Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1033866

Learning the Principles of Art History with convolutional neural networks


Cetinić, Eva; Lipić, Tomislav; Grgić, Sonja
Learning the Principles of Art History with convolutional neural networks // Pattern recognition letters, 129 (2020), 56-62 doi:10.1016/j.patrec.2019.11.008 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1033866 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Learning the Principles of Art History with convolutional neural networks

Autori
Cetinić, Eva ; Lipić, Tomislav ; Grgić, Sonja

Izvornik
Pattern recognition letters (0167-8655) 129 (2020); 56-62

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Convolutional neural networks ; Fine art ; High-level image features ; Wölfflin

Sažetak
Understanding the historical transformation of artistic styles implies the recognition of different stylistic properties. From a computer vision perspective, stylistic properties represent complex image features. In our work we explore the use of convolutional neural networks for learning features that are relevant for understanding properties of artistic styles. We focus on stylistic properties described by Heinrich Wölfflin in his book Principles of Art History (1915). Wölfflin identified five key visual principles, each defined by two contrasting concepts. We refer to each principle as one high- level image feature that measures how much each of the contrasting concepts is present in an image. We introduce convolutional neural network regression models trained to predict values of the five Wölfflin’s features. We provide quantitative and qualitative evaluations of those predictions, as well as analyze how the predicted values relate to different styles and artists. The outcome of our analysis suggests that the models learn to discriminate meaningful features that correspond to the visual characteristics of concepts described by Wölfflin. This indicates that the presented approach can be used to enable new ways of exploring fine art collections based on image features relevant and well-known within art history.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA


Ustanove
Fakultet elektrotehnike i računarstva, Zagreb,
Institut "Ruđer Bošković", Zagreb

Profili:

Avatar Url Eva Cetinić (autor)

Avatar Url Sonja Grgić (autor)

Avatar Url Tomislav Lipić (autor)

Citiraj ovu publikaciju

Cetinić, Eva; Lipić, Tomislav; Grgić, Sonja
Learning the Principles of Art History with convolutional neural networks // Pattern recognition letters, 129 (2020), 56-62 doi:10.1016/j.patrec.2019.11.008 (međunarodna recenzija, članak, znanstveni)
Cetinić, E., Lipić, T. & Grgić, S. (2020) Learning the Principles of Art History with convolutional neural networks. Pattern recognition letters, 129, 56-62 doi:10.1016/j.patrec.2019.11.008.
@article{article, year = {2020}, pages = {56-62}, DOI = {10.1016/j.patrec.2019.11.008}, keywords = {Convolutional neural networks, Fine art, High-level image features, W\"{o}lfflin}, journal = {Pattern recognition letters}, doi = {10.1016/j.patrec.2019.11.008}, volume = {129}, issn = {0167-8655}, title = {Learning the Principles of Art History with convolutional neural networks}, keyword = {Convolutional neural networks, Fine art, High-level image features, W\"{o}lfflin} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati