Image Analysis using Persistent Homology
Organizers
Speaker
Shizuo Kaji
Time
Thursday, April 18, 2024 2:30 PM - 3:30 PM
Venue
A3-4-101
Online
Zoom 928 682 9093
(BIMSA)
Abstract
Deep convolutional networks have proved to be extremely powerful in image analysis. However, they tend to be biased toward local features such as texture and often fail to capture the global structure of image and volume data. Persistent homology (PH), a tool from the emerging field of topological data analysis, has been successfully used to detect global characteristics of data that are overlooked by conventional methods. We present Cubical Ripser, an open-source software designed for high-efficiency computation of PH of cubical complexes. We will discuss how PH can be integrated into a standard image analysis pipeline with some practical applications.