Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)

New representations are developed for 2D IP (implicit polynomial) curves of arbitrary degree. These representations permit shape recognition and pose estimation with essentially single, rather than iterative, computation, and extract and use all the information in the polynomial coefficients. This is accomplished by decomposing polynomial coefficient space into a union of orthogonal subspaces for ... View full abstract»

This paper presents a task-oriented evaluation methodology for edge detectors. Performance is measured based on the task of structure from motion. Eighteen real image sequences from 2 different scenes varying in the complexity and scenery types are used. The task-level ground truth for each image sequence is manually specified in terms of the 3D motion and structure. An automated tool computes the... View full abstract»

Creases are a type of ridge/valley structures that can be characterized by local conditions. Therefore, creaseness refers to local ridgeness and valleyness. The curvature K of the level curves and the mean curvature k_M of the level surfaces are good measures of creaseness for 2-d and 3-d images, respectively. However, the way they are computed gives rise to discontinuities, reducing the... View full abstract»

Previously a new object representation using appearance-based parts and relations to recognize 3D objects from 2D images, in the presence of occlusion and background clutter, was introduced. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained fro... View full abstract»

Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted to use affine invariants for recognition. However, there are two problems with this approach: (1) objects or object classes with inherent variability cannot be adequately treated using invariants; and ... View full abstract»

We describe the generation of a large pose-mosaic dataset: a collection of several thousand digital images, grouped by spatial position into spherical mosaics, each annotated with estimates of the acquiring camera's 6 DOF pose (3 DOF position and 3 DOF orientation) in an absolute coordinate system. The pose-mosaic dataset was generated by acquiring images, grouped by spatial position into nodes (e... View full abstract»

We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we have developed a prototype system which automatically aligns a standard atlas to a subject's data to create a customized atlas. Combined with domain knowledge, the registration algorithm can also detect asymmetries and abnormal variations in the subject's data that... View full abstract»

The computational cost of conventional filter methods for junction characterization is very high. This burden can be attenuated by using steerable filters. However, in order to achieve a high orientational selectivity to characterize complex junctions a large number of basis filters is necessary. From this results a yet too high computational effort for steerable filters. In this paper we present ... View full abstract»

This paper describes a new method for face recognition under drastic changes of the imaging processes through which the facial images are acquired. Unlike the conventional methods that use only the face features, the present method exploits the statistical information of the variations between the face image sets being compared, in addition to the features of the faces themselves. To incorporate b... View full abstract»

This paper considers the effect of spatial quantization on several moment invariants. Of particular interest are the affine moment invariants, which have emerged in recent years as a useful tool for image reconstruction, image registration, and recognition of deformed objects. Traditional analysis assumes moments and moment invariants for images that are defined in the continuous domain. In practi... View full abstract»

In this paper we discuss new results on the Shape From Darkness problem: using the motion of cast shadows to recover scene structure. Our approach is based on collecting a set of images from a fixed viewpoint as a known light source mover; “across the sky”. Previously published solutions to this problem have performed the reconstruction only for cross sections of the scene. In this pap... View full abstract»

Although powerful image representations have been proposed for content-based image retrieval, most of the current systems are “rigid”, i.e. they retrieve a fixed set of images as response to a given query and an image feature. In this paper, our goal is to introduce tools for making image retrieval systems more flexible. More precisely, we use multiple image features, and present in de... View full abstract»

We present a 3-D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin-image representation. The spin-image is a data level shape descriptor that is used to match surfaces represented as surface meshes. We present a compression scheme for spin-ima... View full abstract»

Providing a machine with the ability to learn and use models of natural interaction is a challenging and largely unaddressed problem. A framework is developed enabling both the acquisition of interaction behaviours from the observation of humans, and the use of the acquired behaviour models to simulate a plausible partner during interaction. Statistically based interaction behaviour models are acq... View full abstract»

This paper demonstrates a new visual motion estimation technique that is able to recover high degree-of-freedom articulated human body configurations in complex video sequences. We introduce the use of a novel mathematical technique, the product of exponential maps and twist motions, and its integration into a differential motion estimation. This results in solving simple linear systems, and enabl... View full abstract»

This paper presents a system for automatic extraction and tracking of 2D contours of the tongue surfaces from digital ultrasound image sequences. The input to the system is provided by a Head and Transducer Support System (HATS), which is developed for use in ultrasound imaging of the tongue movement. We developed a novel active contour (snakes) model that uses several temporally adjacent images d... View full abstract»

We propose a new image retrieval method based on human perceptual clustering of color images. This color clustering produces for each image a small set of representative colors which captures the color properties of the image, and a small set of sizable contiguous regions which captures the spatial/geometrical properties of the image. The proposed method outperforms the traditional histogram and i... View full abstract»

Image texture can arise not only from surface albedo variations (2D texture) but also from surface height variations (3D texture). Since the appearance of 3D texture depends on the illumination and viewing direction in a complicated manner, such image texture can be called a bidirectional texture function. A fundamental representation of image texture is the histogram of pixel intensities. Since t... View full abstract»

We introduce a method for segmenting surfaces of three-dimensional objects using two images of the object obtained from the same viewpoint under different illumination conditions. The method allows surface spectral reflectance to vary from point to point and requires only weak conditions on the uncalibrated illumination configuration. The algorithm is based on the local recovery of an illumination... View full abstract»

This paper proposes a novel pattern classification approach, called the nearest linear combination (NLC) approach, for eigenface based face recognition. Assume that multiple prototypical vectors are available per class, each vector being a point in an eigenface space. A linear combination of prototypical vectors belonging to a face class is used to define a measure of distance from the query vecto... View full abstract»

This paper describes an interactive sensor planning system, that can be used to select viewpoints subject to camera visibility, field of view and task constraints. Application areas for this method include surveillance planning, safety monitoring, architectural site design planning, and automated site modeling. Given a description, of the sensor's characteristics, the objects in the 3-D scene, and... View full abstract»

A new framework is presented in this paper for tracking non-rigid motion in image sequences. This method models non-rigid motions as the deformations of connected 2D membrane patches. Local smoothness constraints for each patch are the low-frequency vibration modes obtained from modal analysis. These constraints are incorporated with the template matching algorithm into a local motion estimator. T... View full abstract»

Matching images based on a Hausdorff measure has become popular for computer vision applications. However, no probabilistic model has been used in these applications. This limits the formal treatment of several issues, such as feature uncertainties and prior knowledge. In this paper, we develop a probabilistic formulation of image matching in terms of maximum likelihood estimation that generalizes... View full abstract»