To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network mo...To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.展开更多
Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the f...Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.展开更多
Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier ...Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.展开更多
In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clini...In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clinical operating environments,endoscopic images often suffer from challenges such as low texture,uneven illumination,and non-rigid structures,which affect feature observation and extraction.This can severely impact surgical navigation or clinical diagnosis due to missing feature points in endoscopic images,leading to treatment and postoperative recovery issues for patients.To address these challenges,this paper introduces,for the first time,a Cross-Channel Multi-Modal Adaptive Spatial Feature Fusion(ASFF)module based on the lightweight architecture of EfficientViT.Additionally,a novel lightweight feature extraction and matching network based on attention mechanism is proposed.This network dynamically adjusts attention weights for cross-modal information from grayscale images and optical flow images through a dual-branch Siamese network.It extracts static and dynamic information features ranging from low-level to high-level,and from local to global,ensuring robust feature extraction across different widths,noise levels,and blur scenarios.Global and local matching are performed through a multi-level cascaded attention mechanism,with cross-channel attention introduced to simultaneously extract low-level and high-level features.Extensive ablation experiments and comparative studies are conducted on the HyperKvasir,EAD,M2caiSeg,CVC-ClinicDB,and UCL synthetic datasets.Experimental results demonstrate that the proposed network improves upon the baseline EfficientViT-B3 model by 75.4%in accuracy(Acc),while also enhancing runtime performance and storage efficiency.When compared with the complex DenseDescriptor feature extraction network,the difference in Acc is less than 7.22%,and IoU calculation results on specific datasets outperform complex dense models.Furthermore,this method increases the F1 score by 33.2%and accelerates runtime by 70.2%.It is noteworthy that the speed of CMMCAN surpasses that of comparative lightweight models,with feature extraction and matching performance comparable to existing complex models but with faster speed and higher cost-effectiveness.展开更多
Aiming at the problems of inaccuracy in detecting theαphase contour of TB6 titanium alloy.By combining computer vision technology with human vision mechanisms,the spatial characteristics of theαphase can be simulate...Aiming at the problems of inaccuracy in detecting theαphase contour of TB6 titanium alloy.By combining computer vision technology with human vision mechanisms,the spatial characteristics of theαphase can be simulated to obtain the contour accurately.Therefore,an algorithm forαphase contour detection of TB6 titanium alloy fused with multi-scale fretting features is proposed.Firstly,through the response of the classical receptive field model based on fretting and the suppression of new non-classical receptive field model based on fretting,the information maps of theαphase contour of the TB6 titanium alloy at different scales are obtained;then the information map of the smallest scale contour is used as a benchmark,the neighborhood is constructed to judge the deviation of other scale contour information,and the corresponding weight value is calculated;finally,Gaussian function is used to weight and fuse the deviation information,and the contour detection result of TB6 titanium alloyαphase is obtained.In the Visual Studio 2013 environment,484 metallographic images with different temperatures,strain rates,and magnifications were tested.The results show that the performance evaluation F value of the proposed algorithm is 0.915,which can effectively improve the accuracy ofαphase contour detection of TB6 titanium alloy.展开更多
In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract i...In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.展开更多
Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso...Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.展开更多
Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it cha...Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.展开更多
A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low freq...A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix （or matching result） reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.展开更多
Image matching technology is theoretically significant and practically promising in the field of autonomous navigation.Addressing shortcomings of existing image matching navigation technologies,the concept of high-dim...Image matching technology is theoretically significant and practically promising in the field of autonomous navigation.Addressing shortcomings of existing image matching navigation technologies,the concept of high-dimensional combined feature is presented based on sequence image matching navigation.To balance between the distribution of high-dimensional combined features and the shortcomings of the only use of geometric relations,we propose a method based on Delaunay triangulation to improve the feature,and add the regional characteristics of the features together with their geometric characteristics.Finally,k-nearest neighbor(KNN)algorithm is adopted to optimize searching process.Simulation results show that the matching can be realized at the rotation angle of-8°to 8°and the scale factor of 0.9 to 1.1,and when the image size is 160 pixel×160 pixel,the matching time is less than 0.5 s.Therefore,the proposed algorithm can substantially reduce computational complexity,improve the matching speed,and exhibit robustness to the rotation and scale changes.展开更多
Due to requirements and necessities in digital image research, image matching is considered as a key, essential and complicating point especially for machine learning. According to its convenience and facility, the mo...Due to requirements and necessities in digital image research, image matching is considered as a key, essential and complicating point especially for machine learning. According to its convenience and facility, the most applied algorithm for image feature point extraction and matching is Speeded-Up Robust Feature (SURF). The enhancement for scale invariant feature transform (SIFT) algorithm promotes the effectiveness of the algorithm as well as facilitates the possibility, while the application of the algorithm is being applied in a present time computer vision system. In this research work, the aim of SURF algorithm is to extract image features, and we have incorporated RANSAC algorithm to filter matching points. The images were juxtaposed and asserted experiments utilizing pertinent image improvement methods. The idea based on merging improvement technology through SURF algorithm is put forward to get better quality of feature points matching the efficiency and appropriate image improvement methods are adopted for different feature images which are compared and verified by experiments. Some results have been explained there which are the effects of lighting on the underexposed and overexposed images.展开更多
In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on m...In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.展开更多
Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of it.However,for high-resolution aerial images,there are usually problems such as long time,mis...Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of it.However,for high-resolution aerial images,there are usually problems such as long time,mismatching and sparse feature pairs using traditional algorithms.Therefore,an algorithm is proposed to realize fast,accurate and dense feature matching.The algorithm consists of four steps.Firstly,we achieve a balance between the feature matching time and the number of matching pairs by appropriately reducing the image resolution.Secondly,to realize further screening of the mismatches,a feature screening algorithm based on similarity judgment or local optimization is proposed.Thirdly,to make the algorithm more widely applicable,we combine the results of different algorithms to get dense results.Finally,all matching feature pairs in the low-resolution images are restored to the original images.Comparisons between the original algorithms and our algorithm show that the proposed algorithm can effectively reduce the matching time,screen out the mismatches,and improve the number of matches.展开更多
In photogrammetry and remote sensing, image matching is a basic and crucial process for automatic DEM generation. In this paper we presented a image relaxation matching method based on feature points. This method can ...In photogrammetry and remote sensing, image matching is a basic and crucial process for automatic DEM generation. In this paper we presented a image relaxation matching method based on feature points. This method can be considered as an extention of regular grid point based matching. It avoids the shortcome of grid point based matching. For example, with this method, we can avoid low or even no texture area where errors frequently appear in cross correlaton matching. In the mean while, it makes full use of some mature techniques such as probability relaxation, image pyramid and the like which have already been successfully used in grid point matching process. Application of the technique to DEM generaton in different regions proved that it is more reasonable and reliable.展开更多
The scene matching navigation is a research focus in the field of autonomous navigation,but the real-time performance of image matching algorithm is difficult to meet the needs of real navigation systems.Therefore,thi...The scene matching navigation is a research focus in the field of autonomous navigation,but the real-time performance of image matching algorithm is difficult to meet the needs of real navigation systems.Therefore,this paper proposes a fast image matching algorithm.The algorithm improves the traditional line segment extraction algorithm and combines with the Delaunay triangulation method.By combining the geometric features of points and lines,the image feature redundancy is reduced.Then,the error with confidence criterion is analyzed and the matching process is completed.The simulation results show that the proposed algorithm can still work within 3°rotation and small scale variation.In addition,the matching time is less than 0.5 s when the image size is 256 pixel×256 pixel.The proposed algorithm is suitable for autonomous navigation systems with multiple feature distribution and higher real-time requirements.展开更多
Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important dire...Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important direction and has achieved fruitful results.In this paper,amethodof soft tissue surface feature tracking basedonadepthmatching network is proposed.This method is described based on the triangular matching algorithm.First,we construct a self-made sample set for training the depth matching network from the first N frames of speckle matching data obtained by the triangle matching algorithm.The depth matching network is pre-trained on the ORL face data set and then trained on the self-made training set.After the training,the speckle matching is carried out in the subsequent frames to obtain the speckle matching matrix between the subsequent frames and the first frame.From this matrix,the inter-frame feature matching results can be obtained.In this way,the inter-frame speckle tracking is completed.On this basis,the results of this method are compared with the matching results based on the convolutional neural network.The experimental results show that the proposed method has higher matching accuracy.In particular,the accuracy of the MNIST handwritten data set has reached more than 90%.展开更多
Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (...Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.展开更多
The existing multi-source contour matching studies have focused on the matching methods with consideration of topological relations and similarity measurement based on spatial Euclidean distance,while it is lack of ta...The existing multi-source contour matching studies have focused on the matching methods with consideration of topological relations and similarity measurement based on spatial Euclidean distance,while it is lack of taking the contour geometric features into account,which may lead to mismatching in map boundaries and areas with intensive contours or extreme terrain changes.In light of this,it is put forward that a matching strategy from coarse to precious based on the contour geometric features.The proposed matching strategy can be described as follows.Firstly,the point sequence is converted to feature sequence according to a feature descriptive function based on curvature and angle of normal vector.Then the level of similarity among multi-source contours is calculated by using the longest common subsequence solution.Accordingly,the identical contours could be matched based on the above calculated results.In the experiment for the proposed method,the reliability and efficiency of the matching method are verified using simulative datasets and real datasets respectively.It has been proved that the proposed contour matching strategy has a high matching precision and good applicability.展开更多
In this paper,we propose a new method to achieve automatic matching of multi-scale roads under the constraints of smaller scale data.The matching process is:Firstly,meshes are extracted from two different scales road ...In this paper,we propose a new method to achieve automatic matching of multi-scale roads under the constraints of smaller scale data.The matching process is:Firstly,meshes are extracted from two different scales road data.Secondly,several basic meshes in the larger scale road network will be merged into a composite one which is matched with one mesh in the smaller scale road network,to complete the N∶1(N>1)and 1∶1 matching.Thirdly,meshes of the two different scale road data with M∶N(M>1,N>1)matching relationships will be matched.Finally,roads will be classified into two categories under the constraints of meshes:mesh boundary roads and mesh internal roads,and then matchings between the two scales meshes will be carried out within their own categories according to the matching relationships.The results show that roads of different scales will be more precisely matched using the proposed method.展开更多
Feature matching has been frequently applied in computer vision and pattern recognition.In this paper,the authors propose a fast feature matching algorithm for vector-based feature.Their algorithm searches r-nearest n...Feature matching has been frequently applied in computer vision and pattern recognition.In this paper,the authors propose a fast feature matching algorithm for vector-based feature.Their algorithm searches r-nearest neighborhood clusters for the query point after a k-means clustering,which shows higher efficiency in three aspects.First,it does not reformat the data into a complex tree,so it shortens the construction time twice.Second,their algorithm adopts the r-nearest searching strategy to increase the probability to contain the exact nearest neighbor(NN)and take this NN as the global one,which can accelerate the searching speed by 170 times.Third,they set up a matching rule with a variant distance threshold to eliminate wrong matches.Their algorithm has been tested on large SIFT databases with different scales and compared with two widely applied algorithms,priority search km-tree and random kd-tree.The results show that their algorithm outperforms both algorithms in terms of speed up over linear search,and consumes less time than km-tree.Finally,they carry out the CFI test based on ISKLRS database using their algorithm.The test results show that their algorithm can greatly improve the recognition speed without affecting the recognition rate.展开更多
基金supported by National Natural Science Foundation of China(No.61862037)Lanzhou Jiaotong University Tianyou Innovation Team Project(No.TY202002)。
文摘To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.
基金supported in part by the National Natural Science Foundation of China(Grant No.62062003)Natural Science Foundation of Ningxia(Grant No.2023AAC03293).
文摘Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.
基金supported by the National Natural Science Foundation of China (62276192)。
文摘Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.
基金This work was supported by Science and Technology Cooperation Special Project of Shijiazhuang(SJZZXA23005).
文摘In minimally invasive surgery,endoscopes or laparoscopes equipped with miniature cameras and tools are used to enter the human body for therapeutic purposes through small incisions or natural cavities.However,in clinical operating environments,endoscopic images often suffer from challenges such as low texture,uneven illumination,and non-rigid structures,which affect feature observation and extraction.This can severely impact surgical navigation or clinical diagnosis due to missing feature points in endoscopic images,leading to treatment and postoperative recovery issues for patients.To address these challenges,this paper introduces,for the first time,a Cross-Channel Multi-Modal Adaptive Spatial Feature Fusion(ASFF)module based on the lightweight architecture of EfficientViT.Additionally,a novel lightweight feature extraction and matching network based on attention mechanism is proposed.This network dynamically adjusts attention weights for cross-modal information from grayscale images and optical flow images through a dual-branch Siamese network.It extracts static and dynamic information features ranging from low-level to high-level,and from local to global,ensuring robust feature extraction across different widths,noise levels,and blur scenarios.Global and local matching are performed through a multi-level cascaded attention mechanism,with cross-channel attention introduced to simultaneously extract low-level and high-level features.Extensive ablation experiments and comparative studies are conducted on the HyperKvasir,EAD,M2caiSeg,CVC-ClinicDB,and UCL synthetic datasets.Experimental results demonstrate that the proposed network improves upon the baseline EfficientViT-B3 model by 75.4%in accuracy(Acc),while also enhancing runtime performance and storage efficiency.When compared with the complex DenseDescriptor feature extraction network,the difference in Acc is less than 7.22%,and IoU calculation results on specific datasets outperform complex dense models.Furthermore,this method increases the F1 score by 33.2%and accelerates runtime by 70.2%.It is noteworthy that the speed of CMMCAN surpasses that of comparative lightweight models,with feature extraction and matching performance comparable to existing complex models but with faster speed and higher cost-effectiveness.
基金Supported by Hebei Provincial Key Laboratory for Software Engineering(Grant No.22567637H)the"Rail Vehicle Application Engineering"National International Science and Technology Cooperation Base Open Project Fund(Grant No.BMRV21KF09).
文摘Aiming at the problems of inaccuracy in detecting theαphase contour of TB6 titanium alloy.By combining computer vision technology with human vision mechanisms,the spatial characteristics of theαphase can be simulated to obtain the contour accurately.Therefore,an algorithm forαphase contour detection of TB6 titanium alloy fused with multi-scale fretting features is proposed.Firstly,through the response of the classical receptive field model based on fretting and the suppression of new non-classical receptive field model based on fretting,the information maps of theαphase contour of the TB6 titanium alloy at different scales are obtained;then the information map of the smallest scale contour is used as a benchmark,the neighborhood is constructed to judge the deviation of other scale contour information,and the corresponding weight value is calculated;finally,Gaussian function is used to weight and fuse the deviation information,and the contour detection result of TB6 titanium alloyαphase is obtained.In the Visual Studio 2013 environment,484 metallographic images with different temperatures,strain rates,and magnifications were tested.The results show that the performance evaluation F value of the proposed algorithm is 0.915,which can effectively improve the accuracy ofαphase contour detection of TB6 titanium alloy.
基金the Scientific Research Foundation of Liaoning Provincial Department of Education(No.LJKZ0139)the Program for Liaoning Excellent Talents in University(No.LR15045).
文摘In order to improve the models capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is proposed.The metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric space.To sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature extraction.Additionally,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the experiment.The loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric space.Experimental evaluations are conducted on small-sample datasets mini-ImageNet and CUB200-2011.The method in this paper can achieve higher classification accuracy.Specifically,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two datasets.Moreover,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.
文摘Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.
基金supported in part by the National Natural Science Foundation of China under Grants 62463002,62062021 and 62473033in part by the Guiyang Scientific Plan Project[2023]48–11,in part by QKHZYD[2023]010 Guizhou Province Science and Technology Innovation Base Construction Project“Key Laboratory Construction of Intelligent Mountain Agricultural Equipment”.
文摘Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.
基金supported by the National Natural Science Foundation of China (6117212711071002)+1 种基金the Specialized Research Fund for the Doctoral Program of Higher Education (20113401110006)the Innovative Research Team of 211 Project in Anhui University (KJTD007A)
文摘A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix （or matching result） reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.
基金supported by the National Natural Science Foundations of China(Nos.51205193,51475221)
文摘Image matching technology is theoretically significant and practically promising in the field of autonomous navigation.Addressing shortcomings of existing image matching navigation technologies,the concept of high-dimensional combined feature is presented based on sequence image matching navigation.To balance between the distribution of high-dimensional combined features and the shortcomings of the only use of geometric relations,we propose a method based on Delaunay triangulation to improve the feature,and add the regional characteristics of the features together with their geometric characteristics.Finally,k-nearest neighbor(KNN)algorithm is adopted to optimize searching process.Simulation results show that the matching can be realized at the rotation angle of-8°to 8°and the scale factor of 0.9 to 1.1,and when the image size is 160 pixel×160 pixel,the matching time is less than 0.5 s.Therefore,the proposed algorithm can substantially reduce computational complexity,improve the matching speed,and exhibit robustness to the rotation and scale changes.
文摘Due to requirements and necessities in digital image research, image matching is considered as a key, essential and complicating point especially for machine learning. According to its convenience and facility, the most applied algorithm for image feature point extraction and matching is Speeded-Up Robust Feature (SURF). The enhancement for scale invariant feature transform (SIFT) algorithm promotes the effectiveness of the algorithm as well as facilitates the possibility, while the application of the algorithm is being applied in a present time computer vision system. In this research work, the aim of SURF algorithm is to extract image features, and we have incorporated RANSAC algorithm to filter matching points. The images were juxtaposed and asserted experiments utilizing pertinent image improvement methods. The idea based on merging improvement technology through SURF algorithm is put forward to get better quality of feature points matching the efficiency and appropriate image improvement methods are adopted for different feature images which are compared and verified by experiments. Some results have been explained there which are the effects of lighting on the underexposed and overexposed images.
基金Project(61301095)supported by the National Natural Science Foundation of ChinaProject(QC2012C070)supported by Heilongjiang Provincial Natural Science Foundation for the Youth,ChinaProjects(HEUCF130807,HEUCFZ1129)supported by the Fundamental Research Funds for the Central Universities of China
文摘In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.
基金This work was supported by the Equipment Pre-Research Foundation of China(6140001020310).
文摘Three-dimensional(3D)reconstruction based on aerial images has broad prospects,and feature matching is an important step of it.However,for high-resolution aerial images,there are usually problems such as long time,mismatching and sparse feature pairs using traditional algorithms.Therefore,an algorithm is proposed to realize fast,accurate and dense feature matching.The algorithm consists of four steps.Firstly,we achieve a balance between the feature matching time and the number of matching pairs by appropriately reducing the image resolution.Secondly,to realize further screening of the mismatches,a feature screening algorithm based on similarity judgment or local optimization is proposed.Thirdly,to make the algorithm more widely applicable,we combine the results of different algorithms to get dense results.Finally,all matching feature pairs in the low-resolution images are restored to the original images.Comparisons between the original algorithms and our algorithm show that the proposed algorithm can effectively reduce the matching time,screen out the mismatches,and improve the number of matches.
文摘In photogrammetry and remote sensing, image matching is a basic and crucial process for automatic DEM generation. In this paper we presented a image relaxation matching method based on feature points. This method can be considered as an extention of regular grid point based matching. It avoids the shortcome of grid point based matching. For example, with this method, we can avoid low or even no texture area where errors frequently appear in cross correlaton matching. In the mean while, it makes full use of some mature techniques such as probability relaxation, image pyramid and the like which have already been successfully used in grid point matching process. Application of the technique to DEM generaton in different regions proved that it is more reasonable and reliable.
基金supported by the Fundation of Graduate Innovation Center in Nanjing University of Aeronautics and Astronautics (No.kfjj20191506)
文摘The scene matching navigation is a research focus in the field of autonomous navigation,but the real-time performance of image matching algorithm is difficult to meet the needs of real navigation systems.Therefore,this paper proposes a fast image matching algorithm.The algorithm improves the traditional line segment extraction algorithm and combines with the Delaunay triangulation method.By combining the geometric features of points and lines,the image feature redundancy is reduced.Then,the error with confidence criterion is analyzed and the matching process is completed.The simulation results show that the proposed algorithm can still work within 3°rotation and small scale variation.In addition,the matching time is less than 0.5 s when the image size is 256 pixel×256 pixel.The proposed algorithm is suitable for autonomous navigation systems with multiple feature distribution and higher real-time requirements.
基金supported by the Sichuan Science and Technology Program (Grant:2021YFQ0003,Acquired by Wenfeng Zheng).
文摘Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important direction and has achieved fruitful results.In this paper,amethodof soft tissue surface feature tracking basedonadepthmatching network is proposed.This method is described based on the triangular matching algorithm.First,we construct a self-made sample set for training the depth matching network from the first N frames of speckle matching data obtained by the triangle matching algorithm.The depth matching network is pre-trained on the ORL face data set and then trained on the self-made training set.After the training,the speckle matching is carried out in the subsequent frames to obtain the speckle matching matrix between the subsequent frames and the first frame.From this matrix,the inter-frame feature matching results can be obtained.In this way,the inter-frame speckle tracking is completed.On this basis,the results of this method are compared with the matching results based on the convolutional neural network.The experimental results show that the proposed method has higher matching accuracy.In particular,the accuracy of the MNIST handwritten data set has reached more than 90%.
文摘Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.
基金National Science Foundation of China(Nos.41801388,41901397)。
文摘The existing multi-source contour matching studies have focused on the matching methods with consideration of topological relations and similarity measurement based on spatial Euclidean distance,while it is lack of taking the contour geometric features into account,which may lead to mismatching in map boundaries and areas with intensive contours or extreme terrain changes.In light of this,it is put forward that a matching strategy from coarse to precious based on the contour geometric features.The proposed matching strategy can be described as follows.Firstly,the point sequence is converted to feature sequence according to a feature descriptive function based on curvature and angle of normal vector.Then the level of similarity among multi-source contours is calculated by using the longest common subsequence solution.Accordingly,the identical contours could be matched based on the above calculated results.In the experiment for the proposed method,the reliability and efficiency of the matching method are verified using simulative datasets and real datasets respectively.It has been proved that the proposed contour matching strategy has a high matching precision and good applicability.
基金The National Natural Science Foundation of China(Nos.4110136241471386)。
文摘In this paper,we propose a new method to achieve automatic matching of multi-scale roads under the constraints of smaller scale data.The matching process is:Firstly,meshes are extracted from two different scales road data.Secondly,several basic meshes in the larger scale road network will be merged into a composite one which is matched with one mesh in the smaller scale road network,to complete the N∶1(N>1)and 1∶1 matching.Thirdly,meshes of the two different scale road data with M∶N(M>1,N>1)matching relationships will be matched.Finally,roads will be classified into two categories under the constraints of meshes:mesh boundary roads and mesh internal roads,and then matchings between the two scales meshes will be carried out within their own categories according to the matching relationships.The results show that roads of different scales will be more precisely matched using the proposed method.
文摘Feature matching has been frequently applied in computer vision and pattern recognition.In this paper,the authors propose a fast feature matching algorithm for vector-based feature.Their algorithm searches r-nearest neighborhood clusters for the query point after a k-means clustering,which shows higher efficiency in three aspects.First,it does not reformat the data into a complex tree,so it shortens the construction time twice.Second,their algorithm adopts the r-nearest searching strategy to increase the probability to contain the exact nearest neighbor(NN)and take this NN as the global one,which can accelerate the searching speed by 170 times.Third,they set up a matching rule with a variant distance threshold to eliminate wrong matches.Their algorithm has been tested on large SIFT databases with different scales and compared with two widely applied algorithms,priority search km-tree and random kd-tree.The results show that their algorithm outperforms both algorithms in terms of speed up over linear search,and consumes less time than km-tree.Finally,they carry out the CFI test based on ISKLRS database using their algorithm.The test results show that their algorithm can greatly improve the recognition speed without affecting the recognition rate.
