Iconic and multi-stroke gesture recognition

Many handwritten gestures, characters, and symbols comprise multiple pendown strokes separated by penup strokes. In this paper, a large number of features known from the literature are explored for the recognition of such multi-stroke gestures. Features are computed from a global gesture shape. From its constituent strokes, the mean and standard deviation of each feature are computed. We show that using these new stroke-based features, significant improvements in classification accuracy can be obtained between 10% and 50% compared to global feature representations. These results are consistent over four different databases, containing iconic pen gestures, handwritten symbols, and upper-case characters. Compared to two other multi-stroke recognition techniques, improvements between 25% and 39% are achieved, averaged over all four databases.     

基于多相机的人脸姿态识别

主动形状模型(ASM)算法被用来进行人脸特征点的精确定位,然后在多相机测量的图像中进行特征点的立体匹配,利用双目视觉和相机三维测距技术可以确定人脸特征点的空间三维位置,从而利用这些特征点的相对位置确定出人脸的姿态。实验结果显示,用该方法进行人脸姿态识别能取得比二维识别更高的精确度。     

Studies in automated hand gesture analysis: an overview of functional types and gesture phases

This paper presents an overview of studies on automated hand gesture analysis, which is mainly concerned with recognition and segmentation issues related to functional types and gesture phases. The issues selected for discussion have been arranged in a way that takes account of problems within the Theory of Gestures that each study seeks to address. Their principal computational factors that were involved in conducting the analysis of automated hand gesture have been examined, and an analysis of open research issues has been carried out for each application dealt with in the studies.     

Hand posture and gesture recognition technology

Hand gestures that are performed by one or two hands can be categorized according to their applications into different categories including conversational, controlling, manipulative and communicative gestures. Generally, hand gesture recognition aims to identify specific human gestures and use them to convey information. The process of hand gesture recognition composes mainly of four stages: hand gesture images collection, gesture image preprocessing using some techniques including edge detection, filtering and normalization, capture the main characteristics of the gesture images and the evaluation (or classification) stage where the image is classified to its corresponding gesture class. There are many methods that have been used in the classification stage of hand gesture recognition such as Artificial Neural Networks, template matching, Hidden Markov Models and Dynamic Time Warping. This exploratory survey aims to provide a progress report on hand posture and gesture recognition technology.     

Real-time fingertip tracking and gesture recognition

Augmented desk interfaces and other virtual reality systems depend on accurate, real-time hand and fingertip tracking for seamless integration between real objects and associated digital information. We introduce a method for discerning fingertip locations in image frames and measuring fingertip trajectories across image frames. We also propose a mechanism for combining direct manipulation and symbolic gestures based on multiple fingertip motions. Our method uses a filtering technique, in addition to detecting fingertips in each image frame, to predict fingertip locations in successive image frames and to examine the correspondences between the predicted locations and detected fingertips. This lets us obtain multiple complex fingertip trajectories in real time and improves fingertip tracking. This method can track multiple fingertips reliably even on a complex background under changing lighting conditions without invasive devices or color markers.     

uWave: Accelerometer-based personalized gesture recognition and its applications

The proliferation of accelerometers on consumer electronics has brought an opportunity for interaction based on gestures. We present uWave, an efficient recognition algorithm for such interaction using a single three-axis accelerometer. uWave requires a single training sample for each gesture pattern and allows users to employ personalized gestures. We evaluate uWave using a large gesture library with over 4000 samples for eight gesture patterns collected from eight users over one month. uWave achieves 98.6% accuracy, competitive with statistical methods that require significantly more training samples. We also present applications of uWave in gesture-based user authentication and interaction with 3D mobile user interfaces. In particular, we report a series of user studies that evaluates the feasibility and usability of lightweight user authentication. Our evaluation shows both the strength and limitations of gesture-based user authentication.     

Easy gesture recognition for Kinect

Recent progress in entertainment and gaming systems has brought more natural and intuitive human–computer interfaces to our lives. Innovative technologies, such as Xbox Kinect, enable the recognition of body gestures, which are a direct and expressive way of human communication. Although current development toolkits provide support to identify the position of several joints of the human body and to process the movements of the body parts, they actually lack a flexible and robust mechanism to perform high-level gesture recognition. In consequence, developers are still left with the time-consuming and tedious task of recognizing gestures by explicitly defining a set of conditions on the joint positions and movements of the body parts. This paper presents EasyGR (Easy Gesture Recognition), a tool based on machine learning algorithms that help to reduce the effort involved in gesture recognition. We evaluated EasyGR in the development of 7 gestures, involving 10 developers. We compared time consumed, code size, and the achieved quality of the developed gesture recognizers, with and without the support of EasyGR. The results have shown that our approach is practical and reduces the effort involved in implementing gesture recognizers with Kinect.     

Spatial and temporal pyramid-based real-time gesture recognition

This paper proposes a novel method for real-time gesture recognition. Aiming at improving the effectiveness and accuracy of HGR, spatial pyramid is applied to linguistically segment gesture sequence into linguistic units and a temporal pyramid is proposed to get a time-related histogram for each single gesture. Those two pyramids can help to extract more comprehensive information of human gestures from RGB and depth video. A two-layered HGR is further exploited to further reduce the computation complexity. The proposed method obtains high accuracy and low computation complexity performance on the ChaLearn Gesture Dataset, comprising more than 50, 000 gesture sequences recorded.     

复杂背景下的手势识别

目的 手势识别是人机交互领域的热点问题。针对传统手势识别方法在复杂背景下识别率低,以及现有基于深度学习的手势识别方法检测时间长等问题,提出了一种基于改进TinyYOLOv3算法的手势识别方法。方法 对TinyYOLOv3主干网络重新进行设计,增加网络层数,从而确保网络提取到更丰富的语义信息。使用深度可分离卷积代替传统卷积,并对不同网络层的特征进行融合,在保证识别准确率的同时,减小网络模型的大小。采用CIoU（complete intersection over union）损失对原始的边界框坐标预测损失进行改进,将通道注意力模块融合到特征提取网络中,提高了定位精度和识别准确率。使用数据增强方法避免训练过拟合,并通过超参数优化和先验框聚类等方法加快网络收敛速度。结果 改进后的网络识别准确率达到99.1%,网络模型大小为27.6 MB,相比原网络（TinyYOLOv3）准确率提升了8.5%,网络模型降低了5.6 MB,相比于YOLO（you only look once）v3和SSD（single shot multibox detector）300算法,准确率略有降低,但网络模型分别减小到原来的1/8和1/3左右,相比于YOLO-lite和MobileNet-SSD等轻量级网络,准确率分别提升61.12%和3.11%。同时在自制的复杂背景下的手势数据集对改进后的网络模型进行验证,准确率达到97.3%,充分证明了本文算法的可行性。结论 本文提出的改进Tiny-YOLOv3手势识别方法,对于复杂背景下的手势具有较高的识别准确率,同时在检测速度和模型大小方面都优于其他算法,可以较好地满足在嵌入式设备中的使用要求。     

Kernel-based sparse representation for gesture recognition

In this paper, we propose a novel sparse representation based framework for classifying complicated human gestures captured as multi-variate time series (MTS). The novel feature extraction strategy, CovSVDK, can overcome the problem of inconsistent lengths among MTS data and is robust to the large variability within human gestures. Compared with PCA and LDA, the CovSVDK features are more effective in preserving discriminative information and are more efficient to compute over large-scale MTS datasets. In addition, we propose a new approach to kernelize sparse representation. Through kernelization, realized dictionary atoms are more separable for sparse coding algorithms and nonlinear relationships among data are conveniently transformed into linear relationships in the kernel space, which leads to more effective classification. Finally, the superiority of the proposed framework is demonstrated through extensive experiments.     

A model-based hand gesture recognition system

This paper introduces a model-based hand gesture recognition system, which consists of three phases: feature extraction, training, and recognition. In the feature extraction phase, a hybrid technique combines the spatial (edge) and the temporal (motion) information of each frame to extract the feature images. Then, in the training phase, we use the principal component analysis (PCA) to characterize spatial shape variations and the hidden Markov models (HMM) to describe the temporal shape variations. A modified Hausdorff distance measurement is also applied to measure the similarity between the feature images and the pre-stored PCA models. The similarity measures are referred to as the possible observations for each frame. Finally, in recognition phase, with the pre-trained PCA models and HMM, we can generate the observation patterns from the input sequences, and then apply the Viterbi algorithm to identify the gesture. In the experiments, we prove that our method can recognize 18 different continuous gestures effectively. Received: 19 May 1999 / Accepted: 4 September 2000     

Hash-based early recognition of gesture patterns

In these days, “early recognition” of gesture patterns has been studied by many researchers. Early recognition is a method to make a decision of gesture recognition at the beginning part of it. In traditional method, the key postures for a gesture are utilized for recognition and early recognition is performed frame-by-frame. However, this method has a problem that computational time in recognition processing increases in proportion to size of posture database. If the processing time becomes longer, some input frames will be ignored from the processing. It results in lower recognition accuracy. In this paper, we introduce a hash-based approach to search the posture database. It realizes real-time processing, and keep high performance of recognition.     

A database-based framework for gesture recognition

Gestures are an important modality for human–machine communication. Computer vision modules performing gesture recognition can be important components of intelligent homes, assistive environments, and human–computer interfaces. A key problem in recognizing gestures is that the appearance of a gesture can vary widely depending on variables such as the person performing the gesture, or the position and orientation of the camera. This paper presents a database-based approach for addressing this problem. The large variability in appearance among different examples of the same gesture is addressed by creating large gesture databases, that store enough exemplars from each gesture to capture the variability within that gesture. This database-based approach is applied to two gesture recognition problems: handshape categorization and motion-based recognition of American Sign Language signs. A key aspect of our approach is the use of database indexing methods, in order to address the challenge of searching large databases without violating the time constraints of an online interactive system, where system response times of over a few seconds are oftentimes considered unacceptable. Our experiments demonstrate the benefits of the proposed database-based framework, and the feasibility of integrating large gesture databases into online interacting systems.     

Hand gesture recognition using topological features

Multimedia Tools and Applications - Hand Gestures Recognition (HGR) is one of the main areas of research for Human Computer Interaction applications. Most existing approaches are based on local or...     

基于视觉的动态手势识别

采用隐马尔可夫模型（Hidden Markov Model）算法的缺点，采用纠错算法对其修正，提高了识别率。了对机器人控制的目的，优化了人机交互的接口。训练并识别手势样本，针对HMM的经典训练算法Baum-Welch将识别结果应用于“基于Internet远程机器人控制”项目，达到了对机器人控制的目的，优化了人机交互的接口。     

基于LSSVM的静态手势识别

支持向量机(Support Vector Machine，简称SVM)，是基于统计学习理论的一种新的模式识别方法，较好地解决了小样本学习问题。通过使非线性空间变换为线性空间，降低了算法的复杂性。LSSVM(Least Squares Support Vector Machine)由于使用线性等式代替了标准的SVM算法中的线性不等式，进一步降低了运算量。利用傅立叶描述子获取静态手势特征向量，通过LSSVM大尺度算法求解方程组来得到LSSVM分类器，进行静态手势识别，取得了较高的识别率。说明如何把静态手势识别结果应用到机器人远程控制中，提高人机交互的友好性。     

基于立体视觉的非穿戴指势识别方法

基于彩色图像中红、绿、蓝3分量强度在阴影区域存在差异,根据小波变换在时域和空域均具有优异的局部化特征,结合背景差分,进行小波多尺度变换,提取视频指势对象,所提方法不需场景学习与训练、手工校正及先验假设等信息,可克服动态场景变化、阴影、噪声干扰等影响,具有强的鲁棒性.基于人类生物结构特征,采用不易遮挡和不受人脸朝向、姿态、光照变化等影响的头项特征代替人眼特征,保证了人机交互活动的自由性和自然性,且提高了人机交互的时效性.融合手指尖特征和手臂中心轴线及其外极线的多几何约束策略,采用求解反对应方法.确保手指特征匹配对应的正确性.通过实验验证,证实了上述方法有效、可行,可应用于实时、非穿戴的自然指势视觉3维人机交互中.