Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.]
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 co...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Research Management Institute (RMI)
2017
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/20416/ |
| _version_ | 1848805012828848128 |
|---|---|
| author | Yusof, Noor Hazira Ibrahim, Zaidah Kasiran, Zolidah Abu Mangshor, Nur Nabilah |
| author_facet | Yusof, Noor Hazira Ibrahim, Zaidah Kasiran, Zolidah Abu Mangshor, Nur Nabilah |
| author_sort | Yusof, Noor Hazira |
| building | UiTM Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-14T22:04:16Z |
| format | Article |
| id | uitm-20416 |
| institution | Universiti Teknologi MARA |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T22:04:16Z |
| publishDate | 2017 |
| publisher | Research Management Institute (RMI) |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uitm-204162019-03-11T08:20:55Z https://ir.uitm.edu.my/id/eprint/20416/ Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] srj Yusof, Noor Hazira Ibrahim, Zaidah Kasiran, Zolidah Abu Mangshor, Nur Nabilah Instruments and machines Web-based user interfaces. User interfaces (Computer systems) 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. Research Management Institute (RMI) 2017 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/20416/2/AJ_NURBAITY%20SABRI%20SRJ%2017.pdf 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.]. (2017) Scientific Research Journal <https://ir.uitm.edu.my/view/publication/Scientific_Research_Journal.html>, 14 (2). pp. 49-62. ISSN 1675-7009 https://srj.uitm.edu.my/ |
| spellingShingle | Instruments and machines Web-based user interfaces. User interfaces (Computer systems) Yusof, Noor Hazira Ibrahim, Zaidah Kasiran, Zolidah Abu Mangshor, Nur Nabilah Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title | Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title_full | Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title_fullStr | Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title_full_unstemmed | Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title_short | Text localisation for roman words from shop signage / Nurbaity Sabri ... [et al.] |
| title_sort | text localisation for roman words from shop signage / nurbaity sabri ... [et al.] |
| topic | Instruments and machines Web-based user interfaces. User interfaces (Computer systems) |
| url | https://ir.uitm.edu.my/id/eprint/20416/ https://ir.uitm.edu.my/id/eprint/20416/ |