Building Datasets from Publicly Accessible Social Media Images for Biometric Analysis

Abstract

The world is developing at a rapid pace, and some of its advancement can be accredited to technological innovations that are affecting many aspects of society. A field within computer science that is increasingly reaching many industries is Biometrics, specifically the area face recognition. Researchers, scientists, and organizations actively try to improve the performance of tools and algorithms. Nevertheless, for it to occur, there is a need for high-quality datasets to test and develop new techniques. Never had humanity, in the course of the history of civilization, produced massive amounts of data as it currently does. Social media networks play a significant role due to the amount of traffic that goes through its infrastructure. The content within it varies but is predominately flooded by images. In the era of selfies [1], we propose to aid the lack of datasets by building datasets from social media users' images. However, we acknowledge the complex legal and ethical issues involved with it. The possible collection mechanisms are compared, and a biometric ready dataset is built after the images have been properly processed. Aspects like legislation proposals across regions, controversies, and possible multi-level solutions are examined. This work will explore a solution to a biometric research problem while providing a snapshot of digital interactions in the current society.