Sparsity-based face recognition using discriminative graphical models

Umamahesh Srinivas, Vishal Monga, Yi Chen, Trac D. Tran

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    A key recent advance in face recognition which models a test face image as a sparse linear combination of training face images has demonstrated robustness against a variety of distortions, albeit under the restrictive assumption of perfect image registration. To overcome this misalignment problem, we propose a graphical learning framework for robust automatic face recognition, utilizing sparse signal representations from face images as features for classification. Our approach combines two key ideas from recent work in: (i) locally adaptive block-based sparsity for face recognition, and (ii) discriminative learning of graphical models. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. The graphical models are learnt in a manner such that conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results show that the complementary merits of existing sparsity-based face recognition techniques - which use class specific reconstruction error as a recognition statistic - in comparison with our proposed approach can further be mined into building a powerful meta-classifier for face recognition.

    Original languageEnglish (US)
    Title of host publicationConference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011
    Pages1204-1208
    Number of pages5
    DOIs
    StatePublished - Dec 1 2011
    Event45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011 - Pacific Grove, CA, United States
    Duration: Nov 6 2011Nov 9 2011

    Publication series

    NameConference Record - Asilomar Conference on Signals, Systems and Computers
    ISSN (Print)1058-6393

    Other

    Other45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011
    CountryUnited States
    CityPacific Grove, CA
    Period11/6/1111/9/11

    Fingerprint

    Face recognition
    Image registration
    Classifiers
    Statistics

    All Science Journal Classification (ASJC) codes

    • Signal Processing
    • Computer Networks and Communications

    Cite this

    Srinivas, U., Monga, V., Chen, Y., & Tran, T. D. (2011). Sparsity-based face recognition using discriminative graphical models. In Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011 (pp. 1204-1208). [6190206] (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2011.6190206
    Srinivas, Umamahesh ; Monga, Vishal ; Chen, Yi ; Tran, Trac D. / Sparsity-based face recognition using discriminative graphical models. Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. pp. 1204-1208 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
    @inproceedings{904faa75e3e74c05b46706af4100409b,
    title = "Sparsity-based face recognition using discriminative graphical models",
    abstract = "A key recent advance in face recognition which models a test face image as a sparse linear combination of training face images has demonstrated robustness against a variety of distortions, albeit under the restrictive assumption of perfect image registration. To overcome this misalignment problem, we propose a graphical learning framework for robust automatic face recognition, utilizing sparse signal representations from face images as features for classification. Our approach combines two key ideas from recent work in: (i) locally adaptive block-based sparsity for face recognition, and (ii) discriminative learning of graphical models. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. The graphical models are learnt in a manner such that conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results show that the complementary merits of existing sparsity-based face recognition techniques - which use class specific reconstruction error as a recognition statistic - in comparison with our proposed approach can further be mined into building a powerful meta-classifier for face recognition.",
    author = "Umamahesh Srinivas and Vishal Monga and Yi Chen and Tran, {Trac D.}",
    year = "2011",
    month = "12",
    day = "1",
    doi = "10.1109/ACSSC.2011.6190206",
    language = "English (US)",
    isbn = "9781467303231",
    series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
    pages = "1204--1208",
    booktitle = "Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011",

    }

    Srinivas, U, Monga, V, Chen, Y & Tran, TD 2011, Sparsity-based face recognition using discriminative graphical models. in Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011., 6190206, Conference Record - Asilomar Conference on Signals, Systems and Computers, pp. 1204-1208, 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011, Pacific Grove, CA, United States, 11/6/11. https://doi.org/10.1109/ACSSC.2011.6190206

    Sparsity-based face recognition using discriminative graphical models. / Srinivas, Umamahesh; Monga, Vishal; Chen, Yi; Tran, Trac D.

    Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. p. 1204-1208 6190206 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - Sparsity-based face recognition using discriminative graphical models

    AU - Srinivas, Umamahesh

    AU - Monga, Vishal

    AU - Chen, Yi

    AU - Tran, Trac D.

    PY - 2011/12/1

    Y1 - 2011/12/1

    N2 - A key recent advance in face recognition which models a test face image as a sparse linear combination of training face images has demonstrated robustness against a variety of distortions, albeit under the restrictive assumption of perfect image registration. To overcome this misalignment problem, we propose a graphical learning framework for robust automatic face recognition, utilizing sparse signal representations from face images as features for classification. Our approach combines two key ideas from recent work in: (i) locally adaptive block-based sparsity for face recognition, and (ii) discriminative learning of graphical models. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. The graphical models are learnt in a manner such that conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results show that the complementary merits of existing sparsity-based face recognition techniques - which use class specific reconstruction error as a recognition statistic - in comparison with our proposed approach can further be mined into building a powerful meta-classifier for face recognition.

    AB - A key recent advance in face recognition which models a test face image as a sparse linear combination of training face images has demonstrated robustness against a variety of distortions, albeit under the restrictive assumption of perfect image registration. To overcome this misalignment problem, we propose a graphical learning framework for robust automatic face recognition, utilizing sparse signal representations from face images as features for classification. Our approach combines two key ideas from recent work in: (i) locally adaptive block-based sparsity for face recognition, and (ii) discriminative learning of graphical models. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. The graphical models are learnt in a manner such that conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results show that the complementary merits of existing sparsity-based face recognition techniques - which use class specific reconstruction error as a recognition statistic - in comparison with our proposed approach can further be mined into building a powerful meta-classifier for face recognition.

    UR - http://www.scopus.com/inward/record.url?scp=84861314637&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84861314637&partnerID=8YFLogxK

    U2 - 10.1109/ACSSC.2011.6190206

    DO - 10.1109/ACSSC.2011.6190206

    M3 - Conference contribution

    AN - SCOPUS:84861314637

    SN - 9781467303231

    T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

    SP - 1204

    EP - 1208

    BT - Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011

    ER -

    Srinivas U, Monga V, Chen Y, Tran TD. Sparsity-based face recognition using discriminative graphical models. In Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2011. 2011. p. 1204-1208. 6190206. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2011.6190206