Abstract—Face images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression, and lighting. We describe a compact parametrized model of facial appearance which takes into account all these sources of variability. The model represents both shape and gray-level appearance, and is created by performing a statistical analysis over a training set of face images. A robust multiresolution search algorithm is used to fit the model to faces in new images. This allows the main facial features to be located, and a set of shape, and gray-level appearance parameters to be recovered. A good approximation to a given face can be reconstructed using less than 100 of these parameters. This representation can be used for tasks such as image coding, person identification, 3D pose recovery, gender recognition, and expression recognition. Experimental results are presented for a database of 690 face images obtained under widely varying conditions of 3D pose, lighting, and facial expression. The system performs well on all the tasks listed above.

We describe the use of flexible models for representing the shape and grey-level appearance of human faces. These models are controlled by a small number of parameters which can be used to code the overall appearance of a face for image compression and classification purposes. The model parameters control both inter-class and within-class variation. Discriminant analysis techniques are employed to enhance the effect of those parameters affecting inter-class variation, which are useful for classification. We have performed experiments on face coding and reconstruction and automatic face identification. Good recognition rates are obtained even when significant variation in lighting, expression and 3D viewpoint, is allowed.

We present a method for the hierarchical representation of vector fields. Our approach is based on iterative refinement using clustering and principal component analysis. The input to our algorithm is a discrete set of points with associated vectors. The algorithm generates a top-down segmentation of the discrete field by splitting clusters of points. We measure the error of the various approximation levels by measuring the discrepancy between streamlines generated by the original discrete field and its approximations based on much smaller discrete data sets. Our method assumes no particular structure of the field, nor does it require any topological connectivity information. It is possible to generate multiresolution representations of vector fields using this approach. Keywords: vector field visualization; Hardy's multiquadric method; binary-space partitioning; data simplification. 1 Introduction The rapid increase in the power of computer systems coupled with the improving precis...

This survey compares internal representations of the recent as well as more traditional face recognition techniques to classify them into several broad categories. The categories assessed include template matching and feature measurements, analysis of global and local facial features, and incorporation of interpersonal and intrapersonal variations of human faces. Analysis of the face recognition systems within those broad categories makes it possible to identify strong and weak sides of each group of methods. The paper argues that a fruitful direction for future research may lie in weighing information about facial features together with localized image features in order to provide a better mechanism for

Model based approaches to the interpretation of face images have proved very successful. We have previously described statistically based models of face shape and grey-level appearance and shown how they can be used to perform various coding and interpretation tasks. In the paper we describe improved methods of modelling which couple shape and greylevel information more directly than our existing methods, isolate the changes in appearance due to different sources of variability (person, expression, pose, lighting), and deal with non-linear shape variation. We show that the new methods are better suited to interpretation and tracking tasks. 1 Introduction Model-based approaches to the interpretation and coding of face images have proved very successful. Methods described so far include: Modelling grey-level variation using eigenfaces [1, 2], models based on class specific linear projection [3], combined shape and grey level models[4, 5], models based on the physical and anato...

Having a representative workload of the target domain of a microprocessor is extremely important throughout its design. The composition of a workload involves two issues: (i) which benchmarks to select and (ii) which input data sets to select per benchmark. Unfortunately, it is impossible to select a huge number of benchmarks and respective input sets due to the large instruction counts per benchmark and due to limitations on the available simulation time. In this paper, we use statistical data analysis techniques such as principal components analysis (PCA) and cluster analysis to efficiently explore the workload space. Within this workload space, different input data sets for a given benchmark can be displayed, a distance can be measured between program-input pairs that gives us an idea about their mutual behavioral differences and representative input data sets can be selected for the given benchmark. This methodology is validated by showing that program-input pairs that are close to each other in this workload space indeed exhibit similar behavior. The final goal is to select a limited set of representative benchmark-input pairs that span the complete workload space. Next to workload composition, there are a number of other possible applications, namely getting insight in the impact of input data sets on program behavior and profile-guided compiler optimizations. 1

We present an automatic method for the generation of surface triangulations from sets of scattered points. Given a set of scattered points in three-dimensional space, without connectivity information, our method reconstructs a triangulated surface model in a two-step procedure. First, we apply an adaptive clustering technique to the given set of points, identifying point subsets in regions that are nearly planar. The output of this clustering step is a set of two-manifold "tiles" that locally approximate the underlying, unknown surface. Second, we construct a surface triangulation by triangulating the data within the individual tiles and the gaps between the tiles. This algorithm can generate multiresolution representations by applying the triangulation step to various resolution levels resulting from the hierarchical clustering step. We compute deviation measures for each cluster, and thus we can produce reconstructions with prescribed error bounds.

We describe the use of flexible models for representing the shape and grey-level appearance of human faces. These models are controlled by a small number of parameters which can be used to code the overall appearance of faces for classification purposes. The model parameters control both inter-class and within-class variation. Discriminant analysis techniques are employed to enhance the effect of those affecting inter-class variation, which are useful for classification. We show that with this coding scheme, good recognition results can be obtained, even when viewpoint, illumination and facial expression are allowed to change.

Beef is a commercially important and widely consumed muscle food and central to the protein intake of many societies. In the food industry no technology exists for the rapid and accurate detection of microbiologically spoiled or contaminated beef. Fourier transform infrared (FT-IR) spectroscopy is a rapid, reagentless and non-destructive analytical technique whose continued development is resulting in manifold applications across a wide range of biosciences. FT-IR was exploited to measure biochemical changes within the fresh beef substrate, enhancing and accelerating the detection of microbial spoilage. Separately packaged fresh beef rump steaks were purchased from a national retailer, comminuted for 15 s and left to spoil at ambient room temperature for 24 h. Every hour, FT-IR measurements were collected directly from the sample surface using attenuated total reflectance, in parallel the total viable counts of bacteria were obtained by classical microbiological plating methods. Quantitative interpretation of FT-IR spectra was undertaken using partial least squares regression and allowed for accurate estimates of bacterial loads to be calculated directly from the meat surface in 60 s. Machine learning methods in the form of genetic algorithms and genetic programming were used to elucidate the wavenumbers of interest related to the spoilage process. The results obtained demonstrated that using FT-IR and machine learning it was possible to detect bacterial spoilage rapidly in beef and that the most significant functional groups selected could be directly correlated to the spoilage process which arose from proteolysis, resulting in changes in the levels of amides and amines.

Abstract. Factor model is a very useful and popular model in finance. In this paper, we show the relation between factor model and blind source separation, and we propose to use Independent Component Analysis (ICA) as a data mining tool to construct the underlying factors and hence obtain the corresponding sensitivities for the factor model. 1