Search

Abstract Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET .

Abstract Objectives This study aims to enhance supervised human activity recognition based on spatiotemporal graph convolutional neural networks by addressing two key challenges: (1) extracting local spatial feature information from implicit joint connections that is unobtainable through standard graph convolutions on natural joint connections alone. (2) Capturing long-range temporal dependencies that extend beyond the limited temporal receptive fields of conventional temporal convolutions. Methods To achieve these objectives, we propose three novel modules integrated into the spatiotemporal graph convolutional framework: (1) a connectivity feature extraction module that employs attention to model implicit joint connections and extract their local spatial features. (2) A long-range frame difference feature extraction module that captures extensive temporal context by considering larger frame intervals. (3) A coordinate transformation module that enhances spatial representation by fusing Cartesian and spherical coordinate systems. Findings Evaluation across multiple datasets demonstrates that the proposed method achieves significant improvements over baseline networks, with the highest accuracy gains of 2.76 $$\%$$ % on the NTU-RGB+D 60 dataset (Cross-subject), 4.1 $$\%$$ % on NTU-RGB+D 120 (Cross-subject), and 4.3 $$\%$$ % on Kinetics (Top-1), outperforming current state-of-the-art algorithms. This paper delves into the realm of behavior recognition technology, a cornerstone of autonomous systems, and presents a novel approach that enhances the accuracy and precision of human activity recognition.

Abstract Myocardial infarction (MI) poses a significant clinical challenge, necessitating expeditious and precise detection to mitigate potentially fatal outcomes. Current MI diagnosis predominantly relies on electrocardiography (ECG); however, it is fraught with limitations, including inter-observer variability and a reliance on expert interpretation. This study introduces an automated MI detection framework that capitalizes on hybrid signal processing methodologies and deterministic learning theory. The initial step involves the extraction of the Shannon energy envelope (SEE) and its derivative from a single-lead ECG. Integration of the SEE into the ECG’s phase portrait provides a means to capture the underlying nonlinear system dynamics. Subsequently, the application of fast and adaptive multivariate empirical mode decomposition (FA-MVEMD) yields discriminative features originating from the most energetically dominant intrinsic mode components (IMFs) within the SEE. Profound dissimilarities are discernible between ECG signals recorded from healthy subjects and those afflicted with MI. In the subsequent phase, deterministic learning theory, implemented through neural networks, is employed to facilitate the classification of ECG signals into two distinct groups. The method’s efficacy is meticulously evaluated using the PTB diagnostic ECG database, resulting in a noteworthy average classification accuracy of 99.21 $$\%$$ % within a tenfold cross-validation framework. In summation, the findings affirm that the proposed features not only complement conventional ECG attributes but also align closely with the underlying dynamics of the ECG system, ultimately fortifying the automatic detection of MI. The imperative requirement for early and accurate MI diagnosis is addressed through our approach, offering a robust and dependable means to fulfill this pivotal clinical need.

Abstract Object detection holds a crucial role in medical diagnostics. Tasks like organ segmentation and malignancy diagnosis typically necessitate preliminary localization of corresponding anatomical structures. Precise positioning ensures that only pertinent regions require processing, leading to a potential reduction in computational and storage demands. Conventional image detection approaches necessitate numerous candidate boxes, resulting in redundant computations. Developing techniques capable of accurately detecting medical image objects without reliance on candidate boxes holds substantial practical significance. This paper introduces a 2D method for detecting medical image objects, which leverages multi-agent deep Q-network reinforcement learning and a multi-scale image representation. The method constructs a collaborative environment for multiple agents. These agents individually govern the upper-right corner and lower-left corner positions of the object detection frame, progressively converging toward the actual endpoint through iterative interactions. To expedite the detection process, a multi-scale image representation technique is employed. This method segments the process into three scales. Initially, within the coarse-scale space, the agent approximates the region containing the true endpoint, subsequently executing oscillatory movements. Progressively, it refines its approach within the fine-scale space, advancing toward the genuine endpoint with smaller iterative steps. The detection results demonstrate that collaborative detection among agents yields a 2.45 $$\%$$ % higher intersection over union compared to non-collaborative detection. Agents exhibit varying step sizes and fields of view in different scale spaces, leading to a reduction in detection time by 0.12 s compared to single-scale comparison. Experimental outcomes demonstrate the superiority of the medical image target detection method proposed in this study over prevailing mainstream detection algorithms.

Cervical spondylotic myelopathy (CSM) is the main cause of adult spinal cord dysfunction, mostly appearing in middle-aged and elderly patients. Currently, the diagnosis of this condition depends mainly on the available imaging tools such as X-ray, computed tomography and magnetic resonance imaging (MRI), of which MRI is the gold standard for clinical diagnosis. However, MRI data cannot clearly demonstrate the dynamic characteristics of CSM, and the overall process is far from cost-efficient. Therefore, this study proposes a new method using multiple gait parameters and shallow classifiers to dynamically detect the occurrence of CSM. In the present study, 45 patients with CSM and 45 age-matched asymptomatic healthy controls (HCs) were recruited, and a three-dimensional (3D) motion capture system was utilized to capture the locomotion data. Furthermore, 63 spatiotemporal, kinematic, and nonlinear parameters were extracted, including lower limb joint angles in the sagittal, coronal, and transverse planes. Then, the Shapley Additive exPlanations (SHAP) value was utilized for feature selection and reduction of the dimensionality of features, and five traditional shallow classifiers, including support vector machine (SVM), logistic regression (LR), k-nearest neighbor (KNN), decision tree (DT), and random forest (RF), were used to classify gait patterns between CSM patients and HCs. On the basis of the 10-fold cross-validation method, the highest average accuracy was achieved by SVM (95.56%). Our results demonstrated that the proposed method could effectively detect CSM and thus serve as an automated auxiliary tool for the clinical diagnosis of CSM.

IntroductionThe human brain processes shape and texture information separately through different neurons in the visual system. In intelligent computer-aided imaging diagnosis, pre-trained feature extractors are commonly used in various medical image recognition methods, common pre-training datasets such as ImageNet tend to improve the texture representation of the model but make it ignore many shape features. Weak shape feature representation is disadvantageous for some tasks that focus on shape features in medical image analysis.MethodsInspired by the function of neurons in the human brain, in this paper, we proposed a shape-and-texture-biased two-stream network to enhance the shape feature representation in knowledge-guided medical image analysis. First, the two-stream network shape-biased stream and a texture-biased stream are constructed through classification and segmentation multi-task joint learning. Second, we propose pyramid-grouped convolution to enhance the texture feature representation and introduce deformable convolution to enhance the shape feature extraction. Third, we used a channel-attention-based feature selection module in shape and texture feature fusion to focus on the key features and eliminate information redundancy caused by feature fusion. Finally, aiming at the problem of model optimization difficulty caused by the imbalance in the number of benign and malignant samples in medical images, an asymmetric loss function was introduced to improve the robustness of the model.Results and conclusionWe applied our method to the melanoma recognition task on ISIC-2019 and XJTU-MM datasets, which focus on both the texture and shape of the lesions. The experimental results on dermoscopic image recognition and pathological image recognition datasets show the proposed method outperforms the compared algorithms and prove the effectiveness of our method.

IntroductionIn the clinical setting, it becomes increasingly important to detect epileptic seizures automatically since it could significantly reduce the burden for the care of patients suffering from intractable epilepsy. Electroencephalography (EEG) signals record the brain's electrical activity and contain rich information about brain dysfunction. As a non-invasive and inexpensive tool for detecting epileptic seizures, visual evaluation of EEG recordings is labor-intensive and subjective and requires significant improvement.MethodsThis study aims to develop a new approach to recognize seizures automatically using EEG recordings. During feature extraction of EEG input from raw data, we construct a new deep neural network (DNN) model. Deep feature maps derived from layers placed hierarchically in a convolution neural network are put into different kinds of shallow classifiers to detect the anomaly. Feature maps are reduced in dimensionality using Principal Component Analysis (PCA).ResultsBy analyzing the EEG Epilepsy dataset and the Bonn dataset for epilepsy, we conclude that our proposed method is both effective and robust. These datasets vary significantly in the acquisition of data, the formulation of clinical protocols, and the storage of digital information, making processing and analysis challenging. On both datasets, extensive experiments are performed using a cross-validation by 10 folds strategy to demonstrate approximately 100% accuracy for binary and multi-category classification.DiscussionIn addition to demonstrating that our methodology outperforms other up-to-date approaches, the results of this study also suggest that it can be applied in clinical practice as well.

In the realm of modern medicine, medical imaging stands as an irreplaceable pillar for accurate diagnostics. The significance of precise segmentation in medical images cannot be overstated, especially considering the variability introduced by different practitioners. With the escalating volume of medical imaging data, the demand for automated and efficient segmentation methods has become imperative. This study introduces an innovative approach to heart image segmentation, embedding a multi-scale feature and attention mechanism within an inverted pyramid framework. Recognizing the intricacies of extracting contextual information from low-resolution medical images, our method adopts an inverted pyramid architecture. Through training with multi-scale images and integrating prediction outcomes, we enhance the network’s contextual understanding. Acknowledging the consistent patterns in the relative positions of organs, we introduce an attention module enriched with positional encoding information. This module empowers the network to capture essential positional cues, thereby elevating segmentation accuracy. Our research resides at the intersection of medical imaging and sensor technology, emphasizing the foundational role of sensors in medical image analysis. The integration of sensor-generated data showcases the symbiotic relationship between sensor technology and advanced machine learning techniques. Evaluation on two heart datasets substantiates the superior performance of our approach. Metrics such as the Dice coefficient, Jaccard coefficient, recall, and F-measure demonstrate the method’s efficacy compared to state-of-the-art techniques. In conclusion, our proposed heart image segmentation method addresses the challenges posed by diverse medical images, offering a promising solution for efficiently processing 2D/3D sensor data in contemporary medical imaging.

In the era of artificial intelligence, the significance of images and videos as intuitive conveyors of information cannot be overstated. Computer vision techniques rooted in deep learning have revolutionized our ability to autonomously and accurately identify objects within visual media, making them a focal point of contemporary research. This study addresses the pivotal role of image object detection, particularly in the contexts of autonomous driving and security surveillance, by presenting an in-depth exploration of this field with a focus on enhancing the feature pyramid network. One of the key challenges in existing object detection methodologies lies in mitigating information loss caused by multi-scale feature fusion. To tackle this issue, we propose the enhanced feature pyramid, which adeptly amalgamates features extracted across different scales. This strategic enhancement effectively curbs information attrition across various layers, thereby strengthening the feature extraction capabilities of the foundational network. Furthermore, we confront the issue of excessive classification loss in image object detection tasks by introducing the gradient density loss function, designed to mitigate classification discrepancies. Empirical results unequivocally demonstrate the efficacy of our approach in enhancing the detection of multi-scale objects within images. When evaluated across benchmark datasets, including MS COCO 2017, MS COCO 2014, Pascal VOC 2007, and Pascal VOC 2012, our method achieves impressive average precision scores of 39.4%, 42.0%, 51.5%, and 49.9%, respectively. This performance clearly outperforms alternative state-of-the-art methods in the field. This research not only contributes to the evolving landscape of computer vision and object detection but also has practical implications for a wide range of applications, aligning with the transformative trends in the automotive industry and security technologies.

Accurate real-time kinematics model is very important for the control of a skid-steering mobile robot. In this study, the kinematics model of the skid-steering mobile robots was first designed based on instantaneous rotation centers (ICRs). Then, the extended Kalman filter (EKF) technique was applied to obtain the parameters of ICRs under the same specific terrain online. To adapt to different terrain environments, the fractal dimension-based SFTA (segmentation-based fractal texture analysis) method was used to extract features of different terrains, and the k-nearest neighbor (KNN) method was used to classify the terrains. In the case of real-time terrain recognition, the filter parameters of the EKF for estimating the ICRs are adjusted adaptively. Experiments on a real skid-steering mobile robot show that this method can quickly estimate the kinematics model of the robot in the case of terrain changes, and can meet the needs of practical applications. The average error of odometer estimation based on visual terrain classification is 0.06 m, while the average error of odometer estimation without terrain classification is 0.14 m.

Visual saliency refers to the human’s ability to quickly focus on important parts of their visual field, which is a crucial aspect of image processing, particularly in fields like medical imaging and robotics. Understanding and simulating this mechanism is crucial for solving complex visual problems. In this paper, we propose a salient object detection method based on boundary enhancement, which is applicable to both 2D and 3D sensors data. To address the problem of large-scale variation of salient objects, our method introduces a multi-level feature aggregation module that enhances the expressive ability of fixed-resolution features by utilizing adjacent features to complement each other. Additionally, we propose a multi-scale information extraction module to capture local contextual information at different scales for back-propagated level-by-level features, which allows for better measurement of the composition of the feature map after back-fusion. To tackle the low confidence issue of boundary pixels, we also introduce a boundary extraction module to extract the boundary information of salient regions. This information is then fused with salient target information to further refine the saliency prediction results. During the training process, our method uses a mixed loss function to constrain the model training from two levels: pixels and images. The experimental results demonstrate that our salient target detection method based on boundary enhancement shows good detection effects on targets of different scales, multi-targets, linear targets, and targets in complex scenes. We compare our method with the best method in four conventional datasets and achieve an average improvement of 6.2% on the mean absolute error (MAE) indicators. Overall, our approach shows promise for improving the accuracy and efficiency of salient object detection in a variety of settings, including those involving 2D/3D semantic analysis and reconstruction/inpainting of image/video/point cloud data.

Understanding and analyzing 2D/3D sensor data is crucial for a wide range of machine learning-based applications, including object detection, scene segmentation, and salient object detection. In this context, interactive object segmentation is a vital task in image editing and medical diagnosis, involving the accurate separation of the target object from its background based on user annotation information. However, existing interactive object segmentation methods struggle to effectively leverage such information to guide object-segmentation models. To address these challenges, this paper proposes an interactive image-segmentation technique for static images based on multi-level semantic fusion. Our method utilizes user-guidance information both inside and outside the target object to segment it from the static image, making it applicable to both 2D and 3D sensor data. The proposed method introduces a cross-stage feature aggregation module, enabling the effective propagation of multi-scale features from previous stages to the current stage. This mechanism prevents the loss of semantic information caused by multiple upsampling and downsampling of the network, allowing the current stage to make better use of semantic information from the previous stage. Additionally, we incorporate a feature channel attention mechanism to address the issue of rough network segmentation edges. This mechanism captures richer feature details from the feature channel level, leading to finer segmentation edges. In the experimental evaluation conducted on the PASCAL Visual Object Classes (VOC) 2012 dataset, our proposed interactive image segmentation method based on multi-level semantic fusion demonstrates an intersection over union (IOU) accuracy approximately 2.1% higher than the currently popular interactive image segmentation method in static images. The comparative analysis highlights the improved performance and effectiveness of our method. Furthermore, our method exhibits potential applications in various fields, including medical imaging and robotics. Its compatibility with other machine learning methods for visual semantic analysis allows for integration into existing workflows. These aspects emphasize the significance of our contributions in advancing interactive image-segmentation techniques and their practical utility in real-world applications.

Point cloud semantic segmentation based on deep learning methods is still a challenge due to the irregularity of structures and uncertainty of sampling. Color information often contains a lot of prior information, whereas the existing methods do not attach more importance to it. To deal with this problem, we propose a novel hard attention mechanism, named color-guided convolution. This convolution operator learns the correlation between geometric and color information by reordering the local points with color-indicated vectors. In addition, the global feature fusion is proposed to rectify features selected by the feature selecting unit. Experimental results and comparisons with recent methods demonstrate the superiority of our approach.

Malignant melanoma (MM) recognition in whole-slide images (WSIs) is challenging due to the huge image size of billions of pixels and complex visual characteristics. We propose a novel automatic melanoma recognition method based on the multi-scale features and probability map, named MPMR. First, we introduce the idea of breaking up the WSI into patches to overcome the difficult-to-calculate problem of WSIs with huge sizes. Second, to obtain and visualize the recognition result of MM tissues in WSIs, a probability mapping method is proposed to generate the mask based on predicted categories, confidence probabilities, and location information of patches. Third, considering that the pathological features related to melanoma are at different scales, such as tissue, cell, and nucleus, and to enhance the representation of multi-scale features is important for melanoma recognition, we construct a multi-scale feature fusion architecture by additional branch paths and shortcut connections, which extracts the enriched lesion features from low-level features containing more detail information and high-level features containing more semantic information. Fourth, to improve the extraction feature of the irregular-shaped lesion and focus on essential features, we reconstructed the residual blocks by a deformable convolution and channel attention mechanism, which further reduces information redundancy and noisy features. The experimental results demonstrate that the proposed method outperforms the compared algorithms, and it has a potential for practical applications in clinical diagnosis.

Point set registration is a key method in computer vision and pattern recognition. In this paper, the correntropy and bi-directional distance are introduced into registration framework and a new robust registration model for RGB-D data is proposed. Firstly, as registering point sets with smooth structure, such as surface or plane, is easy failed, the color and position information is fused to establish more precise correspondence between two RGB-D data sets. Secondly, to reduce the influence of noises and eliminate outliers, the registration model based on the maximum correntropy criterion is established. Thirdly, the bi-directional distance measurement is introduced into the registration framework to avoid the model being trapped into local extremum. In addition, to solve this new registration problem, a new iterative closest point (ICP) algorithm is proposed, which converges to the local optimal solution by iterations. In the experiments, the proposed algorithm achieves more robustness and precise registration results than other algorithms.

With the development of RGBD sensors, the high-quality color point cloud can be obtained expediently. In this paper, we propose a novel registration method for 3D color point clouds from different views, which is a critical issue in many applications. Different from traditional feature-based methods, we design a hybrid feature representation with color moments of the point, which could be applied naturally for any color point cloud. And these features are extracted from point clouds based on the supervoxel segmentation. By jointly conducting these features for similarity measure, a weight parameter is dynamically adapted between the color and the spatial information. The registration algorithm is under a classic iterative framework for building the correspondence and estimating transformation parameters. In addition, we provide a mutual correspondence matching condition with hybrid features to build some more robust relationships for estimating transformation parameters. Experimental results demonstrate that our method can effectively reduce the number of point data for registration and achieve good matching results even in a poor initial condition.

In integrated circuit manufacturing industry, in order to meet the high demand of electronic products, wafers are designed to be smaller and smaller, which makes automatic wafer defect detection a great challenge. The existing wafer defect detection methods are mainly based on the precise segmentation of one single wafer, which relies on high-cost and complicated hardware instruments. The segmentation performance obtained is unstable because there are too many limitations brought by hardware implementations such as the camera location, the light source location, and the product location. To address this problem, in this paper, we propose a method for wafer defect detection. This novel method includes two phases, namely wafer segmentation and defect detection. In wafer segmentation phase, the target wafer image is segmented based on the affine iterative closest algorithm with spatial feature points guided (AICP-FP). In wafer defect detection phase, with the inherent characteristics of wafers, a simple and effective algorithm based on machine vision is proposed. The simulations demonstrate that, with these two phases, the higher accuracy and higher speed of wafer defect detection can be achieved at the same time. For real industrial system, this novel method can satisfy the real-time detection requirements of automatic production line.

Automatic and accurate detection of chest X-ray lesion is a challenging task. In the chest X-ray image, the lesions are shown with blurred boundary contours, different sizes, variable shapes, uneven density, etc. Besides, the deep convolutional neural network (CNN) consists of traditional convolution units, which has the limitations of rectangular sampling. The CNN extracts difficultly the deformation and refined features of chest X-ray lesions. Because of these factors, the accuracy of the lesion detection algorithm is not high. To deal with problems, we propose the deformation and refined features based lesion detection on the chest X-ray algorithm called DRCXNet. Firstly, the deformable convolution with amplitude modulation (AMDCN) is built to extract the deformation features of the lesions on the chest X-ray. Secondly, to obtain the refined feature, the global features and local features are fused, which can enrich the feature space of the lesion. Thirdly, the pooling layer combines with the AMDCN and region proposal network to establish the deformable pooling layer, which enhances the model's sensitivity to the lesion location. During the training, the model is optimized by the improved regression loss function with a gradient control factor. On the public datasets RSNA and ChestX-ray8, the proposed method outperforms seven popular detection algorithms. The proposed method is a significant performance in both qualitative and quantitative experiments. Its comprehensive evaluation scores, sensitivity, precision, and the mean dice similarity coefficient are 0.866, 0.914, 0.836 and 0.859 respectively. The proposed algorithm achieves a very satisfactory result.

Accurately estimating the user's gaze is important in many applications, such as human-computer interaction. Due to great convenience, appearance-based methods for gaze estimation have been a popular subject of research for many years. However, the greatest challenges in the appearance-based gaze estimation in a desktop environment are how to simplify the calibration process and deal with other issues such as image noise and low resolution. To address the problems, we adopt a mapping relationship between the high-dimensional eye image features space and the low-dimensional gaze positions and propose a robust and accurate method for gaze estimation with a webcam. First, we utilize Kullback-Leibler divergence to reduce feature dimension and keep similarity between the feature space and the gaze space. Then, we construct the objective function using the maximum correntropy criterion instead of mean squared error, which can enhance the anti-noise ability, especially for outliers or pixel corruption. A regularization term is adopted to adaptively select the sparse training samples for gaze estimation. We conducted extensive experiments in a desktop environment, which verified that the proposed method was robust and efficient in dealing with sparse training samples, pixel corruption, and low-resolution problems in gaze estimation.

The accuracy of classification and retrieval significantly depends on the metric used to compute the similarity between samples. For preserving the geometric structure, the symmetric positive definite (SPD) manifold is introduced into the metric learning problem. However, the SPD constraint is too strict to describe the real data distribution. In this paper, we extend the intrinsic metric learning problem to semi-definite case, by which the data distribution is better described for various classification tasks. First, we formulate the metric learning as a minimization problem to the SPD manifold on subspace, which not only considers to balance the information between inner classes and inter classes by an adaptive tradeoff parameter but also improves the robustness by the low-rank subspaces presentation. Thus, it benefits to design a structure-preserving algorithm on subspace by using the geodesic structure of the SPD subspace. To solve this model, we develop an iterative strategy to update the intrinsic metric and the subspace structure, respectively. Finally, we compare our proposed method with ten state-of-the-art methods on four data sets. The numerical results validate that our method can significantly improve the description of the data distribution, and hence, the performance of the image classification task.

Generative adversarial networks (GANs) have been used to obtain super-resolution (SR) videos that have improved visual perception quality and more coherent details. However, the latest methods perform poorly in areas with dense textures. To better recover the areas with dense textures in video frames and improve the visual perception quality and coherence in videos, this paper proposes a multiresolution mixture generative adversarial network for video super-resolution (MRMVSR). We propose a multiresolution mixture network (MRMNet) as the generative network that can simultaneously generate multiresolution feature maps. In MRMNet, the high-resolution (HR) feature maps can continuously extract information from low-resolution (LR) feature maps to supplement information. In addition, we propose a residual fluctuation loss function for video super-resolution. The residual fluctuation loss function is used to reduce the overall residual fluctuation on SR and HR video frames to avoid a scenario where local differences are too large. Experimental results on the public benchmark dataset show that our method outperforms the state-of-the-art methods for the majority of the test sets.

Real industrial processes usually are equipped with onboard control or diagnostic systems and limit to store a complicated model. Also, measurement samples from real processes are contaminated with noises of different statistical characteristics and are produced by one-by-one way. In this case, learning algorithms with better learning performance and compact model for systems with noises of various statistics are necessary. This paper proposes a new online extreme learning machine (ELM) algorithm, namely, sparse recursive least mean p-power ELM (SRLMP-ELM). In SRLMP-ELM, a novel cost function, i.e., the sparse least mean p-power (SLMP) error criterion, provides a mechanism to update the output weights sequentially and automatically tune some parameters of the output weights to zeros. The SLMP error criterion aims to minimize the combination of the mean p-power of the errors and a sparsity penalty constraint of the output weights. For real industrial system requirements, the proposed on-line learning algorithm is able to provide more higher accuracy, compact model, and better generalization ability than ELM and online sequential ELM, whereas the non-Gaussian noises impact the processes, especially impulsive noises. Simulations are reported to demonstrate the performance and effectiveness of the proposed methods.

In this study, partial registration problem with outliers and missing data in the affine case is discussed. To solve this problem, a novel objective function is proposed based on bidirectional distance and trimmed strategy, and then a new affine trimmed iterative closest point algorithm is given. First, when bidirectional distance measurement is applied, the ill‐posed partial registration problem in the affine case is prevented. Second, the overlapping percentage is solved by using trimmed strategy which uses as many correct overlapping points as possible. The authors’ method computes the affine transformation, correspondence and overlapping percentage automatically at each iterative step. In this way, it handles partially overlapping registration with outliers and missing data in the affine case well. Experimental results demonstrate that their method is more robust and precise than the state‐of‐the‐art algorithms. It also has good convergence and similar running time with traditional algorithms.

Nonlinear registration is an important technique to align two different images and widely applied in medical image analysis. In this paper, we develop a novel nonlinear registration framework based on the diffeomorphic demons, where a reciprocal regularizer is introduced to assume that the deformation between two images is an exact diffeomorphism. In detail, first, we adopt a bidirectional metric to improve the symmetry of the energy functional, whose variables are two reciprocal deformations. Secondly, we slack these two deformations into two independent variables and introduce a reciprocal regularizer to assure the deformations being the exact diffeomorphism. Then, we utilize an alternating iterative strategy to decouple the model into two minimizing subproblems, where a new closed form for the approximate velocity of deformation is calculated. Finally, we compare our proposed algorithm on two data sets of real brain MR images with two relative and conventional methods. The results validate that our proposed method improves accuracy and robustness of registration, as well as the gained bidirectional deformations are actually reciprocal.

The iterative closest point (ICP) algorithm is efficient and accurate for rigid registration but it needs the good initial parameters. It is easily failed when the rotation angle between two point sets is large. To deal with this problem, a new objective function is proposed by introducing a rotation invariant feature based on the Euclidean distance between each point and a global reference point, where the global reference point is a rotation invariant. After that, this optimization problem is solved by a variant of ICP algorithm, which is an iterative method. Firstly, the accurate correspondence is established by using the weighted rotation invariant feature distance and position distance together. Secondly, the rigid transformation is solved by the singular value decomposition method. Thirdly, the weight is adjusted to control the relative contribution of the positions and features. Finally this new algorithm accomplishes the registration by a coarse-to-fine way whatever the initial rotation angle is, which is demonstrated to converge monotonically. The experimental results validate that the proposed algorithm is more accurate and robust compared with the original ICP algorithm.

In this paper, robust first and second-order divided difference filtering algorithms based on correntropy are proposed, which not only retain the advantages of divided difference filters, but also exhibit robustness in the presence of non-Gaussian noises, especially when the measurements are contaminated by heavy-tailed noises. The proposed filters are then applied to the problem of ship positioning. In order to improve the accuracy and reliability of ship positioning, the positioning method combines the Dead Reckoning (DR) algorithm and the Global Positioning System (GPS). Experimental results of an illustrative example show the superior performance of the new algorithms when applied to ship positioning.

We propose a method for non-rigid face alignment which only needs a single template, such as using a person's smile face to match his surprise face. First, in order to be robust to outliers caused by complex geometric deformations, a new local feature matching method called K Patch Pairs (K-PP) is proposed. Specifically, inspired by the state-of-art similarity measure used in template matching, K-PP is to find the mutual K nearest neighbors between two images. A weight matrix is then presented to balance the similarity and the number of local matching. Second, we proposed a modified Lucas-Kanade algorithm combined with local matching constraint to solve the non-rigid face alignment, so that a holistic face representation and local features can be jointly modeled in the object function. Both the flexible ability of local matching and the robust ability of holistic fitting are included in our method. Furthermore, we show that the optimization problem can be efficiently solved by the inverse compositional algorithm. Comparison results with conventional methods demonstrate our superiority in terms of both accuracy and robustness.

This paper proposes a novel multi-label classification method for resolving the spacecraft electrical characteristics problems which involve many unlabeled test data processing, high-dimensional features, long computing time and identification of slow rate. Firstly, both the fuzzy c-means (FCM) offline clustering and the principal component feature extraction algorithms are applied for the feature selection process. Secondly, the approximate weighted proximal support vector machine (WPSVM) online classification algorithms is used to reduce the feature dimension and further improve the rate of recognition for electrical characteristics spacecraft. Finally, the data capture contribution method by using thresholds is proposed to guarantee the validity and consistency of the data selection. The experimental results indicate that the method proposed can obtain better data features of the spacecraft electrical characteristics, improve the accuracy of identification and shorten the computing time effectively.