Browse By Repository:

 
 
 
   

A Signal Processing Perspective With Normalized Silhouette Image (NSI) And Shape Fourier Descriptor (SFD) Towards Human Silhouette

Wong, Poh Ling (2015) A Signal Processing Perspective With Normalized Silhouette Image (NSI) And Shape Fourier Descriptor (SFD) Towards Human Silhouette. Project Report. UTeM, Melaka, Malaysia. (Submitted)

[img] Text (24 Pages)
A Signal Processing Perspective With Normalized Silhouette Image (NSI) And Shape Fourier Descriptor (SFD) Towards Human Silhouette 24 Pages.pdf - Submitted Version

Download (292kB)

Abstract

This study is about the silhouettes in video frames are normalized and the shape of the region in video frames is described by a set of Shape Fourier Descriptors. Shape Fourier Descriptor describes the shape of an object by considering its boundaries which are the shape centroid and calculated by a particular formula through all the video frames after normalized the videos. This shows the changes of the objects with various actions can be recognized and characterized human or non-human in the video frames. Normalized Silhouette Image is significant before the videos are described in descriptors. It focuses in the region based on the object’s ratio in images of the shape of the object and silhouette images are centred after segmentation process. This will reduce the burden of the process in extracting unnecessary part in whole videos. Various human action videos and animal videos are used for the training and testing in this study to make sure the system performed better.

Item Type: Final Year Project (Project Report)
Uncontrolled Keywords: Image processing -- Digital techniques, Image analysis
Subjects: T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Library > Final Year Project > FTMK
Depositing User: Nor Aini Md. Jali
Date Deposited: 14 Nov 2016 00:11
Last Modified: 14 Nov 2016 00:11
URI: http://digitalcollection.utem.edu.my/id/eprint/17575

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year