Unsupervised and Fast Continent Classification of Digital Image Collections using Time

Abstract

Advances in storage capacity means that digital cameras can store huge collections of digital photographs. Typically such images are given non-descriptive filenames names such as a unique identifier, often an integer. Consequently it is time-consuming and difficult to browse and retrieve images from large collections especially on small consumer electronics devices. A strategy for classifying images into geographical regions is presented which allows images to be coarsely sorted into the continent where they were taken. The strategy employs patterns in the time-stamps of images to identify events such as holiday and individual days, and to estimate the approximate longitude where the photographs were taken. Experimental evaluations demonstrate that the continent is correctly estimated for 89 % of the images in arbitrary collections and that the longitude is estimated with a mean error of 27.5 degrees. The strategy is relatively straightforward to implement, also in hardware, and computationally inexpensive.