基于数据融合的遥感图象处理技术

简要地回顾了数据融合技术产生,发展的必然性,以及学者们提出的几种相关定义;尽可能详细地分析了数据融合的框架结构。包括像素层,特征层和决策层三层数据融合,并重点分析了各个数据融合层中的融合方法,以及这些方法在遥感图象处理中的应用,由于数据融合与遥感图象分类,目标检测,变化检测,目标识别的密切相关性,还对数据融合与这些应用的结合作了一定的分析。最后给出了结论和展望。     

基于BGRU-FUS-NN神经网络的姿态情感计算方法研究

情感计算研究是近些年人机交互领域的热门研究方向,其相关研究目前主要集中在面部表情和语音模态,基于姿态模态的情感计算研究相对较少.文中提出了一种基于姿态的新型情感计算算法,利用虚拟现实(VR)设备来唤醒用户的情感,使用摄像机采集用户的非表演动作数据,重新定义了19个人体运动关键点,将用户动作数据转换为相应骨骼点的3D坐标.在已有的基本特征的基础上,加入了高级动态特征,构造了一个能够更加完善地描述肢体运动的80D特征列表.在融合神经网络模型(FUS-NN)的基础上,使用循环门控单元(GRU)替代长短期记忆神经网络(LSTM),并添加正规层(Layer-Normalization),丢弃层(Layer-Dropout)和减少堆叠层数等策略,提出了双向循环门控单元融合神经网络(BGRU-FUS-NN)模型.使用了基于唤醒(arousal)和效价(valence)的情感模型进行情感分类,针对4分类任务和8分类任务,准确率比FUS-NN模型分别提升了7.22%和5.15%.     

基于SVM特征层融合的集成性身份识别模型

多生物特征融合识别是提高身份识别性能的有效方法,提出一种基于特征层融合的识别模型。以人脸与虹膜为例,首先对这两种图像分别进行预处理,然后对人脸采用PCA、Fisherface方法,对虹膜采用小波变换、多通道Gabor滤波方法,进行特征提取得到各自的初始特征向量,由此生成融合特征向量,最后利用SVM对融合特征向量进行分类,实现特征层融合识别。仿真实验结果表明,同等条件下,该融合方法的识别效果优于常见识别方法。     

基于人工情感的脸部表情识别的研究

脸部特征的提取和各种特征所代表的表情状态是识别是脸部表情识别过程中的重要步骤。该文研究了脸部表情识别方面的一些进展,概括论述了面部表情识别的主要研究内容,以及图像预处理,特征提取,图像识别和表情识别的主要算法和方法。研究表明,在正面人脸和无背景时识别效果较好;在复杂背景下,或人脸被部分遮挡或角度偏转角度较大时,识别效果不好,它的识别效果离实用还有较大的距离,还需要进一步研究。     

人脸表情识别研究进展

人脸表情识别(Facial Expression Recognition,FER)是计算机视觉、机器学习、人工智能等领域的重要研究方向,目前已经成为国内外学者的研究热点。介绍了FER系统流程,总结了表情特征提取和表情分类的常用方法以及近年来国内外学者对这些方法的改进,并对这些方法的优缺点进行比较。最后,对目前FER研究的难点问题进行了分析,并对FER未来的发展方向进行展望。     

Automatic facial expression analysis: a survey

Over the last decade, automatic facial expression analysis has become an active research area that finds potential applications in areas such as more engaging human-computer interfaces, talking heads, image retrieval and human emotion analysis. Facial expressions reflect not only emotions, but other mental activities, social interaction and physiological signals. In this survey, we introduce the most prominent automatic facial expression analysis methods and systems presented in the literature. Facial motion and deformation extraction approaches as well as classification methods are discussed with respect to issues such as face normalization, facial expression dynamics and facial expression intensity, but also with regard to their robustness towards environmental changes.     

Face recognition based on pixel-level and feature-level fusion of the top-level’s wavelet sub-bands

The traditional wavelet-based approaches directly use the low frequency sub-band of wavelet transform to extract facial features. However, the high frequency sub-bands also contain some important information corresponding to the edge and contour of face, reflecting the details of face, especially the top-level’s high frequency sub-bands. In this paper, we propose a novel technique which is a joint of pixel-level and feature-level fusion at the top-level’s wavelet sub-bands for face recognition. We convert the problem of finding the best pixel-level fusion coefficients of high frequency wavelet sub-bands to two optimization problems with the help of principal component analysis and linear discriminant analysis, respectively; and propose two alternating direction methods to solve the corresponding optimization problems for finding transformation matrices of dimension reduction and optimal fusion coefficients of the high frequency wavelet sub-bands. The proposed methods make full use of four top-level’s wavelet sub-bands rather than the low frequency sub-band only. Experiments are carried out on the FERET, ORL and AR face databases, which indicate that our methods are effective and robust.     

Representation of facial expression categories in continuous arousal–valence space: Feature and correlation

Representation of facial expressions using continuous dimensions has shown to be inherently more expressive and psychologically meaningful than using categorized emotions, and thus has gained increasing attention over recent years. Many sub-problems have arisen in this new field that remain only partially understood. A comparison of the regression performance of different texture and geometric features and the investigation of the correlations between continuous dimensional axes and basic categorized emotions are two of these. This paper presents empirical studies addressing these problems, and it reports results from an evaluation of different methods for detecting spontaneous facial expressions within the arousal–valence (AV) dimensional space. The evaluation compares the performance of texture features (SIFT, Gabor, LBP) against geometric features (FAP-based distances), and the fusion of the two. It also compares the prediction of arousal and valence, obtained using the best fusion method, to the corresponding ground truths. Spatial distribution, shift, similarity, and correlation are considered for the six basic categorized emotions (i.e. anger, disgust, fear, happiness, sadness, surprise). Using the NVIE database, results show that the fusion of LBP and FAP features performs the best. The results from the NVIE and FEEDTUM databases reveal novel findings about the correlations of arousal and valence dimensions to each of six basic emotion categories.     

基于D-S证据理论的表情识别技术

在情感计算理论基础上,提出了基于D-S理论的信息融合的表情识别技术,设计并实现了系统IFFER.在表情识别模块中的分类器训练采用JAFFE表情库.识别中首先利用色度匹配及亮度匹配将人脸图像进行眼部及嘴部的分割,再分别用训练好的眼部SVM分类器及嘴部SVM分类器进行识别,将识别后的结果利用D-S证据理论进行融合.实验结果表明,对分割后的两部分图像进行识别,无论从训练上还是识别上,数据的维数都大大减少,提高了效率.在识别率上,融合后的结果相对于融合前的有显著的提高.     

基于语音和视频图像的多模态情感识别研究

情感识别依靠分析生理信号、行为特征等分析情感类别,是人工智能重要研究领域之一。为提高情感识别的准确性和实时性,提出基于语音与视频图像的多模态情感识别方法。视频图像模态基于局部二值直方图法（LBPH）+稀疏自动编码器（SAE）+改进卷积神经网络（CNN）实现;语音模态基于改进深度受限波尔兹曼机（DBM）和改进长短时间记忆网络（LSTM）实现;使用SAE获得更多图像的细节特征,用DBM获得声音特征的深层表达;使用反向传播算法（BP）优化DBM和LSTM的非线性映射能力,使用全局均值池化（GAP）提升CNN和LSTM的响应速度并防止过拟合。单模态识别后,两个模态的识别结果基于权值准则在决策层融合,给出所属情感分类及概率。实验结果表明,融合识别策略提升了识别准确率,在中文自然视听情感数据库（cheavd）2.0的测试集达到74.9%的识别率,且可以对使用者的情感进行实时分析。     

信息融合技术在情绪识别领域的研究展望

简要介绍目前几种基于不同数据源的情绪识别方法和信息融合技术基础, 为工程技术人员提供一定的理论背景。对多源信息融合领域的情绪识别现状进行了分类介绍, 说明和分析了基于多源信息融合的情感识别存在的问题, 简述了其在情绪识别领域的应用前景。     

Hi4D-ADSIP 3-D dynamic facial articulation database

The face is an important medium used by humans to communicate, and facial articulation also reflects a person's emotional and awareness states, cognitive activity, personality or wellbeing. With the advances in 3-D imaging technology and ever increasing computing power, automatic analysis of facial articulation using 3-D sequences is becoming viable. This paper describes Hi4D-ADSIP — a comprehensive 3-D dynamic facial articulation database, containing scans with high spatial and temporal resolution. The database is designed not only to facilitate studies on facial expression analysis, but also to aid research into clinical diagnosis of facial dysfunctions. The database currently contains 3360 facial sequences captured from 80 healthy volunteers (control subjects) of various age, gender and ethnicity. The database has been validated using psychophysical experiments used to formally evaluate the accuracy of the recorded expressions. The results of baseline automatic facial expression recognition methods using Eigen- and Fisher-faces are also presented alongside some initial results obtained for clinical cases. This database is believed to be one of the most comprehensive repositories of facial 3-D dynamic articulations to date. The extension of this database is currently under construction aiming at building a comprehensive repository of representative facial dysfunctions exhibited by patients with stroke, Bell's palsy and Parkinson's disease.     

Facial expression recognition on multiple manifolds

Manifold learning has been successfully applied to facial expression recognition by modeling different expressions as a smooth manifold embedded in a high dimensional space. However, the assumption of single manifold is still arguable and therefore does not necessarily guarantee the best classification accuracy. In this paper, a generalized framework for modeling and recognizing facial expressions on multiple manifolds is presented which assumes that different expressions may reside on different manifolds of possibly different dimensionalities. The intrinsic features of each expression are firstly learned separately and the genetic algorithm (GA) is then employed to obtain the nearly optimal dimensionality of each expression manifold from the classification viewpoint. Classification is performed under a newly defined criterion that is based on the minimum reconstruction error on manifolds. Extensive experiments on both the Cohn-Kanade and Feedtum databases show the effectiveness of the proposed multiple manifold based approach.     

基于计算机视觉的表情识别技术综述

介绍了基于计算机视觉的表情识别的定义、应用前景和困难所在；阐述了表情识别的步骤，并比较了与人脸识别的异同；重点按照不同的特征提取和分类器设计方法对表情识别技术进行了综述。介绍了几何特征、统计特征、频率域特征和运动特征的提取方法及线性、神经网络、支持向量机分类器的设计和选择方法，并进行了简单的分析和比较；最后展望了表情识别的发展方向。     

Level of interest sensing in spoken dialog using decision-level fusion of acoustic and lexical evidence

Automatic detection of a user's interest in spoken dialog plays an important role in many applications, such as tutoring systems and customer service systems. In this study, we propose a decision-level fusion approach using acoustic and lexical information to accurately sense a user's interest at the utterance level. Our system consists of three parts: acoustic/prosodic model, lexical model, and a model that combines their decisions for the final output. We use two different regression algorithms to complement each other for the acoustic model. For lexical information, in addition to the bag-of-words model, we propose new features including a level-of-interest value for each word, length information using the number of words, estimated speaking rate, silence in the utterance, and similarity with other utterances. We also investigate the effectiveness of using more automatic speech recognition (ASR) hypotheses (n-best lists) to extract lexical features. The outputs from the acoustic and lexical models are combined at the decision level. Our experiments show that combining acoustic evidence with lexical information improves level-of-interest detection performance, even when lexical features are extracted from ASR output with high word error rate.     

多文化场景下的多模态情感识别

自动情感识别是一个非常具有挑战性的课题,并且有着广泛的应用价值.本文探讨了在多文化场景下的多模态情感识别问题.我们从语音声学和面部表情等模态分别提取了不同的情感特征,包括传统的手工定制特征和基于深度学习的特征,并通过多模态融合方法结合不同的模态,比较不同单模态特征和多模态特征融合的情感识别性能.我们在CHEAVD中文多模态情感数据集和AFEW英文多模态情感数据集进行实验,通过跨文化情感识别研究,我们验证了文化因素对于情感识别的重要影响,并提出3种训练策略提高在多文化场景下情感识别的性能,包括：分文化选择模型、多文化联合训练以及基于共同情感空间的多文化联合训练,其中基于共同情感空间的多文化联合训练通过将文化影响与情感特征分离,在语音和多模态情感识别中均取得最好的识别效果.     

面部表情识别研究进展

面部表情识别是计算机视觉中一个具有挑战性的课题,该文对国内外面部表情识别做了系统综述与比较,分析了面部表情识别目前存在的问题,并对今后发展提出了几点思考.