Improved Image Classification using Topological Persistence

Dey, Tamal Krishna; Mandal, Sayan; Varcho, William

Improved Image Classification using Topological Persistence

Files

161-168.pdf (2.17 MB)

imagepers.zip (5.29 MB)

vmvfinal.mp4 (250.84 MB)

Date

2017

Authors

Dey, Tamal Krishna
Mandal, Sayan
Varcho, William

Publisher

The Eurographics Association

Abstract

Image classification has been a topic of interest for many years. With the advent of Deep Learning, impressive progress has been made on the task, resulting in quite accurate classification. Our work focuses on improving modern image classification techniques by considering topological features as well. We show that incorporating this information allows our models to improve the accuracy, precision and recall on test data, thus providing evidence that topological signatures can be leveraged for enhancing some of the state-of-the art applications in computer vision.

        @inproceedings{10.2312:vmv.20171272
,
booktitle = {Vision, Modeling & Visualization
},
editor = {Matthias Hullin and Reinhard Klein and Thomas Schultz and Angela Yao
},
title = {{Improved Image Classification using Topological Persistence
}},
author = {Dey, Tamal Krishna and 
Mandal, Sayan and 
Varcho, William
},
year = {2017
},
publisher = {The Eurographics Association
},
ISBN = {978-3-03868-049-9
},
DOI = {10.2312/vmv.20171272
}
}