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

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