Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Generation

TL;DR

This paper introduces a biologically inspired hexagonal deep learning framework called Hexnet for generating hexagonal images, demonstrating advantages over traditional square-based methods in complexity and speed.

Contribution

The paper presents a novel hexagonal deep neural network architecture inspired by biological visual systems for improved image generation.

Findings

Hexnet surpasses conventional approaches in image quality.

Models have fewer trainable parameters, reducing complexity.

Test rates are increased compared to square-based models.

Abstract

Whereas conventional state-of-the-art image processing systems of recording and output devices almost exclusively utilize square arranged methods, biological models, however, suggest an alternative, evolutionarily-based structure. Inspired by the human visual perception system, hexagonal image processing in the context of machine learning offers a number of key advantages that can benefit both researchers and users alike. The hexagonal deep learning framework Hexnet leveraged in this contribution serves therefore the generation of hexagonal images by utilizing hexagonal deep neural networks (H-DNN). As the results of our created test environment show, the proposed models can surpass current approaches of conventional image generation. While resulting in a reduction of the models' complexity in the form of trainable parameters, they furthermore allow an increase of test rates in comparison to their square counterparts.