Loading…
Face Recognition Based on Separable Lattice HMMS
In this paper, we propose separable lattice hidden Markov models, in which multiple hidden state sequences interact to model the observation on a lattice. The proposed model can be efficiently applied for modeling images, image sequences, 3-D object models and higher dimensional applications, due to...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | V |
| container_issue | |
| container_start_page | V |
| container_title | |
| container_volume | 5 |
| creator | Kurata, D. Nankaku, Y. Tokuda, K. Kitamura, T. Ghahramani, Z. |
| description | In this paper, we propose separable lattice hidden Markov models, in which multiple hidden state sequences interact to model the observation on a lattice. The proposed model can be efficiently applied for modeling images, image sequences, 3-D object models and higher dimensional applications, due to the composite structure of Markov chains which reduces the complexity while retaining good properties for multi-dimensional data. In case of 2-D lattices, the proposed model performs an elastic matching in both horizontal and vertical directions; this makes it possible to model not only invariances to the size and location of an object but also nonlinear warping in each dimension. We present a training algorithm for separable lattice HMMs based on a variational approximation. Moreover, the deterministic annealing EM (DAEM) algorithm was applied to the variational algorithm for separable lattice HMMs. Face recognition experiments on the XM2VTS database show that the proposed model has good properties for face image modeling |
| doi_str_mv | 10.1109/ICASSP.2006.1661381 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1661381</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1661381</ieee_id><sourcerecordid>1661381</sourcerecordid><originalsourceid>FETCH-ieee_primary_16613813</originalsourceid><addsrcrecordid>eNp9jr0KwjAURi_-gEX7BF36Aq33pjFtRhVFQUGMg5vEepVIrdJ08e11cHb6DpwzfAARYUqEeryeT43ZpQJRpaQUZQV1IBBZrhPSeOxCqPOCpJASpdJFDwKaCEwUST2A0Ps7IpJWucxEALi0Jcd7Lp-32rXuWccz6_kSf8Hwyzb2XHG8sW3rvtlquzUj6F9t5Tn87RCi5eIwXyWOmU-vxj1s8z79fmX_7QeCgTbC</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Face Recognition Based on Separable Lattice HMMS</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kurata, D. ; Nankaku, Y. ; Tokuda, K. ; Kitamura, T. ; Ghahramani, Z.</creator><creatorcontrib>Kurata, D. ; Nankaku, Y. ; Tokuda, K. ; Kitamura, T. ; Ghahramani, Z.</creatorcontrib><description>In this paper, we propose separable lattice hidden Markov models, in which multiple hidden state sequences interact to model the observation on a lattice. The proposed model can be efficiently applied for modeling images, image sequences, 3-D object models and higher dimensional applications, due to the composite structure of Markov chains which reduces the complexity while retaining good properties for multi-dimensional data. In case of 2-D lattices, the proposed model performs an elastic matching in both horizontal and vertical directions; this makes it possible to model not only invariances to the size and location of an object but also nonlinear warping in each dimension. We present a training algorithm for separable lattice HMMs based on a variational approximation. Moreover, the deterministic annealing EM (DAEM) algorithm was applied to the variational algorithm for separable lattice HMMs. Face recognition experiments on the XM2VTS database show that the proposed model has good properties for face image modeling</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424404698</identifier><identifier>ISBN: 142440469X</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2006.1661381</identifier><language>eng</language><publisher>IEEE</publisher><subject>Annealing ; Approximation algorithms ; Computational complexity ; Computer science ; Educational institutions ; Face recognition ; Hidden Markov models ; Image sequences ; Lattices ; Maximum likelihood estimation</subject><ispartof>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 2006, Vol.5, p.V-V</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1661381$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1661381$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kurata, D.</creatorcontrib><creatorcontrib>Nankaku, Y.</creatorcontrib><creatorcontrib>Tokuda, K.</creatorcontrib><creatorcontrib>Kitamura, T.</creatorcontrib><creatorcontrib>Ghahramani, Z.</creatorcontrib><title>Face Recognition Based on Separable Lattice HMMS</title><title>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings</title><addtitle>ICASSP</addtitle><description>In this paper, we propose separable lattice hidden Markov models, in which multiple hidden state sequences interact to model the observation on a lattice. The proposed model can be efficiently applied for modeling images, image sequences, 3-D object models and higher dimensional applications, due to the composite structure of Markov chains which reduces the complexity while retaining good properties for multi-dimensional data. In case of 2-D lattices, the proposed model performs an elastic matching in both horizontal and vertical directions; this makes it possible to model not only invariances to the size and location of an object but also nonlinear warping in each dimension. We present a training algorithm for separable lattice HMMs based on a variational approximation. Moreover, the deterministic annealing EM (DAEM) algorithm was applied to the variational algorithm for separable lattice HMMs. Face recognition experiments on the XM2VTS database show that the proposed model has good properties for face image modeling</description><subject>Annealing</subject><subject>Approximation algorithms</subject><subject>Computational complexity</subject><subject>Computer science</subject><subject>Educational institutions</subject><subject>Face recognition</subject><subject>Hidden Markov models</subject><subject>Image sequences</subject><subject>Lattices</subject><subject>Maximum likelihood estimation</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424404698</isbn><isbn>142440469X</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNp9jr0KwjAURi_-gEX7BF36Aq33pjFtRhVFQUGMg5vEepVIrdJ08e11cHb6DpwzfAARYUqEeryeT43ZpQJRpaQUZQV1IBBZrhPSeOxCqPOCpJASpdJFDwKaCEwUST2A0Ps7IpJWucxEALi0Jcd7Lp-32rXuWccz6_kSf8Hwyzb2XHG8sW3rvtlquzUj6F9t5Tn87RCi5eIwXyWOmU-vxj1s8z79fmX_7QeCgTbC</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Kurata, D.</creator><creator>Nankaku, Y.</creator><creator>Tokuda, K.</creator><creator>Kitamura, T.</creator><creator>Ghahramani, Z.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2006</creationdate><title>Face Recognition Based on Separable Lattice HMMS</title><author>Kurata, D. ; Nankaku, Y. ; Tokuda, K. ; Kitamura, T. ; Ghahramani, Z.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_16613813</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Annealing</topic><topic>Approximation algorithms</topic><topic>Computational complexity</topic><topic>Computer science</topic><topic>Educational institutions</topic><topic>Face recognition</topic><topic>Hidden Markov models</topic><topic>Image sequences</topic><topic>Lattices</topic><topic>Maximum likelihood estimation</topic><toplevel>online_resources</toplevel><creatorcontrib>Kurata, D.</creatorcontrib><creatorcontrib>Nankaku, Y.</creatorcontrib><creatorcontrib>Tokuda, K.</creatorcontrib><creatorcontrib>Kitamura, T.</creatorcontrib><creatorcontrib>Ghahramani, Z.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Explore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kurata, D.</au><au>Nankaku, Y.</au><au>Tokuda, K.</au><au>Kitamura, T.</au><au>Ghahramani, Z.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Face Recognition Based on Separable Lattice HMMS</atitle><btitle>2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings</btitle><stitle>ICASSP</stitle><date>2006</date><risdate>2006</risdate><volume>5</volume><spage>V</spage><epage>V</epage><pages>V-V</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424404698</isbn><isbn>142440469X</isbn><abstract>In this paper, we propose separable lattice hidden Markov models, in which multiple hidden state sequences interact to model the observation on a lattice. The proposed model can be efficiently applied for modeling images, image sequences, 3-D object models and higher dimensional applications, due to the composite structure of Markov chains which reduces the complexity while retaining good properties for multi-dimensional data. In case of 2-D lattices, the proposed model performs an elastic matching in both horizontal and vertical directions; this makes it possible to model not only invariances to the size and location of an object but also nonlinear warping in each dimension. We present a training algorithm for separable lattice HMMs based on a variational approximation. Moreover, the deterministic annealing EM (DAEM) algorithm was applied to the variational algorithm for separable lattice HMMs. Face recognition experiments on the XM2VTS database show that the proposed model has good properties for face image modeling</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2006.1661381</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 2006, Vol.5, p.V-V |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_1661381 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Annealing Approximation algorithms Computational complexity Computer science Educational institutions Face recognition Hidden Markov models Image sequences Lattices Maximum likelihood estimation |
| title | Face Recognition Based on Separable Lattice HMMS |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T20%3A27%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Face%20Recognition%20Based%20on%20Separable%20Lattice%20HMMS&rft.btitle=2006%20IEEE%20International%20Conference%20on%20Acoustics%20Speech%20and%20Signal%20Processing%20Proceedings&rft.au=Kurata,%20D.&rft.date=2006&rft.volume=5&rft.spage=V&rft.epage=V&rft.pages=V-V&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424404698&rft.isbn_list=142440469X&rft_id=info:doi/10.1109/ICASSP.2006.1661381&rft_dat=%3Cieee_6IE%3E1661381%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-ieee_primary_16613813%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1661381&rfr_iscdi=true |