Key frames extraction from movie
Movies and videos play an important role in the modern days not only for entertainment purpose but also to keep us updated with the news and findings around the world. Movies, also known as moving pictures are wonders created by combining multiple stationary images sequentially to illustrate the mot...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/72290 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-72290 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-722902023-07-07T15:59:27Z Key frames extraction from movie Shwe Sin Oo Chau Lap Pui School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Movies and videos play an important role in the modern days not only for entertainment purpose but also to keep us updated with the news and findings around the world. Movies, also known as moving pictures are wonders created by combining multiple stationary images sequentially to illustrate the motion. Key Frames in movies note the part where there are changes such as change of scene, view as well as movements. They usually contains majority of information that is related to a scene, thus they are used in many video processing, transmission and broadcasting works for efficiency in saving time and data. In this project, algorithm is developed to extract key frames from video files by checking the difference of color histogram between two consecutive frames. When the color histogram difference of two frames falls beyond a certain threshold, the frame is selected as key frames. The key frames generated by program will be compared against the overall frames selected visually by human vision for analysis of the experimental results. Bachelor of Engineering 2017-06-01T05:28:59Z 2017-06-01T05:28:59Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/72290 en Nanyang Technological University 61 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 Shwe Sin Oo Key frames extraction from movie |
description |
Movies and videos play an important role in the modern days not only for entertainment purpose but also to keep us updated with the news and findings around the world. Movies, also known as moving pictures are wonders created by combining multiple stationary images sequentially to illustrate the motion. Key Frames in movies note the part where there are changes such as change of scene, view as well as movements. They usually contains majority of information that is related to a scene, thus they are used in many video processing, transmission and broadcasting works for efficiency in saving time and data. In this project, algorithm is developed to extract key frames from video files by checking the difference of color histogram between two consecutive frames. When the color histogram difference of two frames falls beyond a certain threshold, the frame is selected as key frames. The key frames generated by program will be compared against the overall frames selected visually by human vision for analysis of the experimental results. |
author2 |
Chau Lap Pui |
author_facet |
Chau Lap Pui Shwe Sin Oo |
format |
Final Year Project |
author |
Shwe Sin Oo |
author_sort |
Shwe Sin Oo |
title |
Key frames extraction from movie |
title_short |
Key frames extraction from movie |
title_full |
Key frames extraction from movie |
title_fullStr |
Key frames extraction from movie |
title_full_unstemmed |
Key frames extraction from movie |
title_sort |
key frames extraction from movie |
publishDate |
2017 |
url |
http://hdl.handle.net/10356/72290 |
_version_ |
1772826967583752192 |