根据混合选择策略的直觉模糊核匹配追踪集成算法

为了从分类器集成系统中选择出一组差异性大的子分类器,从而提高集成系统的泛化能力,提出了一种基于混合选择策略的直觉模糊核匹配追踪算法.基本思想是通过扰动训练集和特征空间生成一组子分类器;然后采用k均值聚类算法将对所得子分类器进行修剪,删去其中的冗余分类器;最后根据实际识别目标动态选择出较高识别率的分类器组合,使选择性集成规模能够随识别目标的复杂程度而自适应地变化,并基于预期识别精度实现循环集成.实验结果表明,与其他常用的分类器选择方法相比,本文方法灵活高效,具有更好的识别效果和泛化能力.     

一种基于图像区域系综分类的室外场景理解方法

多层感知机分类器是一种有效的数据分类方法，但其分类性能受训练样本空间的限制。通过多层感知机分类器系综提高室外场景理解中图像区域的分类性能，提出了一种自动识别室外场景图像中多种景物所属概念类别的方法。该方法首先提取图像分割区域的低层视觉特征，然后基于系综分类方法建立区域视觉特征和语义类别的对应关系，通过合并相同标注区域，确定图像中景物的高层语义。对包含5种景物的150幅图像进行测试，识别率达到了87％。与基于多层感知机方法的实验结果相比，本文提出的方法取得了更好的性能，这表明该方法适合于图像区域分类。此外，系综方法还可以推广到其他的分类问题。     

Estimating 3D hand pose using hierarchical multi-label classification

This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it is closely related to the problem of locating an articulated object. Each different pattern class corresponds to the hand in a different pose, or set of poses. For this problem obtaining labelled training data of the hand in a given pose can be problematic. Given a parametric 3D model, generating training data in the form of example images is cheap, and we demonstrate that it can be used to design classifiers almost as good as those trained using non-synthetic data. We compare a variety of different template-based classifiers and discuss their merits.     

脑皮层视觉认知量化模型及其在目标检测定位中的应用

MIT大学的Rieseshuber和Poggio提出了脑颞叶皮层视觉认知系统的标准量化模型(QMVC),这种前馈式层级模型很好地仿效了脑皮层视觉从简单认知元到复杂认知元的识别机理.本文由QMVC模型提取出一组新的特征矢量,这组特征矢量具有对目标变换的不变性.基于QMVC模型的特征矢量建立了新的目标识别系统结构,新目标识别系统对各类目标具有不错的识别率和ROC特性.最后本文引入了尺度窗技术,将新特征应用于复杂场景中的目标检测和定位,实验结果说明本文的新目标检测方法是有效的.     

Improving object classification robustness in RGB-D using adaptive SVMs

Nowadays object recognition is a fundamental capability for an autonomous robot in interaction with the physical world. Taking advantage of new sensing technologies providing RGB-D data, the object recognition capabilities increase dramatically. Object recognition has been well studied, however, known object classifiers usually feature poor generality and, therefore, limited adaptivity to different application domains. Although some domain adaptation approaches have been presented for RGB data, little work has been done on understanding the effects of applying object classification algorithms using RGB-D for different domains. Addressing this problem, we propose and comprehensively investigate an approach for object recognition in RGB-D data that uses adaptive Support Vector Machines (aSVM) and, in this way, achieves an impressive robustness in cross-domain adaptivity. For evaluation, two datasets from different application domains were used. Moreover, a study of state-of-the-art RGB-D feature extraction techniques and object classification methods was performed to identify which combinations (object representation - classification algorithm) remain less affected in terms of performance while switching between different application domains.     

英文字符特征提取系统

英文字符识别是模式识别的一个重要分支,具有广泛的应用领域.字符识别主要包括文档切分、单词切分、字符识别及后处理几部分.文中描述的是英文字符识别系统实现了从图像扫描到得到识别结果的全过程, 而字符特征提取是文本的重点内容.以五十二个英文字符为研究对象,具体包括了图像预处理、特征提取、建立模板、分类器设计、后处理等步骤.文章对OCR领域中应用比较广泛的网格特征、外围特征、穿越特征等特征和几种距离分类器分别进行比较分析,并进行大量的实验.实验结果表明识别准确率和识别处理时间方面具有良好性能.     

基于矩特征和证据理论的离线签名识别

论文首先对几种矩特征在离线签名识别中的性能进行了比较,在此基础上选取矩和一种基于中心矩的形状描述子(SDBCM)作为签名图象的形状特征,据此构造了两个距离权重k-NN分类器对签名图象进行初步识别。然后将两个k-NN分类器的度量层输出作为证据,用一种改进的证据理论合成公式对其进行融合得到最终识别结果。实验结果表明,新的识别方法是有效的。     

3D object recognition method with multiple feature extraction from LiDAR point clouds

During autonomous driving, fast and accurate object recognition supports environment perception for local path planning of unmanned ground vehicles. Feature extraction and object recognition from large-scale 3D point clouds incur massive computational and time costs. To implement fast environment perception, this paper proposes a 3D recognition system with multiple feature extraction from light detection and ranging point clouds modified by parallel computing. Effective object feature extraction is a necessary step prior to executing an object recognition procedure. In the proposed system, multiple geometry features of a point cloud that resides in corresponding voxels are computed concurrently. In addition, a scale filter is employed to convert feature vectors from uncertain count voxels to a normalized object feature matrix, which is convenient for object-recognizing classifiers. After generating the object feature matrices of all voxels, an initialized multilayer neural network (NN) model is trained offline through a large number of iterations. Using the trained NN model, real-time object recognition is realized using parallel computing technology to accelerate computation.

     

Combination of multiple classifiers using probabilistic dictionary and its application to postcode recognition

Combination of multiple classifiers is regarded as an effective strategy for achieving a practical system of handwritten character recognition. A great deal of research on the methods of combining multiple classifiers has been reported to improve the recognition performance of single characters. However, in a practical application, the recognition performance of a group of characters (such as a postcode or a word) is more significant and more crucial. With the motivation of optimizing the recognition performance of postcode rather than that of single characters, this paper presents an approach to combine multiple classifiers in such a way that the combination decision is carried out at the postcode level rather than at the single character level, in which a probabilistic postcode dictionary is utilized as well to improve the postcode recognition ability. It can be seen from the experimental results that the proposed approach markedly improves the postcode recognition performance and outperforms the commonly used methods of combining multiple classifiers at the single character level. Furthermore, the sorting performance of some particular bins with respect to the postcodes with low frequency of occurrence can be improved significantly at the same time.     

改进的贝叶斯多分类器组合规则

多分类器组合是提高识别效果的一条有效途径。文中提出一种用于多分类器组合的改进贝叶斯规则,即首先通过对大量样本的统计获得有关每个分类器识别性能的先验知识,将其作为多分类器组合的依据。组合时对每个类设置不同的阈值,使组合效果得以改善,这些阈值可以通过训练获得。在数字识别中的应用结果表明,改进的贝叶斯规则可以使多分类器的组合结果识别率和置信度得到明显提高。     

Class-specific multiple classifiers scheme to recognize emotions from speech signals

Automatic emotion recognition from speech signals is one of the important research areas, which adds value to machine intelligence. Pitch, duration, energy and Mel-frequency cepstral coefficients (MFCC) are the widely used features in the field of speech emotion recognition. A single classifier or a combination of classifiers is used to recognize emotions from the input features. The present work investigates the performance of the features of Autoregressive (AR) parameters, which include gain and reflection coefficients, in addition to the traditional linear prediction coefficients (LPC), to recognize emotions from speech signals. The classification performance of the features of AR parameters is studied using discriminant, k-nearest neighbor (KNN), Gaussian mixture model (GMM), back propagation artificial neural network (ANN) and support vector machine (SVM) classifiers and we find that the features of reflection coefficients recognize emotions better than the LPC. To improve the emotion recognition accuracy, we propose a class-specific multiple classifiers scheme, which is designed by multiple parallel classifiers, each of which is optimized to a class. Each classifier for an emotional class is built by a feature identified from a pool of features and a classifier identified from a pool of classifiers that optimize the recognition of the particular emotion. The outputs of the classifiers are combined by a decision level fusion technique. The experimental results show that the proposed scheme improves the emotion recognition accuracy. Further improvement in recognition accuracy is obtained when the scheme is built by including MFCC features in the pool of features.     

Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object's location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.     

高斯加权的多分类器物体追踪

针对在物体外观快速变化的情况下,大多数弱学习器不能捕获物体新的特征分布,导致追踪失败的问题,提出了高斯加权的联机多分类器增强算法。该算法为每一个领域问题定义一个弱分类器,每个弱分类器包括一个简单的视觉特征和阈值,引入高斯加权函数来权衡每个弱分类器在特定样本上的贡献,通过多分类器联合学习来提高追踪性能。在物体追踪过程中,联机多分类器在对物体定位的同时还能估计物体的姿态,能够成功地学习多模态外观模型,在物体外观快速变化的情况下追踪物体。实验结果表明：所提算法在经过一个较短序列的训练后,平均追踪错误率为12.8%,追踪性能明显提升。     

Methods for adaptive combination of classifiers with application to recognition of handwritten characters

This paper discusses two techniques for improving the recognition accuracy for online handwritten character recognition: committee classification and adaptation to the user. Combining classifiers is a common method for improving recognition performance. Improvements are possible because the member classifiers may make different errors. Much variation exists in handwritten characters, and adaptation is one feasible way of dealing with such variation. Even though adaptation is usually performed for single classifiers, it is also possible to use adaptive committees. Some novel adaptive committee structures, namely, the dynamically expanding context (DEC), modified current best learning (MCBL), and class-confidence critic combination (CCCC), are presented and evaluated. They are shown to be able to improve on their member classifiers, with CCCC offering the best performance. Also, the effect of having either more or less diverse sets of member classifiers is considered.Received: 17 September 2002, Accepted: 22 October 2002, Published online: 4 July 2003     

Stochastic model utilizing spectral and spatial characteristics

In remote sensing, because of physical properties of targets, sensor pixels in spatial proximity to one another are class conditionally correlated. Our main objective is to exploit this spatial correlation. Therefore, a two-dimensional causal first order Markov model was used to extract the spatial and spectral information and, based upon it, new object classifiers with improved performance were developed. First, the minimum distance (MT) and the maximum likelihood (ML) object classifiers are discussed. Then, based on the proposed model, these two classifiers are modified, and a linear object classifier is introduced. Finally, experimental results are presented.     

Recognition and pose estimation of unoccluded three-dimensionalobjects from a two-dimensional perspective view by banks of neuralnetworks

This paper describes a neural network (NN) based system for recognition and pose estimation of an unoccluded three-dimensional (3-D) object from any single two-dimensional (2-D) perspective view. The approach is invariant to translation, orientation, and scale. First, the binary silhouette of the object is obtained and normalized for translation and scale. Then, the object is represented by a set of rotation invariant features derived from the complex orthogonal pseudo-Zernike moments of the image. The recognition scheme combines the decisions of a bank of multilayer perceptron NN classifiers operating in parallel on the same data. These classifiers have different topologies and internal parameters, but are trained on the same set of exemplar perspective views of the objects. Next, two pose parameters, elevation and aspect angles, are obtained by a novel two-stage NN system consisting of a quadrant classifier followed by NN angle estimators. Performance is tested on clean and noisy data bases of military ground vehicles. Comparative studies with three other classifiers (a single NN, the weighted nearest-neighbor classifier, and a binary decision tree) are carried out.     

基于最小代价的多分类器动态集成

本文提出一种基于最小代价准则的分类器动态集成方法．与一般方法不同,动态集成是根据“性能预测特征”,动态地为每一样本选择最适合的一组分类器进行集成．该选择基于使误识代价与时间代价最小化的准则,改变代价函数的定义可以方便地达到识别率与识别速度之间的不同折衷．本文中提出了两种分类器动态集成的方法,并介绍了在联机手写汉字识别中的具体应用．在实验中使了３个分类器进行动态集成,因此,得到７种分类组合．在预先定义的代价意义下,我们比较了动态集成方法和其它７种固定方法的性能．实验结果证明了动态集成方法的高灵活性、实用性和提高系统综合性能的能力．