Search

Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) the similarity between defect and nondefect texture is very high, which eventually leads to recognition or classification errors and 2) the size of defects is tiny, which are much more difficult to be detected than larger ones. To address such problems, this article proposes an adaptive image segmentation network (AIS-Net) for pixelwise segmentation of surface defects. It consists of three main parts: multishuffle-block dilated convolution (MSDC), dual attention context guidance (DACG), and adaptive category prediction (ACP) modules, where MSDC is designed to merge the multiscale defect features for avoiding the loss of tiny defect feature caused by model depth, DACG is designed to capture more contextual information from the defect feature map for locating defect regions and obtaining clear segmentation boundaries, and ACP is used to make classification and regression for predicting defect categories. Experimental results show that the proposed AIS-Net is superior to the state-of-the-art approaches on four actual surface defect datasets (NEU-DET: 98.38% ± 0.03%, DAGM: 99.25% ± 0.02%, Magnetic-tile: 98.73% ± 0.13%, and MVTec: 99.72% ± 0.02%).

The sparse collaborative tracking (SCT) method has been developed for object tracking recently, and it is very efficient and robust to various occlusions. In SCT, sparse representation (SR) plays an essential role because it needs to perform several manipulations of sparse matrix representation (SMR) or nonnegative SMR in each iteration. So one of the most challenging problems in SCT is how to efficiently solve the SMR. However, existing SR algorithms are solely developed for the vectors-based SR. They partition SMR into a set of vector-based SR problems and solve them in the level-2 BLAS (Basic Linear Algebra Subprograms) manner, i.e., matrix-vector operations, which is computationally much less efficient than the direct level-3 BLAS (direct matrix-matrix operations). To solve this problem, by extending the standard SR algorithm from the vector version to the matrix for SMR and nonnegative SMR, BLAS3-based Sparse Learning (BLAS3-SpaL) is first developed, and then the corresponding BLAS3-SpaL-based SCT method (FastSCT-BLAS3SpaL) is further developed for fast robust-object-tracking in this paper. The experiments verified that it achieves robust object tracking by reducing accumulation errors and speeds up tracking with more than double speed.

Accurate segmentation of 3D dental models derived from intra-oral scanners (IOS) is one of the key steps in many digital dental applications such as orthodontics and implants. However, it is difficult to accurately segment individual teeth and gums in 3D dental models due to the following problems: 1) the shape and appearance of adjacent teeth are very similar, which is easy to be misidentified; 2) the boundary between teeth and gums is often indistinct, especially in orthodontic patients with abnormalities such as missing and crowded teeth. To solve such problems, a Dual-Branch Geometric Attention Network (DBGANet) for 3D tooth segmentation is proposed, which can capture tooth geometric structure and detailed boundary information from multi-view geometric features encoded by 3D coordinates and normal vectors. The framework contains two branches, i.e., C-branch and N-branch. First, centroid-guided separable attention is designed in the C-branch to learn global context information by modeling the spatial dependencies of tooth point clouds, which can capture the overall geometric structure of teeth to better distinguish adjacent teeth with similar appearance. Then, Gaussian neighbor attention is designed in the N-branch to encode normal vectors to highlight detailed differences between geometric features at different points, which helps to refine the boundaries of teeth and gingiva for more accurate and smooth tooth segmentation. Extensive experiments on the real-patient datasets of 3D dental models demonstrate that the proposed DBGANet significantly outperforms state-of-the-art methods.

The fetal electrocardiogram (FECG) is of great significance for fetal monitoring during peripartum and intrapartum. However, it is difficult to extract FECG signals from the abdominal signal (ADS) due to the following issues: 1) FECG signals are always corrupted by noise and 2) the FECG signal is often masked by the high-amplitude maternal electrocardiogram (MECG). To address such problems, a correlation-aware attention CycleGAN (CAA-CycleGAN) is proposed for FECG extraction, where the autocorrelation attention encoder (ACAE) module, which can capture waveform details of FECG signals by modeling its autocorrelation in the current convolution layer, is first devised to extract FECG signals corrupted by noise; then, the cross-correlation attention residual (CCAR) module, which can enhance the FECG components by learning its cross-correlation between adjacent convolutional layers, is developed to discriminate FECG signals from MECG signals; finally, the dual-cross-correlation attention decoder (DCCAD) module, which can extract waveform features of FECG signals by exploring its dual-cross-correlation in different-level convolutional layers, is designed to extract FECG signals masked by MECG signals. Experiments demonstrate that the proposed CAA-CycleGAN can achieve excellent performance with the mean square error (MSE) of 0.082, 0.024, and 0.032 on the FECGSYNDB, ADFECGDB, and B2 LABOUR datasets, respectively, which is more accurate than the state-of-the-art methods. The project is available at https://github.com/langdecc511/ CAA-CycleGAN.