Date Estimation in the Wild of Scanned Historical Photos: An Image Retrieval Approach

TL;DR

This paper introduces a retrieval-based approach for estimating the dates of scanned historical photos by ranking images based on embedded date similarity, outperforming traditional classification models.

Contribution

It formulates date estimation as a ranking task using a novel nDCG-based learning objective, diverging from conventional classification or regression methods.

Findings

Outperforms baseline methods in date estimation accuracy

Effective in date-sensitive image retrieval tasks

Validated on the DEW public database

Abstract

This paper presents a novel method for date estimation of historical photographs from archival sources. The main contribution is to formulate the date estimation as a retrieval task, where given a query, the retrieved images are ranked in terms of the estimated date similarity. The closer are their embedded representations the closer are their dates. Contrary to the traditional models that design a neural network that learns a classifier or a regressor, we propose a learning objective based on the nDCG ranking metric. We have experimentally evaluated the performance of the method in two different tasks: date estimation and date-sensitive image retrieval, using the DEW public database, overcoming the baseline methods.