This paper presents a generic method for perceptual grouping, and an analysis of its expected grouping quality. The grouping method is fairly general: it may be used for the grouping of various types of data features, and to incorporate different grouping cues, operating over feature sets of different sizes. The proposed method is divided into two parts: Constructing a graph representation of the available perceptual grouping evidence, and then finding the "best" partition of the graph into groups. The first stage includes a cue enhancement procedure, which integrates the information available from multi-feature cues into very reliable bi-feature cues. Both stages are implemented using known statistical tools such as Wald's SPRT algorithm and the Maximum Likelihood criterion. The accompanying theoretical analysis of this grouping criterion quantifies intuitive expectations and predicts that the expected grouping quality increases with cue reliability. It also shows that investing more computational effort in the grouping algorithm leads to better grouping results. This analysis, which quantifies the grouping power of the Maximum Likelihood criterion, is independent of the grouping domain. To our best knowledge, such an analysis of a grouping process is given here for the first time. Three grouping algorithms, in three different domains, are synthesized as instances of the generic method, They demonstrate the applicability and generality of this grouping method. Keywords : Perceptual Grouping, Grouping Analysis, Graph Clustering, Maximum Likelihood, Wald's SPRT, Performance Prediction, Generic Grouping Algorithm. 1

We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient contours to extract them from the otherwise 2D image clutter. To define a measure for topological classification robust to clutter and broken edges, we use a graph formulation instead of the standard computational topology. The key insight is that a pronounced 1D contour should have a clear ordering of edgels, to which all graph edges adhere, and no long range entanglements persist. Finding the contour grouping by optimizing these topological criteria is challenging. We introduce a novel concept of circular embedding to encode this combinatorial task. Our solution leads to computing the dominant complex eigenvectors/eigenvalues of the random walk matrix of the contour grouping graph. We demonstrate major improvements over state-of-the-art approaches on challenging real images. 1.

Abstract. We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features from a large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over ’exponentially ’ many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images. 1

This paper proposes a new, efficient, figure from ground discrimination method. This algorithm is based on the assumption that background data features can be more easily detected than figure data features, thus emphasizing the background detection task (and implying the name of the method). Along the iterative labeling process, data features are sequentially and permanently labelled as "background", while more global information is being collected to assist with the coming decisions, until the process converges. This procedure creates a bootstrap mechanism which improves performance in very cluttered scenes. The method can be applied to many perceptual grouping cues, and an application to smoothness-based classification of edge points is given. A fast implementation using a kd-tree allows to work on large, realistic images.

Perceptual popout is defined by both feature similarity and local feature contrast. We identify these two measures with attraction and repulsion, and unify the dual processes of association by attraction and segregation by repulsion in a single grouping framework. We generalize normalized cuts to multi-way partitioning with these dual measures. We expand graph partitioning approaches to weight matrices with negative entries, and provide a theoretical basis for solution regularization in such algorithms. We show that attraction, repulsion and regularization each contributes in a unique way to popout. Their roles are demonstrated in various salience detection and visual search scenarios. This work opens up the possibilities of encoding negative correlations in constraint satisfaction problems, where solutions by simple and robust eigendecomposition become possible. 1.

Perceptual organization refers to the process of organizing sensory input into coherent and interpretable perceptual structures. This process is challenging due to the chicken-and-egg nature between the various sub-processes such as image segmentation, figure-ground segregation and object recognition. Low-level processing requires the guidance of high-level knowledge to overcome noise; while high-level processing relies on low-level processes to reduce the computational complexity. Neither process can be sufficient on its own. Consequently, any system that carries out these processes in a sequence is bound to be brittle. An alternative system is one in which all processes interact with each other simultaneously. In this thesis, we develop a set of simple yet realistic interactive processing models for perceptual organization. We model the processing in the framework of spectral graph theory, with a criterion encoding the overall goodness of perceptual organization. We derive fast solutions for near-global optima of the criterion, and demonstrate the efficacy of the models on segmenting a wide range of real images. Through these models, we are able to capture a variety of perceptual phenomena: a unified treatment of various grouping, figure-ground and depth cues to produce popout, region segmentation and depth segregation in one step; and a unified framework for integrating bottom-up and top-down information to produce an object segmentation from spatial and object attention. We achieve these goals by empowering current spectral graph methods with a principled solution for multiclass spectral graph partitioning; expanded repertoire of grouping cues to include similarity, dissimilarity and ordering relationships; a theory for integrating sparse grouping cues; and a model ...

The goal of pre-attentive segmentation is to mark conspicuous image locations such as region boundaries, smooth contours and popout targets against backgrounds. This salience detection relies on not only feature similarity analysis but also local feature contrast. We identify these two measures with attraction and nondirectional repulsion, and unify the dual processes of association by attraction and segregation by repulsion in one grouping framework. We generalize normalized cuts to multi-way partitioning with these dual measures and show that the criterion can be viewed as a stochastic jump-diffusion process, where the probability of jump is determined by the relative strengths of attraction and repulsion. We demonstrate that this extended model can deal with salience detection under various situations as well as the asymmetry in visual search. Through these results, we provide a clear understanding of the role of negative weights in the graph partitioning framework. This opens up the possibilities of encoding negative correlations in constraint satisfaction problems, where solutions by simple and robust eigendecomposition become possible. 1.

Perceptual grouping is traditionally concerned with the use of grouping information (or cues) for image partitioning tasks such as figure ground discrimination, edge completion, segmentation and partition. Here, on the other hand, such grouping cues are not used to partition the image but to confirm a hypothesized segmentation. Hypothesis verification is the last stage in most object recognition methods. It is carried out by evaluating a score for each hypothesis, and choosing the hypotheses associated with the highest score. This paper suggests a grouping-based verification paradigm, relying on the observation that a set of data features belonging to an hypothesized object instance should be a "good group". Therefore it should support perceptual grouping information, available from the image by grouping relations. The proposed score, which is the joint likelihood of these grouping cues, quantifies this observation in a probabilistic framework. Experiments with synthetic and...

Abstract not found