Results 1 
9 of
9
Pictorial Structures for Object Recognition
 IJCV
, 2003
"... In this paper we present a statistical framework for modeling the appearance of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance ..."
Abstract

Cited by 757 (16 self)
 Add to MetaCart
(Show Context)
In this paper we present a statistical framework for modeling the appearance of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by springlike connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. We use these models to address the problem of detecting an object in an image as well as the problem of learning an object model from training examples, and present efficient algorithms for both these problems. We demonstrate the techniques by learning models that represent faces and human bodies and using the resulting models to locate the corresponding objects in novel images.
Reliable and Efficient Pattern Matching Using an Affine Invariant Metric
 International Journal of Computer Vision
, 1997
"... In the field of pattern matching, there is a clear tradeoff between effectiveness, accuracy and robustness on one hand and efficiency and simplicity on the other hand. For example, matching patterns more effectively by using a more general class of transformations usually results in a considera ..."
Abstract

Cited by 32 (1 self)
 Add to MetaCart
In the field of pattern matching, there is a clear tradeoff between effectiveness, accuracy and robustness on one hand and efficiency and simplicity on the other hand. For example, matching patterns more effectively by using a more general class of transformations usually results in a considerable increase of computational complexity. In this paper, we introduce a general pattern matching approach which will be applied to a new measure called the absolute difference. This patternsimilarity measure is affine invariant, which stands out favourably in practical use. The problem of finding a transformation mapping to the minimal absolute difference, like many pattern matching problems, has a high computational complexity. Therefore, we base our algorithm on a hierarchical subdivision of transformation space. The method applies to any affine group of transformations, allowing optimisations for rigid motion. Our implementation of the method performs well in terms of reliabilit...
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 25 (0 self)
 Add to MetaCart
(Show Context)
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.
Shape Similarity Measures, Properties, and Constructions
 In Advances in Visual Information Systems, 4th International Conference, VISUAL 2000
, 2000
"... In this paper we list a number of similarity measures, some of which are not well known (such as the MongeKantorovich metric), or newly introduced (reflection metric). We formulate properties of similarity measures, and introduce new properties. We also give a set of constructions that have been us ..."
Abstract

Cited by 23 (1 self)
 Add to MetaCart
(Show Context)
In this paper we list a number of similarity measures, some of which are not well known (such as the MongeKantorovich metric), or newly introduced (reflection metric). We formulate properties of similarity measures, and introduce new properties. We also give a set of constructions that have been used in the design of some similarity measures, including some new constructions.
MaximumLikelihood Template Matching
, 2000
"... In image matching applications such as tracking and stereo matching, it is common to use the sumofsquareddifferences (SSD) measure to determin the best match for an image template. However, this measure is sensitive to outliers and is not robust to template variations. We describe a robust measur ..."
Abstract

Cited by 17 (2 self)
 Add to MetaCart
(Show Context)
In image matching applications such as tracking and stereo matching, it is common to use the sumofsquareddifferences (SSD) measure to determin the best match for an image template. However, this measure is sensitive to outliers and is not robust to template variations. We describe a robust measure and efficient search strategy for template matching with a binary or greyscale temolate using a maximumlikelihood formulation. In addition to subpixel localization and uncertainty estimation, these techniques allow optimal feature selection based on minimizing the localization uncertainty. We examine the use of these techniques for object recognition, stereo matching, feature selection and tracking.
Planar shape recognition by shape morphing
 PATTERN RECOGNITION
, 2000
"... A novel method based on shape morphing is proposed for 2D shape recognition. In this framework, the shape of objects is described by using their contour. Shape recognition involves a morph between the contours of the objects being compared. The morph is quantified by using a physicsbased formulatio ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
(Show Context)
A novel method based on shape morphing is proposed for 2D shape recognition. In this framework, the shape of objects is described by using their contour. Shape recognition involves a morph between the contours of the objects being compared. The morph is quantified by using a physicsbased formulation. This quantification is used as a dissimilarity measure to find the reference shape most similar to the input. The dissimilarity measure is shown to have the properties of a metric as well as invariance to Euclidean transformations. The recognition paradigm is applicable to both convex and nonconvex shapes. Moreover, the applicability of the method is not constrained to closed shapes. Based on the metric properties of the dissimilarity method, a search strategy is described that obviates an exhaustive search of the template
Object Recognition with Pictorial Structures
, 2001
"... This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable con guration. The appear ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable con guration. The appearance of each part is modeled separately, and the deformable configuration is represented by springlike connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. The problem of detecting an object in an image and the problem of learning an object model using training examples are naturally formulated under a statistical approach. We present efficient algorithms to solve these problems in our framework. We demonstrate our techniques by training models to represent faces and human bodies. The models are then used to locate the corresponding objects in novel images.
Graylevel VisualGlove: Turning
"... Hand tracking for humancomputer interaction with ..."
(Show Context)