Recognizing hand gestures using the weighted elastic graph matching (WEGM) method

This paper proposes a weighted scheme for elastic graph matching hand posture recognition. Visual features scattered on the elastic graph are assigned corresponding weights according to their relative ability to discriminate between gestures. The weights' values are determined using adaptive boosting. A dictionary representing the variability of each gesture class is expressed in the form of a bunch graph. The positions of the nodes in the bunch graph are determined using three techniques: manually, semi-automatically, and automatically. Experimental results also show that the semi-automatic annotation method is efficient and accurate in terms of three performance measures; assignment cost, accuracy, and transformation error. In terms of the recognition accuracy, our results show that the hierarchical weighting on features has more significant discriminative power than the classic method (uniform weighting). The hierarchical elastic graph matching (WEGM) approach was used to classify a lexicon of ten hand postures, and it was found that the poses were recognized with a recognition accuracy of 97.08% on average. Using the weighted scheme, computing cycles can be decreased by only computing the features for those nodes whose weight is relatively high and ignoring the remaining nodes. It was found that only 30% of the nodes need to be computed to obtain a recognition accuracy of over 90%.     

融合关节旋转特征和指尖距离特征的手势识别

作为人机交互的重要方式,手势交互和识别由于其具有的高自由度而成为计算机图形学、虚拟现实与人机交互等领域的研究热点.传统直接提取手势轮廓或手部关节点位置信息的手势识别方法,其提取的特征通常难以准确表示手势之间的区别.针对手势识别中不同手势具有的高自由度以及由于手势图像分辨率低、背景杂乱、手被遮挡、手指形状尺寸不同、个体差异性导致手势特征表示不准确等问题,本文提出了一种新的融合关节旋转特征和指尖距离特征的手势特征表示与手势识别方法.首先从手势深度图中利用手部模板并将手部看成链段结构提取手部20个关节点的3D位置信息;然后利用手部关节点位置信息提取四元数关节旋转特征和指尖距离特征,该表示构成了手势特征的内在表示;最后利用一对一支持向量机对手势进行有效识别分类.本文不仅提出了一种新的手势特征表示与提取方法,该表示融合了关节旋转信息和指尖距离特征;而且从理论上证明了该特征表示能唯一地表征手势关节点的位置信息;同时提出了基于一对一SVM多分类策略进行手势分类与识别.对ASTAR静态手势深度图数据集中8类中国数字手势和21类美国字母手势数据集分别进行了实验验证,其分类识别准确率分别为99.71%和85.24%.实验结果表明,本文提出的基于关节旋转特征和指尖距离特征的融合特征能很好地表示不同手势的几何特征,能准确地表征静态手势并进行手势识别.     

基于特征包支持向量机的手势识别

针对类肤色信息或复杂背景的影响,难以通过手势分割得到精确手势轮廓而对后期手势识别率与实时交互的影响,提出了一种基于特征包支持向量机(BOF-SVM)的手势识别方法。采用SIFT算法提取手势图像局部不变性特征点,将手势局部特征向量(尺度不变特征变换(SIFT)描述子)进行K-means聚类生成视觉码书,并通过视觉码书量化每一幅手势图像的视觉码字集合,以此获得手势图像的固定维数的表征向量来训练支持向量机(SVM)多类分类器。该方法只需框定手势所在区域,无需精确地分割人手。实验表明,该方法对9种交互手势的平均识别率达到92.1%,并具有很好的鲁棒性及实时性,能适应环境的变化。     

A comparison of skin history and trajectory-based representation schemes for the recognition of user-specified gestures

Gesture recognition error rates and the qualitative nature of the errors made are heavily influenced by the choice of visual representation. A direct empirical comparison of two contrasting approaches, namely trajectory- and history-based representation, is presented. Skin colour is used as a common visual cue and recognition is based on hidden Markov models, moment features and normalised template matching. Two novel representation schemes are proposed and evaluated: (i) skin history images and (ii) composite history images which represent occluded motion. Results are reported for an application in which able-bodied and disabled subjects specify their own gesture vocabularies.     

基于几何特征的静态字母手势识别算法

针对聋哑人哑语手势自动识别问题的复杂性,研究了手势几何特征的多样性及提取和识别方法,提出了一种基于几何特征的手势识别算法.首先,对手势图像进行肤色分割、边缘检测以及逻辑运算,然后,计算其质心面积等多项几何特征,通过实验方法测定最佳特征权值,最后,将其与样本图像特征值进行匹配,最佳匹配即为检测结果.根据30个字母手势创建了3套手势库,其中1套作为样本集,2套作为测试集.实验结果表明,通过该方法进行特征提取来识别汉语字母手势,可有效提高识别率,测试集识别率达到93.33％.     

多尺度卷积特征融合的SSD手势识别算法

为了提高对中小占比手势识别的准确性与稳定性,提出了一种多尺度卷积特征融合的SSD(single shot multibox detector)手势识别方法。该方法突出表现在两大方面,其一,在原始的SSD算法的多尺度卷积检测方法基础上,引入了不同卷积层的特征融合思想,经过空洞卷积下采样操作与反卷积上采样操作,实现网络结构中的浅层视觉卷积层与深层语义卷积层的融合,代替原有的卷积层用于手势识别,以提高模型对中小目标手势的识别精度;其二,为了解决正负样本不均衡导致分类性能差的问题,提出一种改进的损失函数,以提升模型对目标手势的分类能力。在手势识别公开的数据集上的实验结果表明,与SSD和Faster R-CNN等识别方法相比,能够在保持较高的手势检测精度的同时,又具有较好的鲁棒性与检测速度。     

Object Recognition as Many-to-Many Feature Matching

Object recognition can be formulated as matching image features to model features. When recognition is exemplar-based, feature correspondence is one-to-one. However, segmentation errors, articulation, scale difference, and within-class deformation can yield image and model features which don’t match one-to-one but rather many-to-many. Adopting a graph-based representation of a set of features, we present a matching algorithm that establishes many-to-many correspondences between the nodes of two noisy, vertex-labeled weighted graphs. Our approach reduces the problem of many-to-many matching of weighted graphs to that of many-to-many matching of weighted point sets in a normed vector space. This is accomplished by embedding the initial weighted graphs into a normed vector space with low distortion using a novel embedding technique based on a spherical encoding of graph structure. Many-to-many vector correspondences established by the Earth Mover’s Distance framework are mapped back into many-to-many correspondences between graph nodes. Empirical evaluation of the algorithm on an extensive set of recognition trials, including a comparison with two competing graph matching approaches, demonstrates both the robustness and efficacy of the overall approach.     

Feature fusion for 3D hand gesture recognition by learning a shared hidden space

Hand gesture recognition has been intensively applied in various human-computer interaction (HCI) systems. Different hand gesture recognition methods were developed based on particular features, e.g., gesture trajectories and acceleration signals. However, it has been noticed that the limitation of either features can lead to flaws of a HCI system. In this paper, to overcome the limitations but combine the merits of both features, we propose a novel feature fusion approach for 3D hand gesture recognition. In our approach, gesture trajectories are represented by the intersection numbers with randomly generated line segments on their 2D principal planes, acceleration signals are represented by the coefficients of discrete cosine transformation (DCT). Then, a hidden space shared by the two features is learned by using penalized maximum likelihood estimation (MLE). An iterative algorithm, composed of two steps per iteration, is derived to for this penalized MLE, in which the first step is to solve a standard least square problem and the second step is to solve a Sylvester equation. We tested our hand gesture recognition approach on different hand gesture sets. Results confirm the effectiveness of the feature fusion method.     

基于卷积神经网络的手势识别初探

提出一种用于手势识别的新算法,使用卷积神经网络来进行手势的识别。该算法避免了手势复杂的前期预处理,可以直接输入原始的手势图像。卷积神经网络具有局部感知区域、层次结构化、特征抽取和分类过程等特点,在图像识别领域获得广泛的应用。试验结果表明,该方法能识别多种手势,精度较高且复杂度较小,具有很好的鲁棒性,也克服传统算法的诸多固有缺点。     

A system for person-independent hand posture recognition againstcomplex backgrounds

A computer vision system for person-independent recognition of hand postures against complex backgrounds is presented. The system is based on the elastic graph matching, which was extended to allow for combinations of different feature types at the graph nodes     

融合深度特征和语义邻域的自动图像标注*

传统图像标注方法中人工选取特征费时费力,传统标签传播算法忽视语义近邻,导致视觉相似而语义不相似,影响标注效果.针对上述问题,文中提出融合深度特征和语义邻域的自动图像标注方法.首先构建基于深度卷积神经网络的统一、自适应深度特征提取框架,然后对训练集划分语义组并建立待标注图像的邻域图像集,最后根据视觉距离计算邻域图像各标签的贡献值并排序得到标注关键词.在基准数据集上实验表明,相比传统人工综合特征,文中提出的深度特征维数更低,效果更好.文中方法改善传统视觉近邻标注方法中的视觉相似而语义不相似的问题,有效提升准确率和准确预测的标签总数.     

Hand gesture recognition based on concentric circular scan lines and weighted K-nearest neighbor algorithm

Human-computer interactions based on hand gestures are of the most popular natural interactive modes, which severely depends on real-time hand gesture recognition approaches. In this paper, a simple but effective hand feature extraction method is described, and the corresponding hand gesture recognition method is proposed. First, based on a simple tortoise model, we segment the human hand images by skin color features and tags on the wrist, and normalize them to create the training dataset. Second, feature vectors are computed by drawing concentric circular scan lines (CCSL) according to the center of the palm, and linear discriminant analysis (LDA) algorithm is used to deal with those vectors. Last, a weighted k-nearest neighbor (W-KNN) algorithm is presented to achieve real-time hand gesture classification and recognition. Besides the efficiency and effectiveness, we make sure that the whole gesture recognition system can be easily implemented and extended. Experimental results with a user-defined hand gesture dataset and multi-projector display system show the effectiveness and efficiency of the new approach.     

The discriminant elastic graph matching algorithm applied to frontal face verification

In this paper a generalized framework for face verification is proposed employing discriminant techniques in all phases of elastic graph matching. The proposed algorithm is called discriminant elastic graph matching (DEGM) algorithm. In the first step of the proposed method, DEGM, discriminant techniques at the node feature vectors are used for feature selection. In the sequel, the two local similarity values, i.e., the similarity measure for the projected node feature vector and the node deformation, are combined in a discriminant manner in order to form the new local similarity measure. Moreover, the new local similarity values at the nodes of the elastic graph are weighted by coefficients that are derived as well from discriminant analysis in order to form a total similarity measure between faces. The proposed method exploits the individuality of the human face and the discriminant information of elastic graph matching in order to improve the verification performance of elastic graph matching. We have applied the proposed scheme to a modified morphological elastic graph matching algorithm. All experiments have been conducted in the XM2VTS database resulting in very low error rates for the test sets.     

基于DTW算法的肌电信号手势识别方法

为了提高肌电信号手势识别算法的准确度,增强实时性,提出了一种基于动态时间规整（DTW）算法的手势识别方法,该方法利用肌电信号（EMG）对个体间的手势进行识别。首先,采用滑动平均能量的方法对原始的EMG信号进行数据分割,探测有效动作;其次,对于分割的数据段使用平均绝对值（MAV）来提取信号特征;最后,用DTW算法将8维的EMG信号融合并计算测试样本和模版的相似度,其中采用了DTW算法寻找规整路径的方法进行了模板制作,实现了个体间的手势识别。实验结果表明,使用DTW算法对肌电信号进行手势识别,其动作识别的准确率达到96.09%,该方法计算速度快,实时性强。     

基于最大池的谱特征匹配算法

为了提高基于谱特征的图像匹配算法的精度和鲁棒性,提出了一种基于最大池的谱特征匹配算法。首先,利用图像特征点邻域信息提取具有旋转不变性和亮度线性变化不变性的谱特征;其次,将以谱特征描述的特征点作为节点、特征点之间的欧氏距离作为边构造属性关系图,将图像匹配问题转化为图匹配问题;最后,引入最大池匹配策略获取图匹配结果。大量实验结果表明,该算法提高了谱特征匹配算法的精度和鲁棒性。     

A neural network approach to CSG-based 3-D object recognition

Describes the recognition subsystem of a computer vision system based on constructive solid geometry (CSG) representation scheme. Instead of using the conventional CSG trees to represent objects, the proposed system uses an equivalent representation scheme-precedence graphs-for object representation. Each node in the graph represents a primitive volume and each are between two nodes represents the relation between them. Object recognition is achieved by matching the scene precedence graph to the model precedence graph. A constraint satisfaction network is proposed to implement the matching process. The energy function associated with the network is used to enforce the matching constraints including match validity, primitive similarity, precedence graph preservation, and geometric structure preservation. The energy level is at its minimum only when the optimal match is reached. Experimental results on several range images are presented to demonstrate the proposed approach     

三维图匹配算法

目的 现有的图匹配算法大多应用于二维图像,对三维图像的特征点匹配存在匹配准确率低和计算速度慢等问题。为解决这些问题,本文将分解图匹配算法扩展应用在了三维图像上。方法 首先将需要匹配的两个三维图像的特征点作为图的节点集;再通过Delaunay三角剖分算法,将三维特征点相连,则相连得到的边就作为图的边集,从而建立有向图;然后,根据三维图像的特征点构建相应的三维有向图及其邻接矩阵;再根据有向图中的节点特征和边特征分别构建节点特征相似矩阵和边特征相似矩阵;最后根据这两个特征矩阵将节点匹配问题转化为求极值问题并求解。结果 实验表明,在手工选取特征点的情况下,本文算法对相同三维图像的特征点匹配有97.56%的平均准确率;对不同三维图像特征点匹配有76.39%的平均准确率;在三维图像有旋转的情况下,有90%以上的平均准确率;在特征点部分缺失的情况下,平均匹配准确率也能达到80%。在通过三维尺度不变特征变换（SIFT）算法得到特征点的情况下,本文算法对9个三维模型的特征点的平均匹配准确率为98.78%。结论 本文提出的基于图论的三维图像特征点匹配算法,经实验结果验证,可以取得较好的匹配效果。     

Static hand gesture recognition using neural networks

This paper presents a novel technique for hand gesture recognition through human–computer interaction based on shape analysis. The main objective of this effort is to explore the utility of a neural network-based approach to the recognition of the hand gestures. A unique multi-layer perception of neural network is built for classification by using back-propagation learning algorithm. The goal of static hand gesture recognition is to classify the given hand gesture data represented by some features into some predefined finite number of gesture classes. The proposed system presents a recognition algorithm to recognize a set of six specific static hand gestures, namely: Open, Close, Cut, Paste, Maximize, and Minimize. The hand gesture image is passed through three stages, preprocessing, feature extraction, and classification. In preprocessing stage some operations are applied to extract the hand gesture from its background and prepare the hand gesture image for the feature extraction stage. In the first method, the hand contour is used as a feature which treats scaling and translation of problems (in some cases). The complex moment algorithm is, however, used to describe the hand gesture and treat the rotation problem in addition to the scaling and translation. The algorithm used in a multi-layer neural network classifier which uses back-propagation learning algorithm. The results show that the first method has a performance of 70.83% recognition, while the second method, proposed in this article, has a better performance of 86.38% recognition rate.     

基于改进特征袋模型的奶牛识别算法

针对特征袋（BOF）模型中存在特征计算耗时、识别精度低的不足,提出一种新的改进BOF模型以提高其目标识别的精度和效率,并将其应用于奶牛个体识别。该算法首先引入优化方向梯度直方图（HOG）特征对图像进行特征提取和描述,然后利用空间金字塔匹配原理（SPM）生成图像基于视觉词典的直方图表示,最后自定义直方图交叉核作为分类器核函数。该算法在项目组自行拍摄的数据集（包含15类奶牛、共7500张奶牛头部图像）上的实验结果表明,使用基于SPM的BOF模型将算法的识别率平均提高2个百分点;使用直方图交叉核相比使用高斯核将算法的识别率平均提高2.5个百分点;使用优化HOG特征,相比使用传统HOG特征将算法识别率平均提高21.3个百分点,运算效率为其1.68倍;相比使用尺度不变特征变换（SIFT）特征,在保证平均识别精度达95.3%的基础上,运算效率为其7.10倍。分析结果可知,该算法在奶牛个体识别领域具有较好的鲁棒性和实用性。