Object recognition using frequency domain blur invariant features

Authors:
Ville Ojansivu;Janne Heikkilä
Affiliations:
Machine Vision Group, Department of Electrical and Information Engineering, University of Oulu, Finland;Machine Vision Group, Department of Electrical and Information Engineering, University of Oulu, Finland
Venue:
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Year:
2007

Citing 5
Cited 4

Degraded Image Analysis: An Invariant Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion blur concealment of digital video using invariant features

ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Phase reconstruction from bispectrum slices

IEEE Transactions on Signal Processing
Recognition of blurred images by the method of moments

IEEE Transactions on Image Processing
Pattern recognition using invariants defined from higher order spectra: 2-D image inputs

IEEE Transactions on Image Processing

A Method for Blur and Affine Invariant Object Recognition Using Phase-Only Bispectrum

ICIAR '08 Proceedings of the 5th international conference on Image Analysis and Recognition
Weighted DFT Based Blur Invariants for Pattern Recognition

SCIA '09 Proceedings of the 16th Scandinavian Conference on Image Analysis
Blur invariants: A novel representation in the wavelet domain

Pattern Recognition
Wavelet domain blur invariants for 1D discrete signals

ICIAR'11 Proceedings of the 8th international conference on Image analysis and recognition - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose novel blur invariant features for the recognition of objects in images. The features are computed either using the phase-only spectrum or bispectrum of the images and are invariant to centrally symmetric blur, such as linear motion or defocus blur as well as linear illumination changes. The features based on the bispectrum are also invariant to translation, and according to our knowledge they are the only combined blur-translation invariants in the frequency domain. We have compared our features to the blur invariants based on image moments in simulated and real experiments. The results show that our features can recognize blurred images better and, in a practical situation, they are faster to compute using FFT.