Event cameras are bio-inspired vision sensors that encode visual information with high dynamic range, high temporal resolution, and low latency. Current state-of-the-art event stream processing methods rely on end-to-end deep learning techniques. However, these models are heavily dependent on data structures, limiting their stability and generalization capabilities across tasks, thereby hindering their deployment in real-world scenarios. To address this issue, we propose a chaotic dynamics event signal processing framework inspired by the dorsal visual pathway of the brain. Specifically, we utilize Continuous-coupled Neural Network (CCNN) to encode the event stream. CCNN encodes polarity-invariant event sequences as periodic signals and polarity-changing event sequences as chaotic signals. We then use continuous wavelet transforms to analyze the dynamical states of CCNN neurons and establish the high-order mappings of the event stream. The effectiveness of our method is validated through integration with conventional classification networks, achieving state-of-the-art classification accuracy on the N-Caltech101 and N-CARS datasets, with results of 84.3% and 99.9%, respectively. Our method improves the accuracy of event camera-based object classification while significantly enhancing the generalization and stability of event representation.

ABSTRACT Bearings are a critical part of various industrial equipment. Existing bearing fault detection methods face challenges such as complicated data preprocessing, difficulty in analysing time series data, and inability to learn multi‐dimensional features, resulting in insufficient accuracy. To address these issues, this study proposes a novel bearing fault diagnosis model called multi‐channel deep pulse‐coupled net (MC‐DPCN) inspired by the mechanisms of image processing in the primary visual cortex of the brain. Initially, the data are transformed into greyscale spectrograms, allowing the model to handle time series data effectively. The method introduces a convolutional coupling mechanism between multiple channels, enabling the framework can learn the features on all channels well. This study conducted experiments using the bearing fault dataset from Case Western Reserve University. On this dataset, a 6‐channel (adjustable to specific tasks) MC‐DPCN was utilized to analyse one normal class and three fault classes. Compared to state‐of‐the‐art bearing fault diagnosis methods, our model demonstrates one of the highest diagnostic accuracies. This method achieved an accuracy of 99.96% in normal vs. fault discrimination and 99.89% in fault type diagnosis (average result of ten‐fold cross‐validation).

Deep generative models, particularly diffusion probabilistic models, have recently shown promise in medical ultrasound image segmentation due to their powerful denoising and detail restoration capabilities. However, most existing generative models focus primarily on image enhancement, with limited consideration for segmentation-specific challenges. To address this, we propose CTrans-SegDiff, a novel segmentation framework that integrates a denoising diffusion probabilistic model with a Transformer-enhanced dynamic conditioning mechanism. Specifically, we design a dual-channel dynamic conditioning module to jointly capture lesion-specific semantics and global contextual dependencies, and a Gaussian Distribution Fusion Module (GDFM) to harmonize the fusion of conditioning features with diffusion-encoded representations. Extensive experiments on two ultrasound datasets demonstrate that our method effectively suppresses noise, enhances structural clarity, and achieves superior segmentation performance compared to existing approaches.

Dunhuang mural inpainting aims to fill in the missing regions of damaged murals with realistic content. Denoising probabilistic diffusion model (DDPM) has made great strides in semantic generation and shown promising results in image inpainting. However, three potential challenges prevent existing diffusion-based methods from restoring the Dunhuang murals: 1) effective visual information cannot be accurately extracted due to historical reasons, with most of the pixels being faded; 2) there are semantic discrepancy between damaged and visible regions in the inpainting results; and 3) the original structure and style of the damaged regions cannot be adequately restored. To this end, we propose a novel adversarial diffusion model for mural inpainting, which consists of: 1) a mural enhancement module named pixel-enhanced fire-controlled pulse-coupled neural network (PEFCPCNN), designed to enhance faded pixels to accurately extract the visual features of the mural; 2) a novel adversarial diffusion framework that optimizes the sampling prediction of mural over time steps; and 3) line drawing and different loss functions to constrain the reconstructed content to approximate the structure and style of original mural. The variational transform layer (VTL) and multi-scale contextual feature aggregation (MCFA) module are proposed to reconstruct content that is structurally coherent and texturally reasonable. Experiments on the Dunhuang mural dataset demonstrate that the proposed method outperforms state-of-the-art methods in terms of both the semantic reasonableness and global semantic consistency of inpainting content.

Exploring and establishing artificial neural networks with electrophysiological characteristics and high computational efficiency is a popular topic that has been explored for many years in the fields of pattern recognition and computer vision. Inspired by the working mechanism of the primary visual cortex, pulse-coupled neural networks (PCNNs) can exhibit the characteristics of synchronous oscillation, refractory period, and exponential decay. These characteristics empower the PCNN model to group pixels with similar spatiality and gray values and to process digital images without training. However, electrophysiological evidence shows that the neurons exhibit highly complex nonlinear dynamics when stimulated by external periodic signals. This chaos phenomenon, also known as the ‘butterfly effect,” cannot be explained by all PCNN models. In this work, we analyze the main obstacle preventing PCNN models from imitating a real primary visual cortex. We consider neuronal excitation as a stochastic process. We then propose a novel neural network of the primary visual cortex, called a continuous-coupled neural network (CCNN). Theoretical analysis indicates that the dynamic behavior of the CCNN is distinct from the PCNN. Numerical results show that the CCNN model exhibits periodic behavior under a DC stimulus, and exhibits chaotic behavior under an AC stimulus, which is consistent with the testing results of primary visual cortex neurons. Furthermore, the image and video processing mechanisms of the CCNN model are analyzed. For image processing tasks, this model encodes the pixel intensity as the frequency of output signals so that it can group pixels with similar gray values. This image processing method can reduce the local gray level difference of the image, and compensate for small local discontinuities in the image. For video processing tasks, the CCNN encodes changing pixels as non-periodic chaotic signals, and it encodes static pixels as periodic signals. It thusachieves the purpose of moving target object recognition by distinguishing the dynamic states corresponding to different neuron clusters in the video. Experimental results on image segmentation indicate that the CCNN model has better performance than the state-of-the-art of visual cortex neural network models.