FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200690557> ?p ?o ?g. }

• W3200690557 abstract "Image representation is a challenging task. In particular, in order to obtain better performances in different image processing applications such as video surveillance, autonomous driving, crime scene detection and automatic inspection, effective and efficient image representation is a fundamental need. The performance of these applications usually depends on how accurately images are classified into their corresponding groups or how precisely relevant images are retrieved from a database based on a query. Accuracy in image classification and precision in image retrieval depend on the effectiveness of image representation. Existing image representation methods have some limitations. For example, spatial pyramid matching, which is a popular method incorporating spatial information in image-level representation, has not been fully studied to date. In addition, the strengths of pyramid match kernel and spatial pyramid matching are not combined for better image matching. Kernel descriptors based on gradient, colour and shape overcome the limitations of histogram-based descriptors, but suffer from information loss, noise effects and high computational complexity. Furthermore, the combined performance of kernel descriptors has limitations related to computational complexity, higher dimensionality and lower effectiveness. Moreover, the potential of a global texture descriptor which is based on human visual perception has not been fully explored to date. Therefore, in this research project, kernel-based effective and efficient image representation methods are proposed to address the above limitations. An enhancement is made to spatial pyramid matching in terms of improved rotation invariance. This is done by investigating different partitioning schemes suitable to achieve rotation-invariant image representation and the proposal of a weight function for appropriate level contribution in image matching. In addition, the strengths of pyramid match kernel and spatial pyramid are combined to enhance matching accuracy between images. The existing kernel descriptors are modified and improved to achieve greater effectiveness, minimum noise effects, less dimensionality and lower computational complexity. A novel fusion approach is also proposed to combine the information related to all pixel attributes, before the descriptor extraction stage. Existing kernel descriptors are based only on gradient, colour and shape information. In this research project, a texture-based kernel descriptor is proposed by modifying an existing popular global texture descriptor. Finally, all the contributions are evaluated in an integrated system. The performances of the proposed methods are qualitatively and quantitatively evaluated on two to four different publicly available image databases. The experimental results show that the proposed methods are more effective and efficient in image representation than existing benchmark methods.%%%%Doctor of Philosophy" @default.
• W3200690557 created "2021-09-27" @default.
• W3200690557 creator A5022170556 @default.
• W3200690557 date "2018-01-01" @default.
• W3200690557 modified "2023-09-26" @default.
• W3200690557 title "Effective and efficient kernel-based image representations for classification and retrieval" @default.
• W3200690557 cites W11273282 @default.
• W3200690557 cites W1481738430 @default.
• W3200690557 cites W1485800236 @default.
• W3200690557 cites W1504116408 @default.
• W3200690557 cites W1529297639 @default.
• W3200690557 cites W1530699444 @default.
• W3200690557 cites W1532325895 @default.
• W3200690557 cites W1566135517 @default.
• W3200690557 cites W163323618 @default.
• W3200690557 cites W1677409904 @default.
• W3200690557 cites W1917380066 @default.
• W3200690557 cites W1964491636 @default.
• W3200690557 cites W1972715665 @default.
• W3200690557 cites W1973264045 @default.
• W3200690557 cites W1980038761 @default.
• W3200690557 cites W1981398227 @default.
• W3200690557 cites W1988355023 @default.
• W3200690557 cites W1988445395 @default.
• W3200690557 cites W1989085630 @default.
• W3200690557 cites W2007972795 @default.
• W3200690557 cites W2011342293 @default.
• W3200690557 cites W2011430131 @default.
• W3200690557 cites W2012982311 @default.
• W3200690557 cites W2019531340 @default.
• W3200690557 cites W2020681746 @default.
• W3200690557 cites W2022987770 @default.
• W3200690557 cites W2028735463 @default.
• W3200690557 cites W2031476339 @default.
• W3200690557 cites W2044465660 @default.
• W3200690557 cites W2052094314 @default.
• W3200690557 cites W2054103873 @default.
• W3200690557 cites W2058942669 @default.
• W3200690557 cites W2066813062 @default.
• W3200690557 cites W2073459066 @default.
• W3200690557 cites W2074142320 @default.
• W3200690557 cites W2075019799 @default.
• W3200690557 cites W2081952833 @default.
• W3200690557 cites W2084351932 @default.
• W3200690557 cites W2085536788 @default.
• W3200690557 cites W2089903940 @default.
• W3200690557 cites W2091825929 @default.
• W3200690557 cites W2097018403 @default.
• W3200690557 cites W2101234009 @default.
• W3200690557 cites W2103399972 @default.
• W3200690557 cites W2103444992 @default.
• W3200690557 cites W2103723258 @default.
• W3200690557 cites W2103851872 @default.
• W3200690557 cites W2104978738 @default.
• W3200690557 cites W2106097867 @default.
• W3200690557 cites W2106126793 @default.
• W3200690557 cites W2107034620 @default.
• W3200690557 cites W2107925163 @default.
• W3200690557 cites W2108556791 @default.
• W3200690557 cites W2114661696 @default.
• W3200690557 cites W2118153703 @default.
• W3200690557 cites W2118384078 @default.
• W3200690557 cites W2119046205 @default.
• W3200690557 cites W2119821739 @default.
• W3200690557 cites W2124861766 @default.
• W3200690557 cites W2125148312 @default.
• W3200690557 cites W2131213661 @default.
• W3200690557 cites W2134089414 @default.
• W3200690557 cites W2138570191 @default.
• W3200690557 cites W2138692949 @default.
• W3200690557 cites W2140582552 @default.
• W3200690557 cites W2142422094 @default.
• W3200690557 cites W2144093206 @default.
• W3200690557 cites W2145072179 @default.
• W3200690557 cites W2146880335 @default.
• W3200690557 cites W2147141800 @default.
• W3200690557 cites W2147238549 @default.
• W3200690557 cites W2147555557 @default.
• W3200690557 cites W2147603200 @default.
• W3200690557 cites W2150593711 @default.
• W3200690557 cites W2151103935 @default.
• W3200690557 cites W2151768982 @default.
• W3200690557 cites W2153635508 @default.
• W3200690557 cites W2155867588 @default.
• W3200690557 cites W2155904486 @default.
• W3200690557 cites W2159727956 @default.
• W3200690557 cites W2161969291 @default.
• W3200690557 cites W2162457093 @default.
• W3200690557 cites W2162915993 @default.
• W3200690557 cites W2163352848 @default.
• W3200690557 cites W2169003124 @default.
• W3200690557 cites W2172196609 @default.
• W3200690557 cites W2172231696 @default.
• W3200690557 cites W2235526797 @default.
• W3200690557 cites W2341944174 @default.
• W3200690557 cites W2345559288 @default.
• W3200690557 cites W2405680777 @default.
• W3200690557 cites W2405807953 @default.
• W3200690557 cites W2474211219 @default.
• W3200690557 cites W2492134165 @default.

• next