光电混合处理系统在机器人视觉目标识别中的应用研究

分析了光电混合处理系统应用于机器人视觉识别的可行性和研究意义,评述了光电 混合处理系统在光学模式识别和机器人视觉识别领域中的研究现状．提出将JTC系统在机器 人视觉识别中的应用划分为五个研究层次,分析综述了与各类研究层次相关的形态学JTC和 三维JTC的代表性算法及JTC硬件结构,以此作为机器人视觉识别光电混合处理系统的研究基 础．     

Improved low-contrast retinal recognition using compression-based joint wavelet transform correlator

Retinal recognition by using compression-based joint wavelet transform correlator (CBJWTC) is proposed in order to solve poor contrast problem of fundus images. The simulation results show that by using a wavelet filter dilated at a proper dilation, the CBJWTC offers better recognition performance than the conventional JTC, regardless of the reference contrast.     

Joint target tracking and classification via RFS-based multiple model filtering

Firstly, a multiple model extension of the random finite set (RFS)-based single-target Bayesian filtering (STBF), referred as MM-STBF, is presented to accommodate the possible target maneuvering behavior in a straightforward manner. This paper is concerned with joint target tracking and classification (JTC) which are closely coupled. In particular, we take into account extraneous target-originated measurements which were not modeled in the existing JTC algorithms. Therefore, the main contribution is that the paper derives a new JTC algorithm based on the MM-STBF, i.e., MM-STBF–JTC. The MM-STBF–JTC is an optimal Bayesian solution, which can simultaneously accommodate unknown data association, miss-detection, clutter and several measurements originated from a target. The MM-STBF–JTC can reduce to a traditional JTC algorithm under some assumptions. The simulation results are provided to demonstrate the tracking and classification performance of the MM-STBF–JTC algorithm.     

运动目标联合跟踪与分类研究综述*

目标跟踪与分类是现代跟踪系统的基本功能,不同的数据特性使得传统研究经常忽视二者之间的联系而将其分开处理。联合跟踪与分类研究则充分利用二者之间的耦合关系,使之互为补充,达到提高各自精度的目的。在分析联合跟踪与分类算法基本原理的基础上,按机理将其分为基于贝叶斯推理、D-S理论和贝叶斯风险框架下的联合跟踪与分类算法,并对三种框架下的算法进行了综述与性能比较。指出了联合跟踪与分类算法研究存在的问题及进一步研究的方向。     

Face recognition robust to left/right shadows; facial symmetry

This paper has proposed an efficient shaded-face pre-processing technique using front-face symmetry. The existing face recognition PCA technique has a shortcoming of making illumination variation lower the recognition performance of a shaded face. The study has aimed to improve the performance by using the symmetry of the left and right face.In order to evaluate the performance of the proposed face recognition method, the study experimented with the Yale face database with left/right shadows. The experimental methods for this are as following: the existing PCA, PCA with first three eigenfaces excluded, histogram equalization and the proposed method. As the result, it was shown that the proposed method has a rather excellent recognition performance (98.9%).     

工业器件上的字符提取及识别

介绍了一个工业器件上字符识别和获取系统.在字符提取阶段,给出了两种字符的提取方法以及互补Ostu二值化方法.在识别阶段,对第一类字符利用TM 矩和仿射不变矩提取特征并且组合成特征向量,然后利用交叉相关来识别; 对第二类字符利用模板匹配法,基于Hu不变矩和TM 矩的交叉相关分别得到各自的识别结果,然后采用投票原则来作出最后的判决.实验结果表明提出的方案是可行的和合理的.     

复杂噪声环境下语音识别研究

语音识别是人机交互的重要方式,针对传统语音识别系统对含噪语音识别性能较差、特征选择不恰当的问题,提出一种基于迁移学习的深度自编码器循环神经网络模型。该模型由编码器、解码器以及声学模型组成,其中,声学模型由堆栈双向循环神经网络构成,用于提升识别性能;编码器和解码器均由全连接层构成,用于特征提取。将编码器结构及参数迁移至声学模型进行联合训练,在含噪Google Commands数据集上的实验表明本文模型有效增强了含噪语音的识别性能,并且具有较好的鲁棒性和泛化性。     

基于知识图谱的智能问答意图识别联合模型

针对现有意图识别联合模型在专业领域知识图谱问答中容易发生识别领域实体以及问句分类错误的情况,提出一个结合了领域知识图谱的意图识别联合模型。该模型有三步,将领域知识图谱中实体对应的本体标签以及本体间关系导入训练数据集,形成包含本体标签的知识文本以及额外包含本体关系的知识文本图;通过字符级嵌入和位置信息嵌入将包含了本体标签的知识文本转化成嵌入表示并依据知识文本图创建实体关系可视矩阵,明确知识文本各成分的相关程度;将嵌入表示和实体关系可视矩阵输入模型编码层进行模型的训练。以高速列车领域知识图谱为例,经过准确率和召回率的验证,以该方法训练出的模型在高速列车领域问答数据集的意图识别任务上取得了更好的表现。     

Facial expression recognition using constructive feedforward neural networks

A new technique for facial expression recognition is proposed, which uses the two-dimensional (2D) discrete cosine transform (DCT) over the entire face image as a feature detector and a constructive one-hidden-layer feedforward neural network as a facial expression classifier. An input-side pruning technique, proposed previously by the authors, is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having five facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images of 20 men are used for generalization and testing. Confusion matrices calculated in both network training and generalization for four facial expressions (smile, anger, sadness, and surprise) are used to evaluate the performance of the trained network. It is demonstrated that the best recognition rates are 100% and 93.75% (without rejection), for the training and generalizing images, respectively. Furthermore, the input-side weights of the constructed network are reduced by approximately 30% using our pruning method. In comparison with the fixed structure back propagation-based recognition methods in the literature, the proposed technique constructs one-hidden-layer feedforward neural network with fewer number of hidden units and weights, while simultaneously provide improved generalization and recognition performance capabilities.     

基于多任务联合判别稀疏表示的人脸识别

针对人脸识别中由于姿态、光照及噪声等影响造成的识别率不高的问题,提出一种基于多任务联合判别稀疏表示的人脸识别方法。首先提取人脸的局部二值特征,并基于多个特征建立一个联合分类误差与表示误差的过完备字典学习目标函数。然后,使用一种多任务联合判别字典学习方法,将多任务联合判别字典与最优线性分类器参数联合学习,得到具有良好表征和鉴别能力的字典及相应的分类器,进而提高人脸识别效果。实验结果表明,所提方法相比其他稀疏人脸识别方法具有更好的识别性能。     

Estimation of a nonvisible field-of-view mobile target incorporating optical and acoustic sensors

This paper presents a nonvisible field-of-view (NFOV) target estimation approach that incorporates optical and acoustic sensors. An optical sensor can accurately localize a target in its field-of-view whereas the acoustic sensor could estimate the target location over a much larger space, but only with limited accuracy. A recursive Bayesian estimation framework where observations of the optical and acoustic sensors are probabilistically treated and fused is proposed in this paper. A technique to construct the observation likelihood when two microphones are used as the acoustic sensor is also described. The proposed technique derives and stores the interaural level difference of observations from the two microphones for different target positions in advance and constructs the likelihood through correlation. A parametric study of the proposed acoustic sensing technique in a controlled test environment, and experiments with an NFOV target in an actual indoor environment are presented to demonstrate the capability of the proposed technique.     

Optimizing image focus for 3D shape recovery through genetic algorithm

Three-dimensional information of objects is advantageous and widely used in multimedia systems and applications. Shape form focus (SFF) is a passive optical technique that reconstructs 3D shape of an object using a sequence of images with varying focus settings. In this paper, we propose an optimization of the focus measure. First, Wiener filter is applied for noise reduction from the image sequence. At the second stage, genetic algorithm (GA) is applied for focus measure optimization. GA finds the maximum focus measurement under a fitness criterion. Finally, 3D shape of the object is determined by maximizing focus measure along the optical direction. The proposed method is tested with image sequences of simulated and real objects. The performance of the proposed technique is analyzed through statistical criteria such as root mean square error (RMSE) and correlation. Comparative analysis shows the effectiveness of the proposed method.     

High performance iris recognition based on 1-D circular feature extraction and PSO–PNN classifier

In this paper, a novel iris feature extraction technique with intelligent classifier is proposed for high performance iris recognition. We use one dimensional circular profile to represent iris features. The reduced and significant features afterward are extracted by Sobel operator and 1-D wavelet transform. So as to improve the accuracy, this paper combines probabilistic neural network (PNN) and particle swarm optimization (PSO) for an optimized PNN classifier model. A comparative experiment of existing methods for iris recognition is evaluated on CASIA iris image databases. The experimental results reveal the proposed algorithm provides superior performance in iris recognition.     

基于分布式压缩感知的可穿戴多传感数据联合重构新方法

为提高可穿戴多传感数据远程联合重构性能,提出了一种基于分布式压缩感知的可穿戴多传感加速度数据联合重构新方法。该方法首先对可穿戴多传感原始数据压缩编码,将数据融合传送至远端服务器;然后,基于可穿戴传感数据的时空相关性,构建块稀疏贝叶斯学习联合重构算法,实现压缩数据解码,准确重构各传感原始数据;最后,新方法对美国加州伯克利大学可穿戴多传感运动数据进行分析。实验结果表明,对不同编码采样率,文章所提方法重构性能明显优于传统的算法,并且能够准确解码压缩数据,有望在远程医疗环境下推广应用。     

相关滤波器和2DPCA相融合的变光照人脸识别

为解决变光照下人脸识别的识别率低问题,提出一种最佳相关滤波和2DPCA相融合的光照人脸识别方法。通过采用特定类2DPCA重构人脸图像,生成一对相关滤波器;测试人脸图像通过相关性滤器将投影到二维子空间中,并根据预先设定的峰旁瓣比阈值进行人脸识别;最后采用PIE和YaleB人脸库进行仿真实验。相比其他人脸识别方法,该方法获得了更高的人脸识别率,鲁棒性更强。     

Farsi/Arabic handwritten digit recognition using quantum neural networks and bag of visual words method

Handwritten digit recognition has long been a challenging problem in the field of optical character recognition and of great importance in industry. This paper develops a new approach for handwritten digit recognition that uses a small number of patterns for training phase. To improve performance of isolated Farsi/Arabic handwritten digit recognition, we use Bag of Visual Words (BoVW) technique to construct images feature vectors. Each visual word is described by Scale Invariant Feature Transform (SIFT) method. For learning feature vectors, Quantum Neural Networks (QNN) classifier is used. Experimental results on a very popular Farsi/Arabic handwritten digit dataset (HODA dataset) show that proposed method can achieve the highest recognition rate compared to other state of the arts methods.     

基于集成的年龄估计方法

近十年来, 由于广泛的应用前景, 关于人脸识别的研究得到了广泛的关注. 但目前有一种影响人脸识别技术的因素尚未被研究者所重视, 那就是年龄变化. 而在适用于年龄变化的人脸识别技术中有一个重要的问题, 即年龄估计. 本文基于典型相关分析和代价敏感学习提出了两种年龄估计算法, 并在此基础上利用集成技术来提高年龄估计的准确性. 最终实验结果验证了本文方法的有效性.     

基于边缘信息的红外与可见光图像匹配技术

对红外、可见光两种不同谱段图像的匹配技术进行研究。在比较不同预处理方法后，采用边缘增强而不是边缘提取的预处理技术，以增强图像的有效边缘信息，突出不同谱段图像的共性特征，然后使用去均值归一化互相关的办法进行相似性度量。在实验中，通过确定影响匹配正确率的关键指标，对不同预处理方法和匹配策略得到的匹配结果进行比较分析，验证方法的有效性。