Simulation System for Document Image Restoration Using Mean Shift Filtering and Multi Directional Wavelet Transform

by Ridha Sefina Samosir
( Institut Teknologi dan Bisnis Kalbe )

Date Published: 02 Dec 2013
Published In: Information Systems International Conference (ISICO)
Volume: 2013
Publisher: Departemen Sistem Informasi, Institut Teknologi Sepuluh Nopember
Language: id-ID

Keywords: Documents,Restoration,Mean Shift Filtering,Multi Directional Wavelet,Transform

Abstract

Indonesia is known as a country that has a lot of heritage, some of them are old historical documents. Each of he old document has meaning and connection towards another documents. Unfortunately, due to the age of the documents, an error in the storage system and quality of the paper or ink cause the documents broken or damaged. The way to solve the problem is using image restoration method like mean shift filtering and multi directional wavelet transform. On one hand, the procedure of mean shift filtering is finding modes from image data set distribution, on the other hand, directional wavelet transform procedure able to exploit the directional property of the strokes which separated the foreground strokes and the interference mainly in different wafelet frequency. Based on the perfomance of each method to restore the damaged document image, this research propose to make a simulation for image restoration using both of these methods. Through this, user can choose which method will give the better output to restore based on the damaged of old document image. The study for this research is an experimental because this research do investigation for the damaged document image. Development and testing of the research output.


© 2019 Open Access Journal of Information Systems (OAJIS) | created by : radityo p.w (http://about.me/radityopw) and rully a.h (eraha99 [at] gmail.com)