Finger vein recognition has gained significant attention for its importance in enhancing security, safeguarding privacy, and ensuring reliable liveness detection. As a foundation of vein recognition systems, vein detection faces challenges, including low feature extraction efficiency, limited robustness, and a heavy reliance on real-world data. Additionally, environmental variability and advancements in spoofing technologies further exacerbate data privacy and security concerns. To address these challenges, this paper proposes MixCFormer, a hybrid CNN–transformer architecture that incorporates Mixup data augmentation to improve the accuracy of finger vein liveness detection and reduce dependency on large-scale real datasets. First, the MixCFormer model applies baseline drift elimination, morphological filtering, and Butterworth filtering techniques to minimize the impact of background noise and illumination variations, thereby enhancing the clarity and recognizability of vein features. Next, finger vein video data are transformed into feature sequences, optimizing feature extraction and matching efficiency, effectively capturing dynamic time-series information and improving discrimination between live and forged samples. Furthermore, Mixup data augmentation is used to expand sample diversity and decrease dependency on extensive real datasets, thereby enhancing the model’s ability to recognize forged samples across diverse attack scenarios. Finally, the CNN and transformer architecture leverages both local and global feature extraction capabilities to capture vein feature correlations and dependencies. Residual connections improve feature propagation, enhancing the stability of feature representations in liveness detection. Rigorous experimental evaluations demonstrate that MixCFormer achieves a detection accuracy of 99.51% on finger vein datasets, significantly outperforming existing methods.

In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network’s detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU loss at the output of YOLOv5 is replaced with WiseIoU loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system using PyQt5 to enhance human–computer interaction. Experimental results on the INRIA public dataset showed that our algorithm achieved a detection accuracy of 98.4%, representing a 10.1% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow.

In traffic scene, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network's detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU Loss at the output of YOLOv5 is replaced with WiseIoU Loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system by using PyQt5 to enhance human-computer interaction. Experimental results on the INRIA public dataset show that our algorithm achieves a detection accuracy of 95.6%, representing a 8.7% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow.

Finger vein recognition, like control systems, requires harmonizing local and global dynamics for optimal performance. To address limitations in existing methods, we propose the wavelet‐transformer algorithm, combining CNNs for local feature extraction, vision transformers (ViT) for global dependency modeling, and discrete wavelet transforms (DWT) for time‐frequency analysis. This modular design mirrors control theory principles, ensuring stability and adaptability. Experiments on FV210 and FV618 datasets show the algorithm's superior performance, achieving recognition accuracies of 99.53% and 97.62%, with equal error rates of 0.35% and 0.71%, highlighting its robustness for intelligent recognition and control applications.

Finger vein recognition has gained significant attention for its importance in enhancing security, safeguarding privacy, and ensuring reliable liveness detection. As a foundation of vein recognition systems, vein detection faces challenges including low feature extraction efficiency, limited robustness, and a heavy reliance on real-world data. Additionally, environmental variability and advancements in spoofing technologies further exacerbate data privacy and security concerns. To address these challenges, this paper proposes MixCFormer, a hybrid CNN-Transformer architecture that incorporates Mixup data augmentation to improve the accuracy of finger vein liveness detection and reduce dependency on large-scale real datasets. First, The MixCFormer model applies baseline drift elimination, morphological filtering, and Butterworth filtering techniques to minimize the impact of background noise and illumination variations, thereby enhancing the clarity and recognizability of vein features. Next, finger vein video data is transformed into feature sequences, optimizing feature extraction and matching efficiency, effectively capturing dynamic time-series information and improving discrimination between live and forged samples. Furthermore, Mixup data augmentation is used to expand sample diversity and decrease dependency on extensive real datasets, thereby enhancing the model’s ability to recognize forged samples across diverse attack scenarios. Finally, the CNN and Transformer architecture leverages both local and global feature extraction capabilities to capture vein feature correlations and dependencies. Residual connections improve feature propagation, enhancing the stability of feature representations in liveness detection. Rigorous experimental evaluations demonstrate that MixCFormer achieves a detection accuracy of 99.51% on finger vein datasets, significantly outperforming existing methods.

Synthetic aperture radar (SAR) ship detection in complex maritime environments remains challenging due to severe background clutter, large-scale variations, and the frequent omission of small and densely distributed vessels. To address these challenges, this paper proposes an attention-guided multi-scale feature learning framework for robust SAR ship detection. The proposed approach focuses on enhancing scale-aware feature representation, adaptive feature refinement, and cross-level feature reconstruction within a unified learning paradigm. Specifically, a multi-scale contextual modeling mechanism is introduced to capture scale-aware dependencies and improve target–background separability in cluttered scenes. An adaptive feature refinement strategy is further developed to enhance the representation of small and weak targets by strengthening shallow feature responses. In addition, an efficient feature reconstruction scheme is designed to improve cross-level feature integration during decoding, thereby enhancing localization accuracy under speckle-contaminated SAR imagery. Extensive experiments on public datasets demonstrate the effectiveness of the proposed method. On the HRSID dataset, the method achieves 94.30% mAP@0.5 and 71.53% mAP@0.5:0.95, showing clear improvements over representative detectors. On the SSDD dataset, it reaches 99.50% mAP@0.5, indicating strong generalization under different imaging conditions. Meanwhile, the proposed framework maintains high computational efficiency with over 100 FPS and low model complexity. Ablation studies further validate the effectiveness of each component and their complementary contributions. The proposed framework provides a robust and efficient solution for SAR-based maritime monitoring and can be extended to other small-object detection tasks in complex environments.