FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2023200581> ?p ?o ?g. }

• W2023200581 endingPage "36" @default.
• W2023200581 startingPage "3" @default.
• W2023200581 abstract "The performance of matching and object recognition methods based on interest points depends on both the properties of the underlying interest points and the choice of associated image descriptors. This paper demonstrates advantages of using generalized scale-space interest point detectors in this context for selecting a sparse set of points for computing image descriptors for image-based matching. For detecting interest points at any given scale, we make use of the Laplacian $$nabla ^2_{norm} L$$ , the determinant of the Hessian $$det {mathcal {H}}_{norm} L$$ and four new unsigned or signed Hessian feature strength measures $${mathcal {D}}_{1,norm} L$$ , $$tilde{mathcal {D}}_{1,norm} L$$ , $${mathcal {D}}_{2,norm} L$$ and $$tilde{mathcal {D}}_{2,norm} L$$ , which are defined by generalizing the definitions of the Harris and Shi-and-Tomasi operators from the second moment matrix to the Hessian matrix. Then, feature selection over different scales is performed either by scale selection from local extrema over scale of scale-normalized derivates or by linking features over scale into feature trajectories and computing a significance measure from an integrated measure of normalized feature strength over scale. A theoretical analysis is presented of the robustness of the differential entities underlying these interest points under image deformations, in terms of invariance properties under affine image deformations or approximations thereof. Disregarding the effect of the rotationally symmetric scale-space smoothing operation, the determinant of the Hessian $$det {mathcal {H}}_{norm} L$$ is a truly affine covariant differential entity and the Hessian feature strength measures $${mathcal {D}}_{1,norm} L$$ and $$tilde{mathcal {D}}_{1,norm} L$$ have a major contribution from the affine covariant determinant of the Hessian, implying that local extrema of these differential entities will be more robust under affine image deformations than local extrema of the Laplacian operator or the Hessian feature strength measures $${mathcal {D}}_{2,norm} L$$ , $$tilde{mathcal {D}}_{2,norm} L$$ . It is shown how these generalized scale-space interest points allow for a higher ratio of correct matches and a lower ratio of false matches compared to previously known interest point detectors within the same class. The best results are obtained using interest points computed with scale linking and with the new Hessian feature strength measures $${mathcal {D}}_{1,norm} L$$ , $$tilde{mathcal {D}}_{1,norm} L$$ and the determinant of the Hessian $$det {mathcal {H}}_{norm} L$$ being the differential entities that lead to the best matching performance under perspective image transformations with significant foreshortening, and better than the more commonly used Laplacian operator, its difference-of-Gaussians approximation or the Harris–Laplace operator. We propose that these generalized scale-space interest points, when accompanied by associated local scale-invariant image descriptors, should allow for better performance of interest point based methods for image-based matching, object recognition and related visual tasks." @default.
• W2023200581 created "2016-06-24" @default.
• W2023200581 creator A5054396186 @default.
• W2023200581 date "2014-10-24" @default.
• W2023200581 modified "2023-10-14" @default.
• W2023200581 title "Image Matching Using Generalized Scale-Space Interest Points" @default.
• W2023200581 cites W1495971627 @default.
• W2023200581 cites W1496395994 @default.
• W2023200581 cites W1501344851 @default.
• W2023200581 cites W1508335110 @default.
• W2023200581 cites W1509918867 @default.
• W2023200581 cites W1514759812 @default.
• W2023200581 cites W1526675046 @default.
• W2023200581 cites W1553200558 @default.
• W2023200581 cites W1563743568 @default.
• W2023200581 cites W1564077651 @default.
• W2023200581 cites W1589362500 @default.
• W2023200581 cites W1597084354 @default.
• W2023200581 cites W1598382901 @default.
• W2023200581 cites W1677409904 @default.
• W2023200581 cites W1684301558 @default.
• W2023200581 cites W1699734612 @default.
• W2023200581 cites W1790926505 @default.
• W2023200581 cites W1794288718 @default.
• W2023200581 cites W1887003147 @default.
• W2023200581 cites W1897281438 @default.
• W2023200581 cites W1941828309 @default.
• W2023200581 cites W1964973491 @default.
• W2023200581 cites W1969579560 @default.
• W2023200581 cites W1970269179 @default.
• W2023200581 cites W1970393892 @default.
• W2023200581 cites W1971348167 @default.
• W2023200581 cites W1974954013 @default.
• W2023200581 cites W1980911747 @default.
• W2023200581 cites W1984757472 @default.
• W2023200581 cites W1986327281 @default.
• W2023200581 cites W1986482242 @default.
• W2023200581 cites W1990690613 @default.
• W2023200581 cites W1996769091 @default.
• W2023200581 cites W1997622868 @default.
• W2023200581 cites W2003370853 @default.
• W2023200581 cites W2005476680 @default.
• W2023200581 cites W2006396452 @default.
• W2023200581 cites W2010001203 @default.
• W2023200581 cites W2010548775 @default.
• W2023200581 cites W2014217370 @default.
• W2023200581 cites W2019085623 @default.
• W2023200581 cites W2022735534 @default.
• W2023200581 cites W2027089475 @default.
• W2023200581 cites W2030488300 @default.
• W2023200581 cites W2033379850 @default.
• W2023200581 cites W2033663049 @default.
• W2023200581 cites W2034501924 @default.
• W2023200581 cites W2036242214 @default.
• W2023200581 cites W2042243448 @default.
• W2023200581 cites W2047799558 @default.
• W2023200581 cites W2050139660 @default.
• W2023200581 cites W2052916917 @default.
• W2023200581 cites W2053941121 @default.
• W2023200581 cites W2055339315 @default.
• W2023200581 cites W2059412355 @default.
• W2023200581 cites W2059871232 @default.
• W2023200581 cites W2060919860 @default.
• W2023200581 cites W2066691567 @default.
• W2023200581 cites W2069782179 @default.
• W2023200581 cites W2073351463 @default.
• W2023200581 cites W2075747175 @default.
• W2023200581 cites W2085207288 @default.
• W2023200581 cites W2087309680 @default.
• W2023200581 cites W2088981779 @default.
• W2023200581 cites W2089435138 @default.
• W2023200581 cites W2091715895 @default.
• W2023200581 cites W2096320880 @default.
• W2023200581 cites W2097887900 @default.
• W2023200581 cites W2098083083 @default.
• W2023200581 cites W2098789800 @default.
• W2023200581 cites W2100711184 @default.
• W2023200581 cites W2101632303 @default.
• W2023200581 cites W2103658758 @default.
• W2023200581 cites W2104853049 @default.
• W2023200581 cites W2104872502 @default.
• W2023200581 cites W2108256719 @default.
• W2023200581 cites W2108642789 @default.
• W2023200581 cites W2111308925 @default.
• W2023200581 cites W2112328181 @default.
• W2023200581 cites W2115313253 @default.
• W2023200581 cites W2117497687 @default.
• W2023200581 cites W2119605622 @default.
• W2023200581 cites W2123175387 @default.
• W2023200581 cites W2123211807 @default.
• W2023200581 cites W2124109021 @default.
• W2023200581 cites W2124386111 @default.
• W2023200581 cites W2125500167 @default.
• W2023200581 cites W2126833203 @default.
• W2023200581 cites W2130502925 @default.
• W2023200581 cites W2131356744 @default.
• W2023200581 cites W2135705692 @default.
• W2023200581 cites W2136009313 @default.

• next