Building Facade Point Clouds Segmentation Based on Optimal Dual-Scale Feature Descriptors

To address the current issues of inaccurate segmentation and the limited applicability of segmentation methods for building facades in point clouds, we propose a facade segmentation algorithm based on optimal dual-scale feature descriptors. First, we select the optimal dual-scale descriptors from a range of feature descriptors. Next, we segment the facade according to the threshold value of the chosen optimal dual-scale descriptors. Finally, we use RANSAC (Random Sample Consensus) to fit the segmented surface and optimize the fitting result. Experimental results show that, compared to commonly used facade segmentation algorithms, the proposed method yields more accurate segmentation results, providing a robust data foundation for subsequent 3D model reconstruction of buildings.

Novel 3D local feature descriptor of point clouds based on spatial voxel homogenization for feature matching

Obtaining a 3D feature description with high descriptiveness and robustness under complicated nuisances is a significant and challenging task in 3D feature matching.This paper proposes a novel feature description consisting of a stable local reference frame(LRF)and a feature descriptor based on local spatial voxels.First,an improved LRF was designed by incorporating distance weights into Z-and X-axis calculations.Subsequently,based on the LRF and voxel segmentation,a feature descriptor based on voxel homogenization was proposed.Moreover,uniform segmentation of cube voxels was performed,considering the eigenvalues of each voxel and its neighboring voxels,thereby enhancing the stability of the description.The performance of the descriptor was strictly tested and evaluated on three public datasets,which exhibited high descriptiveness,robustness,and superior performance compared with other current methods.Furthermore,the descriptor was applied to a 3D registration trial,and the results demonstrated the reliability of our approach.

Novel histogram descriptor for global feature extraction and description

A novel histogram descriptor for global feature extraction and description was presented. Three elementary primitives for a 2×2 pixel grid were defined. The complex primitives were computed by matrix transforms. These primitives and equivalence class were used for an image to compute the feature image that consisted of three elementary primitives. Histogram was used for the transformed image to extract and describe the features. Furthermore, comparisons were made among the novel histogram descriptor, the gray histogram and the edge histogram with regard to feature vector dimension and retrieval performance. The experimental results show that the novel histogram can not only reduce the effect of noise and illumination change, but also compute the feature vector of lower dimension. Furthermore, the system using the novel histogram has better retrieval performance.

Supervised Feature Learning for Offline Writer Identification Using VLAD and Double Power Normalization

As an indispensable part of identity authentication,offline writer identification plays a notable role in biology,forensics,and historical document analysis.However,identifying handwriting efficiently,stably,and quickly is still challenging due to the method of extracting and processing handwriting features.In this paper,we propose an efficient system to identify writers through handwritten images,which integrates local and global features from similar handwritten images.The local features are modeled by effective aggregate processing,and global features are extracted through transfer learning.Specifically,the proposed system employs a pre-trained Residual Network to mine the relationship between large image sets and specific handwritten images,while the vector of locally aggregated descriptors with double power normalization is employed in aggregating local and global features.Moreover,handwritten image segmentation,preprocessing,enhancement,optimization of neural network architecture,and normalization for local and global features are exploited,significantly improving system performance.The proposed system is evaluated on Computer Vision Lab(CVL)datasets and the International Conference on Document Analysis and Recognition(ICDAR)2013 datasets.The results show that it represents good generalizability and achieves state-of-the-art performance.Furthermore,the system performs better when training complete handwriting patches with the normalization method.The experimental result indicates that it’s significant to segment handwriting reasonably while dealing with handwriting overlap,which reduces visual burstiness.

A novel approach for feature extraction from a gamma‑ray energy spectrum based on image descriptor transferring for radionuclide identification

This study proposes a novel feature extraction approach for radionuclide identification to increase the precision of identification of the gamma-ray energy spectrum set.For easier utilization of the information contained in the spectra,the vectors of the gamma-ray energy spectra from Euclidean space,which are fingerprints of the different types of radionuclides,were mapped to matrices in the Banach space.Subsequently,to make the spectra in matrix form easier to apply to image-based deep learning frameworks,the matrices of the gamma-ray energy spectra were mapped to images in the RGB color space.A deep convolutional neural network(DCNN)model was constructed and trained on the ImageNet dataset.The mapped gamma-ray energy spectrum images were applied as inputs to the DCNN model,and the corresponding outputs of the convolution layers and fully connected layers were transferred as descriptors of the images to construct a new classification model for radionuclide identification.The transferred image descriptors consist of global and local features,where the activation vectors of fully connected layers are global features,and activations from convolution layers are local features.A series of comparative experiments between the transferred image descriptors,peak information,features extracted by the histogram of the oriented gradients(HOG),and scale-invariant feature transform(SIFT)using both synthetic and measured data were applied to 11 classical classifiers.The results demonstrate that although the gamma-ray energy spectrum images are completely unfamiliar to the DCNN model and have not been used in the pre-training process,the transferred image descriptors achieved good classification results.The global features have strong semantic information,which achieves an average accuracy of 92.76%and 94.86%on the synthetic dataset and measured dataset,respectively.The results of the statistical comparison of features demonstrate that the proposed approach outperforms the peak-searching-based method,HOG,and SIFT on the synthetic and measured datasets.

Modified Fourier descriptor for shape feature extraction

A modified Fourier descriptor was presented. Information from a local space can be used more efficiently. After the boundary pixel set of an object was computed, centroid distance approach was used to compute shape signature in the local space. A pair of shape signature and boundary pixel gray was used as a point in a feature space. Then, Fourier transform was used for composition of point information in the feature space so that the shape features could be computed. It is proved theoretically that the shape features from modified Fourier descriptors are invariant to translation, rotation, scaling, and change of start point. It is also testified by measuring the retrieval performance of the systems that the shape features from modified Fourier oescriptors are more discriminative than those from other Fourier descriptors.

Motion feature descriptor based moving objects segmentation

A novel moving objects segmentation method is proposed in this paper. A modified three dimensional recursive search （3DRS） algorithm is used in order to obtain motion information accurately. A motion feature descriptor （MFD） is designed to describe motion feature of each block in a picture based on motion intensity, motion in occlusion areas, and motion correlation among neighbouring blocks. Then, a fuzzy C-means clustering algorithm （FCM） is implemented based on those MFDs so as to segment moving objects. Moreover, a new parameter named as gathering degree is used to distinguish foreground moving objects and background motion. Experimental results demonstrate the effectiveness of the proposed method.

Topological distance-constrained feature descriptor learning model for vessel matching in coronary angiographies

Background Feature matching technology is vital to establish the association between virtual and real objects in virtual reality and augmented reality systems.Specifically,it provides them with the ability to match a dynamic scene.Many image matching methods,of which most are deep learning-based,have been proposed over the past few decades.However,vessel fracture,stenosis,artifacts,high background noise,and uneven vessel gray-scale make vessel matching in coronary angiography extremely difficult.Traditional matching methods perform poorly in this regard.Methods In this study,a topological distance-constrained feature descriptor learning model is proposed.This model regards the topology of the vasculature as the connection relationship of the centerline.The topological distance combines the geodesic distance between the input patches and constrains the descriptor network by maximizing the feature difference between connected and unconnected patches to obtain more useful potential feature relationships.Results Matching patches of different sequences of angiographic images are generated for the experiments.The matching accuracy and stability of the proposed method is superior to those of the existing models.Conclusions The proposed method solves the problem of matching coronary angiographies by generating a topological distance-constrained feature descriptor.

A Multisource Contour Matching Method Considering the Similarity of Geometric Features

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.

Recognition of 3-D Aircrafts by Fourier Descriptors with Fast and Efficient Library Search

Fourier descriptors are used as features for 3-D aircraft classification and pose determination from a 2-D image recorded at an arbitrary viewing angle. By the feature ranking of Fourier descriptors, a classification procedure based on the fast nearest neighbour rule is proposed to save the matching time of an unknown aircraft with a partial library search. The testing results of some typical examples indicate this method is generally applicable and efficient in 3-D aircraft recognition.

Active Shape Models Using Scale Invariant Feature Transform

A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.

Improving Protein Sequence Classification Performance Using Adjacent and Overlapped Segments on Existing Protein Descriptors

In protein sequence classification research, it is popular to convert a variable length sequence of protein into a fixed length numerical vector by using various descriptors, for instance, composition of k-mer composition. Such position-independent descriptors are useful since they are applicable to any length of sequence;however, positional information of subsequence is discarded even though it might have high contribution to classification performance. To solve this problem, we divided the original sequence into some segments, and then calculated the numerical features for them. It enables us to partially introduce positional information (for instance, compositions of serine in anterior and posterior segments of a sequence). Through comprehensive experiments on the number of segments and length of overlapping region, we found our classification approach with sequence segmentation and feature selection is effective to improve the performance. We evaluated our approach on three protein classification problems and achieved significant improvement in all cases which have a dataset with sufficient amino acid in each sequence. This result has shown the great potential of using additional segments in protein sequence classification to solve other sequence problems in bioinformatics.

Efficient Selection of Linearly Independent Atomic Features for Accurate Machine Learning Potentials

Machine learning potentials are promising in atomistic simulations due to their comparable accuracy to first-principles theory but much lower computational cost.However,the reliability,speed,and transferability of atomistic machine learning potentials depend strongly on the way atomic configurations are represented.A wise choice of descriptors used as input for the machine learning program is the key for a successful machine learning representation.Here we develop a simple and efficient strategy to automatically select an optimal set of linearly-independent atomic features out of a large pool of candidates,based on the correlations that are intrinsic to the training data.Through applications to the construction of embedded atom neural network potentials for several benchmark molecules with less redundant linearly-independent embedded density descriptors,we demonstrate the efficiency and accuracy of this new strategy.The proposed algorithm can greatly simplify the initial selection of atomic features and vastly improve the performance of the atomistic machine learning potentials.

Fast Image Retrieval of Textile Industrial Accessory Based on Multi-Feature Fusion

A hierarchical retrieval scheme of the accessory image database is proposed based on textile industrial accessory contour feature and region feature. At first smallest enclosed rectangle[1] feature (degree of accessory coordination) is used to filter the image database to decouple the image search scope. After the accessory contour information and region information are extracted, the fusion multi-feature of the centroid distance Fourier descriptor and distance distribution histogram is adopted to finish image retrieval accurately. All the features above are invariable under translation, scaling and rotation. Results from the test on the image database including 1,000 accessory images demonstrate that the method is effective and practical with high accuracy and fast speed.

Matching DSIFT Descriptors Extracted from CSLM Images

The matching of local descriptors represents at this moment a key tool in computer vision, with a wide variety of methods designed for tasks such as image classification, object recognition and tracking, image stitching, or data mining relying on it. Local feature description techniques are usually developed so as to provide invariance to photometric variations specific to the acquisition of natural images, but are nonetheless used in association with biomedical imaging as well. It has been previously shown that the matching of gradient based descriptors is affected by image modifications specific to Confocal Scanning Laser Microscopy (CSLM). In this paper we extend our previous work in this direction and show how specific acquisition or post-processing methods alleviate or accentuate this problem.

基于非线性各向异性滤波的图像特征匹配算法

图像特征匹配是增强现实系统中的关键技术,匹配精度是提升特征匹配性能的关键。提出了一种多尺度特征匹配加强算法(I-AKAZE),通过对非线性各向异性滤波过程中传导函数的改进,减缓图像梯度值大的区域非线性扩散速度,极大程度地保留了匹配图像的边缘特征;同时,结合改进的非线性量化加速稳健特征描述符(NLG-SURF),提高了描述符的识别率。实验结果表明I-AKAZE算法在Mikolajczyk数据集上的可重复性得分相比目前先进的AKAZE算法有着大幅度提升,对应的特征描述符的平均识别率提升8.4%,并且运行速度比经典的SIFT算法快约19%,算法整体在检测和描述阶段上的性能都有提升。

基于直线段检测和LT描述符的矿井图像线特征匹配算法

图像匹配是同步定位与地图构建(SLAM)技术中极为重要的一环,用于根据图像之间的变换关系确定相机位姿。基于线特征的图像匹配方法具有较强的鲁棒性和抗噪能力,更加适用于井下图像匹配,基于深度学习的线描述符对线段遮挡等场景具有较高的鲁棒性,性能优于传统描述符,但卷积神经网络架构的描述符将可变长度线段抽象为固定维进行描述,不利于线段长度及视差变化较大图像的匹配。针对上述问题,提出一种基于直线段检测和线描述符的矿井图像线特征匹配算法。在频域利用单参数同态滤波降低图像的照射分量,并增强反射分量,提升亮度及对比度;在YUV空间利用对比度受限的自适应直方图均衡化(CLAHE)算法对亮度分量进行均衡,使亮度分布更加均匀;变换至RGB空间提取直线段检测(LSD)线,引入一种基于Transformer架构的LT描述符构建LSD线的特征向量,最后完成线特征匹配。实验结果表明:该算法结合了同态滤波和CLAHE算法的优点,增强后图像的亮度适中,对比度良好,灰度分布均匀,增强效果优于单参数同态滤波算法、EnlightenGAN算法;该算法提取的线特征数较原图平均提升了32.92%,在不同相似纹理占比、不同程度旋转与平移变化的井下图像匹配中鲁棒性好,平均正确匹配数为61.75对,平均精度为86.83%,优于线二进制描述符(LBD)算法、LBD_NNDR算法、LT算法,能够满足矿井图像稳健匹配的需求。

基于关键特征增强机制的3D人脸识别

3D人脸识别是计算机视觉领域的重要组成部分,Pointnet依靠深度学习解决了点云的无序性,实现了3D点云的全局特征提取,但由于点云数据缺乏细节纹理,仅靠全局特征很难实现复杂情况下的人脸识别。针对以上问题,基于Pointnet提出了一种局部特征描述子,用于描述点云局部空间的几何特征,并引入关键特征增强机制,通过特征概率分布增强人脸关键信息,该机制能减少不必要特征对任务的干扰,有效提升模型的准确率。在公共数据集CASIA-3D、Lock3DFace、Bosphorus上进行实验测试,结果表明该方法能很好地应对表情变化、部分遮挡以及头部姿态的干扰,在弱光环境下其准确率高于RP-Net 1.1%,并具有良好的实时性。

具有局部自适应阈值的SIFT快速图像匹配算法

针对传统SIFT匹配算法复杂、特征冗余点多、难以满足实时性等问题,本文提出了一种具有局部自适应阈值的SIFT快速图像匹配算法。首先,所提方法在SIFT算法的基础上,对构建的高斯金字塔进行了优化,通过减少金字塔层数来消除冗余特征点以提高检测效率,并根据图像局部对比度来自适应提取FAST算法中的阈值从而实现高质量的特征点检测,筛选出鲁棒性较强的特征点进行更准确的匹配;其次,采用高斯圆形窗口建立32维降维特征向量,提高算法运行效率;最后,根据匹配特征点对之间的几何一致性对特征点进行提纯,有效减少误匹配。实验结果表明,本文方法在匹配精度和运算效率方面的综合表现均优于SIFT算法及其他对比匹配算法,相比传统的SIFT算法,匹配精度提高了约10%,算法运行时间缩短了约49%。在图像发生尺度、旋转以及光照变化的情况下,正确匹配率在93%以上。

LSVSH描述符:高鉴别强鲁棒的点云局部特征统计直方图

三维局部特征描述是三维计算机视觉中的重要任务.现实场景中包含噪声、遮挡和杂波等干扰,使得准确和鲁棒的三维局部特征描述具有很大的挑战性.为提高特征描述的性能,提出一种局部曲面变化统计直方图(local sur-face variation based statistics histogram,LSVSH)描述符.首先设计一种不依赖于局部参考轴(local reference axis,LRA)的新属性(称为曲率属性),增强描述符对LRA误差的稳健性;然后沿径向剖分局部空间,在每个子空间中统计3个角度属性和1个曲率属性生成LSVSH描述符,实现对局部曲面信息的全面稳健描述.在B3R,U3M,U3OR和QuLD这4个数据集上进行大量的实验,结果表明,LSVSH在4个数据集上的RPC下面积(the area under the recall-precision curve,AUCpr)值分别为0.95,0.70,0.54和0.10,优于现有的局部特征描述符的性能;在U3M数据集上的正确配准率和在U3OR数据集上的正确识别率分别达到70%和100%,验证了LSVSH应用于物体配准和识别任务上的有效性.