Abstract

Keywords: Convolutional Neural Networks (CNNs), Style Transfer, Deep Learning, Emotive Art, Expressive AI, Pastiches, Generative Art

Liminal Scape is a visual art installation with an expressive AI system that has been trained to recognize human emotion and generate abstract images at will. The proposed system receives an image (photographic portrait) and labels it based on the recognized emotional valence. Our system takes this initial photo and paints it red, yellow, or blue depending on the recognized emotions (from the facial expression) using a painterly algorithm which in turn becomes an input for a two modified Deep Convolutional Neural Network (CNN) models known as Deep Dream and Neural Style. These systems along with a final particle system pass generate a range of latent images that convey the initial emotion, unique to the given input (photographic portrait) and the labeled category (R, Y or B). Our system combines emergent and arbitrary behavior and breeding aspects of CNNs (in the low level) with a hybrid ML/particle stroking system to explore art creation within a high complexity space of artificial creativity.

• Mahsoo Salimi is a Ph.D. Candidate at Simon Fraser University and an interdisciplinary researcher interested in artificial creativity and Expressive AI. Her current research is bridging swarm intelligence and robotics to create dynamic and visceral relationships between human, robots, and AI.
• Nouf Abukhodair is a Ph.D. Candidate at Simon Fraser University and interdisciplinary researcher, her background is in Computer Science, she is interested in AI, Image Processing and Visual Perception. Her current research is looking at computational creativity, to learn how Deep Learning AI systems can understand visual art. Her work uses modern AI machine learning systems to understand goals and processes, to dynamically adapt the system for best results for art, entertainment and health applications.
• Steve DiPaola is active as an artist and a scientist, he is the past director of the Cognitive Science Program at Simon Fraser University, and leads the iVizLab (ivizlab.sfu.ca), a research lab that strives to make computational systems bend more to the human experience by incorporating biological, cognitive and behavior knowledge models.
• Carlos Castellanos, Assistant Professor, School of Interactive Games & Media (IGM), Rochester Institute of Technology, Rochester, NY, USA. Carlos Castellanos is an interdisciplinary artist and researcher with a wide array of interests such as cybernetics, ecology, embodiment, phenomenology, artificial intelligence and transdisciplinary collaboration. His work bridges science, technology, education and the arts, developing a network of creative interaction with living systems, the natural environment and emerging technologies. His artworks have been exhibited at local, national and international events such as the International Symposium on Electronic Art (ISEA), SIGGRAPH & ZERO1 San Jose. He is also a founding member of DPrime Research, an art-science nonprofit research organization. He holds a Ph.D. from the School of Interactive Arts and Technology (SIAT), Simon Fraser University and an MFA from the CADRE Laboratory for New Media, San Jose State University. ccastellanos.com
• Philippe Pasquier (FR/CA), School of Interactive Arts & Technology, Simon Fraser University, Surrey, BC, Canada. Philippe Pasquier researches the theory and practice of Creative AI, focussing on creative processes and generative systems. He is a scientist specialized in artificial intelligence, a multidisciplinary artist, an educator, and a community builder. His contributions range from theoretical research in multi-agent systems, computational creativity, and machine learning, to applied artistic research and practice in digital art, computer music, and generative art. Philippe is an associate professor at Simon Fraser University’s School for Interactive Arts and Technology, in Vancouver, where he directs the Metacreation Lab for Creative AI. newforms.digital