A new method for representing and matching shapes of natural objects

A new method for the representation and comparison of irregular two-dimensional shapes is presented. This method uses a polar transformation of the contour points about the geometric centre of the object. The distinctive vertices of the shape are extracted and used as comparative parameters to minimize the difference of contour distance from the centre. Experiments are performed, more than 39 000 comparisons of database shapes, provided by Sebastian et al. (ICCV (2001) 755), are made and the results are compared to those obtained therein. In addition, 450 comparisons of leaf shape are made and leaves of very similar shape are accurately distinguished. The method is shown to be invariant to translation, rotation and scaling and highly accurate in shape distinction. The method shows more tolerance to scale variation than that of Sebastian et al. (ICCV (2001) 755) and is less computationally intense.     

Graphical objects

We introduce the concept of graphical objects, the abstraction paradigms to study them, and their applications in computer graphics. Intuitively, graphical objects encompass all the entities manipulated in a graphics system. This notion makes it possible to unify similar research topics appearing in the literature separately. We study the problem of object metamorphosis, which includes the problem of image metamorphosis. Although we are not primarily concerned with implementation issues in this paper, the concepts we introduce can be exploited for system design and development that use object-oriented programming.     

Appearance-based recognition of 3-D objects by cluttered background and occlusions

In this article we present a new appearance-based approach for the classification and the localization of 3-D objects in complex scenes. A main problem for object recognition is that the size and the appearance of the objects in the image vary for 3-D transformations. For this reason, we model the region of the object in the image as well as the object features themselves as functions of these transformations. We integrate the model into a statistical framework, and so we can deal with noise and illumination changes. To handle heterogeneous background and occlusions, we introduce a background model and an assignment function. Thus, the object recognition system becomes robust, and a reliable distinction, which features belong to the object and which to the background, is possible. Experiments on three large data sets that contain rotations orthogonal to the image plane and scaling with together more than 100 000 images show that the approach is well suited for this task.     

Hierarchical vibrations for part-based recognition of complex objects

We propose a technique for the recognition and segmentation of complex shapes in 2D images using a hierarchy of finite element vibration modes in an evolutionary shape search. The different levels of the shape hierarchy can influence each other, which can be exploited in top-down part-based image analysis. Our method overcomes drawbacks of existing structural approaches, which cannot uniformly encode shape variation and co-variation, or rely on training. We present results demonstrating that by utilizing a quality-of-fit function the model explicitly recognizes missing parts of a complex shape, thus allowing for categorization between shape classes.     

An improved generalized Hough transform for the recognition of overlapping objects

The generalized Hough transform (GHT) is a powerful method for recognizing arbitrary shapes as long as the correct match accounts for both much of the model and much of the sensory object. For moderate levels of occlusion, however, the GHT can hypothesize many false solutions. In this paper, we present an improved two-stage GHT procedure for the recognition of overlapping objects. Each boundary point in the image is described by three features including the concavity, radius and normal direction of the curve segment in the neighborhood of the point. The first stage of the voting process determines the rotational angle of the sensory object with respect to the model by matching those points that have the same concavity and radii. The second stage then determines the centroid of the sensory object by matching those points that have the same concavity, radii and rotational angles. The three point features remove the false contribution of votes in the vote generation phase. Experimental results have shown that the proposed algorithm works well for complex objects under severely overlapping conditions.     

Hypercolumn-array based image representation and its application to shape-based object detection

Biological and psychological evidence increasingly reveals that high-level geometrical and topological features are the keys to shape-based object recognition in the brain. Attracted by the excellent performance of neural visual systems, we simulate the mechanism of hypercolumns in the mammalian cortical area V1 that selectively responds to oriented bar stimuli. We design an orderly-arranged hypercolumn array to extract and represent linear or near-linear stimuli in an image. Each unit of this array covers stimuli of various orientations in a small area, and multiple units together produce a low-dimensional vector to describe shape. Based on the neighborhood of units in the array, we construct a graph whose node represents a short line segment with a certain position and slope. Therefore, a contour segment in the image can be represented with a route in this graph. The graph converts an image, comprised of typically unstructured raw data, into structured and semantic-enriched data. We search along the routes in the graph and compare them with a shape template for object detection. The graph greatly upgrades the level of image representation, remarkably reduces the load of combinations, significantly improves the efficiency of object searching, and facilitates the intervening of high-level knowledge. This work provides a systematic infrastructure for shape-based object recognition.     

Edge replacement in the recognition of occluded objects

The Generalized Hough Transform recognizes objects more successfully when all edges are visible. To facilitate recognition, this paper introduces a preliminary Generalized Hough process that restores edges which were invisible because of occlusion or because of lack of contrast between occluding and occluded areas. Space and time complexity of Generalized Hough processes are reduced by chained hashing techniques. Experimental results show that recognition of occluded objects via a Generalized Hough Transform is improved if occluding objects are first recognized and subtracted out of the input picture, and occluded edges are then reconstructed prior to recognition of occluded objects.     

二值图象边界平滑跟踪的一个算法

开发了一个用于二值图象边界平滑跟踪的一个算法。使用这个算法能去掉或修正某些可能是虚假的干扰点。这些点是二值图象边界一个或一组沿特定链码方向的凸点或凹点。重复地使用这个算法，直到边界不含有这些点。这个算法能有效地使用在二值图象的模式识别与机器人视觉的预处理中。     

Planar shape matching based on binary tree shape representation

In this paper we suggest a new way of representing planar two-dimensional shapes and a shape matching method which utilizes the new representation. Through merging of the neighboring boundary runs, a shape can be partitioned into a set of triangles. These triangles are inherently connected according to a binary tree structure. Here we use the binary tree with the triangles as its nodes to represent the shape. This representation is found to be insensitive to shape translation, rotation, scaling and skewing changes due to viewer's location changes (or the object's pose changes). Furthermore, the representation is of multiresolution.

In shape matching we compare the two trees representing two given shapes node by node according to the breadth-first tree traversing sequence. The comparison is done from top of the tree and moving downward, which means that we first compare the lower resolution approximations of the two shapes. If the two approximations are different, the comparison stops. Otherwise, it goes on and compares the finer details of the two shapes. Only when the two shapes are very similar, will the two corresponding trees be compared entirely. Thus, the matching algorithm utilizes the multiresolution characteristic of the tree representation and appears to be very efficient.     

拓扑关系在图形对象表示与识别中的应用

工程图纸识别中,图形对象的表示方法是研究的重点和难点。在矢量化的基础上提出了一种基于拓扑结构的图形对象表示与识别方法,该方法通过矢量化获得各个图形对象的矢量基元,通过建立矢量基元的影响区域确定各矢量基元的拓扑邻接关系图,进而确定图形对象之间的位置关系,为进一步理解识别工程图纸提供了基本的信息。然后介绍了一个应用实例：圆弧角的识别。在实验中,分别用标准数据和真实图纸进行了测试,实验结果显示该算法具有较高的识别精度和识别效率。     

Spectra of shape contexts: An application to symbol recognition

The pixel-level constraint (PLC) histograms are known for robustness and invariance in symbol recognition but limited in O(N³) complexity. This paper proves that matching two PLC histograms can approximately be solved as matching the power spectra of the corresponding shape contexts. As a result, spectra of shape contexts (SSC) inherit robustness and invariance from PLC while the computational cost can be reduced. Moreover, a maximum clique based scheme is proposed for outlier rejection. The theoretical and experimental validation justifies that SSC possesses the desired properties for symbol recognition, that is, robustness, invariance, and efficiency. It outperforms PLC in terms of robustness and time efficiency, and shape context in terms of rotation invariance.     

Shape recognition based on Kernel-edit distance

In this paper a kernel method for shape recognition is proposed. The approach is based on the edit distance between pairs of shapes after transforming them into symbol strings. The transformation of shapes into symbol strings is invariant to similarity transforms and can handle partial occlusions. Representation of shape contours uses the shape contexts and applies dynamic programming for finding the correspondence between points over shape contours. Corresponding points are then transformed into symbolic representation and the normalized edit distance computes the dissimilarity between pairs of strings in the database. Obtained distances are then transformed into suitable kernels which are classified using support vector machines. Experimental results over a variety of shape databases show that the proposed approach is suitable for shape recognition.     

Query-expanded collaborative representation based classification with class-specific prototypes for object recognition

Linear representation based classifiers (LinearRCs) assume that a query image can be represented as a linear combination of dictionary atoms or prototypes with various priors (e.g., sparsity), which have achieved impressive results in face recognition. Recently, a few attempts have been made to deal with more general cases (e.g., multi-view or multi-pose objects, more generic objects, etc.) but with additional requirements. In this paper, we present a query-expanded collaborative representation based classifier with class-specific prototypes (QCRC_CP) from the general perspective. First, we expand a single query in a multi-resolution way to cover rich variations of object appearances, thereby generating a query set. We then condense the gallery images to a small amount of prototypical images by maximizing canonical correlation in a class-specific way, in which the implicit query-dependent data locality discards the outliers. Given the query set, we finally propose a multivariate LinearRC with collaborative prior to identify the query according to the rule of minimum normalized residual (MNR). Experiments on four object recognition datasets (FERET pose, Swedish leaf, Chars74K, and ETH-80) show that our method outperforms the state-of-the-art LinearRCs with performance increases at least 3.1%, 3.8%, 10.4% and 3.1% compared to other classifiers.     

Object representation and recognition in shape spaces

In this paper, we describe a shape space based approach for invariant object representation and recognition. In this approach, an object and all its similarity transformed versions are identified with a single point in a high-dimensional manifold called the shape space. Object recognition is achieved by measuring the geodesic distance between an observed object and a model in the shape space. This approach produced promising results in 2D object recognition experiments: it is invariant to similarity transformations and is relatively insensitive to noise and occlusion. Potentially, it can also be used for 3D object recognition.     

Learning search heuristics for finding objects in structured environments

We consider the problem of efficiently finding an object with a mobile robot in an initially unknown, structured environment. The overall goal is to allow the robot to improve upon a standard exploration technique by utilizing background knowledge from previously seen, similar environments. We present two conceptually different approaches. Whereas the first method, which is the focus of this article, is a reactive search technique that decides where to search next only based on local information about the objects in the robot’s vicinity, the second algorithm is a more global and inference-based approach that explicitly reasons about the location of the target object given all observations made so far. While the model underlying the first approach can be learned from data of optimal search paths, we learn the model of the second method from object arrangements of example environments. Our application scenario is the search for a product in a supermarket. We present simulation and real-world experiments in which we compare our strategies to alternative methods and also to the performance of humans.     

A local approach for 3D object recognition through a set of size functions

In this paper, a local approach for 3D object recognition is presented. It is based on the topological invariants provided by the critical points of the 3D object. The critical points and the links between them are represented by a set of size functions obtained after splitting the 3D object into portions. A suitable similarity measure is used to compare the sets of size functions associated with the 3D objects. In order to validate our approach's recognition performance, we used different collections of 3D objects. The obtained scores are favourably comparable to the related work.     

A general shape context framework for object identification

A general shape context framework is proposed for object/image retrieval in occluded and cluttered environment with hundreds of models as the potential matches of an input. The approach is general since it does not require separation of input objects from complex background. It works by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Its performance degrades gracefully with respect to the amount of structural information that is being occluded or lost. The local neighborhood information applicable to the system can be shape, color, texture feature, etc. Currently, we employ shape information only. The mechanism of voting is based on a novel hyper cube based indexing structure, and driven by dynamic programming. The proposed concepts have been tested on database with thousands of images. Very encouraging results have been obtained.