Uma abordagem computacional para análise de composições artísticas

Autores

  • Feyza Nur Koçer Özgün Istanbul Technical University
  • Sema Alaçam Istanbul Technical University

DOI:

https://doi.org/10.11606/gtp.v18i2.196288

Palavras-chave:

Arte computacional, Análise baseada em pixels, Codificação visual, Mondrian

Resumo

Novas abordagens emergem da análise de obras com ferramentas computacionais e têm potencial para oferecer diferentes perspectivas para obras recriadas em ambientes digitais. Este estudo visa revelar as relações implícitas entre as composições de Mondrian com diferentes representações visuais. No âmbito do estudo, as composições concluídas entre 1938 e 1943, que possuem uma forte relação geometria-cor, foram discutidas pela primeira vez com uma abordagem baseada em pixels. No método de fragmentação seguido, as semelhanças e diferenças são expressas com dados transferidos de pixels para matrizes numéricas em duas etapas distintas: 1. Entre os artefatos em pares, 2. Entre um artefato e todos os outros artefatos selecionados. A visualização das matrizes foi representada por mapas de cores 2D e mapas de texturas 3D. Esses estilos de interpretação permitem que as composições sejam expressas do geral para o específico e novamente do específico para o geral, ganhando um novo significado.

Downloads

Os dados de download ainda não estão disponíveis.

Referências

ALVAREZ-RAMIREZ, J.; IBARRA-VALDEZ, C.; RODRIGUEZ, E. Fractal analysis of Jackson Pollock's painting evolution. Chaos, Solitons & Fractals, 83: 97-104, 2016

ANDRZEJEWSKI, D. et al. Inferring compositional style in the neo-plastic paintings of Piet Mondrian by machine learning. In: Computer Vision and Image Analysis of Art. International Society for Optics and Photonics, p. 75310G, 2010.

BOUNTIS, T.; FOKAS, A.S.; PSARAKIS, E.Z. Fractal analysis of tree paintings by Piet Mondrian (1872-1944). International Journal of Arts and Technology, 10.1: 27-42, 2017.

BOURACHED, A. et al. Recovery of underdrawings and ghost-paintings via style transfer by deep convolutional neural networks: A digital tool for art scholars. Electronic Imaging, 2021.14: 42-1-42-10, 2021.

CETINIC, E.; LIPIC, T.; GRGIC, S. A deep learning perspective on beauty, sentiment, and remembrance of art. IEEE Access, 7: 73694-73710, 2019.

CLEVELAND, Paul. Aesthetics and complexity in digital layout systems. Digital Creativity, 19.1: 33-50, 2018.

SILVA GARZA, Andrés Gómez de; LORES, Aram Zamora. Automating evolutionary art in the style of Mondrian. In: Genetic and Evolutionary Computation Conference. Proceedings. Springer, Berlin, Heidelberg. p. 394-395, 2004.

GARZA, ANDRÉS GÓMEZ DE SILVA; LORES, ARÁM ZAMORA. Evolutionary art revisited: Making the process fully automated. In Proceedings of the 5th World Scientific and Engineering Academy and Society (WSEAS) International Conference on Soft Computing, Optimization, Simulation and Manufacturing Systems (SOSM), 2005.

FEIJS, L. Divisions of the plane by computer: another way of looking at Mondrian's nonfigurative compositions. Leonardo, 37.3: 217-222, 2004.

FEIJS, L. A program for Victory Boogie Woogie. Journal of Mathematics and the Arts, 13.3: 261-285, 2019.

FEIJS, Loe. Analyzing the Structure of Mondrian's 1920-1940 Compositions. arXiv preprint arXiv:2011.00843, 2020.

FRANKE, H. W. Computer Graphics—Computer Art. Springer Science & Business Media, 2012.

GREENFIELD, Gary R. Art by computer program== programmer creativity. Digital Creativity, 2006, 17.01: 25-35.

HERTZMANN, A. Can computers create art?. In: Arts. Multidisciplinary Digital Publishing Institute. p. 18, 2018.

KIM, Diana, et al. Computational Analysis of Content in Fine Art Paintings. In: ICCC. p. 33-40, 2019.

KLEE, P.; MOHOLY-NAGY, S. Pedagogical sketchbook. London: Faber & Faber. 1953.

LEE, J.; LIU, Y.. Modelling Mondrians Design Processes and TheirArchitectural Associations Using Multilayer NeuralNetworks. 1998.

LEFEVRE, Kristen; DEWITT, David J.; RAMAKRISHNAN, Raghu. Mondrian multidimensional k-anonymity. In: 22nd International conference on data engineering (ICDE'06). IEEE, p. 25-25, 2006.

LOPES, A. M.; TENREIRO MACHADO, J. A. Complexity analysis of Escher’s art. Entropy, 21.6: 553, 2019.

MONDAL, J. Morphological Translation of Mondrian’s Neo-plastic 2D Compositions into 3D Embodiments using Shape Grammar. Proceedings of International Conference on Emerging Technologies In Architectural Design (ICETAD2019), Toronto, Canada, 2019.

NOLL, A. M. Human or machine: A subjective comparison of Piet Mondrian’s “Composition with Lines”(1917) and a computer-generated picture. The psychological record, 16.1: 1-10, 1966.

NOVAK, M. An Experiment in Computational Composition. New Ideas and Directions for the 1990's, 1989.

PARK, H. J. Stylistic Reproductions of Mondrian’s Composition With Red, Yellow, and Blue. In Proceedings of the 25th International Conference on Computer-Aided Architectural Design Research in Asia. CAADRIA. 2020.

ROTZLER, W. Constructive Concepts: A History of Constructive Art from Cubism to the Present, Rizzoli, New York. 1989.

ROY, D. M. et al. The Mondrian Process. In: NIPS. p. 1377-1384. 2008

SHAMIR, L.; TARAKHOVSKY, J. A. Computer analysis of art. Journal on Computing and Cultural Heritage (JOCCH), 5.2: 1-11, 2012.

SIGAKI, Y.D.; PERC, M.; RIBEIRO, H. V. History of art paintings through the lens of entropy and complexity. Proceedings of the National Academy of Sciences, 115.37: E8585-E8594. 2018.

Skrodzki, M., & Polthier, K. (2018). Mondrian Revisited: A Peek into the Third Dimension. In Bridges 2018 Conference Proceedings (pp. 99-106). Tessellations Publishing.

SMIRNOV, S.; EGUIZABAL, A. Deep learning for object detection in fine-art paintings. In: 2018 Metrology for Archaeology and Cultural Heritage (MetroArchaeo). IEEE, p. 45-49. 2018.

THOMPSON, Michael. Computer Art: Pictures Composed of Binary Elements on a Square Grid. Leonardo, 271-276. 1977.

TUFTE, E. R.; GOELER, N. H.; BENSON, R. Envisioning information. Cheshire, CT: Graphics Press. 1990.

WANG, Y. et al. Metadata dependent Mondrian processes. In Proceedings: International Conference on Machine Learning. PMLR, p. 1339-1347. 2015.

WANG, Y.; XIE, R. Pixel-Based Approach for Generating Original and Imitating Evolutionary Art. Electronics, 9.8: 1311. 2020.

ZHANG, K.; HARRELL, S.; JI, X. Computational aesthetics: on the complexity of computer-generated paintings. Leonardo, 45.3: 243-248. 2012.

ZIV, Y. Parallels between Suprematism and the Abstract, Vector-Based Motion Graphics of Flash. In Proceedings: Intelligent Agent. 2006.

Downloads

Publicado

2023-11-30

Como Citar

ÖZGÜN, Feyza Nur Koçer; ALAÇAM, Sema. Uma abordagem computacional para análise de composições artísticas . Gestão & Tecnologia de Projetos, São Carlos, v. 18, n. 2, p. 109–121, 2023. DOI: 10.11606/gtp.v18i2.196288. Disponível em: https://www.revistas.usp.br/gestaodeprojetos/article/view/196288.. Acesso em: 15 maio. 2024.