Text

theses

Recent advances in machine learning on various computer vision tasks have shown the great potential for developing an AI system for art through the successful applications in the prediction of style, genre, medium, attribution, school of art, etc. Beyond the categorical information, in this dissertation, a more fundamental level of artistic knowledge is pursued by developing machine learning systems for art principles. The art principles are to know how art is visually formed and identify what content is in it and what symbolic meaning it has. The task necessitates fine-grained semantics to describe art, but art data does not generally accommodate the fine details. The scarcity of data annotation is a primary challenge in this machine learning study. In this dissertation, three research problems are explored; (1) first is to find principal semantics for style recognition. (2) second is to lay the groundwork for computational iconography, i.e. recognize content and discover the co-occurrence and visual similarities among the content in fine art paintings. (3) third is to quantify paintings with finite visual semantics from style through language models. In the system design, well-established knowledge and facts in art theory are leveraged, or general knowledge of art is integrated into the hierarchical architecture of deep-CNN (deep Convolutional Neural Network) as a numerical form after learning it from a corpus of art-texts through contemporary language models in Natural Language Processing. The language modeling is a practical and scalable solution requiring no direct annotation, but it is inevitably imperfect. This dissertation demonstrates how deep learning's hierarchical structure and adaptive nature can create a stronger resilience to the incompleteness of the practical solution than other related methods.

http://dissertations.umi.com/gsnb.rutgers:11787

Ph.D.

Includes bibliographical references

doi:10.7282/t3-80wk-bg95

The author owns the copyright to this work.