hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1001009

Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform

Nisar Ahmed Memon
Syed Asif Mahmood Gilani
Asad Ali

Puni tekst: engleski, pdf (852 KB) str. 169-181 preuzimanja: 779* citiraj
APA 6th Edition
Ahmed Memon, N., Mahmood Gilani, S.A. i Ali, A. (2008). Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform. Journal of computing and information technology, 16 (3), 169-181. https://doi.org/10.2498/cit.1001009
MLA 8th Edition
Ahmed Memon, Nisar, et al. "Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform." Journal of computing and information technology, vol. 16, br. 3, 2008, str. 169-181. https://doi.org/10.2498/cit.1001009. Citirano 28.10.2020.
Chicago 17th Edition
Ahmed Memon, Nisar, Syed Asif Mahmood Gilani i Asad Ali. "Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform." Journal of computing and information technology 16, br. 3 (2008): 169-181. https://doi.org/10.2498/cit.1001009
Harvard
Ahmed Memon, N., Mahmood Gilani, S.A., i Ali, A. (2008). 'Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform', Journal of computing and information technology, 16(3), str. 169-181. https://doi.org/10.2498/cit.1001009
Vancouver
Ahmed Memon N, Mahmood Gilani SA, Ali A. Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform. Journal of computing and information technology [Internet]. 2008 [pristupljeno 28.10.2020.];16(3):169-181. https://doi.org/10.2498/cit.1001009
IEEE
N. Ahmed Memon, S.A. Mahmood Gilani i A. Ali, "Affine Invariant Contour Descriptors Using Independent Component Analysis and Dyadic Wavelet Transform", Journal of computing and information technology, vol.16, br. 3, str. 169-181, 2008. [Online]. https://doi.org/10.2498/cit.1001009

Sažetak
The paper presents a novel technique for affine invariant feature extraction with the view of object recognition based on parameterized contour. The proposed technique first normalizes an input image by removing the affine deformations using independent component analysis which also reduces the noise introduced during contour parameterization. Then four invariant functionals are constructed using the restored object contour, dyadic wavelet transform and conics in the context of wavelets. Experimental results are conducted using three different standard datasets to confirm the validity of the proposed technique. Beside this the error rates obtained in terms of invariant stability are significantly lower when compared to other wavelet based invariants. Also the proposed invariants exhibit higher feature disparity than the method of Fourier descriptors.

Hrčak ID: 44591

URI
https://hrcak.srce.hr/44591

Posjeta: 972 *