Laser cleaning has received extensive attention due to its high efficiency, non-pollution and easy automation. However, how to improve the cleaning quality has become the focus of current research. In this paper, we used a pulsed laser for cleaning experiments on Q235B carbon steel to investigate the effects of different process parameters on the surface cleaning quality. On this basis, a new cleaning method was innovatively proposed to improve the oxide removal efficiency, microstructure, and mechanical properties of cleaned samples. The results showed that pulsed laser cleaning of Q235B carbon steel was the most effective at a laser linewidth of 50 mm, pulsed frequency of 500 kHz, and cleaning speed of 15 mm/s. A great deal of craters formed on the surface of cleaned samples due to the thermal shock of the pulsed laser. Compared with other laser cleaning methods, integrated laser cleaning had an obvious effect in raising the oxide removal efficiency and reducing the surface roughness. The ridge structures on the sample surface also could be successfully eliminated, subsequently achieving smooth structures. Fine-crystalline structures were formed near the surface of tested samples, which significantly decreased the crystal orientation and increased the number of small angle grain boundaries and the GND density. The improvement in hardness was mainly on account of grain refinement in the integrated laser cleaning samples. In addition, a physical model was proposed to illustrate the oxide removal mechanism on integrated pulsed-continuous laser cleaning samples. This research can offer new theoretical and technical support for solving the long-standing problems of efficiency and quality in laser cleaning, thus significantly broadening the application of laser technology in manufacturing fields.

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.

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.