Implementation of Face Detection and Face Tracking
碩士 === 大葉大學 === 資訊工程學系碩士班 === 100 === In the thesis, we implemented a face detection and tracking system. The developed system is composed of two main parts: face detection and face tracking. In the face detection part, a face detector using Haar-Like features trained by Adaboost algorithm is adopte...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/91569976255420901425 |
id |
ndltd-TW-100DYU00392024 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100DYU003920242015-10-13T21:06:54Z http://ndltd.ncl.edu.tw/handle/91569976255420901425 Implementation of Face Detection and Face Tracking 人臉偵測與追蹤之實作 Tsai, Tung-Sheng 蔡東昇 碩士 大葉大學 資訊工程學系碩士班 100 In the thesis, we implemented a face detection and tracking system. The developed system is composed of two main parts: face detection and face tracking. In the face detection part, a face detector using Haar-Like features trained by Adaboost algorithm is adopted to detect facial region. To remove the error of face region, the human eyes information can also be used. After the face detection was completed, each face candidate can be tracked in the temporal domain. In the face tracking part, KLT features are extracted and tracked between two adjacent frames. Based on KLT feature tracking, face tracking can be achieved in the developed system. To evaluate the developed system, several videos with different kinds of face movement are captured by using low-cost webcam. Experimental results show that our proposed system can detect and track facial regions well. The detection rate of our face detection is more than 96% and the detection rate of our face tracking is more than 91%. These results demonstrate that our proposed system can achieve face detection and face tracking in real-world noisy videos. Lin, Guo-Shiang 林國祥 2012 學位論文 ; thesis 59 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 大葉大學 === 資訊工程學系碩士班 === 100 === In the thesis, we implemented a face detection and tracking system. The developed system is composed of two main parts: face detection and face tracking.
In the face detection part, a face detector using Haar-Like features trained by Adaboost algorithm is adopted to detect facial region. To remove the error of face region, the human eyes information can also be used. After the face detection was completed, each face candidate can be tracked in the temporal domain. In the face tracking part, KLT features are extracted and tracked between two adjacent frames. Based on KLT feature tracking, face tracking can be achieved in the developed system.
To evaluate the developed system, several videos with different kinds of face movement are captured by using low-cost webcam. Experimental results show that our proposed system can detect and track facial regions well. The detection rate of our face detection is more than 96% and the detection rate of our face tracking is more than 91%. These results demonstrate that our proposed system can achieve face detection and face tracking in real-world noisy videos.
|
author2 |
Lin, Guo-Shiang |
author_facet |
Lin, Guo-Shiang Tsai, Tung-Sheng 蔡東昇 |
author |
Tsai, Tung-Sheng 蔡東昇 |
spellingShingle |
Tsai, Tung-Sheng 蔡東昇 Implementation of Face Detection and Face Tracking |
author_sort |
Tsai, Tung-Sheng |
title |
Implementation of Face Detection and Face Tracking |
title_short |
Implementation of Face Detection and Face Tracking |
title_full |
Implementation of Face Detection and Face Tracking |
title_fullStr |
Implementation of Face Detection and Face Tracking |
title_full_unstemmed |
Implementation of Face Detection and Face Tracking |
title_sort |
implementation of face detection and face tracking |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/91569976255420901425 |
work_keys_str_mv |
AT tsaitungsheng implementationoffacedetectionandfacetracking AT càidōngshēng implementationoffacedetectionandfacetracking AT tsaitungsheng rénliǎnzhēncèyǔzhuīzōngzhīshízuò AT càidōngshēng rénliǎnzhēncèyǔzhuīzōngzhīshízuò |
_version_ |
1718055206799802368 |