In this paper we introduce a new deformable model, called eigensnake, for segmentation of elongated structures in a probabilistic framework. Instead of snake attraction by specific image features extracted independently of the snake, our eigensnake learns an optimal object description and searches for such image feature in the target image. This is achieved applying principal component analysis...

Your use of the JSTOR archive indicates your acceptance of JSTOR's Terms and Conditions of Use, available at http://www.jstor.org/page/info/about/policies/terms.jsp. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained prior permission, you may not download an entire issue of a journal or multiple copies of articles, and you may use content in the JSTOR archive o...

A. Two quite different forms of nonlinear principal component analysis have been proposed in the literature. The first one is associated with the names of Guttman, Burt, Hayashi, Benzécri, McDonald, De Leeuw, Hill, Nishisato. We call itmultiple correspondence analysis. The second form has been discussed by Kruskal, Shepard, Roskam, Takane, Young, De Leeuw, Winsberg, Ramsay. We call it no...

Principal Component Analysis (PCA) is a feature extraction approach directly based on a whole vector pattern and acquires a set of projections that can realize the best reconstruction for an original data in the mean squared error sense. In this paper, the progressive PCA (PrPCA) is proposed, which could progressively extract features from a set of given data with large dimensionality and the e...

We present an expressive feature model for recognizing the performance effort of human actions. A set of low and high effort examples for an action are initially factored into its three-mode principal components, followed by a learning phase to compute the expressive features required to bring the model estimation of effort into agreement with perceptual judgements. The approach is demonstrated...

In our previous work, we have developed a method for selecting features based on the analysis of class regions approximated by hyperboxes. In this paper, we select features analyzing class regions approximated by ellipsoids. First, for a given set of features, each class region is approximated by an ellipsoid with the center and the covariance matrix calculated by the data belonging to the clas...

14 ERS-1 SAR images were classified using three different classification algorithms. Median filtering and principal component analysis were used in speckle reduction and feature extraction. Feature selection was performed using branch-and-bound algorithm. The best classification accuracy (55-60%) was achieved when principal component images computed from median filtered SAR images were used. In...

This paper investigates the analysis of expert piano playing gestures. It aims to extract quantitative and objective features to represent pianists’ hands gestures, and more specifically to enable characterization of the expertise level of pianists. To do so, four pianists with different expertise levels were recorded with a marker-based optical motion capture system while playing six different...

One class classification is widely used in many applications. Only one target class is well characterized by instances in the training data in one class classification, and no instance is available for other non-target classes, or few instances are present and they cannot form statistically representative samples for the negative concept. A two-step paradigm employing nonnegative matrix factori...

Principal component analysis (PCA) is a dimensionality reduction modeling technique that transforms a set of process variables by rotating their axes of representation. Maximum Likelihood PCA (MLPCA) is an extension that accounts for different noise contributions in each variable. Neither PCA nor its extensions utilize external information about the model or data such as the range or distributi...