Title :
Complex Daubechies wavelet based affine invariant representation for object recognition
Author :
Tieng, Quang Minh ; Boles, W.W.
Author_Institution :
Signal Process. Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
Abstract :
An algorithm based on the dyadic wavelet transform and complex Daubechies wavelets to recognise a planar object undergoing a general affine transformation is presented. The affine transformation most appropriately represents shape distortions arising from observing an object by a camera under arbitrary orientations. The proposed algorithm includes two steps: constructing the representation and the matching process. Experimental results show that the representation is robust and combined with the matching algorithm, it efficiently classifies unknown objects
Keywords :
image classification; image matching; invariance; object recognition; wavelet transforms; algorithm; arbitrary orientations; complex Daubechies wavelet based affine invariant representation; dyadic wavelet transform; general affine transformation; matching process; object classification; object recognition; planar object; representation; shape distortions; Australia; Cameras; Fourier transforms; Layout; Object recognition; Pattern recognition; Robustness; Shape; Signal processing algorithms; Wavelet transforms;
Conference_Titel :
Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6952-7
DOI :
10.1109/ICIP.1994.413303
