Toward Quantifying Ambiguities in Artistic Images

TL;DR

This paper introduces a method to quantify perceptual ambiguities in artistic images by analyzing crowdworker descriptions after varied viewing times, using GAN-generated images and text processing techniques.

Contribution

It presents a novel approach to measure image ambiguity through crowdworker responses and text analysis, addressing limitations of previous methods.

Findings

Text processing reveals detailed ambiguity levels.

GAN-generated images effectively used for ambiguity assessment.

Viewer responses vary with viewing duration, indicating perceptual ambiguity.

Abstract

It has long been hypothesized that perceptual ambiguities play an important role in aesthetic experience: a work with some ambiguity engages a viewer more than one that does not. However, current frameworks for testing this theory are limited by the availability of stimuli and data collection methods. This paper presents an approach to measuring the perceptual ambiguity of a collection of images. Crowdworkers are asked to describe image content, after different viewing durations. Experiments are performed using images created with Generative Adversarial Networks, using the Artbreeder website. We show that text processing of viewer responses can provide a fine-grained way to measure and describe image ambiguities.