Results 1 
6 of
6
Multifeature Hierarchical Template Matching Using Distance Transforms
, 1998
"... We describe a multifeature hierarchical algorithm to efficiently match N objects (templates) with an image using distancetransforms (DTs). The matching is under translation, but it can cover more general transformations by generating the various transformed templates explicitly. The novel part of t ..."
Abstract

Cited by 64 (3 self)
 Add to MetaCart
We describe a multifeature hierarchical algorithm to efficiently match N objects (templates) with an image using distancetransforms (DTs). The matching is under translation, but it can cover more general transformations by generating the various transformed templates explicitly. The novel part of the algorithm is that, in addition to acoarsetofine search over the translation parameters, the N templates aregrouped offline into a template hierarchy based on their similarity. This way, multiple templates can be matched resulting in various speedup factors. Furthermore, in matching, features are distinguishedby type and separate DT's arecomputed for each type (e.g. basedonedge orientations). These concepts are illustrated in the application of traffic sign detection.
Hand Pose Estimation Using Hierarchical Detection
 in Intl. Workshop on HumanComputer Interaction
, 2004
"... This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as ..."
Abstract

Cited by 22 (2 self)
 Add to MetaCart
This paper presents an analysis of the design of classifiers for use in a hierarchical object recognition approach. In this approach, a cascade of classifiers is arranged in a tree in order to recognize multiple object classes. We are interested in the problem of recognizing multiple patterns as it is closely related to the problem of locating an articulated object. Each different pattern class corresponds to the hand in a different pose, or set of poses. For this problem obtaining labelled training data of the hand in a given pose can be problematic. Given a parametric 3D model, generating training data in the form of example images is cheap, and we demonstate that it can be used to design classifiers almost as good as those trained using nonsynthetic data. We compare a variety of different templatebased classifiers and discuss their merits.
Learning models for object recognition
 In
, 2001
"... We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Haus ..."
Abstract

Cited by 21 (0 self)
 Add to MetaCart
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Hausdorff distance between the model and the new shape is small. We show that such object concepts can be seen as halfspaces (linear threshold functions) in a transformed input space. This makes it possible to use a number of standard algorithms to learn object models from training examples. When a good model exists, we are guaranteed to find one that provides (with high probability) a recognition rule that is accurate. Our approach provides a measure which generalizes the Hausdorff distance in a number of interesting ways. To demonstrate our method we trained a system to detect people in images using a single shape model. The learning techniques can be extended to represent objects using multiple model shapes. In this way, we might be able to automatically learn a small set of canonical shapes that characterize the appearance of an object. 1.
A New Bayesian Framework for Object Recognition
 In IEEE Conference on Computer Vision and Pattern Recognition
, 1998
"... We describe a new approach to featurebased object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. The main advantage of this approach is that it allows explicit modeling of dependencies between individual features of an object model. For instance, i ..."
Abstract

Cited by 15 (2 self)
 Add to MetaCart
We describe a new approach to featurebased object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. The main advantage of this approach is that it allows explicit modeling of dependencies between individual features of an object model. For instance, it can capture the fact that unmatched features due to partial occlusion are generally spatially coherent rather than independent. Efficient computation of the MAP estimate in our framework can be accomplished by finding a minimum cut on an appropriately defined graph. A special case of our framework yields even more efficient method, that does not use graph cuts. We call this technique spatially coherent matching. Our framework can also be seen as providing a probabilistic understanding of Hausdorff matching. We present ROC curves from Monte Carlo experiments that illustrate the improvement of the new spatially coherent matching technique over Hausdorff matching. 1 Introduction In this pap...
Learning Models for Object Recognition
"... We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Haus ..."
Abstract
 Add to MetaCart
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an object is represented in terms of a model shape. A new shape is classified as being an instance of the object when the Hausdorff distance between the model and the new shape is small. We show that such object concepts can be seen as halfspaces (linear threshold functions) in a transformed input space. This makes it possible to use a number of standard algorithms to learn object models from training examples. When a good model exists, we are guaranteed to find one that provides (with high probability) a recognition rule that is accurate. Our approach provides a measure which generalizes the Hausdorff distance in a number of interesting ways. To demonstrate our method we trained a system to detect people in images using a single shape model. The learning techniques can be extended to represent objects using multiple model shapes. In this way, we might be able to automatically learn a small set of canonical shapes that characterize the appearance of an object. 1.
A New Bayesian Framework for Object Recognition
"... We introduce an approach to featurebased object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. This approach provides an efficient solution for a wide class of priors that explicitly model dependencies between individual features of an object. Thes ..."
Abstract
 Add to MetaCart
We introduce an approach to featurebased object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. This approach provides an efficient solution for a wide class of priors that explicitly model dependencies between individual features of an object. These priors capture phenomena such as the fact that unmatched features due to partial occlusion are generally spatially correlated rather than independent. The main focus of this paper is a special case of the framework that yields a particularly efficient approximation method. We call this special case spatially coherent matching (SCM), as it reflects the spatial correlation among neighboring features of an object. The SCM method operates directly on the image feature map, rather than relying on the graphbased methods used in the general framework. We present some Monte Carlo experiments showing that SCM yields substantial improvements over Hausdorff matching for cluttered scenes and partially occluded objects. 1