Robust Affine Invariant Region-Based Shape Descriptors: The ICA Zernike Moment Shape Descriptor and the Whitening Zernike Moment Shape Descriptor Export

@article{citeulike:5768478, abstract = {In this letter, we proposed two new affine invariant region-based shape descriptors, the ICA Zernike moment shape descriptor (ICAZMSD) and the whitening Zernike moment shape descriptor (WZMSD). Either independent component analysis (ICA) or whitening, is first used to turn the original shape into a canonical form, in which the effects of scaling and skewing are eliminated. Next, the properties of the Zernike transform are used to further eliminate the effects of any possible rotation and reflection of the canonical shapes, in extracting the Zernike moments as the affine invariant region-based descriptors. Using the proposed ICAZMSD as shape feature, shape-based image retrieval experiments on a 4000 complex shape image database and on a 5600 simple shape image database, show retrieval rates of 99.80\% and 92.25\%, respectively. Using the proposed WZMSD as shape feature, the corresponding retrieval rates are 99.79\% and 92.22\%, respectively. The proposed WZMSD has almost equal performance to the proposed ICAZMSD, while having lower computational requirements.}, author = {Mei, Ye and Androutsos, Dimitrios}, citeulike-article-id = {5768478}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/LSP.2009.2026119}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5109745}, doi = {10.1109/LSP.2009.2026119}, journal = {IEEE Signal Processing Letters}, keywords = {affine, analysis, component, descriptor, ica, independent, invariant, moments, shape, whitening, zernike}, month = {October}, number = {10}, pages = {877--880}, posted-at = {2009-09-10 12:10:20}, priority = {2}, title = {Robust Affine Invariant Region-Based Shape Descriptors: The ICA Zernike Moment Shape Descriptor and the Whitening Zernike Moment Shape Descriptor}, url = {http://dx.doi.org/10.1109/LSP.2009.2026119}, volume = {16}, year = {2009} }

TY - JOUR ID - citeulike:5768478 L3 - citeulike-article-id:5768478 N2 - In this letter, we proposed two new affine invariant region-based shape descriptors, the ICA Zernike moment shape descriptor (ICAZMSD) and the whitening Zernike moment shape descriptor (WZMSD). Either independent component analysis (ICA) or whitening, is first used to turn the original shape into a canonical form, in which the effects of scaling and skewing are eliminated. Next, the properties of the Zernike transform are used to further eliminate the effects of any possible rotation and reflection of the canonical shapes, in extracting the Zernike moments as the affine invariant region-based descriptors. Using the proposed ICAZMSD as shape feature, shape-based image retrieval experiments on a 4000 complex shape image database and on a 5600 simple shape image database, show retrieval rates of 99.80% and 92.25%, respectively. Using the proposed WZMSD as shape feature, the corresponding retrieval rates are 99.79% and 92.22%, respectively. The proposed WZMSD has almost equal performance to the proposed ICAZMSD, while having lower computational requirements. IS - 10 JF - IEEE Signal Processing Letters EP - 880 TI - Robust Affine Invariant Region-Based Shape Descriptors: The ICA Zernike Moment Shape Descriptor and the Whitening Zernike Moment Shape Descriptor VL - 16 SP - 877 KW - affine KW - analysis KW - component KW - descriptor KW - ica KW - independent KW - invariant KW - moments KW - shape KW - whitening KW - zernike AU - Mei, Ye AU - Androutsos, Dimitrios PY - 2009/10// UR - http://dx.doi.org/10.1109/LSP.2009.2026119 ER -