Projective active shape models for pose-variant image analysis of quasi-planar objects: Application to facial analysis

One of the important obstacles in the image-based analysis of the human face is the 3D nature of the problem and the 2D nature of most imaging systems used for biometric applications. Due to this, accuracy is strongly influenced by the viewpoint of the images, being frontal views the most thoroughly studied. However, when fully automatic face analysis systems are designed, capturing frontal-view images cannot be guaranteed. Examples of this situation can be found in surveillance systems, car driver images or whenever there are architectural constraints that prevent from placing a camera frontal to the subject. Taking advantage of the fact that most facial features lie approximately on the same plane, we propose the use of projective geometry across different views. An active shape model constructed with frontal-view images can then be directly applied to the segmentation of pictures taken from other viewpoints. The proposed extension demonstrates being significantly more invariant than the standard approach. Validation of the method is presented in 360 images from the AV@CAR database, systematically divided into three different rotations (to both sides), as well as upper and lower views due to nodding. The presented tests are among the largest quantitative results reported to date in face segmentation under varying poses.     

A machine-vision system for iris recognition

This paper describes a prototype system for personnel verification based on automated iris recognition. The motivation for this endevour stems from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric measurement. In particular, it is known in the biomedical community that irises are as distinct as fingerprints or patterns of retinal blood vessels. Further, since the iris is an overt body, its appearance is amenable to remote examination with the aid of a machine-vision system. The body of this paper details the design and operation of such a system. Also presented are the results of an empirical study in which the system exhibits flawless performance in the evaluation of 520 iris images.     

Stochastic models for recognition of occluded targets

Recognition of occluded objects in synthetic aperture radar (SAR) images is a significant problem for automatic target recognition. Stochastic models provide some attractive features for pattern matching and recognition under partial occlusion and noise. In this paper, we present a hidden Markov modeling based approach for recognizing objects in SAR images. We identify the peculiar characteristics of SAR sensors and using these characteristics we develop feature based multiple models for a given SAR image of an object. The models exploiting the relative geometry of feature locations or the amplitude of SAR radar return are based on sequentialization of scattering centers extracted from SAR images. In order to improve performance we integrate these models synergistically using their probabilistic estimates for recognition of a particular target at a specific azimuth. Experimental results are presented using both synthetic and real SAR images.     

A low complexity approximation of probabilistic appearance models

Appearance models yield a compact representation of shape, pose and illumination variations. The probabilistic appearance model, introduced by Moghaddam et al. (Proceedings of the International Conference on Computer Vision, Cambridge, MA, June 1995, p. 687; IEEE Trans. Pattern Anal. Mach. Intell. 19 (7) (1997) 696) has recently shown excellent performances in pattern detection and recognition, outperforming most other linear and non-linear approaches. Unfortunately, the complexity of this model remains high. In this paper, we introduce an efficient approximation of this model, which enables fast implementations in statistical estimation-based schemes. Gains in complexity and cpu time of more than 10 have been obtained, without any loss in the quality of the results.     

自然图像中混叠的概率模型

我们为建立自然图像中混叠的概率模型提供了一个数学框架。假设：(1)图像是由三维物体的二维投影轮廓组成．(2)在简化条件下．我们推导出自然图像的一种解析概率密度函数。已经证明．这种解析表达式可以很好地比配观测到的密度函数(直方图)。我们首先推导图像像素的边缘概率密度函数，然后推广到多维边缘概率密度函数，最后提出了几种改进措施。     

Interval predictor models: Identification and reliability

This paper addresses the problem of constructing reliable interval predictors directly from observed data. Differently from standard predictor models, interval predictors return a prediction interval as opposed to a single prediction value. We show that, in a stationary and independent observations framework, the reliability of the model (that is, the probability that the future system output falls in the predicted interval) is guaranteed a priori by an explicit and non-asymptotic formula, with no further assumptions on the structure of the unknown mechanism that generates the data. This fact stems from a key result derived in this paper, which relates, at a fundamental level, the reliability of the model to its complexity and to the amount of available information (number of observed data).     

Predictive models of human supervisory control behavioral patterns using hidden semi-Markov models

Behavioral models of human operators engaged in complex, time-critical high-risk domains, such as those typical in Human Supervisory Control (HSC) settings, are of great value because of the high cost of operator failure. We propose that Hidden Semi-Markov Models (HSMMs) can be employed to model behaviors of operators in HSC settings where there is some intermittent human interaction with a system via a set of external controls. While regular Hidden Markov Models (HMMs) can be used to model operator behavior, HSMMs are particularly suited to time-critical supervisory control domains due to their explicit representation of state duration. Using HSMMs, we demonstrate in an unmanned vehicle supervisory control environment that such models can accurately predict future operator behavior both in terms of states and durations.     

Strategies for communicating systems models

Sustainable environmental policies are rooted in knowledge and assumptions that decision-making authorities hold regarding specific social–ecological settings. These decision makers are increasingly informed by systems models. Diverse audiences for environmental science and sustainability policies magnify the importance of clear model communication. This essay offers a summary of best communication practices for situations in which bridging modelers' and non-modelers' conceptions of a given system—their respective mental models—is a principal challenge. Synthesizing social research from technical communication, educational psychology, and science communication disciplines, we discuss common areas of confusion in comprehending and explaining complex information, and present strategies model developers can use to ensure their model presentations are understandable and meaningful to audiences. We argue that accessible and socially adoptable explanations benefit from modelers listening to target audiences and anticipating how and why audiences may fail to understand aspects of a model.     

Reconstructing head models from photographs for individualized 3D‐audio processing

Visual fidelity and interactivity are the main goals in Computer Graphics research, but recently also audio is assuming an important role. Binaural rendering can provide extremely pleasing and realistic three‐dimensional sound, but to achieve best results it's necessary either to measure or to estimate individual Head Related Transfer Function (HRTF). This function is strictly related to the peculiar features of ears and face of the listener. Recent sound scattering simulation techniques can calculate HRTF starting from an accurate 3D model of a human head. Hence, the use of binaural rendering on large scale (i.e. video games, entertainment) could depend on the possibility to produce a sufficiently accurate 3D model of a human head, starting from the smallest possible input. In this paper we present a completely automatic system, which produces a 3D model of a head starting from simple input data (five photos and some key‐points indicated by user). The geometry is generated by extracting information from images and accordingly deforming a 3D dummy to reproduce user head features. The system proves to be fast, automatic, robust and reliable: geometric validation and preliminary assessments show that it can be accurate enough for HRTF calculation.     

Building optimal 2D statistical shape models

Statistical shape models are used widely as a basis for segmenting and interpreting images. A major drawback of the approach is the need, during training, to establish a dense correspondence across a training set of segmented shapes. We show that model construction can be treated as an optimisation problem, automating the process and guaranteeing the effectiveness of the resulting models. This is achieved by optimising an objective function with respect to the correspondence. We use an information theoretic objective function that directly promotes desirable features of the model. This is coupled with an effective method of manipulating correspondence, based on re-parameterising each training shape, to build optimal statistical shape models. The method is evaluated on several training sets of shapes, showing that it constructs better models than alternative approaches.     

On the vulnerability of face verification systems to hill-climbing attacks

In this paper, we use a hill-climbing attack algorithm based on Bayesian adaption to test the vulnerability of two face recognition systems to indirect attacks. The attacking technique uses the scores provided by the matcher to adapt a global distribution computed from an independent set of users, to the local specificities of the client being attacked. The proposed attack is evaluated on an eigenface-based and a parts-based face verification system using the XM2VTS database. Experimental results demonstrate that the hill-climbing algorithm is very efficient and is able to bypass over 85% of the attacked accounts (for both face recognition systems). The security flaws of the analyzed systems are pointed out and possible countermeasures to avoid them are also proposed.     

Adaptive fingerprint pore modeling and extraction

Sweat pores on fingerprints have proven to be discriminative features and have recently been successfully employed in automatic fingerprint recognition systems (AFRS), where the extraction of fingerprint pores is a critical step. Most of the existing pore extraction methods detect pores by using a static isotropic pore model; however, their detection accuracy is not satisfactory due to the limited approximation capability of static isotropic models to various types of pores. This paper presents a dynamic anisotropic pore model to describe pores more accurately by using orientation and scale parameters. An adaptive pore extraction method is then developed based on the proposed dynamic anisotropic pore model. The fingerprint image is first partitioned into well-defined, ill-posed, and background blocks. According to the dominant ridge orientation and frequency on each foreground block, a local instantiation of appropriate pore model is obtained. Finally, the pores are extracted by filtering the block with the adaptively generated pore model. Extensive experiments are performed on the high resolution fingerprint databases we established. The results demonstrate that the proposed method can detect pores more accurately and robustly, and consequently improve the fingerprint recognition accuracy of pore-based AFRS.     

Predictive and interactive controllers for solar absorption cooling systems in buildings

A predictive control approach is proposed for a solar powered hot water storage (SHWS) system which interacts with a simple thermal building control. The primary objective of this first controller is to optimize the use of the solar energy in order to ensure the cooling requirement of the building. The main difficulties are related to the presence of safety constraints and the nonlinearity as well as the hybrid nature of the system. The resulting optimization problem is simplified using various relaxations. The second controller is dedicated to the control of the building temperature. Using a model of the building thermal behavior, it sends its predicted operating profile to the SHWS controller. The performances of these two interacting controllers are illustrated by various simulations on a TRNSYS model of the building and its subsystems.     

基于HMM的击键特征用户身份认证

由于击键过程的时间序列特性和隐马尔可夫模型(HMM)在处理序列化动态信号中的优越性能,该文提出了根据用户击键特征采用HMM对用户身份进行认证的新方法。并对击键特征值的提取、观测值编码等问题进行了分析。实验证实了采用HMM进行击键特征身份验证的有效性。     

On transforming statistical models for non-frontal face verification

We address the pose mismatch problem which can occur in face verification systems that have only a single (frontal) face image available for training. In the framework of a Bayesian classifier based on mixtures of gaussians, the problem is tackled through extending each frontal face model with artificially synthesized models for non-frontal views. The synthesis methods are based on several implementations of maximum likelihood linear regression (MLLR), as well as standard multi-variate linear regression (LinReg). All synthesis techniques rely on prior information and learn how face models for the frontal view are related to face models for non-frontal views. The synthesis and extension approach is evaluated by applying it to two face verification systems: a holistic system (based on PCA-derived features) and a local feature system (based on DCT-derived features). Experiments on the FERET database suggest that for the holistic system, the LinReg-based technique is more suited than the MLLR-based techniques; for the local feature system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR. The results further suggest that extending frontal models considerably reduces errors. It is also shown that the local feature system is less affected by view changes than the holistic system; this can be attributed to the parts based representation of the face, and, due to the classifier based on mixtures of gaussians, the lack of constraints on spatial relations between the face parts, allowing for deformations and movements of face areas.     

Quantitative pharmacophore models with inductive logic programming

Three-dimensional models, or pharmacophores, describing Euclidean constraints on the location on small molecules of functional groups (like hydrophobic groups, hydrogen acceptors and donors, etc.), are often used in drug design to describe the medicinal activity of potential drugs (or ‘ligands’). This medicinal activity is produced by interaction of the functional groups on the ligand with a binding site on a target protein. In identifying structure-activity relations of this kind there are three principal issues: (1) It is often difficult to “align” the ligands in order to identify common structural properties that may be responsible for activity; (2) Ligands in solution can adopt different shapes (or `conformations’) arising from torsional rotations about bonds. The 3-D molecular substructure is typically sought on one or more low-energy conformers; and (3) Pharmacophore models must, ideally, predict medicinal activity on some quantitative scale. It has been shown that the logical representation adopted by Inductive Logic Programming (ILP) naturally resolves many of the difficulties associated with the alignment and multi-conformation issues. However, the predictions of models constructed by ILP have hitherto only been nominal, predicting medicinal activity to be present or absent. In this paper, we investigate the construction of two kinds of quantitative pharmacophoric models with ILP: (a) Models that predict the probability that a ligand is “active”; and (b) Models that predict the actual medicinal activity of a ligand. Quantitative predictions are obtained by the utilising the following statistical procedures as background knowledge: logistic regression and naive Bayes, for probability prediction; linear and kernel regression, for activity prediction. The multi-conformation issue and, more generally, the relational representation used by ILP results in some special difficulties in the use of any statistical procedure. We present the principal issues and some solutions. Specifically, using data on the inhibition of the protease Thermolysin, we demonstrate that it is possible for an ILP program to construct good quantitative structure-activity models. We also comment on the relationship of this work to other recent developments in statistical relational learning. Editors: Tamás Horváth and Akihiro Yamamoto     

Pattern recognition of manufacturing process signals using Gaussian mixture models-based recognition systems

Unnatural patterns exhibited in manufacturing processes can be associated with certain assignable causes for process variation. Hence, accurate identification of various process patterns (PPs) can significantly narrow down the scope of possible causes that must be investigated, and speed up the troubleshooting process. This paper proposes a Gaussian mixture models (GMM)-based PP recognition (PPR) model, which employs a collection of several GMMs trained for PPR. By using statistical features and wavelet energy features as the input features, the proposed PPR model provides more simple training procedure and better generalization performance than using single recognizer, and hence is easier to be used by quality engineers and operators. Furthermore, the proposed model is capable of adapting novel PPs through using a dynamic modeling scheme. The simulation results indicate that the GMM-based PPR model shows good detection and recognition of current PPs and adapts further novel PPs effectively. Analysis from this study provides guidelines in developing GMM – based SPC recognition systems.     

基于改进变量预测模型的变压器故障诊断

针对变压器故障诊断中的小样本、非线性、参数寻优难等问题,提出改进的变量预测模型的变压器故障诊断方法.分析变量预测模型和布谷鸟搜索算法结合解决小样本和非线性问题,指出其后期收敛速度慢,稳定性差,收敛精度不高,易陷入局部极小值问题,在此基础上在谷鸟搜索算法位置更新中引入变异操作,提高解的多样性.引入动态步长和动态发现概率提...