Izvorni znanstveni članak

https://doi.org/10.31803/tg-20240603185810

Computing the Deep Semantics of Visual Communications

Trpimir Jeronim Ježić orcid.org/0009-0008-7461-7325 ; University of Zagreb, Faculty of Graphic Arts, Getaldićeva 2, 10 000 Zagreb, Croatia
Marko Maričević ; University of Zagreb, Faculty of Graphic Arts, Getaldićeva 2, 10 000 Zagreb, Croatia
Ivana Pavlović ; University of Zagreb, Faculty of Graphic Arts, Getaldićeva 2, 10 000 Zagreb, Croatia
Miroslav Mikota ; University of Zagreb, Faculty of Graphic Arts, Getaldićeva 2, 10 000 Zagreb, Croatia *

* Dopisni autor.

Sažetak

The research field of computational aesthetics gives crucial contributions to the development of mechanisms for filtering and/or generating value-laden informational content. This paper acknowledges a recognized escalating problem in the development of contemporary informational technologies and presents a practical solution for communicational quality management by employing an innovative approach to the computational aesthetic evaluation (CAE). After discussing the problem and attempted approaches to its alleviation, the paper offers a novel expert solution by presenting an original research approach and its resulting open-sourced model which outperforms its current state-of-the-art competition in semantic and stylistic classification, at the same time providing an idiomatic measure for objective aesthetic evaluation and demonstrating semantically rich and professionally recognized explanatory power which can serve as the solid basis for development of reliable and user friendly content retrieval, generative or auxiliary design applications. Presented model is resource- and privacy-wise utmost conservative. Its use evades all ethical, legal or security concerns that beset all currently prominent models. Its developmental and operational costs are practically nil.

Ključne riječi

computational aesthetic evaluation; convolutional neural networks; feature engineering; graphic engineering; interpretable machine learning; semantic embeddings

Hrčak ID:

332170

URI

https://hrcak.srce.hr/332170

Datum izdavanja:

15.9.2025.

Posjeta: 115 *