Hierarchical Aggregation Based Deep Aging Feature for Age Prediction

Jiayan Qiu, Yuchao Dai, Yuhang Zhang, Jose M. Alvarez

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    3 Citations (Scopus)

    Abstract

    We propose a new, hierarchical, aggregation-based deep neural network to learn aging features from facial images. Our deep-Aging feature vector is designed to capture both local and global aging cues from facial images. A Convolutional Neural Network (CNN) is employed to extract region-specific features at the lowest level of our hierarchy. These features are then hierarchically aggregated to consecutive higher levels and the resultant aging feature vector, of dimensionality 110, achieves both good discriminative ability and efficiency. Experimental results of age prediction on the MORPH-II databases show that our method outperforms state-of-The-Art aging features by a clear margin. Experimental trails of our method across race and gender provide further confidence in its performance and robustness.

    Original languageEnglish
    Title of host publication2015 International Conference on Digital Image Computing
    Subtitle of host publicationTechniques and Applications, DICTA 2015
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Electronic)9781467367950
    DOIs
    Publication statusPublished - 2015
    EventInternational Conference on Digital Image Computing: Techniques and Applications, DICTA 2015 - Adelaide, Australia
    Duration: 23 Nov 201525 Nov 2015

    Publication series

    Name2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015

    Conference

    ConferenceInternational Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
    Country/TerritoryAustralia
    CityAdelaide
    Period23/11/1525/11/15

    Fingerprint

    Dive into the research topics of 'Hierarchical Aggregation Based Deep Aging Feature for Age Prediction'. Together they form a unique fingerprint.

    Cite this