Semantic Analysis of (Reflectional) Visual Symmetry: A Human-Centred Computational Model for Declarative Explainability

EasyChair Preprint 227

Abstract

We present a computational framework for the semantic interpretation of symmetry in naturalistic scenes. Key features include a human-centred representation, and a declarative, explainable interpretation model supporting deep semantic question-answering founded on an integration of methods in knowledge representation and computer vision. In the backdrop of the visual arts, we showcase the framework's capability to generate human-centred, queryable, relational structures, also evaluating the framework with an empirical study on the human perception of visual symmetry. Our framework represents and is driven by the application of foundational Vision and KR methods in the psychological and social sciences.

Keyphrases: Cognitive Vision, Deep Visuo-Spatial Semantics, Explainable AI, Knowledge Representation and Reasoning, spatial reasoning, visual art, visual perception

@booklet{EasyChair:227,
  author    = {Jakob Suchan and Mehul Bhatt and Srikrishna Varadarajan and Seyed Ali Amirshahi and Stella Yu},
  title     = {Semantic Analysis of (Reflectional) Visual Symmetry: A Human-Centred Computational Model for Declarative Explainability},
  doi       = {10.29007/v963},
  howpublished = {EasyChair Preprint 227},
  year      = {EasyChair, 2018}}