Benjamin B. Kimia

Recognition of shapes by editing their shock graphs

This paper presents a novel framework for the recognition of objects based on their silhouettes. The main idea is to measure the distance between two shapes as the minimum extent of deformation necessary for one shape to match the other. Since the space of deformations is very high-dimensional, three steps are taken to make the search practical: 1) define an equivalence class for shapes based on shock-graph topology, 2) define an equivalence class for deformation paths based on shock-graph transitions, and 3) avoid complexity-increasing deformation paths by moving toward shock-graph degeneracy. Despite these steps, which tremendously reduce the search requirement, there still remain numerous deformation paths to consider. To that end, we employ an edit-distance algorithm for shock graphs that finds the optimal deformation path in polynomial time. The proposed approach gives intuitive correspondences for a variety of shapes and is robust in the presence of a wide range of visual transformations. The recognition rates on two distinct databases of 99 and 216 shapes each indicate highly successful within category matches (100 percent in top three matches), which render the framework potentially usable in a range of shape-based recognition applications.

Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space

We undertake to develop a general theory of two-dimensional shape by elucidating several principles which any such theory should meet. The principles are organized around two basic intuitions: first, if a boundary were changed only slightly, then, in general, its shape would change only slightly. This leads us to propose an operational theory of shape based on incremental contour deformations. The second intuition is that not all contours are shapes, but rather only those that can enclose “physical” material. A theory of contour deformation is derived from these principles, based on abstract conservation principles and Hamilton-Jacobi theory. These principles are based on the work of Sethian (1985a, c), the Osher-Sethian (1988), level set formulation the classical shock theory of Lax (1971; 1973), as well as curve evolution theory for a curve evolving as a function of the curvature and the relation to geometric smoothing of Gage-Hamilton-Grayson (1986; 1989). The result is a characterization of the computational elements of shape: deformations, parts, bends, and seeds, which show where to place the components of a shape. The theory unifies many of the diverse aspects of shapes, and leads to a space of shapes (the reaction/diffusion space), which places shapes within a neighborhood of “similar” ones. Such similarity relationships underlie descriptions suitable for recognition.

On aligning curves

We present a novel approach to finding a correspondence (alignment) between two curves. The correspondence is based on a notion of an alignment curve which treats both curves symmetrically. We then define a similarity metric based on the alignment curve using two intrinsic properties of the curve, namely, length and curvature. The optimal correspondence is found by an efficient dynamic-programming method both for aligning pairs of curve segments and pairs of closed curves, and is effective in the presence of a variety of transformations of the curve. Finally, the correspondence is shown in application to handwritten character recognition, prototype formation, and object recognition, and is potentially useful in other applications such as registration and tracking.

Symmetry-Based Indexing of Image Databases

The use of shape as a cue for indexing into pictorial databases has been traditionally based on global invariant statistics and deformable templates, on the one hand, and local edge correlation on the other. This paper proposes an intermediate approach based on a characterization of the symmetry in edge maps. The use of symmetry matching as a joint correlation measure between pairs of edge elements further constrains the comparison of edge maps. In addition, a natural organization of groups of symmetry into a hierarchy leads to a graph-based representation of relational structure of components of shape that allows for deformations by changing attributes of this relational graph. A graduated assignment graph matching algorithm is used to match symmetry structure in images to stored prototypes or sketches. The results of matching sketches and grey-scale images against a small database consisting of a variety of fish, planes, tools, etc., are promising.

3D object recognition using shape similiarity-based aspect graph

We present an aspect-graph approach to 3D object recognition where the definition of an aspect is motivated by its role in the subsequent recognition step. Specifically, we measure the similarity between two views by a 2D shape metric of similarity measuring the distance between the projected segmented shapes of the 3D object. This endows the viewing sphere with a metric which is used to group similar views into aspects, and to represent each aspect by a prototype. The same shape similarity metric is then used to rate the similarity between unknown views of unknown objects and stored prototypes to identify the object and its pose. The performance of this approach on a database of 18 objects each viewed in five degree increments along the ground viewing plane is demonstrated.

A shock grammar for recognition

We confront the theoretical and practical difficulties of computing a representation for two-dimensional shape, based on shocks or singularities that arise as the shapes boundary is deformed. First, we develop subpixel local detectors for finding and classifying shocks. Second, to show that shock patterns are not arbitrary but obey the rules of a grammar, and in addition satisfy specific topological and geometric constraints. Shock hypotheses that violate the grammar or are topologically or geometrically invalid are pruned to enforce global consistency. Survivors are organized into a hierarchical graph of shock groups computed in the reaction-diffusion space, where diffusion plays a role of regularization to determine the significance of each shock group. The shock groups can be functionally related to the objects parts, protrusions and bends, and the representation is suited to recognition: several examples illustrate its stability with rotations, scale changes, occlusion and movement of parts, even at very low resolutions.

On the Evolution of Curves via a Function of Curvature. I. The Classical Case

Abstract The problem of curve evolution as a function of its local geometry arises naturally in many physical applications. A special case of this problem is the curve shortening problem which has been extensively studied. Here, we consider the general problem and prove an existence theorem for the classical solution. The main theorem rests on lemmas that bound the evolution of length, curvature, and how far the curve can travel.

Euler Spiral for Shape Completion

In this paper we address the curve completion problem, e.g., the geometric continuation of boundaries of objects which are temporarily interrupted by occlusion. Also known as the gap completion or shape completion problem, this problem is a significant element of perceptual grouping of edge elements and has been approached by using cubic splines or biarcs which minimize total curvature squared (elastica), as motivated by a physical analogy. Our approach is motivated by railroad design methods of the early 1900s which connect two rail segments by “transition curves”, and by the work of Knuth on mathematical typography. We propose that in using an energy minimizing solution completion curves should not penalize curvature as in elastica but curvature variation. The minimization of total curvature variation leads to an Euler Spiral solution, a curve whose curvature varies linearly with arclength. We reduce the construction of this curve from a pair of points and tangents at these points to solving a nonlinear system of equations involving Fresnel Integrals, whose solution relies on optimization from a suitable initial condition constrained to satisfy given boundary conditions. Since the choice of an appropriate initial curve is critical in this optimization, we analytically derive an optimal solution in the class of biarc curves, which is then used as the initial curve. The resulting interpolations yield intuitive interpolation across gaps and occlusions, and are extensible, in contrast to the scale-invariant version of elastica. In addition, Euler Spiral segments can be used in other applications of curve completions, e.g., modeling boundary segments between curvature extrema or modeling skeletal branch geometry.

On solving 2D and 3D puzzles using curve matching

We approach the problem of 2D and 3D puzzle solving by matching the geometric features of puzzle pieces three at a time. First, we define an affinity measure for a pair of pieces in two stages, one based on a coarse-scale representation of curves and one based on a fine-scale elastic curve matching method. This re-examination of the top coarse-scale matches at the fine scale results in an optimal relative pose as well as a matching cost which is used as the affinity measure for a pair of pieces. Pairings with overlapping boundaries are impossible and are removed from further consideration, resulting in a set of top valid candidate pairs. Second, triples arising from generic junctions are formed from this rank-ordered list of pairs. The puzzle is solved by a recursive grouping of triples using a best-first search strategy, with backtracking in the case of overlapping pieces. We also generalize aspects of this approach to matching of 3D pieces. Specifically, ridges of 3D fragments scanned using a laser range finder are detected using a dynamic programming method. A pair of ridges are matched using a generalization of the 2D curve matching approach to space curves by using an energy solution involving curvature and torsion, which are computed using a novel robust numerical method. The reconstruction of map fragments and broken tiles using this method is illustrated.

IMPLEMENTING CONTINUOUS-SCALE MORPHOLOGY VIA CURVE EVOLUTION

Abstract A new approach to digital implementation of continuous-scale mathematical morphology is presented. The approach is based on discretization of evolution equations associated with continuous multiscale morphological operations. Those equations, and their corresponding numerical implementation, can be derived either directly from mathematical morphology definitions or from curve evolution theory. The advantages of the proposed approach over the classical discrete morphology are demonstrated.