Menu
Zjistit stav objednávky
Kontaktujte nás
Kniha Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Processing Tobias Schlosser

Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Processing

Autor: Tobias Schlosser
Jazyk: Angličtina
Vazba: Brožovaná
Vydavatel: Technische Universität Chemnitz
Dostupnost: U nakladatele na objednávku
Odesíláme za 17-27 dnů
795 Kč
While current approaches to digital image processing in the context of deep learning are motivated b...

Informace o knize

Autor
Tobias Schlosser
Jazyk
Angličtina
Vazba
Kniha - Brožovaná
Vydáno
2024
Stránek
300
EAN
9783961002139
ISBN
3961002134
Enbook ID
46067565
Vydavatel
Technische Universität Chemnitz
Hmotnost
438
Rozměry
148 x 210 x 19

Kompletní popis

While current approaches to digital image processing in the context of deep learning are motivated by biological processes in the human brain, they are, however, also limited due to the current state of the art of input and output devices. To generate images from real-world scenes, the underlying lattice formats are predominantly based on rectangular or square structures. Yet, the human visual perception system suggests an alternative approach that manifests itself in the sensory cells of the human eye in the form of hexagonal arrangements.This contribution is therefore concerned with the design, implementation, and evaluation of hexagonal solutions in the form of hexagonal deep neural networks (H-DNN). The realized hexagonal functionality had to be built from the ground up as hexagonal counterparts to otherwise conventional square image processing systems, for which hexagonal equivalents for artificial neural network operations, layers, and models had to be implemented.To enable their evaluation, a set of different application areas within astronomical, medical, and industrial image processing are provided that allow an assessment of H-DNNs in terms of their general performance. The presented results demonstrate the possible benefits of H-DNNs for image processing systems. It is shown that H-DNNs can result in increased classification capabilities given different basic geometric shapes and contours, which in turn partially translate into their real-world applications.

Mohlo by vás zajímat

Unreal Engine 5 Game Development with C++ Scripting: Become a professional game developer and create fully functional, high-quality games

Zhenyu George Li
1 032 Kč

Healthcare Policy in Africa

Jean-Germain Gros
1 384 Kč

Unreal Engine Pro

Frahaan Hussain
643 Kč

Multiplayer Game Development with Unreal Engine 5: Create compelling multiplayer games with C++, Blueprints, and Unreal Engine's networking features

Marco Secchi
972 Kč

Principles of Endodontics

Shanon Patel
1 473 Kč

Installation Methods of Offshore Oil-Gas Well Conductor

Jin Yang
2 286 Kč

Computer Vision, Graphics, and Image Processing

Snehasis Mukherjee
1 147 Kč

Father Sergius

Leo Tolstoy
159 Kč

Oracle Stored Programs for Beginners: Creating Your Own Procedures and Functions in PL/SQL

Djoni Darmawikarta
236 Kč

Unreal Engine 4 Scripting with C++ Cookbook

William Sherif
1 257 Kč

Unity of Reason

Dieter Henrich
2 633 Kč

Hexagonal Image Processing

Jayanthi Sivaswamy
2 286 Kč

Hexagonal Image Processing

Jayanthi Sivaswamy
2 286 Kč

Zákaznicí kteří koupili tuto knihu koupili také

Il linfodrenaggio per la tua salute. L'automassaggio contro cellulite, edemi, gonfiori

Dorothea Schneider Siemens
278 Kč

Raumausstattermeister - Das prufungsrelevante Wissen

Sarastro Verlag
976 Kč

Poslanie vášho života

Stephen R. Covey
247 Kč

Frozen - Anna e Elsa 7 - L'ammiratore segreto

Disney
93 Kč

Vanitas 2 - Magická kniha

Džun Močizuki
207 Kč