Age regression from soft aligned face images using low computational resources

Bekios, Juan and Buenaposada Biencinto, José Miguel and Baumela Molina, Luis (2011). Age regression from soft aligned face images using low computational resources. In: "5th Conference of Pattern Recognition and Image Analysis, IbPRIA 2011", 08-10 Jun 2011, Las Palmas de Gran Canaria, España. ISBN 978-3-642-21256-7. pp. 281-288.

Description

Title: Age regression from soft aligned face images using low computational resources
Author/s:
  • Bekios, Juan
  • Buenaposada Biencinto, José Miguel
  • Baumela Molina, Luis
Item Type: Presentation at Congress or Conference (Article)
Event Title: 5th Conference of Pattern Recognition and Image Analysis, IbPRIA 2011
Event Dates: 08-10 Jun 2011
Event Location: Las Palmas de Gran Canaria, España
Title of Book: Pattern Recognition and Image Analysis
Date: 2011
ISBN: 978-3-642-21256-7
Volume: 6669
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (129kB) | Preview

Abstract

The initial step in most facial age estimation systems consists of accurately aligning a model to the output of a face detector (e.g. an Active Appearance Model). This fitting process is very expensive in terms of computational resources and prone to get stuck in local minima. This makes it impractical for analysing faces in resource limited computing devices. In this paper we build a face age regressor that is able to work directly on faces cropped using a state-of-the-art face detector. Our procedure uses K nearest neighbours (K-NN) regression with a metric based on a properly tuned Fisher Linear Discriminant Analysis (LDA) projection matrix. On FG-NET we achieve a state-of-the-art Mean Absolute Error (MAE) of 5.72 years with manually aligned faces. Using face images cropped by a face detector we get a MAE of 6.87 years in the same database. Moreover, most of the algorithms presented in the literature have been evaluated on single database experiments and therefore, they report optimistically biased results. In our cross-database experiments we get a MAE of roughly 12 years, which would be the expected performance in a real world application.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainTIN2010-19654UnspecifiedUnspecifiedUnspecified
Government of SpainCSD2007-00018UnspecifiedUnspecifiedUnspecified

More information

Item ID: 38536
DC Identifier: http://oa.upm.es/38536/
OAI Identifier: oai:oa.upm.es:38536
Official URL: http://www.springer.com/us/book/9783642212567
Deposited by: Memoria Investigacion
Deposited on: 14 Mar 2016 12:32
Last Modified: 27 Nov 2018 09:06
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM