Local invariant object localization based on a reduced color space

Authors:
Rüdiger Heintz;Eduardo Monari;Gerhard Schäfer
Affiliations:
Fakultät für Elektro und Informationstechnik, University of Applied Science, Karlsruhe, Germany;Fakultät für Elektro und Informationstechnik, University of Applied Science, Karlsruhe, Germany;Fakultät für Elektro und Informationstechnik, University of Applied Science, Karlsruhe, Germany
Venue:
SSIP'05 Proceedings of the 5th WSEAS international conference on Signal, speech and image processing
Year:
2005

Citing 4
Cited 0

Simple Gabor feature space for invariant object recognition

Pattern Recognition Letters
Face Authentication Test on the BANCA Database

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Recursive Gabor filtering

IEEE Transactions on Signal Processing
Comparison of texture features based on Gabor filters

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Invariant object localization is one of the challenging tasks in computer vision research. In this paper we present a robust rotation and scale invariant object localization method. A local Gabor filter space is treated as core of this method. Image rotation and scaling operations were transformed into shift operations along the Gabor filter space dimensions. This property enables efficient scale and rotation estimation without segmentation. The used Gabor Filter can deal with complex input data. This feature is used to analyze color images by reducing the color space. The method was tested with two standardized image databases and our own image database. Besides a good quality in localizing rotated and scaled objects, the method has a strong robustness against variations of lightning conditions and 3D viewpoint changes.