Skip to main navigation Skip to search Skip to main content

Improving borderline adulthood facial age estimation through ensemble learning

  • Felix Anda
  • , David Lillis
  • , Aikaterini Kanta
  • , Brett A. Becker
  • , Elias Bou-Harb
  • , Nhien An Le-Khac
  • , Mark Scanlon

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    Abstract

    Achieving high performance for facial age estimation with subjects in the borderline between adulthood and non-adulthood has always been a challenge. Several studies have used different approaches from the age of a baby to an elder adult and different datasets have been employed to measure the mean absolute error (MAE) ranging between 1.47 to 8 years. The weakness of the algorithms specifically in the borderline has been a motivation for this paper. In our approach, we have developed an ensemble technique that improves the accuracy of underage estimation in conjunction with our deep learning model (DS13K) that has been fine-tuned on the Deep Expectation (DEX) model. We have achieved an accuracy of 68% for the age group 16 to 17 years old, which is 4 times better than the DEX accuracy for such age range. We also present an evaluation of existing cloud-based and offline facial age prediction services, such as Amazon Rekognition, Microsoft Azure Cognitive Services, How-Old.net and DEX.

    Original languageEnglish
    Title of host publicationProceedings of the 14th International Conference on Availability, Reliability and Security, ARES 2019
    PublisherAssociation for Computing Machinery
    Number of pages8
    ISBN (Electronic)9781450371643
    DOIs
    Publication statusPublished - 26 Aug 2019
    Event14th International Conference on Availability, Reliability and Security, ARES 2019 - Canterbury, United Kingdom
    Duration: 26 Aug 2019 → 29 Aug 2019

    Conference

    Conference14th International Conference on Availability, Reliability and Security, ARES 2019
    Country/TerritoryUnited Kingdom
    CityCanterbury
    Period26/08/19 → 29/08/19

    UN SDGs

    This output contributes to the following UN Sustainable Development Goals (SDGs)

    1. SDG 8 - Decent Work and Economic Growth
      SDG 8 Decent Work and Economic Growth
    2. SDG 16 - Peace, Justice and Strong Institutions
      SDG 16 Peace, Justice and Strong Institutions

    Keywords

    • Child Exploitation Investigation
    • Deep Learning
    • Digital Forensics
    • Facial Recognition
    • Underage Photo Datasets

    Fingerprint

    Dive into the research topics of 'Improving borderline adulthood facial age estimation through ensemble learning'. Together they form a unique fingerprint.

    Cite this