Using a CNN Model to Assess Paintings' Creativity

TL;DR

This paper introduces a CNN-based model that automatically evaluates the creativity of paintings, achieving high accuracy and faster assessments compared to human raters, thus advancing the efficiency of artistic creativity evaluation.

Contribution

The study develops and validates a CNN model specifically for assessing the creativity of paintings, filling a gap in machine learning applications in art evaluation.

Findings

90% accuracy in creativity assessment

Faster evaluation times than human raters

Effective in distinguishing professional and children's paintings

Abstract

Assessing artistic creativity has long challenged researchers, with traditional methods proving time-consuming. Recent studies have applied machine learning to evaluate creativity in drawings, but not paintings. Our research addresses this gap by developing a CNN model to automatically assess the creativity of human paintings. Using a dataset of six hundred paintings by professionals and children, our model achieved 90% accuracy and faster evaluation times than human raters. This approach demonstrates the potential of machine learning in advancing artistic creativity assessment, offering a more efficient alternative to traditional methods.