Work

Color image recognition with color opponency-based filters and two-layer spiking neural networks

Year: 2025

Type: article

Abstract: Spiking neural networks (SNNs) are the basis of low-power neuromorphic computing systems and hardware. Most previous studies on unsupervised SNNs have tested their ability in grayscale image classification. In this study, we mainly propose color opponency-based filters, inspired by retinal color vision, for color image classification with an unsupervised two-layer SNN and a simple linear classifier. We demonstrate that the color opponency-based filters in multiple visual pathways are more effective than conventional grayscale transform methods in a color image classification task with ETH-80 dataset. Our results suggest that biological color vision mechanisms can expand the potential of shallow SNN models.

Source: Nonlinear Theory and Its Applications IEICE

DOI: 10.1587/nolta.16.290

Authors: Hiroki Shinagawa, Gouhei Tanaka

Institutions: The University of Tokyo, Nagoya Institute of Technology

Language: English

Topic: Advanced Memory and Neural Computing

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: diamond

Funders: Japan Society for the Promotion of Science, Core Research for Evolutional Science and Technology

Awards: G2492563920, Mathematical Foundations of Brain-Inspired Computing Based on Diversity, G6718509927