Image recognition via Vietoris-Rips complex

Abstract

Extracting informative features from images has been of capital importance in computer vision. In this paper, we propose a way to extract such features from images by a method based on algebraic topology. To that end, we construct a weighted graph from an image, which extracts local information of an image. By considering this weighted graph as a pseudo-metric space, we construct a Vietoris-Rips complex with a parameter $\epsilon$ by a well-known process of algebraic topology. We can extract information of complexity of the image and can detect a sub-image with a relatively high concentration of information from this Vietoris-Rips complex. The parameter $\epsilon$ of the Vietoris-Rips complex produces robustness to noise. We empirically show that the extracted feature captures well images' characteristics.

arXiv comment10 pages

References in corpus (7)

• A Survey on Deep Learning in Medical Image Analysis
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Object Detection in 20 Years: A Survey
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Fashion Meets Computer Vision: A Survey
• A Survey on Neural Network Interpretability
• Effective persistent homology of digital images