Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896620413> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2896620413 abstract "This paper proposes a novel approach for content based graphical object retrieval in document images. The chal- lenge is to search for occurrences of a queried graphical objects in document images that can vary in terms of color, shape, texture and quality, increasing considerably the level of difficulty of the retrieval process. To that end, the manual feature engineering is avoided by learning the image representation for the retrieval task using a Convolutional Neural Network (CNN). However, such a representation should be as compact as possible to allow a fast document image retrieval and storage. Thus, a pretrained CNN model is used to cope with the lack of training data, which is fine tuned to achieve a compact yet discriminant representation of the graphical objects. From experiments conducted on the public Tobacco800 document image collection, we show that the proposed method compares favorably against state-of-the- art document image retrieval methods, reaching 0.72 of average precision $(mathrm {m}mathrm {A}mathrm {P})$. In addition, an increase of 4 percentage points in the average precision is observed using a compact deep representation in which the number of features is reduced by 16 times, thus allowing a reduction of 47% in terms of computation time by the image retrieval task." @default.
- W2896620413 created "2018-10-26" @default.
- W2896620413 creator A5007251630 @default.
- W2896620413 creator A5021057873 @default.
- W2896620413 creator A5038884704 @default.
- W2896620413 creator A5064965581 @default.
- W2896620413 creator A5074262951 @default.
- W2896620413 date "2018-07-08" @default.
- W2896620413 modified "2023-10-16" @default.
- W2896620413 title "Document Image Retrieval Using Deep Features" @default.
- W2896620413 cites W1508960934 @default.
- W2896620413 cites W1606495911 @default.
- W2896620413 cites W1849277567 @default.
- W2896620413 cites W1913628733 @default.
- W2896620413 cites W1922773808 @default.
- W2896620413 cites W1984034752 @default.
- W2896620413 cites W2010181071 @default.
- W2896620413 cites W2015268479 @default.
- W2896620413 cites W2015861736 @default.
- W2896620413 cites W2062389676 @default.
- W2896620413 cites W2080850829 @default.
- W2896620413 cites W2088049833 @default.
- W2896620413 cites W2111993661 @default.
- W2896620413 cites W2112796928 @default.
- W2896620413 cites W2114360444 @default.
- W2896620413 cites W2117942284 @default.
- W2896620413 cites W2123229215 @default.
- W2896620413 cites W2128119911 @default.
- W2896620413 cites W2132064754 @default.
- W2896620413 cites W2141152990 @default.
- W2896620413 cites W2161381512 @default.
- W2896620413 cites W2163605009 @default.
- W2896620413 cites W2210803143 @default.
- W2896620413 cites W2255846051 @default.
- W2896620413 cites W2261310161 @default.
- W2896620413 cites W2295537791 @default.
- W2896620413 cites W2340690086 @default.
- W2896620413 cites W2552666852 @default.
- W2896620413 cites W2556472504 @default.
- W2896620413 cites W2560583282 @default.
- W2896620413 cites W2587313095 @default.
- W2896620413 cites W2962835968 @default.
- W2896620413 cites W7746136 @default.
- W2896620413 hasPublicationYear "2018" @default.
- W2896620413 type Work @default.
- W2896620413 sameAs 2896620413 @default.
- W2896620413 citedByCount "2" @default.
- W2896620413 countsByYear W28966204132019 @default.
- W2896620413 crossrefType "proceedings-article" @default.
- W2896620413 hasAuthorship W2896620413A5007251630 @default.
- W2896620413 hasAuthorship W2896620413A5021057873 @default.
- W2896620413 hasAuthorship W2896620413A5038884704 @default.
- W2896620413 hasAuthorship W2896620413A5064965581 @default.
- W2896620413 hasAuthorship W2896620413A5074262951 @default.
- W2896620413 hasConcept C115961682 @default.
- W2896620413 hasConcept C154945302 @default.
- W2896620413 hasConcept C1667742 @default.
- W2896620413 hasConcept C23123220 @default.
- W2896620413 hasConcept C31972630 @default.
- W2896620413 hasConcept C41008148 @default.
- W2896620413 hasConceptScore W2896620413C115961682 @default.
- W2896620413 hasConceptScore W2896620413C154945302 @default.
- W2896620413 hasConceptScore W2896620413C1667742 @default.
- W2896620413 hasConceptScore W2896620413C23123220 @default.
- W2896620413 hasConceptScore W2896620413C31972630 @default.
- W2896620413 hasConceptScore W2896620413C41008148 @default.
- W2896620413 hasLocation W28966204131 @default.
- W2896620413 hasOpenAccess W2896620413 @default.
- W2896620413 hasPrimaryLocation W28966204131 @default.
- W2896620413 hasRelatedWork W1926504679 @default.
- W2896620413 hasRelatedWork W2088097596 @default.
- W2896620413 hasRelatedWork W2130228941 @default.
- W2896620413 hasRelatedWork W2161229648 @default.
- W2896620413 hasRelatedWork W2353314619 @default.
- W2896620413 hasRelatedWork W2519881370 @default.
- W2896620413 hasRelatedWork W2993674027 @default.
- W2896620413 hasRelatedWork W3097853387 @default.
- W2896620413 hasRelatedWork W3150772620 @default.
- W2896620413 hasRelatedWork W4287330208 @default.
- W2896620413 isParatext "false" @default.
- W2896620413 isRetracted "false" @default.
- W2896620413 magId "2896620413" @default.
- W2896620413 workType "article" @default.