Regularized least-squares coding with unlabeled dictionary for image-set based face recognition

Muhammad Uzair, Ajmal Mian

    Research output: Chapter in Book/Conference paperConference paper

    2 Citations (Scopus)

    Abstract

    © 2014 IEEE. Image set based face recognition provides more opportunities compared to single mug-shot face recognition. However, modelling the variations in an image set is a challenging task. We propose a computationally efficient and accurate image set modelling technique. The idea is to reconstruct each image set sample with an unlabeled dictionary using the computationally efficient regularized least squares. The reconstruction coefficients form a latent representation of an image set and efficiently model its underlying structure. We propose max and sum pooling to aggregate the latent representations into a single compact feature vector representation per set. We then perform Linear Discriminant Analysis on the pooled reconstruction coefficients to increase the discrimination and reduce the dimensionality of the proposed features. The proposed algorithm is extensively evaluated for the task of image set based face recognition on the Honda/UCSD, CMU Mobo and YouTube celebrities datasets. Experimental results show that the proposed algorithm outperforms current state-of-the-art image set classification algorithms in terms of both accuracy and execution time.
    Original languageEnglish
    Title of host publication2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-7
    ISBN (Print)9781479954094
    DOIs
    Publication statusPublished - 2014
    EventRegularized least-squares coding with unlabeled dictionary for image-set based face recognition - Wollongong, New South Wales, Australia
    Duration: 1 Jan 2014 → …

    Conference

    ConferenceRegularized least-squares coding with unlabeled dictionary for image-set based face recognition
    Period1/01/14 → …

    Fingerprint Dive into the research topics of 'Regularized least-squares coding with unlabeled dictionary for image-set based face recognition'. Together they form a unique fingerprint.

  • Cite this

    Uzair, M., & Mian, A. (2014). Regularized least-squares coding with unlabeled dictionary for image-set based face recognition. In 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 1-7). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2014.7008128