Spectra of shape contexts: An application to symbol recognition

The pixel-level constraint (PLC) histograms are known for robustness and invariance in symbol recognition but limited in O(N³) complexity. This paper proves that matching two PLC histograms can approximately be solved as matching the power spectra of the corresponding shape contexts. As a result, spectra of shape contexts (SSC) inherit robustness and invariance from PLC while the computational cost can be reduced. Moreover, a maximum clique based scheme is proposed for outlier rejection. The theoretical and experimental validation justifies that SSC possesses the desired properties for symbol recognition, that is, robustness, invariance, and efficiency. It outperforms PLC in terms of robustness and time efficiency, and shape context in terms of rotation invariance.     

Shape recognition based on Kernel-edit distance

In this paper a kernel method for shape recognition is proposed. The approach is based on the edit distance between pairs of shapes after transforming them into symbol strings. The transformation of shapes into symbol strings is invariant to similarity transforms and can handle partial occlusions. Representation of shape contours uses the shape contexts and applies dynamic programming for finding the correspondence between points over shape contours. Corresponding points are then transformed into symbolic representation and the normalized edit distance computes the dissimilarity between pairs of strings in the database. Obtained distances are then transformed into suitable kernels which are classified using support vector machines. Experimental results over a variety of shape databases show that the proposed approach is suitable for shape recognition.     

Hand movement recognition based on biosignal analysis

This paper proposes a methodology that analyses and classifies the electromyographic (EMG) signals using neural networks to control multifunction prostheses. The control of these prostheses can be made using myoelectric signals taken from surface electrodes. Finger motions discrimination is the key problem in this study. Thus the emphasis, in the proposed work, is put on myoelectric signal processing approaches. The EMG signals classification system was established using the linear neural network. The experimental results show a promising performance in classification of motions based on biosignal patterns.     

用形状分布识别圆环体

给出了一种结合最小有向包围盒以及形状分布的识别圆环体及其参数的算法。首先建立基本体素的最小有向包围盒,对体素进行标准化;然后生成其D2形状分布曲线,计算此曲线分别与标准球体形状分布曲线、标准圆形状分布曲线的EMD（Earth Mover’s Distance）值以及相应的副半径;最后通过比较两个副半径的大小来判断此体素是否为圆环体,并由最小有向包围盒的边长给出圆环体的参数。该算法不需要任何交互操作,而且能够识别发生一定外形改变的圆环体,抗噪能力强。     

基于距离限定优化的人脸识别

针对现有人脸识别方法对人脸角度、表情、姿态等因素较为敏感且准确率低的问题,提出了一种基于距离限定优化算法的人脸识别模型。该模型对人脸识别方法的改进有两点：a)利用LBP算子提取人脸图像纹理谱特征图,然后与原始人脸图像的R、G、B通道进行融合,将融合后的图像矩阵作为神经网络的输入,丰富了人脸的纹理特征;b)对误差函数进行改进,使用阈值和边界值约束特征向量的距离,对模型构建新的优化目标,使得相同对象的人脸图像在特征空间中具有较小的欧氏距离,不同对象的人脸图像在特征空间中具有较大的欧氏距离。通过在非限制场景下的LFW人脸库上进行实验,表明该模型准确率分别达到99.15%,能有效地提高人脸识别准确率,具有很好的鲁棒性。     

基于距离分布直方图的数字识别算法

由于自由字体与手写体数字形态的多变性,以往研究中具有较高准确率的算法往往牺牲了快速性,而具有实时性优势的算法却容易引起错误率的上升。针对这个问题,提出一种适用于快速数字识别的特征描述子——距离分布直方图(DDH),并在形状上下文的基础上提出一种既易于实现又具一定鲁棒性的描述子——形状累积直方图(SAH);然后将上述两个特征与其他改进后的拓扑特征相结合,组成最终的多特征矢量,由于其子矢量是由不同方法提取出的独特的特征,因此具有互补性;与此同时,算法中用三种组合特征训练了三个支持向量机来作分类器,综合它们给出的结果和自信度来给出最后的分类结果。在自建数据集、MNIST和USPS数据集上的实验结果显示,平均正确率最高达到了99.21%,证明了算法的高效性和鲁棒性。     

基于测地距离的KPCA人脸识别

针对人脸检测数据集中的信息均为高维特征向量且人脸识别易受表情变化影响等问题,本文提出一种基于测地距离的KPCA人脸识别方法,该方法利用非线性方法提取主成分。先采用KPCA方法把人脸数据映射到高维空间,进而在高维空间中提取人脸的主成分,其中核函数为多项式核函数;然后引入测地距离替换原来的欧氏距离进行相似度量,其能更准确地测量出两像素点间的实际距离,使得人脸识别率受表情变化影响小。该方法不但可以实现降维,而且还能达到有效提取特征的目的。在ORL人脸库上的实验结果表明,该方法的识别率明显优于PCA、KPCA等方法的识别率。     

基于Bag of Features的手势识别

基于视觉的手势识别中,手势的识别效果易受手势旋转,光照亮度的影响,针对该问题,借鉴了目标识别和图像检索领域的Bag of Features(特征袋)算法,将Bag of Features算法应用到手势识别领域.通过SURF(加速鲁棒性特征)算法提取手势图像的特征描述符,使手势对尺度、旋转、光照具有很强的适应力,再应用Bag of Features算法把SURF特征描述符映射到一个统一维度的向量,即Bag of Features特征向量,再用支持向量机对图像得到的特征向量进行训练分类.实验结果表示,该方法不仅具有较高的时间效率,满足手势识别的实时性,而且即使在很大角度的旋转以及亮度的变化下,仍能达到较高的识别率.     

Hand gesture recognition using a neural network shape fitting technique

A new method for hand gesture recognition that is based on a hand gesture fitting procedure via a new Self-Growing and Self-Organized Neural Gas (SGONG) network is proposed. Initially, the region of the hand is detected by applying a color segmentation technique based on a skin color filtering procedure in the YCbCr color space. Then, the SGONG network is applied on the hand area so as to approach its shape. Based on the output grid of neurons produced by the neural network, palm morphologic characteristics are extracted. These characteristics, in accordance with powerful finger features, allow the identification of the raised fingers. Finally, the hand gesture recognition is accomplished through a likelihood-based classification technique. The proposed system has been extensively tested with success.     

基于几何形状分析的藏文字符识别

在分析藏文的几何结构的基础上,提出了一种基于几何形状分析的藏文识别方法。通过对藏文的辅音和元音符号的几何特征提取,达到学习的目的,根据印刷体藏文的组成结构特征,对其进行切分,进而分别对切分结果进行识别,将藏文字符转译为拉丁文,使得即使不认识藏文的人也能“读”藏文。实验结果表明,该方法的正确率达89%以上。     

Efficient shape matching using shape contexts

We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of shape contexts to obtain prototypical shape pieces.     

一种基于二次直方图距离的人脸识别方法

提出一种非约束条件下的人脸识别方法。利用Prewitte算子将人脸图像转换成特征图像以保护更多的局部信息,并将特征图像划分为多个区域特征向量表示人脸,通过调整二次直方图距离中的权系数矩阵以降低干扰因素的影响,利用改进的距离测度计算特征图像间的相似度。实验结果表明该算法与传统的识别方法相比,有一定的人脸特征描述和识别性能。     

基于量子模距离的说话人识别方法

概率测度和距离测度是模式识别最基本的两种测度,矢量量化算法是典型的基于距离测度的模式识别算法。根据量子模距离测度理论,在矢量量化算法的基础上,探索一种基于量子模距离的说话人识别方法。该方法针对说话人语音的时变性、随机性、特征维数较高等特点,将一帧语音信号视为一个量子态,并根据量子测量理论,对量子态之间进行模距离测量,从而对量子态进行有效的分类和聚类。研究表明该方法能有效地降低语音信号处理的复杂度。在经典计算机上的仿真表明,该方法在运行时间上略优于矢量量化算法,在识别率上明显优于矢量量化算法,为说话人识别的理论研究提供了新的途径。     

基于距离度量学习的煤岩识别方法

提出了一种基于距离度量学习的煤岩识别方法。该方法首先从煤岩图像训练集中提取煤岩图像特征;然后学习到特定的距离度量,使得煤样本特征间、岩石样本特征间距离变小,煤样本特征与岩石样本特征间距离变大,以提高分类识别效果;最后采用分类器进行煤岩识别。实验结果表明,对于煤岩样本图像的LBP特征、HOG特征、GLCM特征,与基于欧式距离、LDA、ITML的煤岩识别方法相比,该方法具有更高的煤岩识别率。     

Hand gesture recognition based on dynamic Bayesian network framework

In this paper, we propose a new method for recognizing hand gestures in a continuous video stream using a dynamic Bayesian network or DBN model. The proposed method of DBN-based inference is preceded by steps of skin extraction and modelling, and motion tracking. Then we develop a gesture model for one- or two-hand gestures. They are used to define a cyclic gesture network for modeling continuous gesture stream. We have also developed a DP-based real-time decoding algorithm for continuous gesture recognition. In our experiments with 10 isolated gestures, we obtained a recognition rate upwards of 99.59% with cross validation. In the case of recognizing continuous stream of gestures, it recorded 84% with the precision of 80.77% for the spotted gestures. The proposed DBN-based hand gesture model and the design of a gesture network model are believed to have a strong potential for successful applications to other related problems such as sign language recognition although it is a bit more complicated requiring analysis of hand shapes.     

基于Kinect和变形雅可比-傅里叶矩的手势识别

为了使人机交互变得更加自然,提出利用Kinect体感器获取手势深度图像;利用变形雅可比-傅里叶矩对手势图像进行特征提取;利用最小欧氏距离分类器进行建模、分类,实现手势识别.用Kinect体感器获取手部深度数据流,深度数据结合阈值分割法,可以有效地实现手势的分割.变形雅可比-傅里叶矩是一种不变矩,不变矩具有灰度、平移、旋转和尺度不变性,适合用于多畸变不变图像的特征提取.实验对5种手势进行了测试,平均识别率为95.2％,实验结果表明:该方法具有较高的识别率.     

基于Leap Motion和支持向量机的手势识别

为了使手势识别在更多的领域得到推广及应用,提出了基于Leap Motion体感设备实时跟踪技术获取手势三维空间坐标信息的方法,并从中分别提取角度信息和相对坐标信息,构建手势特征数据,建立手势识别模型.对特征数据进行归一化处理后,利用支持向量机(SVM)分类器进行训练、建模和分类,实现手势识别.实验结果表明:以角度数据和坐标数据作为手势特征的方法可行,平均识别率分别为96.6%和91.8%.通过对比可以得出:以角度数据作为特征值具有较高的准确性和鲁棒性,并避免了单纯依照一种特征值产生的局限性.     

利用基于颜色的自适应形状模型实现手势跟踪

提出了一种基于颜色的自适应形状模型,并利用该模型实现了图像序列中的实时手势跟踪.跟踪算法基于自适应的颜色模型实现准确的手部轮廓提取,并利用基于二维颜色模型的粒子滤波器实现序列图像中跟踪目标的运动估计.实验结果表明了基于颜色的自适应形状模型对凸形与凹形手部轮廓均能达到准确的手部轮廓提取,并能满足图像序列手势跟踪的实行性要求.     

Stop-sign recognition based on color/shape processing

This paper presents a robust vision-based stop-sign reconition technique based on sequential processing of color and shape. The primary red-green-blue color coordinate system is first transformed into the saturation-hue-brightness color coordinate system. This color coordinate system allows the red color area of a stop sign to be bounded under various brightness conditions caused by weather, sun angle, or shadows. A combination of a median filter, a morphological filter, Sobel edge operator, and Hough transform is then employed to obtain the boundary contour. It is demonstrated that the parameters of eight straight lines representing the octagonal sides are sufficient for this purpose. Experimental results indicate that stop signs are successfully distinguished from other traffic sighs and background clutter.