mesh and other different approaches in term of classification rate obtained by Support Vector Machine (SVM).

Availability

B00523 (wh) Available

Detail Information

Series Title: -
Call Number: 523
Publisher: : Swiss German University., 2009
Collation: -
Language: English
ISBN/ISSN: -
Classification: NONE
Content Type: -
Media Type: -
Carrier Type: -
Edition: -
Subject(s): IT
Specific Detail Info: -
Statement of Responsibility: -

Other version/related

No other version available

File Attachment

No Data

Comments

You must be logged in to post a comment