Learning a discriminative classifier using shape context distances

Authors:
Hao Zhang;litendra Malik
Affiliations:
Computer Science Division, University of California at Berkeley, Berkeley, CA;Computer Science Division, University of California at Berkeley, Berkeley, CA
Venue:
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Year:
2003

Citing 10
Cited 11

Principal Warps: Thin-Plate Splines and the Decomposition of Deformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Joint Induction of Shape Features and Tree Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Classification by pairwise coupling

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Comparing Images Using the Hausdorff Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pedestrian Detection Using Wavelet Templates

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Hierarchical Mixtures of Experts and the EM Algorithm

Hierarchical Mixtures of Experts and the EM Algorithm
Reducing multiclass to binary: a unifying approach for margin classifiers

The Journal of Machine Learning Research
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Solving multiclass learning problems via error-correcting output codes

Journal of Artificial Intelligence Research

Multi-views tracking within and across uncalibrated camera streams

IWVS '03 First ACM SIGMM international workshop on Video surveillance
Persistent Objects Tracking Across Multiple Non Overlapping Cameras

WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Online and Offline Character Recognition Using Alignment to Prototypes

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Shape Classification Using the Inner-Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Pyramid Match Kernel: Efficient Learning with Sets of Features

The Journal of Machine Learning Research
BoostMap: An Embedding Method for Efficient Nearest Neighbor Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time shape retrieval for robotics using skip Tri-grams

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A subspace approach for matching 2D shapes under affine distortions

Pattern Recognition
Sketch-based instancing of parameterized 3D models

Edutainment'10 Proceedings of the Entertainment for education, and 5th international conference on E-learning and games
The Global-Local transformation for noise resistant shape representation

Computer Vision and Image Understanding
An intelligent driver location system for smart parking

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

For purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, the outputs of the classifiers are combined using the method called "error correcting output codes". The overall classifier is tested on benchmark dataset and is shown to outperform existing methods with far fewer prototypes.