Oriented filters for object recognition: an empirical study

Authors:
Jerry Jun Yokono;Tomaso Poggio
Affiliations:
Center for Biological and Computational Learning, M.I.T., Cambridge, MA and Sony Corporation, Networked CE Development Lab., Tokyo, Japan;Center for Biological and Computational Learning, M.I.T., Cambridge, MA
Venue:
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Year:
2004

Citing 12
Cited 6

Scaling Theorems for Zero Crossings

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Design and Use of Steerable Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
SEEMORE: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition

Neural Computation
Local Grayvalue Invariants for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognition without Correspondence using MultidimensionalReceptive Field Histograms

International Journal of Computer Vision
Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
Scale-Space Theory in Computer Vision

Scale-Space Theory in Computer Vision
Object Recognition Using Multidimensional Receptive Field Histograms

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Training Support Vector Machines: an Application to Face Detection

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A General Framework for Object Detection

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Face recognition: component-based versus global approaches

Computer Vision and Image Understanding - Special issue on Face recognition

AdaBoost Multiple Feature Selection and Combination for Face Recognition

IbPRIA '09 Proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis
Orientation invariant features for multiclass object recognition

CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Matching deformable features based on oriented multi-scale filter banks

AMDO'06 Proceedings of the 4th international conference on Articulated Motion and Deformable Objects
Sharing visual features for animal categorization: an empirical study

ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II
Affine invariant gradient based shape descriptor

MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Solving the correspondence problem in stereo vision by internal simulation

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Our performance criterion for a local descriptor is based on the tradeoff between selectivity and invariance. In this paper, we evaluate several local descriptors with respect to selectivity and invariance. The descriptors that we evaluated are Gaussian derivatives up to the third order, gray image patches, and Laplacian-based descriptors with either three scales or one scale filters. We compare selectivity and invariance to several affine changes. The overall results indicate a good performance by the descriptor based on a set of oriented Gaussian filters. Finally, we discuss briefly an object detection system based on the Gaussian descriptor that we have implemented: preliminary results confirm robust performance in cluttered scenes in the presence of partial occlusions.