Affine invariant contour descriptors using independent component analysis and dyadic wavelet transform

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 nois...

Full description

Permalink: http://skupnikatalog.nsk.hr/Record/nsk.NSK01000709883/Details
Matična publikacija: CIT. Journal of computing and information technology
16 (2008), 3 ; str. 169-181
Glavni autor: Ali, Asad (-)
Ostali autori: Gilani, Syed Asif Mahmood (-), Memon, Nisar Ahmed
Vrsta građe: Članak
Jezik: eng
Predmet:
Online pristup: eCIT - Home page
LEADER 01917caa a2200301 ir4500
001 NSK01000709883
003 HR-ZaNSK
005 20110120115217.0
007 ta
008 090818s2008 ci ||| ||eng
035 |9 (HR-ZaNSK)712431 
035 |a (HR-ZaNSK)000709883 
040 |a HR-ZaNSK  |b hrv  |c HR-ZaNSK  |e ppiak 
042 |a croatica 
080 |a 004  |2 MRF 1998. 
080 |a 51  |2 MRF 1998. 
100 1 |a Ali, Asad 
245 1 0 |a Affine invariant contour descriptors using independent component analysis and dyadic wavelet transform /  |c Asad Ali, Syed Asif Mahmood Gilani and Nisar Ahmed Memon. 
300 |b Ilustr. 
504 |a Bibliografija: 21 jed 
520 |a 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 
653 |a Prepoznavanje oblika  |a Matematičke metode 
700 1 |a Gilani, Syed Asif Mahmood 
700 1 |a Memon, Nisar Ahmed 
773 0 |t CIT. Journal of computing and information technology  |x 1330-1136  |g 16 (2008), 3 ; str. 169-181  |w nsk.(HR-ZaNSK)000018028 
981 |b B02/08 
998 |a luko090818  |c rpeo110120 
856 4 2 |u http://cit.zesoi.fer.hr/home.php  |y eCIT - Home page