Accurate neuron stitching across large-scale electron microscopy volumes is crucial for reconstructing complete neural circuits. We propose TransStitch, a distributed Transformer-based framework that addresses these challenges by integrating multimodal feature fusion with topology-aware self- and cross-attention mechanisms to model global structural dependencies across adjacent electron microscopy blocks. To refine uncertain predictions, a dynamic 1-nearest-neighbor strategy progressively converts the probabilistic connectivity matrix into discrete associations without relying on a fixed threshold. Additionally, a mapping-based lazy relabeling strategy reduces merging complexity from voxel to fragment level, significantly improving computational efficiency and scalability. Extensive experiments on public electron microscopy datasets (SNEMI3D, CREMI-C, FIB25) with ground truth demonstrate superior stitching accuracy of proposed method compared to baseline, while qualitative evaluation on a large-scale, self-collected zebrafish whole-brain dataset confirms coherent 3D reconstruction across tens of thousands of sections. These results highlight TransStitch as an accurate and scalable solution for large-scale connectomics reconstruction.

Face Recognition is the process of identifying people by extracting their facial features, and it is widely utilized in several applications, including authentication, healthcare, and security. The traditional approaches faced troubles in providing better accuracy and computational efficiency due to the lack of identifying the facial patterns. Therefore, a Root Cause Analysis (RCA) is essential in a face recognition system to prevent failures in recognizing faces. Hence, the Channel and Spatial Attention-based Explainable Convolutional Network (CSA-ECNet) model is proposed to enhance the face recognition results through detecting the defects and analyzing the root causes. The incorporation of an explainable technique helps to provide insights to the CSA-ECNet model in detecting the root causes, thereby increasing the performance of the CSA-ECNet model in recognizing faces without any failures. The incorporation of the Channel and Spatial Attention (CSA) facilitates increasing the accuracy by enabling the CSA-ECNet model to selectively concentrate on the vital spatial regions and feature channels, which strengthens the model’s ability to handle various aspects, including poor lighting. Experimental results demonstrate the exceptional performance of the CSA-ECNet model, reporting the high sensitivity of 97.79%, specificity of 98.44%, and accuracy of 98.11% for 90% of training data on Face recognition dataset

We present a weighted competitive nonnegative representation (WCNR) method. Specifically, WCNR introduces a competitive term, which leverages the competitive ability of training data from distinct classes to strengthen the connection between the representation and classification phases. In addition, WCNR incorporates a weight constraint. The weight constraint of each class imposed on the representation coefficients endows similar classes with more representation contributions, which boosts the discriminative power of the representation coefficients. To assess the classification performance of WCNR, extensive experiments are carried out on benchmarking datasets. Experimental results confirm that WCNR exceeds the state-of-the-art representation-based classification methods (RBCM) and also surpasses several deep learning approaches. The MATLAB code of WCNR is available at https://github.com/yinhefeng/WCNR.

Hyperspectral image (HSI) classification remains challenging due to the high dimensionality of spectral data, the strong coupling between spatial and spectral information, and the difficulty of learning robust representations under limited annotated samples. To address this, we propose 3D W-Net, a novel deep learning framework that integrates 3D convolution into the U-Net architecture and introduces a parallel–serial multi-scale feature learning strategy tailored for HSIs. The encoder incorporates a parallel spectraldimension multi-scale feature processing module, which employs three 3D convolution kernels with different spectral receptive fields to capture diverse spectral-scale features. An adjacent-scale selective fusion strategy is then applied to enrich spectral representations while reducing redundancy. The decoder features a serial spatial-dimension multiscale feature restoration module that progressively merges high-level semantic and lowlevel spatial details, preserving spatial–spectral correlations and mitigating information loss typically caused by flattening operations. This design forms a distinctive “W”-shaped feature propagation path that enhances multi-scale feature interaction. Extensive experiments on five public datasets(Botswana, Pavia University, Chikusei, Houston 2013, and WHU-Hi-HongHu) demonstrate that 3D W-Net achieves superior performance compared to six state-of-the-art methods, attaining overall accuracies of 99.6%, 99.1%, 100%, 99.3%, and 99.5%, respectively. The results highlight the effectiveness of the proposed parallel–serial multi-scale strategy in improving classification accuracy and generalization capability for complex HSI scenarios.

Recognizing historical documents is vital in protecting cultural heritage by facilitating access, search, and analysis of important archival materials. Nonetheless, current techniques face difficulties due to factors like poor image quality, diverse handwriting styles, erased or missing words, damaged documents, and intricate page designs. These challenges affect precise text extraction and reduce the overall efficiency of automated recognition systems. In this work, a Pine Makeup Optimization enabled Convolutional Generative Transformer Network (PMO_CGTN) is proposed for missing character recognition in historical documents. Firstly, an input historical document image is applied for image enhancement using the Multi-scale Gray World Algorithm. Then, segmentation of each text line and segmentation of each word within the lines is performed using the Semantic Text Segmentation Network (STSN). Finally, missing character recognition and filling of missed characters are accomplished using CGTN. Here, a Convolutional Neural Network (CNN) model is modified by incorporating a Generative Pre-Trained Transformer (GPT) layer to form CGTN, which is trained using a Pine Makeup Optimization (PMO), and is a merging of Pine Cone Optimization Algorithm (PCOA) and Makeup Artist Optimization Algorithm (MAOA). Lastly, an Optical Character Recognition (OCR) document is obtained as the output.

Image denoising is a very important topic in many real-life applications. In most existing works, the noise level is assumed to be constant over the whole image. Nevertheless, this can be violated in practice. In this paper, we improve the bivariate wavelet shrinkage (BivShrink) to deal with spatially varying noise. Instead of a constant noise level, we estimate the noise levels locally within a small neighborhood so that we can deal with spatially varying noise more effectively. Our new method is very fast for image denoising, and it can deal with spatially varying noise levels, which can happen in real-life images. Experiments demonstrate the success of our new method for reducing both spatially varying noise and uniform noise from noisy images.

Let [Formula: see text] be a homogeneous function of degree zero on the unit sphere [Formula: see text] satisfying the zero-mean condition and belonging to [Formula: see text] for some [Formula: see text]. In this paper, we establish the boundedness of the singular integral operator [Formula: see text] with kernel [Formula: see text] on Bourgain–Morrey space [Formula: see text], and we also consider its related maximal operator [Formula: see text]. Suppose [Formula: see text], the commutator [Formula: see text] generated by the function [Formula: see text] and the operator [Formula: see text] is investigated as well. We further prove that [Formula: see text] is the sufficient condition for the boundedness of the commutator [Formula: see text] on Bourgain–Morrey space [Formula: see text].

Traditional industrial component inspection methods rely primarily on creating templates on the basis of component shape and color features, resulting in high rates of missed defects. To reduce this rate, we propose a defect detection algorithm based on Conditional Generative Adversarial Networks (GANs) for high-precision detection and identification of random two-dimensional surface defects in industrial defective products. First, a dataset of identical socket panels was constructed through data augmentation. Next, a conditional GAN (pix2pix) was employed as the backbone architecture for the detection model. This generated repaired images of the defective panels, which were subtracted from the original images to produce difference maps. Sobel edge features were subsequently extracted from both the input image and its corresponding repaired image, and the edge features from both sources were differentially processed. By weighting and fusing the edge feature differences with the difference map, the detection and localization of panel defects were achieved. The experimental results validate that the proposed algorithm can efficiently detect and locate defects precisely on socket panels even in the presence of reflective interference while maintaining high accuracy and reliability.

Stereo image super-resolution aims to reconstruct high-resolution images from lowresolution stereo pairs by leveraging complementary information between binocular views, which is essential for a wide range of computer vision applications. To address the limitations in cross-view feature matching of existing methods, particularly in weaktextured regions, we propose the Adaptive Multi-Scale Cross-Attention Stereo Image Super-Resolution Network (AMCASSR). The network comprises two principal modules: the Adaptive Multi-Scale Cross-Attention (AMSCA) module, which enhances reconstruction performance in weak-textured regions by expanding the receptive field and adaptively fusing multi-scale features; and the Multi-Scale Cross-Attention Feature Block (MSCFB), which facilitates the integration of intra-view feature learning and cross-view interaction. Additionally, the network optimizes cross-view interaction while maintaining computational efficiency. Experimental evaluations on the KITTI2012, KITTI2015, Middlebury, and Flickr1024 datasets show that AMCASSR achieves significant improvements in both PSNR and SSIM metrics over current state-of-the-art methods, especially in weak-textured regions. Validation on downstream tasks further supports its practical applicability in feature and stereo matching.

Uncertainty-aware deep learning methods have shown promising results in medical image segmentation, maintaining accuracy while quantifying prediction confidence. However, existing evidence-theory-based approaches fail to exploit multi-scale uncertainty and overlook evidence quality, leading to belief conflicts and evidence scarcity. They also rely on single-channel attention, resulting in biased and unreliable channel scores. Accordingly, this paper proposes a novel uncertainty-aware network with opinion conjunction and evidence-driven channel attention (UACNet) for medical image segmentation. Initially, a certainty-aware mechanism filters ambiguous features during feature extraction. Secondly, an opinion conjunction operator captures multi-scale uncertainty, converted to a joint certainty mask for skip connections to improve boundary accuracy and prevent risk oversight. Furthermore, a dual-path evidence-driven channel attention (DECA) module is designed to dynamically fuse dual-path attention scores with uncertainty awareness, focusing on critical channels while enabling self-assessment. Finally, three evidence-based losses mitigate belief conflicts and evidence insufficiency problems. Extensive experiments demonstrate the superiority of UACNet over state-of-the-art methods.