Expression Recognition using Cascade Local Deformation Code

碩士 === 國立臺灣科技大學 === 機械工程系 === 100 === An appearance-based coding scheme, called Cascade Local Deformation Code (CLDC), is proposed for expression recognition. CLDC has two component codes, Human Observable Code (HOC) and Haar-like Feature Code (HFC). The HOC encodes the local deformation regions cau...

Full description

Bibliographic Details
Main Authors: Yu-Shan Lin, 林鈺山
Other Authors: Gee-Sern Hsu
Format: Others
Language:zh-TW
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/836p6p
id ndltd-TW-100NTUS5489176
record_format oai_dc
spelling ndltd-TW-100NTUS54891762019-05-15T20:51:12Z http://ndltd.ncl.edu.tw/handle/836p6p Expression Recognition using Cascade Local Deformation Code 聯結式局部特徵編碼之表情辨識 Yu-Shan Lin 林鈺山 碩士 國立臺灣科技大學 機械工程系 100 An appearance-based coding scheme, called Cascade Local Deformation Code (CLDC), is proposed for expression recognition. CLDC has two component codes, Human Observable Code (HOC) and Haar-like Feature Code (HFC). The HOC encodes the local deformation regions caused by facial muscle contractions observable to humans, and the HFC encodes the Haar-like features selected by an AdaBoost algorithm. Given a training set, one first selects the observable local deformation regions, and trains a HOC detector which encodes the local deformation regions into HOC codewords according to seven predefined expressions. The training set is also used for the extraction of Haar-like features and encoding of the features into HFC codewords for the seven expressions. The combination of HOC and HFC gives the CLDC, which is proven to outperform either component in the decoding phase for the expression recognition on disjoint testing sets. Experiments on the CK+, JAFFE and the latest FERA databases show that the performance of the CLDC is competitive to the state-of-the-art approaches. Gee-Sern Hsu 徐繼聖 2012 學位論文 ; thesis 79 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立臺灣科技大學 === 機械工程系 === 100 === An appearance-based coding scheme, called Cascade Local Deformation Code (CLDC), is proposed for expression recognition. CLDC has two component codes, Human Observable Code (HOC) and Haar-like Feature Code (HFC). The HOC encodes the local deformation regions caused by facial muscle contractions observable to humans, and the HFC encodes the Haar-like features selected by an AdaBoost algorithm. Given a training set, one first selects the observable local deformation regions, and trains a HOC detector which encodes the local deformation regions into HOC codewords according to seven predefined expressions. The training set is also used for the extraction of Haar-like features and encoding of the features into HFC codewords for the seven expressions. The combination of HOC and HFC gives the CLDC, which is proven to outperform either component in the decoding phase for the expression recognition on disjoint testing sets. Experiments on the CK+, JAFFE and the latest FERA databases show that the performance of the CLDC is competitive to the state-of-the-art approaches.
author2 Gee-Sern Hsu
author_facet Gee-Sern Hsu
Yu-Shan Lin
林鈺山
author Yu-Shan Lin
林鈺山
spellingShingle Yu-Shan Lin
林鈺山
Expression Recognition using Cascade Local Deformation Code
author_sort Yu-Shan Lin
title Expression Recognition using Cascade Local Deformation Code
title_short Expression Recognition using Cascade Local Deformation Code
title_full Expression Recognition using Cascade Local Deformation Code
title_fullStr Expression Recognition using Cascade Local Deformation Code
title_full_unstemmed Expression Recognition using Cascade Local Deformation Code
title_sort expression recognition using cascade local deformation code
publishDate 2012
url http://ndltd.ncl.edu.tw/handle/836p6p
work_keys_str_mv AT yushanlin expressionrecognitionusingcascadelocaldeformationcode
AT línyùshān expressionrecognitionusingcascadelocaldeformationcode
AT yushanlin liánjiéshìjúbùtèzhēngbiānmǎzhībiǎoqíngbiànshí
AT línyùshān liánjiéshìjúbùtèzhēngbiānmǎzhībiǎoqíngbiànshí
_version_ 1719104769847459840