All the people around me: face discovery in egocentric photo-streams

TL;DR

This paper introduces an unsupervised method for clustering faces in egocentric photo-streams, effectively identifying individuals despite appearance variations in real-world conditions.

Contribution

It presents a novel bottom-up pipeline that arranges images into events, localizes faces, and groups appearances across events without supervision.

Findings

Effective face clustering in egocentric data

Handles appearance variations in real-world conditions

Validated on one-month wearable camera dataset

Abstract

Given an unconstrained stream of images captured by a wearable photo-camera (2fpm), we propose an unsupervised bottom-up approach for automatic clustering appearing faces into the individual identities present in these data. The problem is challenging since images are acquired under real world conditions; hence the visible appearance of the people in the images undergoes intensive variations. Our proposed pipeline consists of first arranging the photo-stream into events, later, localizing the appearance of multiple people in them, and finally, grouping various appearances of the same person across different events. Experimental results performed on a dataset acquired by wearing a photo-camera during one month, demonstrate the effectiveness of the proposed approach for the considered purpose.