Quantifying Aesthetics of Visual Design Applied to Automatic Design

In this thesis, the author makes several contributions to the study of design of graphical materials. The thesis begins with a review of the relationship between design and aesthetics, and the use of mathematical models to capture this relationship. Then, a novel method for linking linguistic concepts to colors using the Latent Dirichlet Allocation Dual Topic Model is proposed. Next, the thesis studies the relationship between aesthetics and spatial layout by formalizing the notion of visual balance. Applying principles of salience and Gaussian mixture models over a body of about 120,000 aesthetically rated professional photographs, the author provides confirmation of Arnhem's theory about spatial layout. The thesis concludes with a description of tools to support automatically generating personalized design.

Nominated as an outstanding Ph.D. thesis by Purdue University, USA Focuses on the automatic design of visual media and the quantification of such designs' aesthetics Tackles the understanding of visual design concepts and principles to create solutions and interactions for users who are part of the design creation system Proposes approaches toward understanding design thinking in design of self-publishing media Includes supplementary material: sn.pub/extras

Autorentext

Dr. Ali Jahanian graduated with a Ph.D. from the School of Electrical and Computer Engineering at Purdue University, and is currently at the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory.

Inhalt

Introduction.- On The Legitimacy Of Quantifying Aesthetics.- Design Mining Color Semantics.- Design Mining Visual Balance.- Automatic Design Of Self-Published Media: A Case Study Of Magazine Covers.- Recommendation System For Automatic Design.