Results 1  10
of
35
Recognition without Correspondence using Multidimensional Receptive Field Histograms
 International Journal of Computer Vision
, 2000
"... . The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represente ..."
Abstract

Cited by 209 (19 self)
 Add to MetaCart
. The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of such local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the paper develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that these techniques can identify over 100 objects in the presence of major occlusions. Most remarkably, the techniques have low complexity and therefore run in realtime. 1. Introduction The paper proposes a framework for the statistical representation of the appearance of arbitrary 3D objects. This representation consists of a probability density function or jo...
A probabilistic approach to object recognition using local photometry and global geometry
 European Conference on Computer Vision
, 1998
"... Abstract. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial con guration. We introduce a simpli ed model of a deformable object class and derive the optimal detector for this model. However, the optimal detector is not realizab ..."
Abstract

Cited by 148 (13 self)
 Add to MetaCart
Abstract. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial con guration. We introduce a simpli ed model of a deformable object class and derive the optimal detector for this model. However, the optimal detector is not realizable except under special circumstances (independent part positions). A cousin of the optimal detector is developed which uses \soft " part detectors with a probabilistic description of the spatial arrangement of the parts. Spatial arrangements are modeled probabilistically using shape statistics to achieve invariance to translation, rotation, and scaling. Improved recognition performance over methods based on \hard " part detectors is demonstrated for the problem of face detection in cluttered scenes. 1
A Simple Algorithm for Nearest Neighbor Search in High Dimensions
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1997
"... Abstract—The problem of finding the closest point in highdimensional spaces is common in pattern recognition. Unfortunately, the complexity of most existing search algorithms, such as kd tree and Rtree, grows exponentially with dimension, making them impractical for dimensionality above 15. In ne ..."
Abstract

Cited by 126 (1 self)
 Add to MetaCart
Abstract—The problem of finding the closest point in highdimensional spaces is common in pattern recognition. Unfortunately, the complexity of most existing search algorithms, such as kd tree and Rtree, grows exponentially with dimension, making them impractical for dimensionality above 15. In nearly all applications, the closest point is of interest only if it lies within a userspecified distance e. We present a simple and practical algorithm to efficiently search for the nearest neighbor within Euclidean distance e. The use of projection search combined with a novel data structure dramatically improves performance in high dimensions. A complexity analysis is presented which helps to automatically determine e in structured problems. A comprehensive set of benchmarks clearly shows the superiority of the proposed algorithm for a variety of structured and unstructured search problems. Object recognition is demonstrated as an example application. The simplicity of the algorithm makes it possible to construct an inexpensive hardware search engine which can be 100 times faster than its software equivalent. A C++ implementation of our algorithm is available upon request to search@cs.columbia.edu/CAVE/.
Shape Matching: Similarity Measures and Algorithms
, 2001
"... Shape matching is an important ingredient in shape retrieval, recognition and classification, alignment and registration, and approximation and simplification. This paper treats various aspects that are needed to solve shape matching problems: choosing the precise problem, selecting the properties o ..."
Abstract

Cited by 91 (1 self)
 Add to MetaCart
Shape matching is an important ingredient in shape retrieval, recognition and classification, alignment and registration, and approximation and simplification. This paper treats various aspects that are needed to solve shape matching problems: choosing the precise problem, selecting the properties of the similarity measure that are needed for the problem, choosing the specific similarity measure, and constructing the algorithm to compute the similarity. The focus is on methods that lie close to the field of computational geometry.
Efficient Image Retrieval through Vantage Objects
 Pattern Recognition
, 1999
"... We describe a new indexing structure for general image retrieval that relies solely on a distance function giving the similarity between two images. For each image object in the database, its distance to a set of m predetermined vantage objects is calculated; the mvector of these distances specifie ..."
Abstract

Cited by 48 (7 self)
 Add to MetaCart
We describe a new indexing structure for general image retrieval that relies solely on a distance function giving the similarity between two images. For each image object in the database, its distance to a set of m predetermined vantage objects is calculated; the mvector of these distances specifies a point in the mdimensional vantage space. The database objects that are similar (in terms of the distance function) to a given query object can be determined by means of an efficient nearestneighbor search on these points. We demonstrate the viability of our approach through experimental results obtained with a database of about 48,000 hieroglyphic polylines.
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 30 (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...
Probabilistic Affine Invariants for Recognition
 In Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn
, 1998
"... 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) obj ..."
Abstract

Cited by 30 (4 self)
 Add to MetaCart
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 (2) in practice the calculated affine invariants can be quite sensitive to errors in the image plane measurements. In this paper we use probability distributions to address both of these difficulties. Under the assumption that the feature positions of a planar object can be modeled using a jointly Gaussian density, we have derived the joint density over the corresponding set of affine coordinates. Even when the assumptions of a planar object and a weak perspective camera model do not strictly hold, the results are useful because deviations from the ideal can be treated as deformability in the ...
Partial Surface and Volume Matching in Three Dimensions
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1997
"... In this paper we present a new technique for partial surface and volume matching of images in three dimensions. In this ..."
Abstract

Cited by 27 (1 self)
 Add to MetaCart
In this paper we present a new technique for partial surface and volume matching of images in three dimensions. In this
Toward Selecting and Recognizing Natural Landmarks
 In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
, 1994
"... Landmarks are often used as a basis for mobile robot navigation. In this paper, we consider the problem of automatically selecting from a set of 3D features the subset which is most likely to be recognized from noisy monocular image data and is least likely to be confused with any of the other group ..."
Abstract

Cited by 21 (0 self)
 Add to MetaCart
Landmarks are often used as a basis for mobile robot navigation. In this paper, we consider the problem of automatically selecting from a set of 3D features the subset which is most likely to be recognized from noisy monocular image data and is least likely to be confused with any of the other groups of features. Assuming perspective projection, real valued recognition functions are constructed for a set of features. The value returned from such functions are invariant to changes of viewpoint and can be evaluated directly from image measurements without prior knowledge of the position and orientation of the camera. With image noise, the recognition function no longer evaluates to a constant value. Because of the possibility of false matches, a Bayes detector is used to determine the optimal range of values of the recognition function that will be accepted as image features of the model. The model with the lowest Bayes cost is selected as the most distinguishable landmark. We show imple...