小波变换和特征加权融合的人脸识别

在人脸识别领域,提取人脸特征和降低维数是人脸识别的关键。传统的基于小波变换的人脸识别算法仅在小波分解的低频分量上提取用于分类的图像特征,造成了高频分量中部分对识别有利信息的丢失。为了更有效地提取人脸图像特征,提出一种基于小波变换和特征加权融合的人脸识别算法。首先通过小波变换对人脸图像进行降维处理,然后对4个小波子图分别运用主成分分析法(PCA)提取特征,并把这4部分特征加权融合,最后利用支持向量机(SVM)进行分类识别。在ORL人脸库上进行实验验证,识别准确率可达到97.5%,实验结果表明该算法能够有效提高人脸识别能力,与传统识别算法相比具有较高的识别准确率和识别速度。     

一种基于自动特征识别确定模具脱模方向的方法

判定脱模方向是实现模具自动设计的第一步,也是评估塑件或浇注件能否模具成型的重要因素,文中以基于广义痕迹的自动特征识别方法来识别塑件模型中的所有特征。首先,通过确定每类塑件特征的候选和可行脱模方向,针对每个识别出的特征,自动产生该特候选的脱模方向,然后把所有具有机或完全相反的候选的脱模方向组成一组,并对每组方向,进行选定的模具因子计算,最终胡定优选的脱模方向。实例测试表明,本文提出的方法具有很高的效     

In Defense of Active Part Selection for Fine-Grained Classification

Fine-grained classification is a recognition task where subtle differences distinguish between different classes. To tackle this classification problem, part-based classification methods are mostly used. Partbased methods learn an algorithm to detect parts of the observed object and extract local part features for the detected part regions. In this paper we show that not all extracted part features are always useful for the classification. Furthermore, given a part selection algorithm that actively selects parts for the classification we estimate the upper bound for the fine-grained recognition performance. This upper bound lies way above the current state-of-the-art recognition performances which shows the need for such an active part selection method. Though we do not present such an active part selection algorithm in this work, we propose a novel method that is required by active part selection and enables sequential part-based classification. This method uses a support vector machine (SVM) ensemble and allows to classify an image based on arbitrary number of part features. Additionally, the training time of our method does not increase with the amount of possible part features. This fact allows to extend the SVM ensemble with an active part selection component that operates on a large amount of part feature proposals without suffering from increasing training time.     

Edge-based identification of DP-features on free-form solids

Numerous applications in mechanical CAD/CAM need robust algorithms for the identification of protrusion and depression features (DP-features) on geometric models with free-form (B-spline) surfaces. This paper reports a partitioning algorithm that first identifies the boundary edges of DP-features and then creates a surface patch to cover the depressions or isolate the protrusions. The novelty of the method lies in the use of tangent continuity between edge segments to identify DP-feature boundaries that cross multiple faces and geometries.     

回转体逆时序右特征识别及内外轮廓自动重构

特征自动化识别与解读是回转体零件加工代码自适应生成的重要基础,而回转体内外轮廓的几何特征信息是加工轨迹生成的重要依据。针对多种信息混合的CAD载体中回转体零件几何特征解读问题,提出了顺时序最右侧判别法自动识别回转体零件的内外轮廓特征。利用DXF结构化存储的图形信息和回转体零件对称性的特点去除尺寸标注,剖面线、粗糙度标注,形位公差标注等多余线,最后沿着逆时针寻找相对于当前轮廓最右侧的路径为下一轮廓。与传统方法相比,所提出算法的复杂度进一步降低,能够准确可靠地在干扰信息中识别出零件的内外轮廓精确信息。     

Recognition of machining features for cast then machined parts

Mechanical parts are typically manufactured using multiple manufacturing processes. Primary processes such as casting realize the primary shape of the part, while secondary processes such as machining generate more detailed shape of the part. This paper presents a feature recognition method to support machining process planning for cast-then-machined parts. From the part model including the specification of machined faces, we generate the starting workpiece for machining, which represents the casting output in sufficient detail to support machining process planning. The starting workpiece is generated by identifying faces to be made by casting followed by machining, then offsetting the part through these faces by a uniform machining thickness to obtain cast faces, and combining the halfspaces induced by machined faces and the halfspaces induced by their bounding cast faces to enclose removal volumes. Machining features are then recognized from the removal volumes using a volume decomposition method called Alternating Sum of Volumes with Partitioning.     

Classification,representation, and automatic extraction of deformation features in sheet metal parts

This paper presents classification, representation and extraction of deformation features in sheet-metal parts. The thickness is constant for these shape features and hence these are also referred to as constant thickness features. The deformation feature is represented as a set of faces with a characteristic arrangement among the faces. Deformation of the base-sheet or forming of material creates Bends and Walls with respect to a base-sheet or a reference plane. These are referred to as Basic Deformation Features (BDFs). Compound deformation features having two or more BDFs are defined as characteristic combinations of Bends and Walls and represented as a graph called Basic Deformation Features Graph (BDFG). The graph, therefore, represents a compound deformation feature uniquely. The characteristic arrangement of the faces and type of bends belonging to the feature decide the type and nature of the deformation feature. Algorithms have been developed to extract and identify deformation features from a CAD model of sheet-metal parts. The proposed algorithm does not require folding and unfolding of the part as intermediate steps to recognize deformation features. Representations of typical features are illustrated and results of extracting these deformation features from typical sheet metal parts are presented and discussed.     

Recognition in the near infrared spectrum for face,gender and facial expressions

Visible face recognition systems are subjected to failure when recognizing the faces in unconstrained scenarios. So, recognizing faces under variable and low illumination conditions are more important since most of the security breaches happen during night time. Near Infrared (NIR) spectrum enables to acquire high quality images, even without any external source of light and hence it is a good method for solving the problem of illumination. Further, the soft biometric trait, gender classification and non verbal communication, facial expression recognition has also been addressed in the NIR spectrum. In this paper, a method has been proposed to recognize the face along with gender classification and facial expression recognition in NIR spectrum. The proposed method is based on transfer learning and it consists of three core components, i) training with small scale NIR images ii) matching NIR-NIR images (homogeneous) and iii) classification. Training on NIR images produce features using transfer learning which has been pre-trained on large scale VIS face images. Next, matching is performed between NIR-NIR spectrum of both training and testing faces. Then it is classified using three, separate SVM classifiers, one for face recognition, the second one for gender classification and the third one for facial expression recognition. It has been observed that the method gives state-of-the-art accuracy on the publicly available, challenging, benchmark datasets CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, PolyU, CBSR, IIT Kh and HITSZ for face recognition. Further, for gender classification the Oulu-CASIA NIR-VIS, PolyU,and IIT Kh has been analyzed and for facial expression the Oulu-CASIA NIR-VIS dataset has been analyzed.

     

Recognition of virtual loops on 3D CAD models based on the B-rep model

Loops are critical elements in boundary representation (B-rep) models because they link all edges corresponding to a face. Loops can be used in feature recognition for identifying depressions or protrusions. In real 3D CAD models, however, features typically lie across multiple faces, which is beyond the data structure of current B-rep models. This study presents a virtual loop concept to account for all loop types used in CAD models, and develops algorithms for recognizing them. In accordance with the complexity of the recognition algorithm, this study defines three types of loop: single, virtual, and multivirtual. A single loop is the current loop recorded in the B-rep model. A virtual loop lies across faces that are at least G¹ continuous. Finally, a multivirtual loop lies across faces that are either G⁰ or G¹ continuous. The proposed loop structure provides a more complete data structure for recognizing various types of features in feature-recognition modules. Several realistic CAD models are presented to confirm the feasibility of the proposed loop-recognition and feature-recognition methods.     

基于类矩阵和特征融合的加权自适应人脸识别

为了准确快速地进行人脸识别,提出了一种基于类矩阵和特征融合的加权自适应人脸识别算法,该算法首先,提取人脸的全局特征和6个关键部分的局部特征,同时给出了局部特征权值的动态选择方法,由于该法可以根据不同的训练集得出不同的权值,因而增强了算法的自适应能力;然后通过将全局和局部特征加权融合来得出样本的特征矩阵;接着设计出了一种加权PCA方法用于对样本矩阵进行降维;再进一步提出类矩阵的概念,同时给出并证明了类矩阵的推导公式,并据此得出一种新的投影准则;最后,将类矩阵和试验样本分别进行投影,并根据其欧氏距离的大小得出试验人脸的最终类别。试验表明,该算法不仅计算速度快、识别率高,而且能有效解决LDA小样本空间问题,应用前景良好。     

基于监督式机器学习的零件几何特征智能识别

针对在采用机器视觉的无夹具定位的壳体类零件几何参数检测过程中,需要先智能识别零件几何特征以规划检测路径的问题,提出一种基于监督式机器学习的几何特征智能识别方法。利用壳体零件待识别特征的中心位置关系构成特征矩阵,利用监督式机器学习算法进行识别,提出一种基于特征唯一性的纠错方法对分类过程中产生的识别错误进行纠正。对于所涉研究实例,零件共有4个待识别孔,在5次监督式训练后智能识别准确度达100%。     

Extraction of spiculated parts of mammogram tumors to improve accuracy of classification

Spiculated parts of masses are significant features to classify tumors in digital mammography; however, segmentation, which is used to extract the shape and contour of a tumor, eliminates them. To address this problem, the current study proposes a novel algorithm for extraction of the spiculated pixels of a tumor that are of similar intensity along a line. It first applies the sums of the differences between the central pixel and neighboring pixels in different symmetric orthogonal directions. The minimum difference between two symmetric orthogonal directions specifies the similarity of pixels in one direction as denoting a spiculated part of the mass. These parts then are added to the segmented image to enhance the shape of tumor. The features of the tumor are extracted from the final segmented image to allow its classification as benign or malignant. Simulation results showed that the accuracy and the area under the ROC curve of the proposed method for mini-MIAS and DDSM databases were 91.37% and 93.22% and 0.9776 and 0.9752, respectively. This confirms the effectiveness of the proposed algorithm for extraction of the spiculated parts of a malignant tumor with the aim of increasing the classification accuracy.

     

面向数控加工工时估算的模型特征识别

利用数控加工结构件的特征具有层次分布式特点,提出了基于面邻接关系 的特征识别方法,将零件的面先分成基础面和约束面,再根据凹凸邻接关系组合为相应的层 集合,以层作为特征识别的基础,通过层的识别和组合获得数控加工结构件的特征,并提取 相关特征参数信息,结合机床的加工参数,对零件加工工时进行了估算,并进行了实例验证。     

Pattern recognition using feature feedback: Application to face recognition

In this paper, we propose a new pattern recognition method using feature feedback and present its application to face recognition. Conventional pattern recognition methods extract the features employed for classification using PCA, LDA and so on. On the other hand, in the proposed method, the extracted features are analyzed in the original space using feature feedback. Using reverse mapping from the extracted features to the original space, we can identify the important part of the original data that affects the classification. In this way, we can modify the data to obtain a higher classification rate, make it more compact or abbreviate the required sensors. To verify the applicability of the proposed method, we apply it to face recognition using the Yale Face Database. Each face image is divided into two parts, the important part and unimportant part, using feature feedback, and the classification performed using the feature mask obtained from feature feedback. Also, we combine face recognition with image compression. The experimental results show that the proposed method works well.     

人脸样貌独立判别的协作表情识别算法

为了降低样貌、姿态、眼镜以及表情定义不统一等因素对人脸表情识别的影响,提出一种人脸样貌独立判别的协作表情识别算法。首先,采用自动的人脸检测算法定位、对齐视频每帧的人脸区域,并从人脸视频序列中选择峰值表情的人脸;然后,采用峰值人脸与某个表情类内的所有人脸产生表情类内差异人脸信息,并通过计算峰值表情人脸与表情类内差异人脸的差异信息获得协作的表情表示;最终,采用基于稀疏的分类器与表情表示决定每个人脸表情的标签。采用欧美与亚洲人脸的数据库进行仿真实验,结果表明本算法获得了较好的表情识别准确率,对不同样貌、佩戴眼镜的人脸样本也具有较好的识别效果。     

An evidential reasoning based classification algorithm and its application for face recognition with class noise

For classification problems, in practice, real-world data may suffer from two types of noise, attribute noise and class noise. It is the key for improving recognition performance to remove as much of their adverse effects as possible. In this paper, a formalism algorithm is proposed for classification problems with class noise, which is more challenging than those with attribute noise. The proposed formalism algorithm is based on evidential reasoning theory which is a powerful tool to deal with uncertain information in multiple attribute decision analysis and many other areas. Thus, it may be more effective alternative to handle noisy label information. And then a specific algorithm—Evidential Reasoning based Classification algorithm (ERC) is derived to recognize human faces under class noise conditions. The proposed ERC algorithm is extensively evaluated on five publicly available face databases with class noise and yields good performance.     

Building a water feature extraction model by integrating aerial image and lidar point clouds

An innovative model for extracting water regions from aerial images fused with light detection and ranging (lidar) data is proposed in this article. This model extracts water features from coarse to fine levels of accuracy by considering special spectral bands of existing airborne lidar systems and their spectral characteristics. The particular model consists of two parts, namely inexact water region recognition and precise water extraction. (1) A strategy of using a triangulated irregular network (TIN) is introduced to describe point clouds with a particular structure. A TIN coarsely divides the network into water and non-water regions through a threshold, which can be determined through an equation by inputting the minimum width and point density of water regions. The coarsely defined water region can be detected through overlay analysis between the aerial image and the raster surface generated from the TIN. (2) An improved mean-shift algorithm is used to remove most land pixels from the roughly recognized water to obtain precise water edges from coarse water. A new empirical formula to describe distance between multi-dimensional data is adopted. Using the mean-shift algorithm and empirical distance function, accurate water edge features are extracted from inexact water region(s). In addition, the classification field of lidar point clouds is used to remove land pixels from water features.

A case study based on a point cloud data set and an aerial image is conducted to evaluate the feasibility and accuracy of the proposed model. Spatial distances between checkpoints and extracted water edges, as well as the confusion matrix of mean-shift classification, are adopted as measurements of accuracy for the extracted water edges in two case regions. Evaluation results show that the proposed model achieved continuous water-edge features, and that spatial accuracy of water edges is 0.3 to 0.4 m, at approximately the 1–2-pixel level, which is more than four times better than the maximum-likelihood classification method. General accuracy of the confusion matrix shows that mean-shift classification in the proposed model is better than 95%, which indicates excellent results.     

均值漂移LDA优化FSIF的三维人脸识别

针对传统的三维人脸识别算法受光照、姿态、表情及场景变化影响导致耗时过多及成本过高的问题,提出了一种基于均值漂移线性判别分析优化尺度不变特征融合(FSIF)算法。使用均值漂移线性判别分析找到五个类似于查询人脸的最佳候选类;利用尺度不变特征融合提取出候选人脸及查询人脸的融合特征描述符,并进行特征匹配得到目标人脸;根据特征描述符的匹配关键点数目完成人脸的识别。在USCD/Honda、FRGC v2及自己搜集的人脸数据集上的实验结果表明,该算法解决了降低FSIF人脸识别的计算复杂度,并在不降低识别性能的前提下大大地节约了成本,相比几种较为先进的三维人脸识别算法,该算法取得了更好的识别效果。     

Graph-based recognition of morphological features

Automatic recognition of the shapes of objects represented as solid models is very important in design optimization. Object shape also governs ease of manufacture, ease of orientability, field use and all other life-cycle applications. Characteristic attributes of an object shape such as chamfers, protrusions and depressions, play a significant role in process planning, design for manufacture, etc. These attributes are popularly known as morphological features. In this paper, the problem of identifying such morphological features is divided into two phases: the feature extraction phase and the feature classification phase. In feature extraction, the mechanical part is decomposed into its constituent features such as holes, protrusions and depressions based on the connectivity class in the edge-face graph of the part. In feature classification, on the other hand, the extracted features are identified and classified. This paper describes a feature classification scheme based on topological and geometric attributes of a morphological feature. The feature classification scheme outlined in this paper is capable of identifying new features with minimal human interface.