We present a Wilson–Cowan reservoir computer (WC–RC) that treats a retinotopic excitatory–inhibitory neural field as a structured reservoir. Travelling waves and bounded oscillations provide an interpretable spatiotemporal basis, while a two-stage sampler (40 sites $$\times$$ 200 steps) exports 8000 features per input—a $$>99\%$$ reduction with unchanged integration cost. On MNIST and Fashion-MNIST, recurrent readouts trained on these features achieve strong performance within this fixed export budget: Att-LSTM reaches $$85.4\%/79.0\%$$ , while GRU and vanilla LSTM yield similar accuracies (all with tight Wilson 95% confidence intervals). A simple MLP readout performs markedly worse ( $$45.6\%/54.2\%$$ ), whereas a compact ridge classifier still attains non-trivial performance ( $$71.2\%/72.7\%$$ ), indicating that the exported WC–RC representation is partially linearly decodable but benefits further from temporal modelling. Selective suppression of lateral couplings ( $$\lambda \in \{0,0.25,0.5,0.75,1\}$$ ) shows that reinstating wave dynamics improves recurrent models while degrading the MLP, supporting a functional role for propagating dynamics. A complementary neighbour-coupling ablation, implemented via a diffusion-like scaling factor $$\psi$$ , shows that increasing lateral spread beyond the baseline regime reduces late-time spatial variance and degrades recurrent-readout accuracy, indicating that useful computation depends on balanced wave dynamics rather than maximal smoothing. At matched exported-feature and readout budgets, ESN baselines underperform ( $$\approx 64\%/\approx 73\%$$ ), whereas compact CNNs achieve higher accuracy but with larger parameter and MAC budgets and without wave interpretability. Supplementary analyses confirm numerical fidelity and relate performance gains to propagation coherence. We outline a fixed-point streaming-convolution mapping for FPGA/ASIC deployment, positioning WC–RC as an interpretable, energy-aware reservoir for neuromorphic vision.

Neuromorphic computing represents a transformative approach in artificial vision, drawing inspiration from the human brain's visual processing capabilities. This review explores the latest advancements in neuromorphic vision systems, with a particular focus on biologically inspired, wave-based dynamics. We examine how cortical travelling waves and neural oscillations, key to synchronising activity in the brain’s visual cortex, provide a blueprint for developing computational models that mimic biological efficiency and adaptability. The review delves into the integration of wave-based computation through frameworks such as Physics-Informed Neural Networks (PINNs), reservoir computing, and spiking neural networks (SNNs), highlighting their potential to revolutionise real-time visual processing. From memristive devices, photonic components, to optoelectronic polymers, are discussed for their roles in facilitating in-sensor processing and reducing energy consumption. These advances are positioned within the broader context of computational neuroscience and machine intelligence, where the goal is to bridge the gap between biological vision and artificial systems. We conclude by identifying the current challenges and future directions, particularly the need for scalable training algorithms, energy-efficient hardware, and improved theoretical models. This review demonstrates how a synthesis of wave-based dynamics and neuromorphic computing frameworks can pave the way for the next generation of bio-inspired artificial vision systems.