Deformable model fitting has been actively pursued in the computer vision community for over a decade. As a result, numerous approaches have been proposed with varying degrees of success. A class of approaches that has shown substantial promise is one that makes independent predictions regarding locations of the model’s landmarks, which are combined by enforcing a prior over their joint motion. A common theme in innovations to this approach is the replacement of the distribution of probable landmark locations, obtained from each local detector, with simpler parametric forms. This simplification substitutes the true objective with a smoothed version of itself, reducing sensitivity to local minima and outlying detections. In this work, a principled optimization strategy is proposed where a nonparametric representation of the landmark distributions is maximized within a hierarchy of smoothed estimates. The resulting update equations are reminiscent of mean-shift but with a subspace constraint placed on the shape’s variability. This approach is shown to outperform other existing methods on the task of generic face fitting. 1.

Abstract not found

Efficient and accurate fitting of Active Appearance Models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is Inverse Compositional Image Alignment (ICIA). While ICIA is extremely fast, it is also known to have a small convergence radius. Convergence is especially bad when training and testing images differ strongly, as in multi-person AAMs. We describe “forward ” compositional image alignment in a consistent framework which also incorporates methods previously termed “inverse ” compositional, and use it to develop two novel fitting methods. The first method, Compositional Gradient Descent (CoDe), is approximately four times slower than ICIA, while having a convergence radius which is even larger than that achievable by direct Quasi-

In this paper we demonstrate that the support vector tracking (SVT) framework first proposed by Avidan is equivalent to the canonical Lucas-Kanade (LK) algorithm with a weighted Euclidean norm. From this equivalence we empirically demonstrate that in many circumstances the canonical SVT approach is unstable, and characterize these circumstances theoretically. We then propose a novel “nonpositive support kernel machine ” (NSKM) to circumvent this limitation and allow the effective use of discriminative classification within the weighted LK framework. This approach ensures that the pseudo-Hessian realized within the weighted LK algorithm is positive semidefinite which allows for fast convergence and accurate alignment/tracking. A further benefit of our proposed method is that the NSKM solution results in a much sparser kernel machine than the canonical SVM leading to sizeable computational savings and much improved alignment performance. 1.

The Active Appearance Model (AAM) provides an efficient method for localizing objects that vary in both shape and texture, and uses a linear regressor to predict updates to model parameters based on current image residuals. This study investigates using additive (or ‘boosted’) predictors, both linear and non-linear, as a substitute for the linear predictor in order to improve accuracy and efficiency. We demonstrate: (a) a method for training additive models that is several times faster than the standard approach without sacrificing accuracy; (b) that linear additive models can serve as an effective substitute for linear regression; (c) that linear models are as effective as non-linear models when close to the true solution. Based on these observations, we compare a ‘hybrid ’ AAM to the standard AAM for both the XM2VTS and BioID datasets, including cross-dataset evaluations. 1

This PDF receipt will only be used as the basis for generating PubMed Central (PMC) documents. PMC documents will be made available for review after conversion (approx. 2-3 weeks time). Any corrections that need to be made will be done at that time. No materials will be released to PMC without the approval of an author. Only the PMC documents will appear on

Local experts have been used to great effect for fitting deformable models to images. Typically, the best location in an image for the deformable model’s landmarks are found through a locally exhaustive search using these experts. In order to achieve efficient fitting, these experts should afford an efficient evaluation, which often leads to forms with restricted discriminative capacity. In this work, a framework is proposed in which multiple simple experts can be utilized to increase the capacity of the detections overall. In particular, the use of a mixture of linear classifiers is proposed, the computational complexity of which scales linearly with the number of mixture components. The fitting objective is maximized using the expectation maximization (EM) algorithm, where approximations to the true objective are made in order to facilitate efficient and numerically stable fitting. The efficacy of the proposed approach is evaluated on the task of generic face fitting where performance improvement is observed over two existing methods. 1.

Abstract. Statistical models of the shape and appearance of deformable objects have become widely used in Computer Vision and Medical Image Analysis. Here we give an overview of such models and of two efficient algorithms for matching such models to new images (Active Shape Models and Active Appearance Models). We also describe recent work on automatically constructing such models from minimally labelled training images. 1 Statistical Shape Models Many objects of interest in computer vision can be considered to be some deformed version of an ”average ” shape. For instance, most human faces have two eyes, a nose and a mouth in similar relative positions, and good approximations to each face can be generated by modest distortions of a standard template. Similarly many anatomical structures (such as human bones, or the heart) have broadly similar shapes across a population. Statistical shape models seek to represent such objects. Since their introduction

Abstract The face is one of the most powerful channels of nonverbal communication. Facial expression provides cues about emotion, intention, alertness, pain, personality, regulates interpersonal behavior, and communicates psychiatric and biomedical status among other functions. Within the past 15 years, there has been increasing interest in automated facial expression analysis within the computer vision and machine learning communities. This chapter reviews fundamental approaches to facial measurement by behavioral scientists and current efforts in automated facial expression recognition. We consider challenges, review databases available to the research community, approaches to feature detection, tracking, and representation, and both supervised and unsupervised learning.

Parameterized Appearance Models (PAMs) (e.g. Eigentracking, . . . Morphable Models) are commonly used to model the appearance and shape variation of objects in images. While PAMs have numerous advantages relative to alternate approaches, they have at least two drawbacks. First, they are especially prone to local minima in the fitting process. Second, often few if any of the local minima of the cost function correspond to acceptable solutions. To solve these problems, this paper proposes a method to learn a cost function by explicitly optimizing that the local minima occur at and only at the places corresponding to the correct fitting parameters. To the best of our knowledge, this is the first paper to address the problem of learning a cost function to explicitly model local properties of the error surface to fit PAMs. Synthetic and real examples show improvement in alignment performance in comparison with traditional approaches.