A New Feature Set for Face Detection
碩士 === 國立清華大學 === 資訊系統與應用研究所 === 93 === Viola and Jones introduce a fast face detection system which uses a cascaded structure that can achieve high detection rate and low false positive rate. Their system uses integral images to compute values from features. This thesis introduces two new types of...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2005
|
Online Access: | http://ndltd.ncl.edu.tw/handle/25044260112501168862 |
id |
ndltd-TW-093NTHU5394040 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-093NTHU53940402015-10-13T11:15:49Z http://ndltd.ncl.edu.tw/handle/25044260112501168862 A New Feature Set for Face Detection 使用新特徵的人臉偵測系統 Chung-Chih Tsai 蔡忠志 碩士 國立清華大學 資訊系統與應用研究所 93 Viola and Jones introduce a fast face detection system which uses a cascaded structure that can achieve high detection rate and low false positive rate. Their system uses integral images to compute values from features. This thesis introduces two new types of integral images which are called triangle integral images and two corresponding features which are named triangle features. And this thesis proposes a method to lower training error by modifying Discrete AdaBoost. As results, to use triangle features can decrease the numbers of features; this research achieves lower false positive rate and fewer features are used. Jyh-Shing Roger Jang 張智星 2005 學位論文 ; thesis 36 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立清華大學 === 資訊系統與應用研究所 === 93 === Viola and Jones introduce a fast face detection system which uses a cascaded structure that can achieve high detection rate and low false positive rate. Their system uses integral images to compute values from features. This thesis introduces two new types of integral images which are called triangle integral images and two corresponding features which are named triangle features. And this thesis proposes a method to lower training error by modifying Discrete AdaBoost. As results, to use triangle features can decrease the numbers of features; this research achieves lower false positive rate and fewer features are used.
|
author2 |
Jyh-Shing Roger Jang |
author_facet |
Jyh-Shing Roger Jang Chung-Chih Tsai 蔡忠志 |
author |
Chung-Chih Tsai 蔡忠志 |
spellingShingle |
Chung-Chih Tsai 蔡忠志 A New Feature Set for Face Detection |
author_sort |
Chung-Chih Tsai |
title |
A New Feature Set for Face Detection |
title_short |
A New Feature Set for Face Detection |
title_full |
A New Feature Set for Face Detection |
title_fullStr |
A New Feature Set for Face Detection |
title_full_unstemmed |
A New Feature Set for Face Detection |
title_sort |
new feature set for face detection |
publishDate |
2005 |
url |
http://ndltd.ncl.edu.tw/handle/25044260112501168862 |
work_keys_str_mv |
AT chungchihtsai anewfeaturesetforfacedetection AT càizhōngzhì anewfeaturesetforfacedetection AT chungchihtsai shǐyòngxīntèzhēngderénliǎnzhēncèxìtǒng AT càizhōngzhì shǐyòngxīntèzhēngderénliǎnzhēncèxìtǒng AT chungchihtsai newfeaturesetforfacedetection AT càizhōngzhì newfeaturesetforfacedetection |
_version_ |
1716840610991702016 |