Can You All Look Here? Towards Determining Gaze Uniformity In Group Images

Abstract

Since the advent of the smartphone, the number of group images taken every day is rising exponentially. The photographers' struggle is to make sure everyone looks at the camera while taking the picture. More specifically, in a group image, if everybody is not looking in the same direction, then the image's aesthetic quality and utility are depreciated. The photographer usually discards the image, and then subsequently, several images are taken to mitigate this issue. Usually, users have to manually check if the image is uniformly gazed, which is tedious and time-consuming. This paper proposes a method for classifying a given group image as uniformly gazed or nonuniformly gazed by calculating the Gaze Uniformity Index. We evaluate the proposed method on a subset of the ‘Images of Groups' dataset. The proposed method achieved an accuracy of 67%.