Ship imaging has an impact on the visual judgment of the steersman and influences ship navigation safety. Traditional image enhancement methods struggle under adverse conditions and fail to account for the physiological mechanisms of human visual perception. Therefore, a novel method was proposed to enhance ship imaging by combining a visual neural signal encoding mechanism (accomplished by multi-scale spiking neural networks) with a multi-scale frequency-domain stochastic resonance model. First, the noisy image is encoded by mapping the neuron pulse count per unit time, and then the encoded signal is directionally filtered by constructing a spatial dot-matrix dual-view perception receptive field model to achieve preliminary low-level noise reduction. Second, a stochastic resonance system is constructed and applied in series to enhance the decomposed multi-scale wavelet coefficients. Finally, considering the brightness characteristics of the visual system, the processed wavelet coefficients of each scale are inversely transformed and reconstructed. The reconstructed image is then fused with the image obtained by directional filtering of the spatial dot-matrix dual-view pathway receptive field model to produce the final enhanced image. According to the experimental results, compared with the original noisy image, the peak signal-to-noise ratio (PSNR) and visual information fidelity (VIF) improve by 27% and 30%, respectively. These findings indicate that the proposed method can effectively enhance ship images in a manner more consistent with the physiological characteristics of human visual imaging and signal processing.

Extracting multi-level information in colony images facilitates analysis and identification tasks of biomedical informatics. In order to achieve multi-level segmentation in colony images with multiple contrast levels, a closed-loop neural network model based on the stochastic resonance (SR) mechanism of neurons is proposed. First, this paper realizes the detection of transition pulses in sinusoidal, non-periodic bipolar binary signals, and one-dimensional strong and weak transition signals with multiple amplitude values. Then, through enhancement processing for the detection by the SR-based closed-loop neural network model, combined with the coati optimization algorithm, multi-target detection is achieved. Eventually, it can be applied to the segmentation of multi-level grayscale signals in two-dimensional images. Experimental results show that the proposed method can simultaneously detect strong and weak contrast edges, enrich image details, highlight image contours, and enhance the hierarchical sense of image edges, while exhibiting strong robustness against external noise. As a result, the proposed method provides a novel research framework for multi-contrast grayscale image segmentation under strong noise background.