|
This article is cited in 2 scientific papers (total in 2 papers)
IMAGE PROCESSING, PATTERN RECOGNITION
Detection of the homotopy type of an object using differential invariants of an approximating map
S. V. Kurochkin Russian Academy of Science, Federal Research Centre “Computer Science and Control”, Moscow, Russia
Abstract:
A method of topological data analysis is proposed that allows one to find out the homotopy type of the object under study. Unlike mature and widely used methods based on persistent homologies, our method is based on computing differential invariants of some map associated with
an approximating map. Differential topology tools and the analogy with the main result in Morse theory are used. The approximating map can be constructed in the usual way using a neural network or otherwise. The method allows one to identify the homotopy type of an object in the plane because the number of circles in the homotopy equivalent object representation as a wedge is expressed through the degree of some map associated with the approximating map. The performance of the algorithm is illustrated by examples from the MNIST database and transforms thereof. Generalizations and open questions relating to a higher-dimension case are discussed.
Keywords:
machine learning, topological invariants, degree of a map, image processing.
Received: 19.11.2018 Accepted: 04.07.2019
Citation:
S. V. Kurochkin, “Detection of the homotopy type of an object using differential invariants of an approximating map”, Computer Optics, 43:4 (2019), 611–617
Linking options:
https://www.mathnet.ru/eng/co684 https://www.mathnet.ru/eng/co/v43/i4/p611
|
Statistics & downloads: |
Abstract page: | 178 | Full-text PDF : | 60 | References: | 17 |
|