Dating Historical Color Images

People

Frank Palermo
James Hays (Brown University)
Alexei A. Efros

Abstract

We introduce the task of automatically estimating the age of historical color photographs. We suggest features which attempt to capture temporally discriminative information based on the evolution of color imaging processes over time and evaluate the performance of both these novel features and existing features commonly utilized in other problem domains on a novel historical image data set. For the challenging classification task of sorting historical color images into the decade during which they were photographed, we demonstrate significantly greater accuracy than that shown by untrained humans on the same data set. Additionally, we apply the concept of data-driven camera response function estimation to historical color imagery, demonstrating its relevance to both the age estimation task and the popular application of imitating the appearance of vintage color photography.

Paper

ECCV 2012 Paper (Preprint, PDF, 2.6MB)

@inproceedings{DBLP:conf/eccv/PalermoHE12,
  author    = {Frank Palermo and
               James Hays and
               Alexei A. Efros},
  title     = {Dating Historical Color Images},
  booktitle = {ECCV (6)},
  year      = {2012},
  pages     = {499-512},
  crossref  = {DBLP:conf/eccv/2012-6},
}

@proceedings{DBLP:conf/eccv/2012-6,
  editor    = {Andrew Fitzgibbon and
               Svetlana Lazebnik and
               Yoichi Sato and
               Cordelia Schmid},
  title     = {Computer Vision - ECCV 2012, 12th European Conference on
               Computer Vision, Firenze, Italy, October 7-13,
               2012, Proceedings, Part VI},
  booktitle = {ECCV (6)},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {7577},
  year      = {2012},
}
	

Code

The software developed during the course of this research is currently being prepared for release to the public. During this time, the link below will always point to the most current version of all source code which has been made publically available. Please check back periodically for updates.

ECCV 2012 Source Code (Partial) (Revision 20121002, TAR.BZ2, 3.1MB)

Data

• Historical Color Image Database (TAR, 212MB)
• Technicolor® Process 4 Database (TAR, 254MB)

Technicolor® is a registered trademark. Technicolor SA is neither affiliated with nor has endorsed this research.

Funding

This research is supported by:

• Google
• NSF CAREER Award 1149853 to James Hays

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder, except when identified by Creative Commons License 2.0, in which case the license applies to both the original and modified versions of the images.

Comments, questions to Frank Palermo. We support web standards; this page is valid XHTML 1.1 and CSS Level 3.