Topic related video segmentation
This report addresses the problem of recovering the person-of-interest in a broadcast video. This is extremely challenging due to the imaged appearance variation of the person-of-interest in the video. However, the abstraction of the meaningful data is somehow similar to a table of content; it can s...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/52602 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-52602 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-526022023-07-07T17:03:57Z Topic related video segmentation Xie, Henry Cheng You Teoh Eam Khwang School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering This report addresses the problem of recovering the person-of-interest in a broadcast video. This is extremely challenging due to the imaged appearance variation of the person-of-interest in the video. However, the abstraction of the meaningful data is somehow similar to a table of content; it can serve as a useful index table, enabling users to browse through huge amounts of data in a non-linear manner. In order to achieve a useful index table, key frames are commonly used in applications such as video editing and non-linear data browsing. This report presents two methods for key frame selection: capturing of Euclidean distances between their color histograms and secondly, measuring the similarity between two images by viewing the images being compared with the other image regarded as perfect quality. Thus, this report will present two discriminative key-frame selection methods, and the experimental results will be discussed. Lastly, based on the sparsity, a recognition performance can be achieved by a simple algorithm and the face of interest will have the name label on it. Bachelor of Engineering 2013-05-21T02:28:11Z 2013-05-21T02:28:11Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/52602 en Nanyang Technological University 99 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Xie, Henry Cheng You Topic related video segmentation |
description |
This report addresses the problem of recovering the person-of-interest in a broadcast video. This is extremely challenging due to the imaged appearance variation of the person-of-interest in the video. However, the abstraction of the meaningful data is somehow similar to a table of content; it can serve as a useful index table, enabling users to browse through huge amounts of data in a non-linear manner.
In order to achieve a useful index table, key frames are commonly used in applications such as video editing and non-linear data browsing. This report presents two methods for key frame selection: capturing of Euclidean distances between their color histograms and secondly, measuring the similarity between two images by viewing the images being compared with the other image regarded as perfect quality. Thus, this report will present two discriminative key-frame selection methods, and the experimental results will be discussed.
Lastly, based on the sparsity, a recognition performance can be achieved by a simple algorithm and the face of interest will have the name label on it. |
author2 |
Teoh Eam Khwang |
author_facet |
Teoh Eam Khwang Xie, Henry Cheng You |
format |
Final Year Project |
author |
Xie, Henry Cheng You |
author_sort |
Xie, Henry Cheng You |
title |
Topic related video segmentation |
title_short |
Topic related video segmentation |
title_full |
Topic related video segmentation |
title_fullStr |
Topic related video segmentation |
title_full_unstemmed |
Topic related video segmentation |
title_sort |
topic related video segmentation |
publishDate |
2013 |
url |
http://hdl.handle.net/10356/52602 |
_version_ |
1772827096953913344 |