In this paper, we identify two issues involved in developing an automated feature subset selection algorithm for unlabeled data: the need for finding the number of clusters in conjunction with feature selection, and the need for normalizing the bias of feature selection criteria with respect to dimension. We explore the feature selection problem and these issues through FSSEM (Feature Subset Selection using Expectation-Maximization (EM) clustering) and through two different performance criteria for evaluating candidate feature subsets: scatter separability and maximum likelihood. We present proofs on the dimensionality biases of these feature criteria, and present a cross-projection normalization scheme that can be applied to any criterion to ameliorate these biases. Our experiments show the need for feature selection, the need for addressing these two issues, and the effectiveness of our proposed solutions.

This paper explores the problem of feature subset selection for unsupervised learning within the wrapper framework. In particular, we examine feature subset selection wrapped around expectation-maximization (EM) clustering with order identification (identifying the number of clusters in the data). We investigate two di erent performance criteria for evaluating candidate feature subsets: scatter separability and maximum likelihood. When the "true" number of clusters k is unknown, our experiments on simulated Gaussian data and real data sets show that incorporating the search for k within the feature selection procedure obtains better "class" accuracy than fixing k to be the number of classes. There are two reasons: 1) the "true" number of Gaussian components is not necessarily equal to the number of classes and 2) clustering with different feature subsets can result in di erent numbers of "true" clusters. Our empirical evaluation shows that feature selection reduces the number of features and improves clustering performance with respect to the chosen performance criteria.

Abstract. Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant and have good resistance to local occlusions and to geometric and photometric variations, but they are not able to exploit spatial co-occurrence statistics at scales larger than their local input patches. We present a new multilevel visual representation, ‘hyperfeatures’, that is designed to remedy this. The starting point is the familiar notion that to detect object parts, in practice it often suffices to detect co-occurrences of more local object fragments – a process that can be formalized as comparison (e.g. vector quantization) of image patches against a codebook of known fragments, followed by local aggregation of the resulting codebook membership vectors to detect cooccurrences. This process converts local collections of image descriptor vectors into somewhat less local histogram vectors – higher-level but spatially coarser descriptors. We observe that as the output is again a local descriptor vector, the process can be iterated, and that doing so captures and codes ever larger assemblies of object parts and increasingly abstract or ‘semantic ’ image properties. We formulate the hyperfeatures model and study its performance under several different image coding methods including clustering based Vector Quantization, Gaussian Mixtures, and combinations of these with Latent Dirichlet Allocation. We find that the resulting high-level features provide improved performance in several object image and texture image classification tasks. 1

For many feature selection problems, a human denes the features that are potentially useful, and then a subset is chosen from the original pool of features using an automated feature selection algorithm. In contrast to supervised learning, class information is not available to guide the feature search for unsupervised learning tasks. In this paper, we introduce Visual-FSSEM (Visual Feature Subset Selection using Expectation-Maximization Clustering), which incorporates visualization techniques, clustering, and user interaction to guide the feature subset search and to enable a deeper understanding of the data. Visual-FSSEM, serves both as an exploratory and multivariate-data visualization tool. We illustrate Visual-FSSEM on a high-resolution computed tomography lung image data set. 1. INTRODUCTION Most research in unsupervised clustering assumes that when creating the target data set, the data analyst in conjunction with the domain expert was able to identify a small relevant set of ...

Abstract—We develop a new class of hierarchical stochastic image models called spatial random trees (SRTs) which admit polynomial-complexity exact inference algorithms. Our framework of multitree dictionaries is the starting point for this construction. SRTs are stochastic hidden tree models whose leaves are associated with image data. The states at the tree nodes are random variables, and, in addition, the structure of the tree is random and is generated by a probabilistic grammar. We describe an efficient recursive algorithm for obtaining the maximum a posteriori estimate of both the tree structure and the tree states given an image. We also develop an efficient procedure for performing one iteration of the expectation-maximization algorithm and use it to estimate the model parameters from a set of training images. We address other inference problems arising in applications such as maximization of posterior marginals and hypothesis testing. Our models and algorithms are illustrated through several image classification and segmentation experiments, ranging from the segmentation of synthetic images to the classification of natural photographs and the segmentation of scanned documents. In each case, we show that our method substantially improves accuracy over a variety of existing methods. Index Terms—Dictionary, estimation, grammar, hierarchical model, image classification, probabilistic context-free grammar, segmentation, statistical image model, stochastic context-free grammar, tree model. I.

borders); (b) shows cutouts using these scribbles. A naïve interactive co-segmentation setup would force a user to examine all cutouts for mistakes, and then iteratively scribble on the worst segmentation to obtain better results. Cutouts needing correction are shown with red borders. (c) shows the region prompted for more scribbles by iCoseg, thus avoiding exhaustive examination of all cutouts by users. This paper presents an algorithm for Interactive Cosegmentation of a foreground object from a group of related images. While previous approaches focus on unsupervised co- segmentation, we use successful ideas from the interactive object- cutout literature. We develop an algorithm that allows users to decide what foreground is, and then guide the output of the co- segmentation algorithm towards it via scribbles. Interestingly, keeping a user in the loop leads to simpler and highly parallelizable energy functions, allowing us to work with significantly more images per group. However, unlike the interactive single image counterpart, a

In this paper we propose an extension of the sequence mining paradigm to (temporally-)annotated sequential patterns, where each transition in a sequential pattern is annotated with a typical transition time derived from the source data. Then, we present a basic solution for the novel mining problem based on the combination of sequential pattern mining and clustering, and assess this solution on two realistic datasets, illustrating how potentially useful patterns of the new form are extracted. 1.

In this paper, we present a cartoon face animation system for multimedia HCI applications. We animate face cartoons not only from input speech, but also based on emotions derived from speech signal. Using a corpus of over 700 utterances from different speakers, we have trained SVMs (support vector machines) to recognize four categories of emotions: neutral, happiness, anger and sadness. Given each input speech phrase, we identify its emotion content as a mixture of all four emotions, rather than classifying it into a single emotion. Then, facial expressions are generated from the recovered emotion for each phrase, by morphing different cartoon templates that correspond to various emotions. To ensure smooth transitions in the animation, we apply lowpass filtering to the recovered (and possibly jumpy) emotion sequence. Moreover, lip-syncing is applied to produce the lip movement from speech, by recovering a statistical audiovisual mapping. Experimental results demonstrate that cartoon animation sequences generated by our system are of good and convincing quality. Categories and Subject Descriptors 3 [multimedia tools, end-systems and applications]: user interfaces, multimedia in telecommunications

Statistical methods of discrete tomographic reconstruction pose new problems both in stochastic modeling to define an optimal reconstruction, and in optimization to find that reconstruction. Multiscale models have succeeded in improving representation of structure of varying scale in imagery, a chronic problem for common Markov random fields. This chapter shows that associated multiscale methods of optimization also avoid local minima of the log a posteriori probability better than single-resolution techniques. These methods are applied here to both segmentation/reconstruction of the unknown cross-sections, and estimation of unknown parameters represented by the discrete levels. 1.1 Introduction The reconstruction of images from projections is important in a variety of problems including tasks in medical imaging and non-destructive testing. Perhaps, the reconstruction technique most frequently used in commercial applications is convolution backprojection (CBP) [1]. While CBP...

In this paper we present a new stochastic model for pixels in an edge-enhanced image. The model is robust because it allows for the possibilities of false and multiple edges, and may be e#ciently estimated using a expectation-maximization technique with a minimum description length metric. The direct applicability of the model for the sequential edge linking algorithm is investigated. 1. INTRODUCTION An important operation in image processing and computer vision is the detection of edges [1]. Generally, edge detection may be thought of as a two step process. In the first step the edges are enhanced, usually based on estimating spatial derivatives of the image [1, 2]. The second step is determining whether a particular pixel is an edge. In this paper we describe a new stochastic model for edge-enhanced images which allows a more accurate determination of the distribution of the pixels in the image. When applied to an edge detection technique such as Sequential Edge Linking (SEL) it pro...