Abstract
In this project, Shape-Based Image Retrieval of Malaysia Birds is proposed. An earlier development of Malaysia Birds Image Retrieval system using color layout descriptor was done. It used color as the feature representation to retrieve similar images from the user's query image of a bird. This project attempts to improve the retrieval accuracy by adding the element of shape of the birds in order to retrieve the same set of the query image. Edge histogram descriptor (EHD) is used as the shape feature to describe the birds. The project is developed using Microsoft Visual Studio 2017 with C# programming language. EHD is used to extract the feature of the birds before with retrieval process. After dividing the image into sub-images, EHD will detects the edges as there are five types of edges, namely four directional edges and one non-directional edge.
Metadata
Item Type: | Thesis (Degree) |
---|---|
Creators: | Creators Email / ID Num. Hasni, Nur Hanisah 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: | Birds, image retrieval, color layout |
Date: | 2017 |
URI: | https://ir.uitm.edu.my/id/eprint/87217 |
Download
87217.pdf
Download (120kB)