Feature Matching Research Articles

Stitching method for panoramic nail fold images based on capillary contour enhancement.

Nail fold capillaroscopy is an important means of monitoring human health. Panoramic nail fold images improve the efficiency and accuracy of examinations. However, the acquisition of panoramic nail fold images is seldom studied and the problem manifests of few matching feature points when image stitching is used for such images. Therefore, this paper presents a method for panoramic nail fold image stitching based on vascular contour enhancement, which first solves the problem of few matching feature points by pre-processing the image with contrast-constrained adaptive histogram equalization (CLAHE), bilateral filtering (BF), and sharpening algorithms. The panoramic images of the nail fold blood vessels are then successfully stitched using the fast robust feature (SURF), fast library of approximate nearest neighbors (FLANN) and random sample agreement (RANSAC) algorithms. The experimental results show that the panoramic image stitched by this paper's algorithm has a field of view width of 7.43 mm, which improves the efficiency and accuracy of diagnosis.

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching.

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins.

Shape-Scale Co-Awareness Network for 3D Brain Tumor Segmentation.

The accurate segmentation of brain tumor is significant in clinical practice. Convolutional Neural Network (CNN)-based methods have made great progress in brain tumor segmentation due to powerful local modeling ability. However, brain tumors are frequently pattern-agnostic, i.e. variable in shape, size and location, which can not be effectively matched by traditional CNN-based methods with local and regular receptive fields. To address the above issues, we propose a shape-scale co-awareness network (S2CA-Net) for brain tumor segmentation, which can efficiently learn shape-aware and scale-aware features simultaneously to enhance pattern-agnostic representations. Primarily, three key components are proposed to accomplish the co-awareness of shape and scale. The Local-Global Scale Mixer (LGSM) decouples the extraction of local and global context by adopting the CNN-Former parallel structure, which contributes to obtaining finer hierarchical features. The Multi-level Context Aggregator (MCA) enriches the scale diversity of input patches by modeling global features across multiple receptive fields. The Multi-Scale Attentive Deformable Convolution (MS-ADC) learns the target deformation based on the multiscale inputs, which motivates the network to enforce feature constraints both in terms of scale and shape for optimal feature matching. Overall, LGSM and MCA focus on enhancing the scale-awareness of the network to cope with the size and location variations, while MS-ADC focuses on capturing deformation information for optimal shape matching. Finally, their effective integration prompts the network to perceive variations in shape and scale simultaneously, which can robustly tackle the variations in patterns of brain tumors. The experimental results on BraTS 2019, BraTS 2020, MSD BTS Task and BraTS2023-MEN show that S2CA-Net has superior overall performance in accuracy and efficiency compared to other state-of-the-art methods. Code: https://github.com/jiangyu945/S2CA-Net.

MSGA-Net: Progressive Feature Matching via Multi-Layer Sparse Graph Attention

MSGA-Net: Progressive Feature Matching via Multi-Layer Sparse Graph Attention

Data processing algorithm of cone-cylinder forgings process based on spectral graph theory and Hungarian matching

This paper presents a novel data processing algorithm. This algorithm is used to solve the problem of incomplete and misaligned of point cloud data due to the complexity of nuclear power containment cone-cylinder forgings and the limitation of laser scanner. Based on spectral graph theory and Hungarian matching, this paper first introduces the lazy random walk, and point cloud state vector is calculated during the walk to judge the local information, thereby eliminate the influence of noise. Then, characteristic edges are extracted using spectral graph theory. Additionally, the feature descriptors are calculated and the cost matrix is constructed using the feature descriptors. The Hungarian algorithm is applied for feature matching, facilitating a coarse registration of the point clouds. Finally, the improved point-to-plane iteration closest point is used for fine registration to ensure accurate alignment between point clouds. The experimental results demonstrate the algorithm's effectiveness in the registration of point clouds for nuclear power containment cone-cylinder forgings.

A Federated Learning-Based Industrial Health Prognostics for Heterogeneous Edge Devices Using Matched Feature Extraction

Data-driven industrial health prognostics require rich training data to develop accurate and reliable predictive models. However, stringent data privacy laws and the abundance of edge industrial data necessitate decentralized data utilization. Thus, the industrial health prognostics field is well suited to significantly benefit from federated learning (FL), a decentralized and privacy-preserving learning technique. However, FL-based health prognostics tasks have hardly been investigated due to the complexities of meaningfully aggregating model parameters trained from heterogeneous data to form a high performing federated model. Specifically, data heterogeneity among edge devices, stemming from dissimilar degradation mechanisms and unequal dataset sizes, poses a critical statistical challenge for developing accurate federated models. We propose a pioneering FL-based health prognostic model with a feature similarity-matched parameter aggregation algorithm to discriminatingly learn from heterogeneous edge data. The algorithm searches across the heterogeneous locally trained models and matches neurons with probabilistically similar feature extraction functions first, before selectively averaging them to form the federated model parameters. As the algorithm only averages similar neurons, as opposed to conventional naive averaging of coordinate-wise neurons, the distinct feature extractors of local models are carried over with less dilution to the resultant federated model. Using both cyclic degradation data of Li-ion batteries and non-cyclic data of turbofan engines, we demonstrate that the proposed method yields accuracy improvements as high as 44.5\% and 39.3\% for state-of-health estimation and remaining useful life estimation, respectively.

INVARIANT ZERO-WATERMARKING ALGORITHM IN DWT-DCT DOMAIN USING ROBUST FEATURES MATCHING

In order to protect the copyright of the digital contents, the robust watermarking techniques are employed based on frequency domains or combined frequency domains. Another techniques, called zero-watermarking which does not modify the original image to embed the watermark but create a watermark from its robust features, is a useful technique for resolving the tension between robustness and invisibility. In this paper, we propose a new zero-watermarking algorithm based on discrete wavelet transform and discrete cosine transform domain with significant feature points matching for improving the robustness. In our proposed method, the original image is firstly separated into three components (Y, Cr, Cb), then its Y-component is performed with discrete wavelet transform, afterwards its LL3 is transformed with discrete cosine transform. To generate the master share of the original image, the DCT-based image is binarized. After performing the Arnold transformation on the watermark, the owner share is generated by taking the XOR operation on the scrambled watermark and master share. The robustness of the our proposed algorithm for imaging processes is analyzed, and the results show that the proposed algorithm is robust to common signal processing such as noise, filtering, JPEG compression, geometric attacks such as rotation, scaling, translation and so on.

A robust feature matching algorithm based on adaptive feature fusion combined with image superresolution reconstruction

A robust feature matching algorithm based on adaptive feature fusion combined with image superresolution reconstruction

LightSGM: Local feature matching with lightweight seeded

Addressing the quintessential challenge of local feature matching in computer vision, this study introduces a novel fast sparse seed graph structure named LightSGM. This structure aims to refine the characterization of graph features while minimizing superfluous connections. Initially, a subset of high-quality seed feature points is curated using a confidence filter. Subsequently, keypoint features are assimilated into this seed set via graph pooling, and the composite features are further processed through a memory and computation-efficient seed transformer to capture rich contextual information about the keypoints. The seed feature points are then relayed back to the original keypoints using an inverse process known as graph unpooling. The paper also introduce an adaptive mechanism to determine the optimal number of model layers based on the intricacy of matching image pairs. A Matching Point Prediction Header is employed to extract the final set of matching points. Through extensive experimentation on image matching and position estimation, LightSGM has demonstrated its prowess in delivering competitive matching accuracy while maintaining a balance with real-time processing capabilities.

A Novel High-Fidelity Simulation for Finishing Operations: Hybrid Image Mosaic and Wavelet Decomposition.

In finishing simulations, achieving accurate results can be challenging due to the minimal amount of material removal and the limited measurement range of surface micro-topography instruments. To overcome these limitations, a novel high-fidelity modeling method combining image mosaic and wavelet decomposition technologies is proposed in this paper. We achieve the stitching of narrow field and high pixel micro morphology images through four steps: image feature extraction, overlapped feature matching, feature fusion, and stitching effect evaluation. On this basis, the wavelet decomposition method is employed to separate detection signals based on their respective frequencies, allowing the establishment of a datum plane and a roughness surface. The point cloud model undergoes a transformation into a continuous geometric model via the Poisson reconstruction algorithm. In the case study, four sample images of an aluminum alloy sheet after barrel finishing were collected using the ZeGage Plus optical profiler. Each image has an actual size of 834.37 μm × 834.37 μm. Subsequently, a comparison was carried out between the physical and simulation experiments. The results clearly indicate that the proposed method has the potential to enhance the accuracy of the finishing simulation by over 30%. The error between the resulting model and the actual surface of the part can be controlled within 1 μm.

Prediction model of burn-through point with data correction based on feature matching of cross-section frame at discharge end

Accurately predicting the burn-through point (BTP) is crucial for achieving stable control of the sintering process. However, accurately measuring the raw BTP is difficult due to the harsh production environment and poor thermocouple measurement accuracy of the temperature of exhaust gas in bellows. This paper proposes a prediction model of the BTP with data correction based on the feature matching of cross-section frame at discharge end. Firstly, a feature extraction method of cross-section frames at discharge end is designed. Next, the cross-section frame at discharge end features matching method is used to correct the raw BTP, and this method corrects anomalous data resulting from sensor failures. Finally, the temporal convolutional neural network and gated recurrent unit are used to predict the corrected BTP. The prediction model considers the cross-section frame feature at discharge end and state parameters as inputs, and it can achieve accurate prediction of the corrected BTP. A series of comparative experiments are conducted to verify the feasibility and effectiveness of the proposed model. At the same time, this paper also designs industrial implementation plan,and use actual operation data to verify the feasibility of the designed industrial implementation plan.

Stereo visual-inertial localization algorithm for orchard robots based on point-line features

The vision-based localization of orchard mobile robots is an indispensable component of orchard intelligent management, applicable to scenarios such as navigation and harvesting. Due to the rugged terrain and lack of texture features in orchard environments, the accuracy of Visual-Inertial Odometry (VIO) based on feature point is compromised, making it challenging to meet practical application requirements. Addressing these issues, this paper proposes an algorithm for stereo visual-inertial localization based on point-line features, by enhancing VINS-Fusion. The algorithm incorporates the line feature detector algorithm (LSD) into the odometry front-end to detect line features, addressing the insufficient effective feature points and low-quality feature matching issues in orchard environments. Simultaneously, strategies for length filtering and feature matching are introduced for line features, eliminating poor-quality line features and matches caused by rugged terrain, thereby reducing adverse impacts on localization accuracy. To prevent keyframe redundancy due to a scarcity of stable feature points in areas with missing textures, such as tree trunks and leaves, a keyframe criteria optimization method based on point-line features is designed. Back-end optimization minimizes the cost function containing residuals of point-line features, prior information, and IMU, ultimately improving the localization accuracy of mobile robots. To validate the effectiveness and practicality of the proposed algorithm, a self-built dataset was created in real orchard environments, including scenes from banana plantation, mango orchard, and wampee orchard. Localization experiments were conducted using Rosario, EuRoC public datasets and self-built orchard dataset. Results indicate that the proposed algorithm consistently achieves lower ATE-RMSE than VINS-Fusion, with a maximum reduction of 79.2 % in the Rosario dataset sequence, 23.3 % in the EuRoC dataset sequence, and ATE-RMSE values of 0.091 m, 0.107 m, and 0.093 m in banana plantation, mango orchard, and wampee orchard, respectively. These represent reductions of 22.9 %, 7.6 %, and 27.3 % compared to VINS-Fusion. In the self-built orchard dataset, the average frame processing times for the algorithm front-end is 56.3 ms, while for the back-end is 31 ms, meeting the practical localization requirements. The proposed algorithm effectively enhances the localization accuracy of orchard mobile robots, offering a viable solution for autonomous navigation in orchard robot systems.

CDTracker: Coarse-to-Fine Feature Matching and Point Densification for 3D Single-Object Tracking

Three-dimensional (3D) single-object tracking (3D SOT) is a fundamental yet not well-solved problem in 3D vision, where the complexity of feature matching and the sparsity of point clouds pose significant challenges. To handle abrupt changes in appearance features and sparse point clouds, we propose a novel 3D SOT network, dubbed CDTracker. It leverages both cosine similarity and an attention mechanism to enhance the robustness of feature matching. By combining similarity embedding and attention assignment, CDTracker performs template and search area feature matching in a coarse-to-fine manner. Additionally, CDTracker addresses the problem of sparse point clouds, which commonly leads to inaccurate tracking. It incorporates relatively dense sampling based on the concept of point cloud segmentation to retain more target points, leading to improved localization accuracy. Extensive experiments on both the KITTI and Waymo datasets demonstrate clear improvements in CDTracker over its competitors.

Vessel Wall Imaging Features of Spontaneous Intracranial Carotid Artery Dissection.

Intracranial dissection is an important cause of stroke often with nonspecific angiographic features. Vessel wall imaging (VWI) can detect dissections, but intracranial applications remain unvalidated by pathologic specimens. We sought to determine the ability of VWI to identify the rarely reported spontaneous intracranial carotid dissection (sICD) guided by postmortem validation. VWI features of sICD, validated by postmortem specimen analysis in 1 patient, included luminal enhancement within a hypoenhancing outer wall, narrowing the mid to distal ophthalmic (C6) segment, relatively sparing the communicating (C7) segment. VWI examinations were reviewed to identify patients (1) with matching imaging features, (2) no evidence of other vasculopathies (i.e., inflammatory, intracranial atherosclerotic disease [ICAD]), and (3) adequate image quality. These sICD VWI features were compared with those in patients with known ICAD causing similar narrowing of C6 and relative sparing of C7 by a Fisher exact test accounting for multiple samples. Among 407 VWI examinations, 8 patients were identified with 14 sICDs, all women aged 30-56 years, 6 (75%) bilateral. All patients with sICD had risk factors of dissection (e.g., recently postpartum, fibromuscular dysplasia, and hypertension) and 3 (37.5%) had intracranial dissections elsewhere. Seven (87.5%) were diagnosed as moyamoya syndrome on initial angiography. Enhancing lesions varied from thin flap-like defects (n = 6) to thick tissue along the superolateral wall of the internal carotid artery, within the hypoenhancing outer wall. Compared with 10 intracranial carotid plaques in 8 patients with ICAD, sICD demonstrated stronger (84.6% vs 20.0%, p = 0.003-0.025) and more homogeneous (61.5% vs 0.0%, p = 0.005-0.069) enhancement and less positive remodeling (0.0% vs 60.0%, p = 0.004-0.09). T1 hyperintensity was identified in 5 sICDs in 3 patients but not identified in ICAD. Three patients with serial imaging (8- to 39.8-month maximum intervals) revealed little to no changes in stenosis, wall thickening, or enhancement. sICD is distinguishable on VWI from ICAD by enhancement characteristics, less positive remodeling, and clinical parameters. These VWI features should raise suspicion especially in young women with risk factors of dissection. Temporal stability and a lack of T1 hyperintensity should not discourage diagnosing sICD.

Image Fusion of Multi-Temporal Images of Eyes Feature using Hybrid Approach of PCA and SWT

A wide variety of information is represented by an image feature, which may be applied in various applications such as mage fusion, video processing, medical diagnosis, traffic safety monitoring, visual surveillance, feature matching, image segmentation, pattern matching, person identification, sentiment analysis, human computer interaction and many more fields. This paper focused on multi-temporal feature extraction of eyes feature from human face images captured in two different time slots to reduce the semantic gap from images and to improve the image quality by image fusion using PCA, SWT and hybrid approach of PCA and SWT algorithm. In this paper, comparative study of multi-temporal image fusion using Principle Component Analysis (PCA), Stationary Wavelet Transform (SWT) algorithms and hybrid approach of PCA and SWT are employed and its experimental results are evaluated with its performance analysis. Image fusion performance is compared based on eight quantitative quality measures as SSIM, MSE, NAE, CC , SC , AD, SD and MI.The outcomes of comparison show that employing the hybrid approach of PCA+SWT transform can improve image fusion performance. The applicability of this work approach may have several uses when the utilization of human facial features is feasible.

Class-agnostic counting and localization with feature augmentation and scale-adaptive aggregation

Compared to traditional class-specific counting, class-agnostic counting (CAC) enables the counting of arbitrary novel categories with only a few exemplars. The core issue of CAC lies in feature matching between the query image and exemplars. However, the scarce user-given exemplars make it difficult to adequately cover the diverse appearance of target objects, which poses challenges for feature matching. In this paper, we propose a Class-Agnostic Counting and Localization model (CACL) to enrich the exemplars by mining more inherent instances from the query feature. Specifically, CACL consists mainly of Self-Augment Feature Matching (SAFM) and Scale-Adaptive Spatial Aggregation (SASA). SAFM collects features of target instances frequently occurring in the query feature to augment the limited user-given exemplar, thus producing more comprehensive semantic features of the target category. To improve the robustness against scale variation, we design the SASA to enable the model to aggregate multiscale features adaptively. Compared to previous density map-based approaches, our method can locate the target objects which is more practical in real-world applications. Extensive experiments on FSC-147 suggest that our method achieves a competitive counting performance compared to state-of-the-art methods. Moreover, cross-dataset experiments demonstrate superior generalization in class-specific counting tasks.

PDE-Constrained Scale Optimization Selection for Feature Detection in Remote Sensing Image Matching

Feature detection and matching is the key technique for remote sensing image processing and related applications. In this paper, a PDE-constrained optimization model is proposed to determine the scale levels advantageous for feature detection. A variance estimation technique is introduced to treat the observation optical images polluted by additive zero-mean Gaussian noise and determine the parameter of a nonlinear scale space governed by the partial differential equation. Additive Operator Splitting is applied to efficiently solve the PDE constraint, and an iterative algorithm is proposed to approximate the optimal subset of the original scale level set. The selected levels are distributed more uniformly in the total variation sense and helpful for generating more accurate and robust feature points. The experimental results show that the proposed method can achieve about a 30% improvement in the number of correct matches with only a small increase in time cost.

A Self-Distillation Contrastive Learning Architecture for Global and Local Underwater Terrain Feature Extraction and Matching

A Self-Distillation Contrastive Learning Architecture for Global and Local Underwater Terrain Feature Extraction and Matching

VA-LOAM: Visual Assist LiDAR Odometry and Mapping for Accurate Autonomous Navigation.

In this study, we enhanced odometry performance by integrating vision sensors with LiDAR sensors, which exhibit contrasting characteristics. Vision sensors provide extensive environmental information but are limited in precise distance measurement, whereas LiDAR offers high accuracy in distance metrics but lacks detailed environmental data. By utilizing data from vision sensors, this research compensates for the inadequate descriptors of LiDAR sensors, thereby improving LiDAR feature matching performance. Traditional fusion methods, which rely on extracting depth from image features, depend heavily on vision sensors and are vulnerable under challenging conditions such as rain, darkness, or light reflection. Utilizing vision sensors as primary sensors under such conditions can lead to significant mapping errors and, in the worst cases, system divergence. Conversely, our approach uses LiDAR as the primary sensor, mitigating the shortcomings of previous methods and enabling vision sensors to support LiDAR-based mapping. This maintains LiDAR Odometry performance even in environments where vision sensors are compromised, thus enhancing performance with the support of vision sensors. We adopted five prominent algorithms from the latest LiDAR SLAM open-source projects and conducted experiments on the KITTI odometry dataset. This research proposes a novel approach by integrating a vision support module into the top three LiDAR SLAM methods, thereby improving performance. By making the source code of VA-LOAM publicly available, this work enhances the accessibility of the technology, fostering reproducibility and transparency within the research community.

Advanced Image Stitching Method for Dual-Sensor Inspection.

Efficient image stitching plays a vital role in the Non-Destructive Evaluation (NDE) of infrastructures. An essential challenge in the NDE of infrastructures is precisely visualizing defects within large structures. The existing literature predominantly relies on high-resolution close-distance images to detect surface or subsurface defects. While the automatic detection of all defect types represents a significant advancement, understanding the location and continuity of defects is imperative. It is worth noting that some defects may be too small to capture from a considerable distance. Consequently, multiple image sequences are captured and processed using image stitching techniques. Additionally, visible and infrared data fusion strategies prove essential for acquiring comprehensive information to detect defects across vast structures. Hence, there is a need for an effective image stitching method appropriate for infrared and visible images of structures and industrial assets, facilitating enhanced visualization and automated inspection for structural maintenance. This paper proposes an advanced image stitching method appropriate for dual-sensor inspections. The proposed image stitching technique employs self-supervised feature detection to enhance the quality and quantity of feature detection. Subsequently, a graph neural network is employed for robust feature matching. Ultimately, the proposed method results in image stitching that effectively eliminates perspective distortion in both infrared and visible images, a prerequisite for subsequent multi-modal fusion strategies. Our results substantially enhance the visualization capabilities for infrastructure inspection. Comparative analysis with popular state-of-the-art methods confirms the effectiveness of the proposed approach.