Matches in SemOpenAlex for { <https://semopenalex.org/work/W612784517> ?p ?o ?g. }
- W612784517 abstract "We are concerned in this thesis by the problem of automated 2D image classification and general object detection. Advances in this field of research contribute to the elaboration of intelligent systems such as, but not limited to, autonomous robots and the semantic web. In this context, designing adequate image representations and classifiers for these representations constitute challenging issues. Our work provides innovative solutions to both these problems: image representation and classification. In order to generate our image representation, we extract visual features from the image and build a graphical structure based on properties of spatial proximity between the feature points. We show that certain spectral properties of this graph constitute good invariants to rigid geometric transforms. Our representation is based on these invariant properties. Experiments show that this representation constitutes an improvement over other similar representations that do not integrate the spatial layout of visual features. However, a drawback of this method is that it requires a lossy quantisation of the visual feature space in order to be combined with a state-of-the-art support vector machine (SVM) classifier. We address this issue by designing a new classifier. This generic classifier relies on a nearest-neighbour distance to classify objects that can be assimilated to feature sets, i.e: point clouds. The linearity of this classifier allows us to perform object detection, in addition to image classification. Another interesting property is its ability to combine different types of visual features in an optimal manner. We take advantage of this property to produce a new formulation for the classification of visual feature graphs. Experiments are conducted on a wide variety of publicly available datasets to justify the benefits of our approach." @default.
- W612784517 created "2016-06-24" @default.
- W612784517 creator A5012235449 @default.
- W612784517 date "2010-09-15" @default.
- W612784517 modified "2023-09-27" @default.
- W612784517 title "Visual feature graphs and image recognition" @default.
- W612784517 cites W1514107797 @default.
- W612784517 cites W1532257412 @default.
- W612784517 cites W1566135517 @default.
- W612784517 cites W1576767704 @default.
- W612784517 cites W1578099820 @default.
- W612784517 cites W1625255723 @default.
- W612784517 cites W1639227073 @default.
- W612784517 cites W1640070940 @default.
- W612784517 cites W1677409904 @default.
- W612784517 cites W1917380066 @default.
- W612784517 cites W1977866540 @default.
- W612784517 cites W1991605728 @default.
- W612784517 cites W1993713305 @default.
- W612784517 cites W2001141328 @default.
- W612784517 cites W2004586880 @default.
- W612784517 cites W2010541316 @default.
- W612784517 cites W2019599312 @default.
- W612784517 cites W2022735534 @default.
- W612784517 cites W2023308661 @default.
- W612784517 cites W2045798786 @default.
- W612784517 cites W2050147204 @default.
- W612784517 cites W2055839530 @default.
- W612784517 cites W2057175746 @default.
- W612784517 cites W2062692054 @default.
- W612784517 cites W2072692661 @default.
- W612784517 cites W2087347434 @default.
- W612784517 cites W2099930951 @default.
- W612784517 cites W2103038452 @default.
- W612784517 cites W2103658758 @default.
- W612784517 cites W2104170135 @default.
- W612784517 cites W2104978738 @default.
- W612784517 cites W2107034620 @default.
- W612784517 cites W2109200236 @default.
- W612784517 cites W2109294083 @default.
- W612784517 cites W2109863423 @default.
- W612784517 cites W2111308925 @default.
- W612784517 cites W2112020727 @default.
- W612784517 cites W2113201641 @default.
- W612784517 cites W2115313253 @default.
- W612784517 cites W2115733720 @default.
- W612784517 cites W2117138270 @default.
- W612784517 cites W2118544710 @default.
- W612784517 cites W2120419212 @default.
- W612784517 cites W2130470622 @default.
- W612784517 cites W2132054709 @default.
- W612784517 cites W2132914434 @default.
- W612784517 cites W2136120429 @default.
- W612784517 cites W2138100172 @default.
- W612784517 cites W2140169211 @default.
- W612784517 cites W2143668817 @default.
- W612784517 cites W2148116692 @default.
- W612784517 cites W2148141929 @default.
- W612784517 cites W2149684865 @default.
- W612784517 cites W2149954907 @default.
- W612784517 cites W2151768982 @default.
- W612784517 cites W2152132697 @default.
- W612784517 cites W2152942156 @default.
- W612784517 cites W2156145178 @default.
- W612784517 cites W2156406284 @default.
- W612784517 cites W2156718197 @default.
- W612784517 cites W2157041524 @default.
- W612784517 cites W2159727956 @default.
- W612784517 cites W2161597143 @default.
- W612784517 cites W2161969291 @default.
- W612784517 cites W2164877691 @default.
- W612784517 cites W2165181841 @default.
- W612784517 cites W2165315123 @default.
- W612784517 cites W2165874743 @default.
- W612784517 cites W2166118928 @default.
- W612784517 cites W2173213060 @default.
- W612784517 cites W2177274842 @default.
- W612784517 cites W2186094539 @default.
- W612784517 cites W2911678770 @default.
- W612784517 cites W2913233705 @default.
- W612784517 hasPublicationYear "2010" @default.
- W612784517 type Work @default.
- W612784517 sameAs 612784517 @default.
- W612784517 citedByCount "0" @default.
- W612784517 crossrefType "dissertation" @default.
- W612784517 hasAuthorship W612784517A5012235449 @default.
- W612784517 hasConcept C115961682 @default.
- W612784517 hasConcept C12267149 @default.
- W612784517 hasConcept C153180895 @default.
- W612784517 hasConcept C154945302 @default.
- W612784517 hasConcept C1667742 @default.
- W612784517 hasConcept C167611913 @default.
- W612784517 hasConcept C189391414 @default.
- W612784517 hasConcept C31972630 @default.
- W612784517 hasConcept C41008148 @default.
- W612784517 hasConcept C52622490 @default.
- W612784517 hasConcept C64876066 @default.
- W612784517 hasConcept C75294576 @default.
- W612784517 hasConcept C83665646 @default.
- W612784517 hasConcept C95623464 @default.