GARGI: Selecting Gaze-Aware Representative Group Image from a Live Photo

Abstract

The number of photos, especially group photos in live mode, has increased tremendously in today's world. Selecting a representative image in a live photo that preserves the aesthetic quality is a challenging task. In this paper, we propose a method to select a Gaze-Aware Representative Group Image, called GARGI, that considers the uni-formity, or consequently the deviation, of the people's gaze in live-mode group photos to make it aesthetically pleasing. We tested this method on our own live-mode group image dataset. We argue that the inbuilt representative im-age selection mechanism in an Apple iPhone does not con-sider the subject's gaze, especially in a group image. The GARGI considers the deviation of gazes for each subject with respect to their expected gaze directions and deter-mines an aesthetically better representative image with the least amount of gaze deviation for all the subjects. The re-sults presented in the paper also justify this claim. They can be used to pave the way for becoming a standard in any keyframe selection mechanisms that will include human subjects in live photos, burst mode shots, or even in videos.