Using local integral invariants for object recognition in complex scenes

Authors:
Alaa Halawani;Hashem Tamimi;Hans Burkhardt;Andreas Zell
Affiliations:
Chair of Pattern Recognition and Image Processing, University of Freiburg, Freiburg, Germany;Computer Science Dept., University of Tübingen, Tübingen, Germany;Chair of Pattern Recognition and Image Processing, University of Freiburg, Freiburg, Germany;Computer Science Dept., University of Tübingen, Tübingen, Germany
Venue:
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II
Year:
2006

Citing 9
Cited 0

Color indexing

International Journal of Computer Vision
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
Local Grayvalue Invariants for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Algorithm for Finding Best Matches in Logarithmic Expected Time

ACM Transactions on Mathematical Software (TOMS)
Object Recognition Using Multidimensional Receptive Field Histograms

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Invariant Features for Gray Scale Images

Mustererkennung 1995, 17. DAGM-Symposium
Object-based queries using color points of interest

CBAIVL '01 Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries (CBAIVL'01)
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates the use of local descriptors that are based on integral invariants for the purpose of object recognition in cluttered scenes. Integral invariants capture the local structure of the neighborhood around the points where they are computed. This makes them very well suited for constructing highly-discriminative local descriptors. The features are by definition invariant to Euclidean motion. We show how to extend the local features to be scale invariant. Regarding the robustness to intensity changes, two types of kernels used for extracting the feature vectors are investigated. The effect of the feature vector dimensionality and the performance in the presence of noise are also examined. Promising results are obtained using a dataset that contains instances of objects that are viewed in difficult situations that include clutter and occlusion.