Abstract
Handwriting is the expressing of language, just like speech and it also leaves a lasting trace. Some people call handwriting as the „Language by the Hand‟. Besides that, to get similar handwriting is so difficult because everyone have different handwriting. Handwriting can be classified such as margin, slant, and size of the handwriting. The aim for this project is to extract the structure of handwriting using HT technique. The FEHT application, HT method has been applied due to the no research reported by applying this technique for Malay and English handwriting feature extraction. Besides that, this technique is used to detect the circle and line on handwriting image. This technique has been implementing on the original and rotate image in order to evaluate its performance. From the study, the result shows that the HT technique is not very suitable to be implemented to extract the structure of handwriting. The future work for this project are applying different method of feature extraction to extract the structure of handwriting, analyze HT technique based on noise removal and extend the methodology until the classification and recognition stage.
Metadata
Item Type: | Thesis (Degree) |
---|---|
Creators: | Creators Email / ID Num. Nor Hanim, Mokhtar 2013917473 |
Contributors: | Contribution Name Email / ID Num. Thesis advisor Normah, Mohd Rawi UNSPECIFIED |
Subjects: | A General Works > Academies and learned societies (General) |
Divisions: | Universiti Teknologi MARA, Perak > Tapah Campus > Faculty of Computer and Mathematical Sciences |
Keywords: | Handwriting based, feature extraction, hough transform |
Date: | 29 January 2016 |
URI: | https://ir.uitm.edu.my/id/eprint/32700 |
Download
![[thumbnail of 32700.pdf]](https://ir.uitm.edu.my/style/images/fileicons/text.png)
32700.pdf
Download (265kB)
Digital Copy
![](/images/terminal.jpg)
Physical Copy
ID Number
32700
Indexing
![](https://library.uitm.edu.my/images/2020/01/23/googlescholar-01.png)
![](https://www.base-search.net/interface/images/base_logo_kl.png)