Is local colour normalization good enough for local appearance-based classification?

Authors:
Donovan H. Parks;Martin D. Levine
Affiliations:
Dalhousie University, Faculty of Computer Science, 6050 University Avenue, B3H 1W5, Halifax, NS, Canada;McGill University, Centre for Machine Intelligence, Montreal, QC, Canada
Venue:
Machine Vision and Applications - Integrated Imaging and Vision Techniques for Industrial Inspection
Year:
2010

Citing 12
Cited 0

Color indexing

International Journal of Computer Vision
Visual learning and recognition of 3-D objects from appearance

International Journal of Computer Vision
Detectability, Uniqueness, and Reliability of Eigen Windows for Stable Verification of Partially Occluded Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Color Constant Color Indexing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Comprehensive Colour Image Normalization

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Is Machine Colour Constancy Good Enough?

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Object Recognition Using Composed Receptive Field Histograms of Higher Dimensionality

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
The Amsterdam Library of Object Images

International Journal of Computer Vision
Random Subwindows for Robust Image Classification

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints

International Journal of Computer Vision
Eigenfaces for recognition

Journal of Cognitive Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper evaluates the effectiveness of colour normalization techniques when they are applied to small image patches as opposed to the entire image. We evaluate five colour normalization techniques using three different local appearance-based classifiers. Our test sets allow us to independently examine the influence of illumination changes due to lighting colour and geometry. We demonstrate that local colour normalization can significantly improve the performance of a local appearance-based classifier. However, we observe that the effectiveness of local colour normalization depends on both the underlying classifier and the type of illumination variation.