Automatic Main Character Recognition for Photographic Studies

TL;DR

This paper presents an automated approach to identify main characters in photographs using machine learning and computer vision, aiming to assist photographic studies and media analysis.

Contribution

It introduces a novel method combining pose estimation and vision techniques for main character recognition, validated on a new annotated dataset.

Findings

Achieved an F1 score of 0.83 on the full dataset.

Reaching an F1 score of 0.96 on clear, important images.

High agreement among human annotators on main character identification.

Abstract

Main characters in images are the most important humans that catch the viewer's attention upon first look, and they are emphasized by properties such as size, position, color saturation, and sharpness of focus. Identifying the main character in images plays an important role in traditional photographic studies and media analysis, but the task is performed manually and can be slow and laborious. Furthermore, selection of main characters can be sometimes subjective. In this paper, we analyze the feasibility of solving the main character recognition needed for photographic studies automatically and propose a method for identifying the main characters. The proposed method uses machine learning based human pose estimation along with traditional computer vision approaches for this task. We approach the task as a binary classification problem where each detected human is classified either as a main character or not. To evaluate both the subjectivity of the task and the performance of our method, we collected a dataset of 300 varying images from multiple sources and asked five people, a photographic researcher and four other persons, to annotate the main characters. Our analysis showed a relatively high agreement between different annotators. The proposed method achieved a promising F1 score of 0.83 on the full image set and 0.96 on a subset evaluated as most clear and important cases by the photographic researcher.