Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804051023> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2804051023 abstract "The face recognition method is proposed for cases of an insufficient training set, when the input data consists only of two facial images (full face and profile). The 3D model of a face is created semi-automatically using the input data (two images), which is then used for the recognition process. The training set for the recognition process consists of these created 3D models of faces. The basic problem of face recognition is the insufficient information about the proportions of the unidentified person's face, images can also contain some artefacts, for example eyeglasses, beard, moustache that can decrease the precision of the recognition process and make the image analysis more difficult. Another important aspect is illumination, which can practically change the results of the classification. The proposed recognition method consists of several steps: unknown image face alignment, facial reference points estimation using gradient maps using dlib (http://dlib.net/) and OpenCV (https://opencv.org/) open source computer vision libraries. After features extraction it is necessary to perform thresholding on some facial reference points, which is most important for recognition process. For this purpose, several important features are selected and distances between them are calculated. The training set consists of early created 3D models of faces that could be used to get the missing information about the proportions of the person's face. The proposed algorithm is used for classification. Using this method classification results are approximately 90% positive compared to when using only the insufficient training set that contains only two images." @default.
- W2804051023 created "2018-06-01" @default.
- W2804051023 creator A5027331609 @default.
- W2804051023 creator A5056990182 @default.
- W2804051023 date "2018-05-24" @default.
- W2804051023 modified "2023-09-30" @default.
- W2804051023 title "Face recognition method for cases of an insufficient training set, using 3D models of face that were created using two facial images" @default.
- W2804051023 cites W2006902452 @default.
- W2804051023 cites W2040937469 @default.
- W2804051023 cites W2121647436 @default.
- W2804051023 cites W2163999590 @default.
- W2804051023 cites W2284800790 @default.
- W2804051023 cites W2498256984 @default.
- W2804051023 doi "https://doi.org/10.1117/12.2306637" @default.
- W2804051023 hasPublicationYear "2018" @default.
- W2804051023 type Work @default.
- W2804051023 sameAs 2804051023 @default.
- W2804051023 citedByCount "0" @default.
- W2804051023 crossrefType "proceedings-article" @default.
- W2804051023 hasAuthorship W2804051023A5027331609 @default.
- W2804051023 hasAuthorship W2804051023A5056990182 @default.
- W2804051023 hasConcept C111919701 @default.
- W2804051023 hasConcept C115961682 @default.
- W2804051023 hasConcept C144024400 @default.
- W2804051023 hasConcept C153180895 @default.
- W2804051023 hasConcept C154945302 @default.
- W2804051023 hasConcept C177264268 @default.
- W2804051023 hasConcept C191178318 @default.
- W2804051023 hasConcept C199360897 @default.
- W2804051023 hasConcept C2779304628 @default.
- W2804051023 hasConcept C31510193 @default.
- W2804051023 hasConcept C31972630 @default.
- W2804051023 hasConcept C36289849 @default.
- W2804051023 hasConcept C41008148 @default.
- W2804051023 hasConcept C4641261 @default.
- W2804051023 hasConcept C54654163 @default.
- W2804051023 hasConcept C88799230 @default.
- W2804051023 hasConcept C98045186 @default.
- W2804051023 hasConceptScore W2804051023C111919701 @default.
- W2804051023 hasConceptScore W2804051023C115961682 @default.
- W2804051023 hasConceptScore W2804051023C144024400 @default.
- W2804051023 hasConceptScore W2804051023C153180895 @default.
- W2804051023 hasConceptScore W2804051023C154945302 @default.
- W2804051023 hasConceptScore W2804051023C177264268 @default.
- W2804051023 hasConceptScore W2804051023C191178318 @default.
- W2804051023 hasConceptScore W2804051023C199360897 @default.
- W2804051023 hasConceptScore W2804051023C2779304628 @default.
- W2804051023 hasConceptScore W2804051023C31510193 @default.
- W2804051023 hasConceptScore W2804051023C31972630 @default.
- W2804051023 hasConceptScore W2804051023C36289849 @default.
- W2804051023 hasConceptScore W2804051023C41008148 @default.
- W2804051023 hasConceptScore W2804051023C4641261 @default.
- W2804051023 hasConceptScore W2804051023C54654163 @default.
- W2804051023 hasConceptScore W2804051023C88799230 @default.
- W2804051023 hasConceptScore W2804051023C98045186 @default.
- W2804051023 hasLocation W28040510231 @default.
- W2804051023 hasOpenAccess W2804051023 @default.
- W2804051023 hasPrimaryLocation W28040510231 @default.
- W2804051023 hasRelatedWork W1586081892 @default.
- W2804051023 hasRelatedWork W2043649191 @default.
- W2804051023 hasRelatedWork W2189561366 @default.
- W2804051023 hasRelatedWork W2282077488 @default.
- W2804051023 hasRelatedWork W2327681752 @default.
- W2804051023 hasRelatedWork W2341576090 @default.
- W2804051023 hasRelatedWork W2402106151 @default.
- W2804051023 hasRelatedWork W2554450537 @default.
- W2804051023 hasRelatedWork W2787092242 @default.
- W2804051023 hasRelatedWork W2892944782 @default.
- W2804051023 hasRelatedWork W2967424080 @default.
- W2804051023 hasRelatedWork W2969268800 @default.
- W2804051023 hasRelatedWork W2982315592 @default.
- W2804051023 hasRelatedWork W3202997712 @default.
- W2804051023 hasRelatedWork W1484010418 @default.
- W2804051023 hasRelatedWork W2225020969 @default.
- W2804051023 hasRelatedWork W2268664172 @default.
- W2804051023 hasRelatedWork W2470527482 @default.
- W2804051023 hasRelatedWork W2497517914 @default.
- W2804051023 hasRelatedWork W2502570084 @default.
- W2804051023 isParatext "false" @default.
- W2804051023 isRetracted "false" @default.
- W2804051023 magId "2804051023" @default.
- W2804051023 workType "article" @default.