Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.]

Yusof, Noor Hazira and Ibrahim, Zaidah and Kasiran, Zolidah and Abu Mangshor, Nur Nabilah (2017) Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.]. Scientific Research Journal, 14 (2). pp. 49-62. ISSN 1675-7009

Official URL: https://srj.uitm.edu.my/


Text localisation determinesthe location of the text in an image. This process is performed prior to text recognition. Localising text on shop signage is a challenging task since the images of the shop signage consist of complex background, and the text occurs in various font types, sizes, and colours. Two popular texture features that have been applied to localise text in scene images are a histogram of oriented gradient (HOG) and speeded up robust features (SURF). A comparative study is conducted in this paper to determine which is better with support vector machine (SVM) classifier. The performance of SVM is influenced by its kernel function and another comparative study is conducted to identify the best kernel function. The experiments have been conducted using primary data collected by the authors. Resultsindicate that HOG with quadratic kernel function localises text for shop signage better than SURF.


Item Type: Article
CreatorsEmail / ID. Num
Yusof, Noor HaziraUNSPECIFIED
Ibrahim, ZaidahUNSPECIFIED
Kasiran, ZolidahUNSPECIFIED
Abu Mangshor, Nur NabilahUNSPECIFIED
Subjects: Q Science > QA Mathematics > Instruments and machines
Q Science > QA Mathematics > Web-based user interfaces. User interfaces (Computer systems)
Divisions: Universiti Teknologi MARA, Shah Alam > Research Management Centre (RMC)
Journal or Publication Title: Scientific Research Journal
Journal: UiTM Journal > Scientific Research Journal (SRJ)
ISSN: 1675-7009
Volume: 14
Number: 2
Page Range: pp. 49-62
Official URL: https://srj.uitm.edu.my/
Item ID: 20416
Uncontrolled Keywords: HOG, SURF and SVM
URI: http://ir.uitm.edu.my/id/eprint/20416


[img] Text

Download (5MB)

ID Number



View in Google Scholar

Actions (login required)

View Item View Item


Downloads per month over past year