- Titel
- Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Processing
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:ch1-qucosa2-906679
- Datum der Einreichung
- 25.04.2023
- Datum der Verteidigung
- 16.01.2024
- ISBN
- 978-3-96100-213-9
- DOI
- https://doi.org/10.51382/978-3-96100-213-9
- Abstract (EN)
- While current approaches to digital image processing within the context of machine learning and deep learning are motivated by biological processes within the human brain, they are, however, also limited due to the current state of the art of input and output devices as well as the algorithms that are concerned with the processing of their data. In order to generate digital images from real-world scenes, the utilized digital images' underlying lattice formats are predominantly based on rectangular or square structures. Yet, the human visual perception system suggests an alternative approach that manifests itself within the sensory cells of the human eye in the form of hexagonal arrangements. As previous research demonstrates that hexagonal arrangements can provide different benefits to image processing systems in general, this contribution is concerned with the synthesis of both worlds in the form of the biologically inspired hexagonal deep learning for hexagonal image processing. This contribution is therefore concerned with the design, the implementation, and the evaluation of hexagonal solutions to currently developed approaches in the form of hexagonal deep neural networks. For this purpose, the respectively realized hexagonal functionality had to be built from the ground up as hexagonal counterparts to otherwise conventional square lattice format based image processing and deep learning based systems. Furthermore, hexagonal equivalents for artificial neural network based operations, layers, as well as models and architectures had to be realized. This also encompasses the related evaluation metrics for hexagonal lattice format based representations of digital images and their conventional counterparts in comparison. Therefore, the developed hexagonal image processing and deep learning framework Hexnet functions as a first general application-oriented open science framework for hexagonal image processing within the context of machine learning. To enable the evaluation of hexagonal approaches, a set of different application areas and use cases within conventional and hexagonal image processing – astronomical, medical, and industrial image processing – are provided that allow an assessment of hexagonal deep neural networks in terms of their classification capabilities as well as their general performance. The obtained and presented results demonstrate the possible benefits of hexagonal deep neural networks and their hexagonal representations for image processing systems. It is shown that hexagonal deep neural networks can result in increased classification capabilities given different basic geometric shapes and contours, which in turn partially translate into their real-world applications. This is indicated by a relative improvement in F1-score for the proposed hexagonal and square models, ranging from 1.00 (industrial image processing) to 1.03 (geometric primitives) with single classes even reaching a relative improvement of over 1.05. However, possible disadvantages are also given by the increased complexity of hexagonal algorithms. This is evident by the present potential in regard to runtime optimizations that have yet to be realized for certain hexagonal operations in comparison to their currently deployed square equivalents.
- Freie Schlagwörter (EN)
- Computer Vision, Pattern Recognition, Deep Learning, Convolutional Neural Networks, Residual Neural Networks, Hexagonal Image Processing, Hexagonal Lattice, Hexagonal Sampling
- Klassifikation (DDC)
- 006
- Normschlagwörter (GND)
- Artificial Intelligence, Machine Learning, Deep Learning
- GutachterIn
- Jun.-Prof. Dr. Danny Kowerko
- Univ.-Prof. Dr. Maximilian Eibl
- BetreuerIn Hochschule / Universität
- Jun.-Prof. Dr. Danny Kowerko
- Univ.-Prof. Dr. Maximilian Eibl
- Verlag
- Universitätsverlag Chemnitz, Chemnitz
- Den akademischen Grad verleihende / prüfende Institution
- Technische Universität Chemnitz, Chemnitz
- Förder- / Projektangaben
- Europäischer Sozialfonds für Deutschland (ESF)
Landesinnovationspromotionstipendium
Robuste Objektklassifikation zur klinischen sowie industriellen Bild- und Videoverarbeitung auf Basis der hexagonalen Bildrasterung für maschinelle Lernverfahren - Bundesministerium für Bildung und Forschung (BMBF)
InnoProfile-Transfer
localizeIT
(localizeIT)
ID: 03IPT608X - Novartis Pharma GmbH (Novartis)
OphthalVis 2.0 – Entwicklung individueller Therapie-Ansätze bei AMD, DMÖ und RVV durch Analyse aufbereiteter Massendaten mit maschinellen Lernverfahren
(OphthalVis 2.0)
ID: P2511623 - Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:ch1-qucosa2-906679
- Veröffentlichungsdatum Qucosa
- 27.05.2024
- Dokumenttyp
- Dissertation
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0- Inhaltsverzeichnis
1 Introduction and Motivation 2 Fundamentals and Methods 3 Implementation 4 Test Results, Evaluation, and Discussion 5 Conclusion and Outlook