Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969398210> ?p ?o ?g. }
- W2969398210 abstract "Facial image retrieval is a challenging task since faces have many similar features (areas), which makes it difficult for the retrieval systems to distinguish faces of different people. With the advent of deep learning, deep networks are often applied to extract powerful features that are used in many areas of computer vision. This paper investigates the application of different deep learning models' (layers) for face image retrieval, namely, Alexlayer6, Alexlayer7, VGG16layer6, VGG16layer7, VGG19layer6 and VGG19layer7, with two types of dictionary learning techniques, namely K-means and K-SVD. We also investigate some coefficient learning techniques such as the Homotopy, Lasso, Elastic Net and SSF and their effect on the face retrieval system. The comparative results of the experiments conducted on three standard face image datasets show that the best performers for face image retrieval are Alexlayer7 with K-means and SSF, Alexlayer6 with K-SVD and SSF and Alexlayer6 with K-means and SSF. The APR and ARR of these methods were further compared to some of the state-of-the-art methods based on local descriptors. The experimental results show that deep learning outperforms most of those methods and therefore can be recommended for use in practice of face image retrieval." @default.
- W2969398210 created "2019-08-29" @default.
- W2969398210 creator A5013654326 @default.
- W2969398210 creator A5032563975 @default.
- W2969398210 creator A5036867425 @default.
- W2969398210 creator A5053581579 @default.
- W2969398210 creator A5059612866 @default.
- W2969398210 creator A5089788790 @default.
- W2969398210 date "2019-06-01" @default.
- W2969398210 modified "2023-10-11" @default.
- W2969398210 title "Deep Face Image Retrieval: a Comparative Study with Dictionary Learning" @default.
- W2969398210 cites W1546200464 @default.
- W2969398210 cites W1885185971 @default.
- W2969398210 cites W1927170233 @default.
- W2969398210 cites W2005539193 @default.
- W2969398210 cites W2016278923 @default.
- W2969398210 cites W2059652177 @default.
- W2969398210 cites W2063756240 @default.
- W2969398210 cites W2097777575 @default.
- W2969398210 cites W2108598243 @default.
- W2969398210 cites W2123921160 @default.
- W2969398210 cites W2125874614 @default.
- W2969398210 cites W2129812935 @default.
- W2969398210 cites W2132201434 @default.
- W2969398210 cites W2145947562 @default.
- W2969398210 cites W2151517435 @default.
- W2969398210 cites W2156001867 @default.
- W2969398210 cites W2160547390 @default.
- W2969398210 cites W2163398148 @default.
- W2969398210 cites W2297240532 @default.
- W2969398210 cites W2320725294 @default.
- W2969398210 cites W2345557152 @default.
- W2969398210 cites W2507989420 @default.
- W2969398210 cites W2511925907 @default.
- W2969398210 cites W2512351403 @default.
- W2969398210 cites W2536626143 @default.
- W2969398210 cites W2594439983 @default.
- W2969398210 cites W2613173840 @default.
- W2969398210 cites W2769908547 @default.
- W2969398210 cites W2790858115 @default.
- W2969398210 cites W2793699148 @default.
- W2969398210 cites W2801096891 @default.
- W2969398210 cites W2803396742 @default.
- W2969398210 cites W2890011953 @default.
- W2969398210 cites W2896791469 @default.
- W2969398210 cites W2898051438 @default.
- W2969398210 cites W2901922404 @default.
- W2969398210 cites W4205213118 @default.
- W2969398210 cites W4242648443 @default.
- W2969398210 doi "https://doi.org/10.1109/iacs.2019.8809127" @default.
- W2969398210 hasPublicationYear "2019" @default.
- W2969398210 type Work @default.
- W2969398210 sameAs 2969398210 @default.
- W2969398210 citedByCount "16" @default.
- W2969398210 countsByYear W29693982102020 @default.
- W2969398210 countsByYear W29693982102021 @default.
- W2969398210 countsByYear W29693982102022 @default.
- W2969398210 countsByYear W29693982102023 @default.
- W2969398210 crossrefType "proceedings-article" @default.
- W2969398210 hasAuthorship W2969398210A5013654326 @default.
- W2969398210 hasAuthorship W2969398210A5032563975 @default.
- W2969398210 hasAuthorship W2969398210A5036867425 @default.
- W2969398210 hasAuthorship W2969398210A5053581579 @default.
- W2969398210 hasAuthorship W2969398210A5059612866 @default.
- W2969398210 hasAuthorship W2969398210A5089788790 @default.
- W2969398210 hasBestOaLocation W29693982102 @default.
- W2969398210 hasConcept C108583219 @default.
- W2969398210 hasConcept C115961682 @default.
- W2969398210 hasConcept C144024400 @default.
- W2969398210 hasConcept C153180895 @default.
- W2969398210 hasConcept C154945302 @default.
- W2969398210 hasConcept C1667742 @default.
- W2969398210 hasConcept C2779304628 @default.
- W2969398210 hasConcept C31510193 @default.
- W2969398210 hasConcept C31972630 @default.
- W2969398210 hasConcept C36289849 @default.
- W2969398210 hasConcept C41008148 @default.
- W2969398210 hasConcept C81363708 @default.
- W2969398210 hasConceptScore W2969398210C108583219 @default.
- W2969398210 hasConceptScore W2969398210C115961682 @default.
- W2969398210 hasConceptScore W2969398210C144024400 @default.
- W2969398210 hasConceptScore W2969398210C153180895 @default.
- W2969398210 hasConceptScore W2969398210C154945302 @default.
- W2969398210 hasConceptScore W2969398210C1667742 @default.
- W2969398210 hasConceptScore W2969398210C2779304628 @default.
- W2969398210 hasConceptScore W2969398210C31510193 @default.
- W2969398210 hasConceptScore W2969398210C31972630 @default.
- W2969398210 hasConceptScore W2969398210C36289849 @default.
- W2969398210 hasConceptScore W2969398210C41008148 @default.
- W2969398210 hasConceptScore W2969398210C81363708 @default.
- W2969398210 hasLocation W29693982101 @default.
- W2969398210 hasLocation W29693982102 @default.
- W2969398210 hasOpenAccess W2969398210 @default.
- W2969398210 hasPrimaryLocation W29693982101 @default.
- W2969398210 hasRelatedWork W2098693229 @default.
- W2969398210 hasRelatedWork W2384651879 @default.
- W2969398210 hasRelatedWork W3029198973 @default.
- W2969398210 hasRelatedWork W3133861977 @default.
- W2969398210 hasRelatedWork W3167935049 @default.
- W2969398210 hasRelatedWork W3193565141 @default.