Longin Jan Latecki

Shape descriptors for non-rigid shapes with a single closed contour

The Core Experiment CE-Shape-1 for shape descriptors performed for the MPEG-7 standard gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour. There are two main differences with respect to other comparison results reported in the literature: (1) For each shape descriptor the experiments were carried out by an institute that is in favor of this descriptor. This implies that the parameters for each system were optimally determined and the implementations were thoroughly rested. (2) It was possible to compare the performance of shape descriptors based on totally different mathematical approaches. A more theoretical comparison of these descriptors seems to be extremely hard. In this paper we report on the MPEG-7 Core Experiment CE-Shape.

Shape similarity measure based on correspondence of visual parts

A cognitively motivated similarity measure is presented and its properties are analyzed with respect to retrieval of similar objects in image databases of silhouettes of 2D objects. To reduce influence of digitization noise, as well as segmentation errors, the shapes are simplified by a novel process of digital curve evolution. To compute our similarity measure, we first establish the best possible correspondence of visual parts (without explicitly computing the visual parts). Then, the similarity between corresponding parts is computed and aggregated. We applied our similarity measure to shape matching of object contours in various image databases and compared it to well-known approaches in the literature. The experimental results justify that our shape matching procedure gives an intuitive shape correspondence and is stable with respect to noise distortions.

Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution

In this paper, we introduce a new skeleton pruning method based on contour partitioning. Any contour partition can be used, but the partitions obtained by discrete curve evolution (DCE) yield excellent results. The theoretical properties and the experiments presented demonstrate that obtained skeletons are in accord with human visual perception and stable, even in the presence of significant noise and shape variations, and have the same topology as the original skeletons. In particular, we have proven that the proposed approach never produces spurious branches, which are common when using the known skeleton pruning methods. Moreover, the proposed pruning method does not displace the skeleton points. Consequently, all skeleton points are centers of maximal disks. Again, many existing methods displace skeleton points in order to produces pruned skeletons

Convexity Rule for Shape Decomposition Based on Discrete Contour Evolution

We concentrate here on decomposition of 2D objects into meaningfulparts of visual form, orvisual parts. It is a simple observation that convex parts of objects determine visual parts. However, the problem is that many significant visual parts are not convex, since a visual part may have concavities. We solve this problem by identifying convex parts at different stages of a proposed contour evolution method in which significant visual parts will become convex object parts at higher stages of the evolution. We obtain a novel rule for decomposition of 2D objects into visual parts, called the hierarchical convexity rule, which states that visual parts are enclosed by maximal convex (with respect to the object) boundary arcs at different stages of the contour evolution. This rule determines not only parts of boundary curves but directly the visual parts of objects. Moreover, the stages of the evolution hierarchy induce a hierarchical structure of the visual parts. The more advanced the stage of contour evolution, the more significant is the shape contribution of the obtained visual parts.

Path Similarity Skeleton Graph Matching

This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geodesic paths between skeleton endpoints. In contrast to typical tree or graph matching methods, we do not consider the topological graph structure. Our approach is motivated by the fact that visually similar skeleton graphs may have completely different topological structures. The proposed comparison of geodesic paths between endpoints of skeleton graphs yields correct matching results in such cases. The skeletons are pruned by contour partitioning with discrete. Curve evolution, which implies that the endpoints of skeleton branches correspond to visual parts of the objects. The experimental results demonstrate that our method is able to produce correct results in the presence of articulations, stretching, and contour deformations.

Learning Context-Sensitive Shape Similarity by Graph Transduction

Shape similarity and shape retrieval are very important topics in computer vision. The recent progress in this domain has been mostly driven by designing smart shape descriptors for providing better similarity measure between pairs of shapes. In this paper, we provide a new perspective to this problem by considering the existing shapes as a group, and study their similarity measures to the query shape in a graph structure. Our method is general and can be built on top of any existing shape similarity measure. For a given similarity measure, a new similarity is learned through graph transduction. The new similarity is learned iteratively so that the neighbors of a given shape influence its final similarity to the query. The basic idea here is related to PageRank ranking, which forms a foundation of Google Web search. The presented experimental results demonstrate that the proposed approach yields significant improvements over the state-of-art shape matching algorithms. We obtained a retrieval rate of 91.61 percent on the MPEG-7 data set, which is the highest ever reported in the literature. Moreover, the learned similarity by the proposed method also achieves promising improvements on both shape classification and shape clustering.

Incremental Local Outlier Detection for Data Streams

Outlier detection has recently become an important problem in many industrial and financial applications. This problem is further complicated by the fact that in many cases, outliers have to be detected from data streams that arrive at an enormous pace. In this paper, an incremental LOF (local outlier factor) algorithm, appropriate for detecting outliers in data streams, is proposed. The proposed incremental LOF algorithm provides equivalent detection performance as the iterated static LOF algorithm (applied after insertion of each data record), while requiring significantly less computational time. In addition, the incremental LOF algorithm also dynamically updates the profiles of data points. This is a very important property, since data profiles may change over time. The paper provides theoretical evidence that insertion of a new data point as well as deletion of an old data point influence only limited number of their closest neighbors and thus the number of updates per such insertion/deletion does not depend on the total number of points TV in the data set. Our experiments performed on several simulated and real life data sets have demonstrated that the proposed incremental LOF algorithm is computationally efficient, while at the same time very successful in detecting outliers and changes of distributional behavior in various data stream applications

Maximum weight cliques with mutex constraints for video object segmentation

In this paper, we address the problem of video object segmentation, which is to automatically identify the primary object and segment the object out in every frame. We propose a novel formulation of selecting object region candidates simultaneously in all frames as finding a maximum weight clique in a weighted region graph. The selected regions are expected to have high objectness score (unary potential) as well as share similar appearance (binary potential). Since both unary and binary potentials are unreliable, we introduce two types of mutex (mutual exclusion) constraints on regions in the same clique: intra-frame and inter-frame constraints. Both types of constraints are expressed in a single quadratic form. We propose a novel algorithm to compute the maximal weight cliques that satisfy the constraints. We apply our method to challenging benchmark videos and obtain very competitive results that outperform state-of-the-art methods.

Improving Shape Retrieval by Learning Graph Transduction

Shape retrieval/matching is a very important topic in com- puter vision. The recent progress in this domain has been mostly driven by designing smart features for providing better similarity measure be- tween pairs of shapes. In this paper, we provide a new perspective to this problem by considering the existing shapes as a group, and study their similarity measures to the query shape in a graph structure. Our method is general and can be built on top of any existing shape match- ing algorithms. It learns a better metric through graph transduction by propagating the model through existing shapes, in a way similar to com- puting geodesics in shape manifold. However, the proposed method does not require learning the shape manifold explicitly and it does not require knowing any class labels of existing shapes. The presented experimen- tal results demonstrate that the proposed approach yields significant improvements over the state-of-art shape matching algorithms. We ob- tained a retrieval rate of 91% on the MPEG-7 data set, which is the highest ever reported in the literature.

Shape matching and classification using height functions

We propose a novel shape descriptor for matching and recognizing 2D object silhouettes. The contour of each object is represented by a fixed number of sample points. For each sample point, a height function is defined based on the distances of the other sample points to its tangent line. One compact and robust shape descriptor is obtained by smoothing the height functions. The proposed descriptor is not only invariant to geometric transformations such as translation, rotation and scaling but also insensitive to nonlinear deformations due to noise and occlusion. In the matching stage, the Dynamic Programming (DP) algorithm is employed to find out the optimal correspondence between sample points of every two shapes. The height function provides an excellent discriminative power, which is demonstrated by excellent retrieval performances on several popular shape benchmarks, including MPEG-7 data set, Kimias data set and ETH-80 data set.