Fringe projection profilometry (FPP) is prone to phase unwrapping error (PUE) due to phase noise and measurement conditions. Most of the existing PUE-correction methods detect and correct PUE on a pixel-by-pixel or partitioned block basis and do not make full use of the correlation of all information in the unwrapped phase map. In this study, a new method for detecting and correcting PUE is proposed. First, according to the low rank of the unwrapped phase map, multiple linear regression analysis is used to obtain the regression plane of the unwrapped phase, and thick PUE positions are marked on the basis of the tolerance set according to the regression plane. Then, an improved median filter is used to mark random PUE positions and finally correct marked PUE. Experimental results show that the proposed method is effective and robust. In addition, this method is progressive in the treatment of highly abrupt or discontinuous regions.

In this work, we propose a 3D occlusion facial recognition network based on a multi-feature combination threshold (MFCT-3DOFRNet). First, we design and extract the depth information of the 3D face point cloud, the elevation, and the azimuth angle of the normal vector as new 3D facially distinctive features, so as to improve the differentiation between 3D faces. Next, we propose a multi-feature combinatorial threshold that will be embedded at the input of the backbone network to implement the removal of occlusion features in each channel image. To enhance the feature extraction capability of the neural network for missing faces, we also introduce a missing face data generation method that enhances the training samples of the network. Finally, we use a Focal-ArcFace loss function to increase the inter-class decision boundaries and improve network performance during the training process. The experimental results show that the method has excellent recognition performance for unoccluded faces and also effectively improves the performance of 3D occlusion face recognition. The average Top-1 recognition rate of the proposed MFCT-3DOFRNet for the Bosphorus database is 99.52%, including 98.94% for occluded faces and 100% for unoccluded faces. For the UMB-DB dataset, the average Top-1 recognition rate is 95.08%, including 93.41% for occluded faces and 100% for unoccluded faces. These 3D face recognition experiments show that the proposed method essentially meets the requirements of high accuracy and good robustness.

In offline signature verification, extracting effective features and enhancing identification accuracy remain critical challenges. Traditional feature extraction modules struggle to capture comprehensive, detailed characteristics from signatures alone and often suffer from overfitting issues. This paper introduces ResT, a novel approach that integrates the Residual Network (ResNet) and Transformer architectures for multi-scale feature extraction. The proposed method comprises two components: ResNet blocks and Transformer blocks, designed to extract local and global signature characteristics, respectively. Within the ResNet blocks, we integrate two modules—Spatial-to-Depth Convolution (SPD-Conv) and Spatial and Channel Reconstruction Convolution (SCConv)—to emphasize stroke-level features, thereby improving local feature extraction. For the Transformer blocks, Vision Transformer (ViT) is employed to analyze the signature’s overall shape and stroke trends, capturing global features. To evaluate performance, we implement a writer-independent (WI) verification system and conduct extensive experiments on four public datasets: GPDS, CEDAR, BHSig-Bengali, and BHSig-Hindi. Results demonstrate that the proposed ResT model effectively distinguishes genuine from forged signatures and achieves competitive performance compared to existing methods.

With the rapid advancement of aerospace technology, the maneuverability of spacecraft has increasingly improved, creating a pressing demand for star sensors with a high attitude update rate and high precision. Star identification, as the most complex and time-consuming algorithm of star sensors, faces stringent requirements for enhanced identification speed and an enhanced identification rate. Furthermore, as the space environment is becoming more complex, the need for star sensors with heightened detection sensitivity is growing to facilitate real-time and accurate alerts for various non-cooperative targets, which has led to a sharp increase in the number of high-magnitude navigation stars in the star catalog, significantly impeding the speed and rate of star identification. Traditional methods are no longer adequate to meet the current demand for star sensors with high identification speed and a high identification rate. Addressing these challenges, a voting-based star identification algorithm using a partitioned star catalog is proposed. Initially, a uniform partitioning method for the star catalog is introduced. Building on this, a navigation feature library using partitioned catalog neighborhoods as a basic unit is constructed. During star identification, a method based on a voting decision is employed for feature matching in the basic unit. Compared to conventional methods, the proposed algorithm significantly simplifies the navigation feature library and narrows the retrieval region during star identification, markedly enhancing identification speed while effectively reducing the probability of redundant and false matching. The performance of the proposed algorithm is validated through a simulation experiment and nighttime star observation experiment. Experimental results indicate an average identification rate of 99.760% and an average identification time of 8.861 milliseconds, exhibiting high robustness against position errors, magnitude errors, and false stars. The proposed algorithm presents a clear advantage over other common star identification methods, meeting the current requirement for star sensors with high star identification speed and a high identification rate.

In the field of forensic document examination, accurately determining the chronological sequence of intersecting lines between seal ink and handwriting is a crucial technical step for verifying document authenticity, identifying contract tampering, and detecting forged signatures. This technique analyzes the physical superimposition relationship formed by the deposition of the two media on the paper substrate to provide objective scientific evidence for judicial practice. Although traditional methods such as microscopic imaging and mass spectrometry analysis have achieved some progress, they still suffer from common limitations including high equipment costs, complex operation, and potential damage to samples. This study proposes and validates an innovative non-destructive determination method that integrates structured light 3D reconstruction technology with deep learning algorithms. The research captures the microscopic 3D morphological features of the ink intersection area using a high-precision structured light scanning system and effectively eliminates noise interference caused by paper substrate undulation through Gaussian flattening technology. Subsequently, a multimodal fusion strategy combines 2D texture images with 3D depth information to construct a dataset rich in features. On this basis, a deep learning model based on an improved Residual Neural Network (ResNet) is designed, incorporating the ELU activation function and an EMA mechanism to enhance the model’s feature extraction capability and convergence stability. Experimental results demonstrate that the proposed method achieves a recognition accuracy of 94.39% on the test set, fully validating its effectiveness and application potential in the non-destructive determination of ink stroke sequencing.

Accurate 3D detection of surface defects is essential for quality control in the manufacturing of ceramic package substrates. However, this task faces two major challenges: the reliable representation of subtle local surface geometric anomalies and the accurate localization and reliable candidate ranking of small defects with diverse morphologies. To address these challenges, we propose SurfDet3D, which preserves within-column relative geometry across multiple stages of a sparse backbone and introduces bi-scale surface statistics to enhance subtle geometric features. It further combines whole-box geometric constraints with localization quality estimation to improve bounding-box regression and candidate ranking. Experiments on the public CPS3D-Det benchmark show that SurfDet3D achieves AP_3D,R11, AP_BEV,R11, AP_3D,R40, and AP_BEV,R40 values of 48.13%, 46.45%, 46.38%, and 45.42%, respectively. These results demonstrate the effectiveness of SurfDet3D in representing subtle local surface geometric anomalies and improving the localization and candidate ranking of small defects with diverse morphologies. Ablation studies further verify the contribution of each proposed component.