As the number of 3D models available on the Web grows, there is an increasing need for a search engine to help people find them. Unfortunately, traditional text-based search techniques are not always effective for 3D data. In this paper, we investigate new shape-based search methods. The key challenges are to develop query methods simple enough for novice users and matching algorithms robust enough to work for arbitrary polygonal models. We present a web-based search engine system that supports queries based on 3D sketches, 2D sketches, 3D

Measuring the similarity between 3D shapes is a fundamental problem, with applications in computer vision, molecular biology, computer graphics, and a variety of other fields. A challenging aspect of this problem is to find a suitable shape signature that can be constructed and compared quickly, while still discriminating between similar and dissimilar shapes. In this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The primary motivation for this approach is to reduce the shape matching problem to the comparison of probability distributions, which is a simpler problem than the comparison of 3D surfaces by traditional shape matching methods that require pose registration, feature correspondence, or model fitting. We find that the dissimilarities be...

this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The primary motivation for this approach is to reduce the shape matching problem to the comparison of probability distributions, which is simpler than traditional shape matching methods that require pose registration, feature correspondence, or model fitting

This paper presents a portable system and method for recognizing the 26 hand shapes of the American Sign Language alphabet, using a novel glove-like device. Two additional signs, 'space', and 'enter ' are added to the alphabet to allow the user to form words or phrases and send them to a speech synthesizer. Since the hand shape for a letter varies from one signer to another, this is a 28class pattern recognition system. A three-level hierarchical classifier divides the problem into "dispatchers " and "recognizers. " After reducing pattern dimension from ten to three, the projection of class distributions onto horizontal planes makes it possible to apply simple linear discrimination in 2D, and Bayes ' Rule in those cases where classes had features with overlapped distributions. Twenty-one out of 26 letters were recognized with 100 % accuracy; the worst case, letter U, achieved 78%. 1.

. Two new methods for reducing complexity of size graphs are described. Some theoretical results are given together with various examples. Keywords: shape, size graph, discrete size function. 1991 Mathematics Subject Classification: Primary 05C90, 68R10; Secondary 05C78, 05C85 1 Introduction: Size Graphs and the Reduction Problem Size Theory is a new approach to the problem of comparing "shapes" of topological spaces, based on a mathematical transform named size function. Such a theory appears to be particularly useful in Computer Vision, when the topological spaces to be described and compared are images or parts of images. In fact, size functions have interesting properties such as resistance to noise and capability to be useful also in presence of occlusions (cf. [7]). Moreover, their modularity allows us to make them invariant under the transformation group we are interested in, e.g. the group of isometries or affine or projective transformations. Size Theory has turned out to b...

As the number of 3D models available on the Web grows, there is an increasing need for a search engine to help people find them. Unfortunately, traditional text-based search techniques are not always effective for 3D data. In this paper, we investigate new shape-based search methods. The key challenges are to develop query methods simple enough for novice users and matching algorithms robust enough to work for arbitrary polygonal models. We present a web-based search engine system that supports queries based on 3D sketches, 2D sketches, 3D models, and/or text keywords. For the shape-based queries, we have developed a new matching algorithm that uses spherical harmonics to compute discriminating similarity measures without requiring repair of model degeneracies or alignment of orientations. It provides 46--245% better performance than related shape matching methods during precision-recall experiments, and it is fast enough to return query results from a repository of 20,000 models in under a second. The net result is a growing interactive index of 3D models available on the Web (i.e., a Google for 3D models).

Virtual environments have huge potential in education [1]. This paper presents a virtual learning environment which is aimed at making sign language lessons accessible to the general community. The system presented is a practical and interactive teaching environment which instructs and gives real-time feedback on the users’ performance of the signs. 1.

This paper describes a system which enables a robot to recognize and respond to hand gestures from a human operator. The robot uses a color camera on a pantilt unit to track an operator as both the robot and the operator move, with the operator controlling the robot through visual gestures. The system uses a segmentation based on the hue of the image to find skin-colored areas. It then uses a convexity-based feature detector to find possible fingertips. The fingertips are filtered through geometry constraints to identify possible finger candidates. These are then matched against hand models to perform gesture recognition. This system is capable of recognizing a few simple gestures from a wide range of operators in an environment with complex backgrounds.

This paper discusses a novel approach for capturing and translating isolated gestures of American Sign Language into spoken and written words. The instrumented part of the system combines an AcceleGlove and a two-link arm skeleton. Gestures of the American Sign Language are broken down into unique sequences of phonemes called Poses and Movements, recognized by software modules trained and tested independently on volunteers with different hand sizes and signing ability. Recognition rates of independent modules reached up to 100 % for 42 postures, 6 orientations, 11 locations and 7 movements using linear classification. The overall sign recognizer was tested using a subset of the American Sign Language dictionary comprised by 30 one-handed signs, achieving 98 % accuracy. The system proved to be scalable: when the lexicon was extended to 176 signs and tested without retraining, the accuracy was 95%. This represents an improvement over classification based on Hidden Markov Models and Neural Network.