Dating color images with ordinal classification

Paul Martin 1, 2 Antoine Doucet 2 Frédéric Jurie 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
2 Equipe Hultech - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : This paper proposes a new approach for automatically dating a photograph, based solely on its content. Building on recent advances in computer vision, the images are first described by a set of features. Then, the age group of every image is predicted by a classifier trained with annotated data. The key strength of our approach -- which makes it perform better than existing ones -- is the introduction of an ordinal classification framework, particularly adapted to the type of data to be predicted (age groups). The approach is validated on a recent challenging dataset for which it produces state-of-the-art results.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01011234
Contributor : Yvain Queau <>
Submitted on : Monday, June 23, 2014 - 1:11:45 PM
Last modification on : Saturday, April 20, 2019 - 9:02:25 AM
Long-term archiving on : Tuesday, September 23, 2014 - 11:17:55 AM

File

14_ICMR-dating-color-images.pd...
Files produced by the author(s)

Identifiers

Citation

Paul Martin, Antoine Doucet, Frédéric Jurie. Dating color images with ordinal classification. ICMR'14 - ACM International Conference on Multimedia Retrieval, Apr 2014, Glasgow, United Kingdom. 4 pp, ⟨10.1145/2578726.2578790⟩. ⟨hal-01011234⟩

Share

Metrics

Record views

308

Files downloads

240