Automatic image annotation based on shape / Norazirah Ramli

Ramli, Norazirah (2009) Automatic image annotation based on shape / Norazirah Ramli. Degree thesis, Universiti Teknologi MARA (UiTM).

Abstract

The project is titled Automatic Image Annotation based on Shape. This project annotated people and rock in the beach scenery images. The project also used global shape descriptors approach in the annotating. Nowadays, there are many approaches in automatic annotation system. One of the ways is through region-based technique that involved is global shape descriptors. Even though, these projects choose to use compactness and eccentricity technique which are suitable for non-occluded object. The techniques were applied after image pre-processing stage. Several steps such grayscale, segmentation and dilation have been used to pre-processing the images. Then, the objects in the images were determined. Finally, the image is annotated through the caption the object of the image.

Metadata

Item Type: Thesis (Degree)
Creators:
Creators
Email / ID Num.
Ramli, Norazirah
UNSPECIFIED
Contributors:
Contribution
Name
Email / ID Num.
Thesis advisor
Jamil, Nursuriati
UNSPECIFIED
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Computer and Mathematical Sciences
Programme: Bachelor of Computer Science (Hons) Multimedia Computing
Keywords: Shape, grayscale, automatic annotation
Date: 2009
URI: https://ir.uitm.edu.my/id/eprint/87212
Edit Item
Edit Item

Download

[thumbnail of 87212.pdf] Text
87212.pdf

Download (4MB)

Digital Copy

Digital (fulltext) is available at:

Physical Copy

Physical status and holdings:
Item Status:
On Shelf

ID Number

87212

Indexing

Statistic

Statistic details