Text localization from photos

Author

Guarnera, Mirko ; Messina, Giuseppe ; Ardizzone, Edoardo ; Agro, Leonardo

Author_Institution

AST Catania Lab., STMicroelectronics

fYear

2009

Firstpage

1

Lastpage

2

Abstract

In this paper a new text extraction algorithm is proposed. In real scenes the text is usually overlapped or is part of the background. To identify the text regions, in complex conditions, a method exploiting a ldquomulti-resolution feature based methodrdquo for extracting text with undefined dimension has been developed. Once identified, the multi-resolution information are merged and skimmed through a set of Support Vector Machines (SVM). The tests and the comparisons with other techniques, performed on heterogeneous images, have shown the effectiveness of the proposed.

Keywords

character recognition; content-based retrieval; feature extraction; image resolution; support vector machines; character recognition; content-based retrieval; feature extraction; multi-resolution information; support vector machines; text extraction; text localization; Computer networks; Data mining; Image color analysis; Image converters; Image edge detection; Neural networks; Noise reduction; Optical character recognition software; Optical imaging; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics, 2009. ICCE '09. Digest of Technical Papers International Conference on

Conference_Location

Las Vegas, NV

Print_ISBN

978-1-4244-4701-5

Electronic_ISBN

978-1-4244-2559-4

Type

conf

DOI

10.1109/ICCE.2009.5012184

Filename

5012184