A snake is an energy-minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines and edges. Snakes are active contour models: they lock onto nearby edges, localizing them accurately. Scale-space continuation can be used to enlarge the cap-ture region surrounding a feature. Snakes provide a unified account of a number of visual problems, in-cluding detection of edges, lines, and subjective contours; motion tracking; and stereo matching. We have used snakes successfully for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest.

We present an approach for recovering surface shape from the occluding contour using an active (i.e., moving) observer. It is based onarelation between the geometries of a surface inascene and its occluding contour: If the viewing direction of the observer is along a principal direction for a surface point whose projection is on the contour, surface shape (i.e., curvature) at the surfacepoint can be recovered from the contour. Unlike previous approaches for recovering shape from the occluding contour, we use an observer that purposefully changes viewpoint in order to achieve a well-de ned geometric relationship with respect to a 3D shape prior to its recognition. We show that there is a simple and e cient viewing strategy that allows the observer to align the viewing direction with one of the two principal directions for a point on the surface. Experimental results demonstrate that our method can be easily implemented and can provide reliable shape information. 1

This thesis presents an integrated approach in modeling, extracting, detecting and classifying deformable contours directly from noisy images. We begin by conducting a case study on regularization, formulation and initialization of the active contour models (snakes). Using minimax principle, we derive a regularization criterion whereby the values can be automatically and implicitly determined along the contour. Furthermore, we formulate a set of energy functionals which yield snakes that contain Hough transform as a special case. Subsequently, we consider the problem of modeling and extracting arbitrary deformable contours from noisy images. We combine a stable, invariant and unique contour model with Markov random field to yield prior distribution that exerts influence over an arbitrary global model while allowing for deformation. Under the Bayesian framework, contour extraction turns into posterior estimation, which is in turn equivalent to energy minimization in a generalized active...

Perceptual understanding systems often involve building hierarchical groupings. The elements of such a hierarchy range from primitive elements at the lowest levels (such as pixels, in the case of image-understanding systems) to representations of complete real-world objects at higher levels. At each level, data are grouped together because they are identified as component parts of a single feature at the next level; the domain-specific work lies in correctly identifying these groups through all the levels. The construction of such a hierarchy generally proceeds from raw data input up to top-level explanations, however, it usually cannot operate in a strictly bottomup fashion. Often a number of hypotheses must be made as to the correct grouping, one of which is eventually selected according to a higher-level constraint; that is, there is also a top-down aspect to the process. The number of primitive elements is typically quite large, and if several levels of hypothesizing are necessary,...

Videostroboscopy is an examination which yields a permanent record of the moving vocal folds. Thus, it allows the diagnosis of abnormalities which contribute to voice disorders. In this paper, in order to find and quantify the deformation of the vocal folds in videostroboscopic recordings, an active contours (snakes) based approach is used to delineate the vocal folds in each frame of the videostroboscopic image sequence. After this delineation, a new elastic registration algorithm is used to register the vocal fold contours between adjacent frames of the video sequence. This algorithm is based on the regularization principle and is very effective when large deformations are present. A least-squares approach is used to fit an affine model to the displacement vectors found by elastic registration. The parameters of this model, rotation, translation, and deformation along two principle axes, quantify the deformation and allow the succinct characterization of the videostroboscopic recordi...

Contract Number NAS2- 13326 1 2

This thesis presents an integrated approach in modeling, extracting, detecting and classifying deformable contours directly from noisy images. We begin by conducting a case study on regularization, formulation and initialization of the active contour models (snakes). Using minimax principle, we derive a regularization criterion whereby the values can be automatically and implicitly determined along the contour. Furthermore, we formulate a set of energy functionals which yield snakes that contain Hough transform as a special case. Subsequently, we consider the problem of modeling and extracting arbitrary deformable contours from noisy images. We combine a stable, invariant and unique contour model with Markov random field to yield prior distribution that exerts influence over an arbitrary global model while allowing for deformation. Under the Bayesian framework, contour extraction turns into posterior estimation, which is in turn equivalent to energy minimization in a generalized active...

Coalitional aggression evolved because it allowed participants in such coalitions to promote their fitness by gaining access to disputed reproduction enhancing resources that would otherwise be denied to them. Far fewer species manifest coalitional aggression than would be expected on the basis of the actual distribution of social conditions that would favor its evolution. The exploitation of such opportunities depends on the solution by individuals of highly complex and specialized information processing problems of cooperation and social exchange, and the difficulty of evolving cognitive mechanisms capable of solving such complex computational tasks may account for the phylogenetic rarity of such multi-individual coalitions. We propose that humans and a few other cognitively pre-adapted species have evolved specialized cognitive programs, that govern coalitional behavior, and constitute a distinctive coalitional psychology. An adaptive task analysis of what such algorithms need to accomplish, in the decisions regulating coalition formation, participation, cost and benefit allocation, allows the preliminary mapping of this coalitional psychology. Scrutinization of the adaptive features of coalitional aggression reveals some surprising characteristics, including that, under certain conditions, mortality rates do not negatively impact the fitness of males in the coalition, suggesting why warfare is so favored an activity, despite its risks to participating individuals ' welfare.