Detecting visual design principles in art and architecture through deep convolutional neural networks

Abstract

Visual design is associated with the use of some basic design elements and principles. Those are applied by the designers in the various disciplines for aesthetic purposes, relying on an intuitive and subjective process. Thus, numerical analysis of design visuals and disclosure of the aesthetic value embedded in them are considered as hard. However, it has become possible with emerging artificial intelligence technologies. This research aims at a neural network model, which recognizes and classifies the design principles over different domains. The domains include artwork produced since the late 20th century; professional photos; and facade pictures of contemporary buildings. The data collection and curation processes, including the production of computationally-based synthetic dataset, is genuine. The proposed model learns from the knowledge of myriads of original designs, by capturing the underlying shared patterns. It is expected to consolidate design processes by providing an aesthetic evaluation of the visual compositions with objectivity.

Visual aesthetics and multisensory engagement in online food delivery services

“…repetition, compositional lines, contrast, balance, rhythm) (Demir et al, 2021). Effective use of visual design principles helps accomplish intended effects of communicating the visual design to viewers (Graves, 1951;Demir et al, 2021). Drawing from Berlyne's aesthetic theory (1971) and theory of grounded cognition (Barsalou, 2008), our findings demonstrated that repetition and compositional lines created by alignments evoke a multisensory experience involving visual appeal and imagined taste, making it easier for viewers to simulate tasting the presented food.…”

“…lines, color and shape) are visually organized (e.g. repetition, compositional lines, contrast, balance, rhythm) (Demir et al, 2021). Effective use of visual design principles helps accomplish intended effects of communicating the visual design to viewers (Graves, 1951;Demir et al, 2021).…”

“…lines, color and shape) are visually organized (e.g. repetition, compositional lines, contrast, balance, rhythm) (Demir et al. , 2021).…”

Stone masonry design automation via reinforcement learning

“…As ML and AI methods are founded upon computational analysis (e.g., finite element method, FEA), building surrogate models to accelerate the assessment of architectural structure has been also investigated to facilitate design exploration (Wortmann et al, 2015; Zheng et al, 2020). Other approaches also include the evaluation of architectural designs in quantitative aspects, such as visual design principles, esthetics, and creativity (Mars et al, 2020; Demir et al, 2021). However, existing approaches still cannot address the challenges involving stone masonry designs: organizing heterogeneous shapes of natural stones in proper order considering the complex interaction across their joints, without prescribed knowledge.…”

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology

“…In recent years, with the continuous development of theory and technology in the eld of arti cial intelligence (AI), its related research results have been widely used. For example, language recognition, image recognition, natural language processing, and other related achievements have brought a lot of convenience to all aspects of people's lives [1][2][3][4]. Robotics is one of the main technologies in the eld of AI.…”