A hybrid hint-based and graph-based framework for recognition of interacting milling features

Among the existing feature recognition approaches, graph-based and hint-based approaches are more popular. While graph-based algorithms are quite successful in recognizing isolated features, hint based approaches intrinsically show better performance in handling interacting features. In this paper, feature traces as defined by hint based approaches are implemented and represented in concave graph forms helping the recognition of interacting features with less computational effort. The concave graphs are also used to handle curved 2.5D features while many of the previous graph-based approaches have merely dealt with polyhedral features. The method begins by decomposing the part graph to generate a set of concave sub-graphs. A feature is then recognized based on the properties of the whole concave graph or the properties of its nodes. Graph-based approaches are not intrinsically suitable to provide volumetric representation for the features, but the complete boundary information of a feature can be more effectively obtained volumetrically. Therefore, in this research a method to generate feature volumes for the recognized sub-graphs is also proposed. The approach shows better recognition ability than sub-graph isomorphism methods.     

隐式特征和循环神经网络的多声部音乐生成系统

音乐生成是一种使用算法来生成音乐序列的研究。本文针对音乐样本特征提取以及自动作曲问题提出了一种基于音乐隐式特征和循环神经网络（recurrent neural network, RNN）的多声部音乐生成算法。该方法通过使用栈式自编码器对多声部音乐序列每个时间步的音符隐式特征进行提取,结合长短期记忆循环神经网络（long short-term memory, LSTM）,以序列预测的方式搭建了基于隐式特征的音乐生成模型。仿真结果表明,该音乐生成算法在使用相同风格的音乐数据训练后,得到的模型可以生成旋律与和弦匹配较好的多声部音乐数据。     

Volumetric feature recognition for machining components with freeform surfaces

This paper describes a procedure for the extraction of features of a part containing a combination of 2.5D features and freeform surfaces. This work invokes a previous algorithm that was designed to recognize machining features from 2.5D parts destined to be machined on a 3-axis milling machine. The essence of that algorithm was a volume decomposition based on a recursive descent into the part, yielding a feature graph that captured both the geometry and the spatial relationships of the features. This work augments the previous algorithm with the ability to handle a limited class of components having freeform surfaces. Freeform features are defined similar to the 2.5D features as comprising a planar contour, but substituting a bottom freeform surface for the depth. Covering faces, defined as projection of the freeform surface on the faces of the bounding box of the surface, are used as equivalent planar faces for performing the recursive descent. Inter-feature open edges are used to signal the relationship between the freeform feature and other neighboring features. Examples of molds and components that were machined using the proposed algorithms are also presented.     

多维注意力特征聚合立体匹配算法

现有基于深度学习的立体匹配算法在学习推理过程中缺乏有效信息交互, 而特征提取和代价聚合两个子模块的特征维度存在差异, 导致注意力方法在立体匹配网络中应用较少、方式单一. 针对上述问题, 本文提出了一种多维注意力特征聚合立体匹配算法. 设计2D注意力残差模块, 通过在原始残差网络中引入无降维自适应2D注意力残差单元, 局部跨通道交互并提取显著信息, 为匹配代价计算提供丰富有效的特征. 构建3D注意力沙漏聚合模块, 以堆叠沙漏结构为骨干设计3D注意力沙漏单元, 捕获多尺度几何上下文信息, 进一步扩展多维注意力机制, 自适应聚合和重新校准来自不同网络深度的代价体. 在三大标准数据集上进行评估, 并与相关算法对比, 实验结果表明所提算法具有更高的预测视差精度, 且在无遮挡的显著对象上效果更佳.     

三维数字牙颌模型分析诊断系统设计

利用三维测量技术获取含咬合信息的数字牙颌模型,建立网格包围盒层次表示结构,并在其基础上实现网格单元快速拾取框架,结合特征提取算法,实现模型分析的常用功能;参考正常合数据库中的标准值生成初步诊断报表．应用该系统有助于提高正畸临床的诊断水平。     

Robot vision using a feature search strategy generated from a 3Dobject model

A robot vision system that automatically generates an object recognition strategy from a 3D model and recognizes the object using this strategy is presented. The appearance of an object from various viewpoints is described in terms of visible 2D features such as parallel lines and ellipses. Features are then ranked according to the number of viewpoints from which they are visible. The rank and feature extraction cost of each feature are used to generate a treelike strategy graph. This graph gives an efficient feature search order when the viewpoint is unknown, starting with commonly occurring features and ending with features specific to a certain viewpoint. The system searches for features in the order indicated by the graph. After detection, the system compares a lines representation generated from the 3D model with the image features to localize the object. Perspective projection is used in the localization process to obtain the precise position and attitude of the object, whereas orthographic projection is used in the strategy generation process to allow symbolic manipulation. Experimental results are given     

Feature‐Preserving Displacement Mapping With Graphics Processing Unit (GPU) Tessellation

Displacement mapping reconstructs a high‐frequency surface by adding geometric details encoded in the displacement map to the coarse base surface. In the context of hardware tessellation supported by GPUs, this paper aims at feature‐preserving surface reconstruction, and proposes the generation of a displacement map that displaces more vertices towards the higher‐frequency feature parts of the target mesh. In order to generate the feature‐preserving displacement map, surface features of the target mesh are estimated, and then the target mesh is parametrized and sampled using the features. At run time, the base surface is semi‐uniformly tessellated by hardware, and then the vertices of the tessellated mesh are displaced non‐uniformly along the 3‐D vectors stored in the displacement map. The experimental results show that the surfaces reconstructed by the proposed method are of a higher quality than those reconstructed by other methods.     

Convolutional deep learning for 3D object retrieval

In recent years, with the development of 3D technologies, 3D model retrieval has become a hot topic. The key point of 3D model retrieval is to extract robust feature for 3D model representation. In order to improve the effectiveness of method on 3D model retrieval, this paper proposes a feature extraction model based on convolutional neural networks (CNN). First, we extract a set of 2D images from 3D model to represent each 3D object. SIFT detector is utilized to detect interesting points from each 2D image and extract interesting patches to represent local information of each 3D model. X-means is leveraged to generate the CNN filters. Second, a single CNN layer learns low-level features which are then given as inputs to multiple recursive neural networks (RNN) in order to compose higher order features. RNNs can generate the final feature for 2D image representation. Finally, nearest neighbor is used to compute the similarity between different 3D models in order to handle the retrieval problem. Extensive comparison experiments were on the popular ETH and MV-RED 3D model datasets. The results demonstrate the superiority of the proposed method.     

3D clipping algorithm for feature mapping across domains

This paper describes an algorithm based on 3D clipping for mapping feature models across domains. The problem is motivated by the need to identify feature models corresponding to different domains. Feature mapping (also referred to as feature conversion) involves obtaining a feature model in one domain given a feature model in another. This is in contrast to feature extraction which works from the boundary representation of the part. Most techniques for feature mapping have focused on obtaining negative feature models only. We propose an algorithm that can convert a feature model with mixed features (both positive and negative) to a feature model containing either only positive or only negative features.The input to the algorithm is a feature model in one domain. The algorithm for mapping this model to another feature model is based on classification of faces of features in the model and 3D clipping. 3D clipping refers to the splitting of a solid by a surface. The feature mapping process involves three major steps. In the first step, faces forming the features in the input model are classified with respect to one another. The spatial arrangement of faces is used next to derive the dependency relationship amongst features in the input model and a Feature Relationship Graph (FRG) is constructed. In the second step, using the FRG, features are clustered and interactions between features (if any) are resolved. In the final step, the 3D clipping algorithm is used to determine the volumes corresponding to the features in the target domain. These volumes are then classified to identify the features for obtaining the feature model in the target domain. Multiple feature sets (where possible) can be obtained by varying the sequence of faces used for clipping. Results of implementation are presented.     

CMOS电路开关级测试生成的一种新算法

本文提出了一种新的CMOS电路开关级测试生成算法,该算法以Hayes模型为基础,以开关级代数为工具,充分利用CMOS电路自身的特点,生成CMOS电路的完全测试集,这种算法较之于已有的算法简单而有效,检测CMOS电路的常开型故障需一对测试码,本文给出了一种简单的求一对稳健测试码的方法,基于这种算法,我们开发了一个测试自动生成软件。     

A new hybrid feature selection approach using feature association map for supervised and unsupervised classification

Feature selection, both for supervised as well as for unsupervised classification is a relevant problem pursued by researchers for decades. There are multiple benchmark algorithms based on filter, wrapper and hybrid methods. These algorithms adopt different techniques which vary from traditional search-based techniques to more advanced nature inspired algorithm based techniques. In this paper, a hybrid feature selection algorithm using graph-based technique has been proposed. The proposed algorithm has used the concept of Feature Association Map (FAM) as an underlying foundation. It has used graph-theoretic principles of minimal vertex cover and maximal independent set to derive feature subset. This algorithm applies to both supervised and unsupervised classification. The performance of the proposed algorithm has been compared with several benchmark supervised and unsupervised feature selection algorithms and found to be better than them. Also, the proposed algorithm is less computationally expensive and hence has taken less execution time for the publicly available datasets used in the experiments, which include high-dimensional datasets.     

一种基于Curv-SAE特征融合的人脸降维和识别方法

相比于传统的降维算法,深度学习中的栈式自编码器(Stacked Autoencoder,SAE)能够有效地学习特征并实现高效降维,然而对输入特征极其敏感。第二代离散曲波变换(Discrete Curvelet Transform,DCT)能够提取出人脸的各向信息(包含边缘和概貌特征),确保SAE的输入特征充分,从而弥补了其不足。因此,提出了一种基于Curv-SAE特征融合的人脸识别降维算法,即对人脸图像进行DCT得到特征脸并将其作为SAE的输入特征进行训练,特征融合后将其输入到分类器中进行识别。在ORL和FERET人脸数据库上的实验表明,与小波变换相比,曲波的特征信息更丰富;与传统的降维算法相比,SAE的特征表达更充分且识别精度更高。     

On classification with incomplete data

We address the incomplete-data problem in which feature vectors to be classified are missing data (features). A (supervised) logistic regression algorithm for the classification of incomplete data is developed. Single or multiple imputation for the missing data is avoided by performing analytic integration with an estimated conditional density function (conditioned on the observed data). Conditional density functions are estimated using a Gaussian mixture model (GMM), with parameter estimation performed using both expectation-maximization (EM) and variational Bayesian EM (VB-EM). The proposed supervised algorithm is then extended to the semisupervised case by incorporating graph-based regularization. The semisupervised algorithm utilizes all available data-both incomplete and complete, as well as labeled and unlabeled. Experimental results of the proposed classification algorithms are shown     

3D fingerprint reconstruction system using feature correspondences and prior estimated finger model

The paper studies a 3D fingerprint reconstruction technique based on multi-view touchless fingerprint images. This technique offers a solution for 3D fingerprint image generation and application when only multi-view 2D images are available. However, the difficulties and stresses of 3D fingerprint reconstruction are the establishment of feature correspondences based on 2D touchless fingerprint images and the estimation of the finger shape model. In this paper, several popular used features, such as scale invariant feature transformation (SIFT) feature, ridge feature and minutiae, are employed for correspondences establishment. To extract these fingerprint features accurately, an improved fingerprint enhancement method has been proposed by polishing orientation and ridge frequency maps according to the characteristics of 2D touchless fingerprint images. Therefore, correspondences can be established by adopting hierarchical fingerprint matching approaches. Through an analysis of 440 3D point cloud finger data (220 fingers, 2 pictures each) collected by a 3D scanning technique, i.e., the structured light illumination (SLI) method, the finger shape model is estimated. It is found that the binary quadratic function is more suitable for the finger shape model than the other mixed model tested in this paper. In our experiments, the reconstruction accuracy is illustrated by constructing a cylinder. Furthermore, results obtained from different fingerprint feature correspondences are analyzed and compared to show which features are more suitable for 3D fingerprint images generation.     

结合可变形卷积与双边网格的立体匹配网络

双目立体匹配被广泛应用于无人驾驶、机器人导航、增强现实等三维重建领域。在基于深度学习的立体匹配网络中采用多尺度2D卷积进行代价聚合,存在对目标边缘处的视差预测鲁棒性较差以及特征提取性能较低的问题。提出将可变形卷积与双边网格相结合的立体匹配网络。通过改进的特征金字塔网络进行特征提取,并将注意力特征增强、注意力机制、Meta-ACON激活函数引入到改进的特征金字塔网络中,以充分提取图像特征并减少语义信息丢失,从而提升特征提取性能。利用互相关层进行匹配计算,获得多尺度3D代价卷,采用2D可变形卷积代价聚合结构对多尺度3D代价卷进行聚合,以解决边缘膨胀问题,使用双边网格对聚合后的低分辨率代价卷进行上采样,经过视差回归得到视差图。实验结果表明,该网络在Scene Flow数据集中的端点误差为0.75,相比AANet降低13.8%,在KITTI2012数据集中3px的非遮挡区域误差率为1.81%,能准确预测目标边缘及小区域处的视差。     

基于视觉注意力分析的3D内容生成方法

由于在某些特殊场景中获取深度线索的难度较高,使得已有3D内容生成方法的应用受到限制.为此,以显著图代替深度图进行2D-3D转换,提出一种3D内容生成方法.使用全卷积网络(FCN)生成粗糙的显著图,通过条件随机场对FCN的输出结果进行优化.实验结果表明,该方法可以解决现有方法中因使用低等级特征进行视觉注意力分析而导致显著图质量不高的问题,且能够生成具有良好视觉效果的3D内容.     

A fast registration algorithm of rock point cloud based on spherical projection and feature extraction

Point cloud registration is an essential step in the process of 3D reconstruction. In this paper, a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP) algorithm. In our proposed algorithm, the point cloud data of single station scanner is transformed into digital images by spherical polar coordinates, then image features are extracted and edge points are removed, the features used in this algorithm is scale-invariant feature transform (SIFT). By analyzing the corresponding relationship between digital images and 3D points, the 3D feature points are extracted, from which we can search for the two-way correspondence as candidates. After the false matches are eliminated by the exhaustive search method based on random sampling, the transformation is computed via the Levenberg-Marquardt-Iterative Closest Point (LM-ICP) algorithm. Experiments on real data of rock mass show that the proposed algorithm has the similar accuracy and better registration efficiency compared with the ICP algorithm and other algorithms.     

Generating multiple alternative clusterings via globally optimal subspaces

Clustering analysis is important for exploring complex datasets. Alternative clustering analysis is an emerging subfield involving techniques for the generation of multiple different clusterings, allowing the data to be viewed from different perspectives. We present two new algorithms for alternative clustering generation. A distinctive feature of our algorithms is their principled formulation of an objective function, facilitating the discovery of a subspace satisfying natural quality and orthogonality criteria. The first algorithm is a regularization of the Principal Components analysis method, whereas the second is a regularization of graph-based dimension reduction. In both cases, we demonstrate a globally optimum subspace solution can be computed. Experimental evaluation shows our techniques are able to equal or outperform a range of existing methods.     

3-D Head Model Retrieval Using a Single Face View Query

In this paper, a novel 3D head model retrieval approach is proposed, in which only a single 2D face view query is required. The proposed approach will be important for multimedia application areas such as virtual world construction and game design, in which 3D virtual characters with a given set of facial features can be rapidly constructed based on 2D view queries, instead of having to generate each model anew. To achieve this objective, we construct an adaptive mapping through which each 2D view feature vector is associated with its corresponding 3D model feature vector. Given this estimated 3D model feature vector, similarity matching can then be performed in the 3D model feature space. To avoid the explicit specification of the complex relationship between the 2D and 3D feature spaces, a neural network approach is adopted in which the required mapping is implicitly specified through a set of training examples. In addition, for efficient feature representation, principal component analysis (PCA) is adopted to achieve dimensionality reduction for facilitating both the mapping construction and the similarity matching process. Since the linear nature of the original PCA formulation may not be adequate to capture the complex characteristics of 3D models, we also consider the adoption of its nonlinear counterpart, i.e., the so-called kernel PCA approach, in this work. Experimental results show that the proposed approach is capable of successfully retrieving the set of 3D models which are similar in appearance to a given 2D face view.