Facial expression recognition through modeling age-related spatial patterns

In this paper we tackle the problem of expression recognition by exploiting age-related spatial facial expression patterns, which carry crucial information that have not been thoroughly exploited. First, we conduct two statistic hypothesis tests to investigate age effect on the spatial patterns of expressions and on facial expression recognition respectively. Second, we propose two methods to recognize expressions by modeling age-related spatial facial expression patterns. One is a three-node Bayesian Network to classify expressions with the help of age from person-independent geometric features. The other is to construct multiple Bayesian networks to explicitly capture the spatial facial expression patterns for different ages. For both methods, age information is used as privileged information, which is only available during training, and is exploited during training to construct a better classifier. Statistic analyses on two benchmark databases, i.e. the Lifespan and the FACES, verify the age effect on spatial patterns of expressions and on facial expression recognition. Experimental results of expression recognition demonstrate the effectiveness of the proposed methods in modelling age-related spatial patterns as well as their superior expression recognition performance to existing approaches.     

A new method for positive and unlabeled learning with privileged information

Positive and unlabeled learning (PU learning) has been studied to address the situation in which only positive and unlabeled examples are available. Most of the previous work has been devoted to identifying negative examples from the unlabeled data, so that the supervised learning approaches can be applied to build a classifier. However, for the remaining unlabeled data, they either exclude them from the learning phase or force them to belong to a class, and this always limits the performance of PU learning. In addition, previous PU methods assume the training data and the testing data have the same features representations. However, we can always collect the features that the training data have while the test data do not have, these kinds of features are called privileged information. In this paper, we propose a new method, which is based on similarity approach for the problem of positive and unlabeled learning with privileged information (SPUPIL), which consists of two steps. The proposed SPUPIL method first conducts KNN method to generate the similarity weights and then the similarity weights and privileged information are incorporated to the learning model based on Ranking SVM to build a more accurate classifier. We also use the Lagrangian method to transform the original model into its dual problem, and solve it to obtain the classifier. Extensive experiments on the real data sets show that the performance of the SPUPIL is better than the state-of-the-art PU learning methods.

     

Integrating prior domain knowledge into discriminative learning using automatic model construction and phantom examples

Domain knowledge captures an expert's approximate understanding of the world, its objects, and their properties. When available, it should serve to augment the information in a classification learner's training set. But this form of prior knowledge does not easily fit into the statistical learning paradigm. We propose and evaluate the use of phantom examples to remedy this. Our system performs automated model construction and learns generative models for phantom examples that adapt to the need of individual tasks. The approach is validated on the challenging real-world task of distinguishing handwritten Chinese characters. The approach improves learning significantly, provides additional robustness, and works well even though the domain knowledge is imperfect and approximate.     

Efficiently learning the preferences of people

This paper presents a framework for optimizing the preference learning process. In many real-world applications in which preference learning is involved the available training data is scarce and obtaining labeled training data is expensive. Fortunately in many of the preference learning situations data is available from multiple subjects. We use the multi-task formalism to enhance the individual training data by making use of the preference information learned from other subjects. Furthermore, since obtaining labels is expensive, we optimally choose which data to ask a subject for labelling to obtain the most of information about her/his preferences. This paradigm—called active learning—has hardly been studied in a multi-task formalism. We propose an alternative for the standard criteria in active learning which actively chooses queries by making use of the available preference data from other subjects. The advantage of this alternative is the reduced computation costs and reduced time subjects are involved. We validate empirically our approach on three real-world data sets involving the preferences of people.     

一种基于改进CP网络与HMM相结合的混合音素识别方法

提出了一种基于改进对偶传播（ＣＰ）神经网络与隐驰尔可夫模型（ＨＭＭ）相结合的混合音素识别方法．这一方法的特点是用一个具有有指导学习矢量量化（ＬＶＱ）和动态节点分配等特性的改进的ＣＰ网络生成离散ＨＭＭ音素识别系统中的码书。因此,用这一方法构造的混合音素识别系统中的码书实际上是一个由有指导ＬＶＱ算法训练的具有很强分类能力的高性能分类器,这就意味着在用ＨＭＭ对语音信号进行建模之前,由码书产生的观测序列中     

The adaptive approach to abnormal situations recognition using images from condition monitoring systems

Decision support in equipment condition monitoring systems with image processing is analyzed. Long-run accumulation of information about earlier made decisions is used to realize the adaptiveness of the proposed approach. It is shown that unlike conventional classification problems, the recognition of abnormalities uses training samples supplemented with reward estimates of earlier decisions and can be tackled using reinforcement learning algorithms. We consider the basic stages of contextual multi-armed bandit algorithms during which the probabilistic distributions of each state are evaluated to evaluate the current knowledge of the states, and the decision space is explored to increase the decision-making efficiency. We propose a new decision-making method, which uses the probabilistic neural network to classify abnormal situation and the softmax rule to explore the decision space. A modelling experiment in image processing was carried out to show that our approach allows a higher accuracy of abnormality detection than other known methods, especially for small-size initial training samples.     

Individual recognition using gait energy image

In this paper, we propose a new spatio-temporal gait representation, called gait energy image (GEI), to characterize human walking properties for individual recognition by gait. To address the problem of the lack of training templates, we also propose a novel approach for human recognition by combining statistical gait features from real and synthetic templates. We directly compute the real templates from training silhouette sequences, while we generate the synthetic templates from training sequences by simulating silhouette distortion. We use a statistical approach for learning effective features from real and synthetic templates. We compare the proposed GEI-based gait recognition approach with other gait recognition approaches on USF HumanID Database. Experimental results show that the proposed GEI is an effective and efficient gait representation for individual recognition, and the proposed approach achieves highly competitive performance with respect to the published gait recognition approaches.     

Semi-supervised ranking for document retrieval

Ranking functions are an important component of information retrieval systems. Recently there has been a surge of research in the field of “learning to rank”, which aims at using labeled training data and machine learning algorithms to construct reliable ranking functions. Machine learning methods such as neural networks, support vector machines, and least squares have been successfully applied to ranking problems, and some are already being deployed in commercial search engines.Despite these successes, most algorithms to date construct ranking functions in a supervised learning setting, which assume that relevance labels are provided by human annotators prior to training the ranking function. Such methods may perform poorly when human relevance judgments are not available for a wide range of queries. In this paper, we examine whether additional unlabeled data, which is easy to obtain, can be used to improve supervised algorithms. In particular, we investigate the transductive setting, where the unlabeled data is equivalent to the test data.We propose a simple yet flexible transductive meta-algorithm: the key idea is to adapt the training procedure to each test list after observing the documents that need to be ranked. We investigate two instantiations of this general framework: The Feature Generation approach is based on discovering more salient features from the unlabeled test data and training a ranker on this test-dependent feature-set. The importance weighting approach is based on ideas in the domain adaptation literature, and works by re-weighting the training data to match the statistics of each test list. We demonstrate that both approaches improve over supervised algorithms on the TREC and OHSUMED tasks from the LETOR dataset.     

Learning person-specific models for facial expression and action unit recognition

A key assumption of traditional machine learning approach is that the test data are draw from the same distribution as the training data. However, this assumption does not hold in many real-world scenarios. For example, in facial expression recognition, the appearance of an expression may vary significantly for different people. As a result, previous work has shown that learning from adequate person-specific data can improve the expression recognition performance over the one from generic data. However, person-specific data is typically very sparse in real-world applications due to the difficulties of data collection and labeling, and learning from sparse data may suffer from serious over-fitting. In this paper, we propose to learn a person-specific model through transfer learning. By transferring the informative knowledge from other people, it allows us to learn an accurate model for a new subject with only a small amount of person-specific data. We conduct extensive experiments to compare different person-specific models for facial expression and action unit (AU) recognition, and show that transfer learning significantly improves the recognition performance with a small amount of training data.     

Unsupervised learning for human activity recognition using smartphone sensors

To provide more sophisticated healthcare services, it is necessary to collect the precise information on a patient. One impressive area of study to obtain meaningful information is human activity recognition, which has proceeded through the use of supervised learning techniques in recent decades. Previous studies, however, have suffered from generating a training dataset and extending the number of activities to be recognized. In this paper, to find out a new approach that avoids these problems, we propose unsupervised learning methods for human activity recognition, with sensor data collected from smartphone sensors even when the number of activities is unknown. Experiment results show that the mixture of Gaussian exactly distinguishes those activities when the number of activities k is known, while hierarchical clustering or DBSCAN achieve above 90% accuracy by obtaining k based on Caliński–Harabasz index, or by choosing appropriate values for ɛ and MinPts when k is unknown. We believe that the results of our approach provide a way of automatically selecting an appropriate value of k at which the accuracy is maximized for activity recognition, without the generation of training datasets by hand.     

基于Gabor特征与投影字典对学习的人脸识别算法

为了提高人脸的识别率及其识别速度,提出了一种基于Gabor特征与投影字典对学习的人脸识别算法。由于Gabor特征对表情、光照和角度等变化具有较强的鲁棒性,首先提取人脸图像多方向多尺度的Gabor局部特征,并将经主成分分析降维后的增广Gabor特征作为训练数据,代替原始的训练样本。然后,根据训练数据同时学习综合字典与分析字典,综合字典具有重构能力,分析字典可以快速求出系数矩阵。最后,根据各类别的重构误差进行分类,以达到人脸识别的目的。在扩展的YaleB、ORL和AR人脸数据库上的实验结果表明,提出的算法不仅具有较高的识别率,而且能够有效地提高识别速度。     

Active learning enabled activity recognition

Activity recognition in smart environment has been investigated rigorously in recent years. Researchers are enhancing the underlying activity discovery and recognition process by adding various dimensions and functionalities. But one significant barrier still persists which is collecting the ground truth information. Ground truth is very important to initialize a supervised learning of activities. Due to a large variety in number of Activities of Daily Living (ADLs), acknowledging them in a supervised way is a non-trivial research problem. Most of the previous researches have referenced a subset of ADLs and to initialize their model, they acquire a vast amount of informative labeled training data. On the other hand to collect ground truth and differentiate ADLs, human intervention is indispensable. As a result it takes an immense effort and raises privacy concerns to collect a reasonable amount of labeled data. In this paper, we propose to use active learning to alleviate the labeling effort and ground truth data collection in activity recognition pipeline. We investigate and analyze different active learning strategies to scale activity recognition and propose a dynamic k-means clustering based active learning approach. Experimental results on real data traces from a retirement community-(IRB #HP-00064387) help validate the early promise of our approach.     

深度学习批归一化及其相关算法研究进展

深度学习已经广泛应用到各个领域, 如计算机视觉和自然语言处理等, 并都取得了明显优于早期机器学习算法的效果. 在信息技术飞速发展的今天, 训练数据逐渐趋于大数据集, 深度神经网络不断趋于大型化, 导致训练越来越困难, 速度和精度都有待提升. 2013年, Ioffe等指出训练深度神经网络过程中存在一个严重问题: 中间协变量迁移(Internal covariate shift), 使网络训练过程对参数初值敏感、收敛速度变慢, 并提出了批归一化(Batch normalization, BN)方法, 以减少中间协变量迁移问题, 加快神经网络训练过程收敛速度. 目前很多网络都将BN作为一种加速网络训练的重要手段, 鉴于BN的应用价值, 本文系统综述了BN及其相关算法的研究进展. 首先对BN的原理进行了详细分析. BN虽然简单实用, 但也存在一些问题, 如依赖于小批量数据集的大小、训练和推理过程对数据处理方式不同等, 于是很多学者相继提出了BN的各种相关结构与算法, 本文对这些结构和算法的原理、优势和可以解决的主要问题进行了分析与归纳. 然后对BN在各个神经网络领域的应用方法进行了概括总结, 并且对其他常用于提升神经网络训练性能的手段进行了归纳. 最后进行了总结, 并对BN的未来研究方向进行了展望.     

SLAVE: a genetic learning system based on an iterative approach

SLAVE is an inductive learning algorithm that uses concepts based on fuzzy logic theory. This theory has been shown to be a useful representational tool for improving the understanding of the knowledge obtained from a human point of view. Furthermore, SLAVE uses an iterative approach for learning based on the use of a genetic algorithm (GA) as a search algorithm. We propose a modification of the initial iterative approach used in SLAVE. The main idea is to include more information in the process of learning one individual rule. This information is included in the iterative approach through a different proposal of calculus of the positive and negative example to a rule. Furthermore, we propose the use of a new fitness function and additional genetic operators that reduce the time needed for learning and improve the understanding of the rules obtained     

持续学习改进的人脸表情识别

目的 大量标注数据和深度学习方法极大地提升了图像识别性能。然而,表情识别的标注数据缺乏,训练出的深度模型极易过拟合,研究表明使用人脸识别的预训练网络可以缓解这一问题。但是预训练的人脸网络可能会保留大量身份信息,不利于表情识别。本文探究如何有效利用人脸识别的预训练网络来提升表情识别的性能。方法 本文引入持续学习的思想,利用人脸识别和表情识别之间的联系来指导表情识别。方法指出网络中对人脸识别整体损失函数的下降贡献最大的参数与捕获人脸公共特征相关,对表情识别来说为重要参数,能够帮助感知面部特征。该方法由两个阶段组成：首先训练一个人脸识别网络,同时计算并记录网络中每个参数的重要性;然后利用预训练的模型进行表情识别的训练,同时通过限制重要参数的变化来保留模型对于面部特征的强大感知能力,另外非重要参数能够以较大的幅度变化,从而学习更多表情特有的信息。这种方法称之为参数重要性正则。结果 该方法在RAF-DB（real-world affective faces database）,CK+（the extended Cohn-Kanade database）和Oulu-CASIA这3个数据集上进行了实验评估。在主流数据集RAF-DB上,该方法达到了88.04%的精度,相比于直接用预训练网络微调的方法提升了1.83%。其他数据集的实验结果也表明了该方法的有效性。结论 提出的参数重要性正则,通过利用人脸识别和表情识别之间的联系,充分发挥人脸识别预训练模型的作用,使得表情识别模型更加鲁棒。     

CHORD RECOGNITION USING NEURAL NETWORKS BASED ON PARTICLE SWARM OPTIMIZATION

A sequence of musical chords can facilitate musicians in music arrangement and accompaniment. To implement an intelligent system for chord recognition, in this article we propose a novel approach using artificial neural networks (ANN) trained bythe particle swarm optimization (PSO) technique and back-propagation (BP) learning algorithm. All of the training and testing data are generated from musical instrument digital interface (MIDI) symbolic data. Furthermore, in order to improve the recognition efficiency, an additional feature of cadencesis included. In other words, cadence is not only the structural punctuation of a melodic phrase but is considered as the important feature for chord recognition. Experimental results of our proposed approach show that adding a cadence feature significantly improves recognition rate, and the ANN-PSO method outperforms ANN-BP in chord recognition. In addition, because preliminary experimental recognition rates are generally not stable enough, we chose the optimal ANNs to propose a two-phase ANN model to integrate the results among many models.     

Uncooperative gait recognition by learning to rank

Gait is a useful biometric because it can operate from a distance and without subject cooperation. However, it is affected by changes in covariate conditions (carrying, clothing, view angle, etc.). Existing methods suffer from lack of training samples, can only cope with changes in a subset of conditions with limited success, and implicitly assume subject cooperation. We propose a novel approach which casts gait recognition as a bipartite ranking problem and leverages training samples from different people and even from different datasets. By exploiting learning to rank, the problem of model over-fitting caused by under-sampled training data is effectively addressed. This makes our approach suitable under a genuine uncooperative setting and robust against changes in any covariate conditions. Extensive experiments demonstrate that our approach drastically outperforms existing methods, achieving up to 14-fold increase in recognition rate under the most difficult uncooperative settings.     

Grocery product detection and recognition

Object detection and recognition are challenging computer vision tasks receiving great attention due to the large number of applications. This work focuses on the detection/recognition of products in supermarket shelves; this framework has a number of practical applications such as providing additional product/price information to the user or guiding visually impaired customers during shopping. The automatic creation of planograms (i.e., actual layout of products on shelves) is also useful for commercial analysis and management of large stores.Although in many object detection/recognition contexts it can be assumed that training images are representative of the real operational conditions, in our scenario such assumption is not realistic because the only training images available are acquired in well-controlled conditions. This gap between the training and test data makes the object detection and recognition tasks far more complex and requires very robust techniques. In this paper we prove that good results can be obtained by exploiting color and texture information in a multi-stage process: pre-selection, fine-selection and post processing. For fine-selection we compared a classical Bag of Words technique with a more recent Deep Neural Networks approach and found interesting outcomes. Extensive experiments on datasets of varying complexity are discussed to highlight the main issues characterizing this problem, and to guide toward the practical development of a real application.