Computer analysis of art

Authors:
Lior Shamir;Jane A. Tarakhovsky
Affiliations:
Lawrence Technological University, Southfield, MI;Lawrence Technological University, Southfield, MI
Venue:
Journal on Computing and Cultural Heritage (JOCCH)
Year:
2012

Citing 7
Cited 0

Identification of drawing tools by classification of textural and boundary features of strokes

Pattern Recognition Letters
Evaluation of Face Datasets as Tools for Assessing the Performance of Face Recognition Methods

International Journal of Computer Vision
WND-CHARM: Multi-purpose image classification using compound image transforms

Pattern Recognition Letters
Stochastic modeling western paintings for effective classification

Pattern Recognition
Impressionism, expressionism, surrealism: Automated recognition of painters and schools of art

ACM Transactions on Applied Perception (TAP)
Image and pattern analysis for the determination of the method of drawing celebrated thera wall-paintings circa 1650 B.C.

Journal on Computing and Cultural Heritage (JOCCH)
Rhythmic Brushstrokes Distinguish van Gogh from His Contemporaries: Findings via Automated Brushstroke Extraction

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Analysis of visual art is a highly complex cognitive task that depends on the very many aspects of the art as well as complex brain connectivity, and the examination of visual art and the analysis of influential links between artists and artistic movements require the trained eye of knowledgeable art historians. However, while the human eye and brain can perceive visual art and notice the differences, similarities, and influential links between painters, computers employing artificial intelligence find this task far more challenging. In this article we show that computers can automatically analyze paintings of different artists and different schools of art in an unsupervised fashion. Experimental results show that the automatic computer analysis can group artists by their artistic movements, and provide a map of similarities and influential links that is largely in agreement with the analysis of art historians. These results demonstrate that machine vision and pattern recognition algorithms are able to mimic the complex cognitive task of the human perception of visual art, and can be used to measure and quantify visual similarities between paintings, painters, and schools of art.