Extracting Farsi text from a video in the wavelet domain

Author

Ravangard, Zeynab ; Zargari, Farzad ; Nezamabadi-pour, Hossein ; Moghadam, Amir Kosari

Author_Institution

Sci. & Res. Tehran, Islamic Azad Univ., Tehran, Iran

fYear

2013

fDate

28-30 May 2013

Firstpage

307

Lastpage

311

Abstract

In this paper, a new method for extracting Farsi text from a video in the wavelet domain is proposed. In an image including text, due to the complexity of the background and the quick changes of contrast in the text areas, the energy intensity variation is high. Therefore, by exploiting this property a method is proposed for extracting text. Moreover, for increasing the accuracy of the proposed method, some motion characteristics of the movies have been used. The proposed method is able to localize both Farsi and Latin Text in video with a high performance. The experimental results confirms the effectiveness of the proposed method.

Keywords

computational complexity; feature extraction; image motion analysis; natural language processing; text analysis; video signal processing; wavelet transforms; Farsi text extraction; Latin text; background complexity; contrast changes; energy intensity variation; motion characteristics; text areas; video; wavelet domain; Conferences; Data mining; Image edge detection; Wavelet domain; Wavelet transforms; Farsi text extraction; Video; Wavelet energy; Wavelet transform; motion;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Knowledge Technology (IKT), 2013 5th Conference on

Conference_Location

Shiraz

Print_ISBN

978-1-4673-6489-8

Type

conf

DOI

10.1109/IKT.2013.6620084

Filename

6620084