Matches in SemOpenAlex for { <https://semopenalex.org/work/W2247447165> ?p ?o ?g. }
- W2247447165 abstract "In this paper we introduce a new dataset and pose invariant sampling method and describe the ensemble methods used for recognizing faces in 3D scenes, captured using commodity depth sensors. We use the 3D SIFT key point detector to take advantage of the similarities between faces, which leads to a set of points of interest based on the curvature of the face. For all key points, features are extracted using a 3D feature descriptor. Then, a variable-sized amount of features are generated per each 3D face image. The first ensemble method we constructed uses a K-nearest neighbors classifier to classify each key point-sampled feature vector as belonging to one of the subjects recorded in our dataset. All votes over all key points are combined. In the second ensemble technique, the key points are clustered with K-means, using the feature vectors and approximated sampling positions relative to the face. This leads to a set of experts that specialize for a specific region. Then a K-nearest neighbors classifier is trained on the examples falling in each expert's specialized region. Finally, for a new 3D face image, votes from all experts are combined in a sum ensemble technique to categorize the 3D face. We also introduce 6 new real world datasets with different variances: 3 types of 3D rotations, distance to sensor, expressions, and an all-in-one dataset. The results show very high cross validation accuracies for the same type of variance. In addition, 36 variance specific pair-tests in which the system is trained on one dataset and tested on a completely different dataset also show encouraging results." @default.
- W2247447165 created "2016-06-24" @default.
- W2247447165 creator A5028858025 @default.
- W2247447165 creator A5054885916 @default.
- W2247447165 creator A5060596453 @default.
- W2247447165 date "2015-12-01" @default.
- W2247447165 modified "2023-10-18" @default.
- W2247447165 title "Ensemble Methods for Robust 3D Face Recognition Using Commodity Depth Sensors" @default.
- W2247447165 cites W1643185111 @default.
- W2247447165 cites W194047500 @default.
- W2247447165 cites W1989702938 @default.
- W2247447165 cites W1995884877 @default.
- W2247447165 cites W2008073424 @default.
- W2247447165 cites W2049981393 @default.
- W2247447165 cites W2065054546 @default.
- W2247447165 cites W2079844951 @default.
- W2247447165 cites W2082498363 @default.
- W2247447165 cites W2083624955 @default.
- W2247447165 cites W2093717447 @default.
- W2247447165 cites W2098693229 @default.
- W2247447165 cites W2098951409 @default.
- W2247447165 cites W2101231430 @default.
- W2247447165 cites W2106309519 @default.
- W2247447165 cites W2109002458 @default.
- W2247447165 cites W2114388147 @default.
- W2247447165 cites W2117715370 @default.
- W2247447165 cites W2120538588 @default.
- W2247447165 cites W2121601095 @default.
- W2247447165 cites W2121647436 @default.
- W2247447165 cites W2122111042 @default.
- W2247447165 cites W2126355928 @default.
- W2247447165 cites W2130972944 @default.
- W2247447165 cites W2131846894 @default.
- W2247447165 cites W2134849720 @default.
- W2247447165 cites W2137659841 @default.
- W2247447165 cites W2151103935 @default.
- W2247447165 cites W2152864241 @default.
- W2247447165 cites W2154716422 @default.
- W2247447165 cites W2160126058 @default.
- W2247447165 cites W2160643963 @default.
- W2247447165 cites W2162915993 @default.
- W2247447165 cites W2166164984 @default.
- W2247447165 cites W2166335841 @default.
- W2247447165 cites W2166743687 @default.
- W2247447165 cites W2171896402 @default.
- W2247447165 cites W2229412420 @default.
- W2247447165 cites W2912934387 @default.
- W2247447165 doi "https://doi.org/10.1109/ssci.2015.36" @default.
- W2247447165 hasPublicationYear "2015" @default.
- W2247447165 type Work @default.
- W2247447165 sameAs 2247447165 @default.
- W2247447165 citedByCount "3" @default.
- W2247447165 countsByYear W22474471652016 @default.
- W2247447165 countsByYear W22474471652018 @default.
- W2247447165 crossrefType "proceedings-article" @default.
- W2247447165 hasAuthorship W2247447165A5028858025 @default.
- W2247447165 hasAuthorship W2247447165A5054885916 @default.
- W2247447165 hasAuthorship W2247447165A5060596453 @default.
- W2247447165 hasBestOaLocation W22474471652 @default.
- W2247447165 hasConcept C138885662 @default.
- W2247447165 hasConcept C144024400 @default.
- W2247447165 hasConcept C153180895 @default.
- W2247447165 hasConcept C154945302 @default.
- W2247447165 hasConcept C2776401178 @default.
- W2247447165 hasConcept C2779304628 @default.
- W2247447165 hasConcept C31510193 @default.
- W2247447165 hasConcept C31972630 @default.
- W2247447165 hasConcept C36289849 @default.
- W2247447165 hasConcept C41008148 @default.
- W2247447165 hasConcept C41895202 @default.
- W2247447165 hasConcept C45942800 @default.
- W2247447165 hasConcept C52622490 @default.
- W2247447165 hasConcept C61265191 @default.
- W2247447165 hasConcept C95623464 @default.
- W2247447165 hasConceptScore W2247447165C138885662 @default.
- W2247447165 hasConceptScore W2247447165C144024400 @default.
- W2247447165 hasConceptScore W2247447165C153180895 @default.
- W2247447165 hasConceptScore W2247447165C154945302 @default.
- W2247447165 hasConceptScore W2247447165C2776401178 @default.
- W2247447165 hasConceptScore W2247447165C2779304628 @default.
- W2247447165 hasConceptScore W2247447165C31510193 @default.
- W2247447165 hasConceptScore W2247447165C31972630 @default.
- W2247447165 hasConceptScore W2247447165C36289849 @default.
- W2247447165 hasConceptScore W2247447165C41008148 @default.
- W2247447165 hasConceptScore W2247447165C41895202 @default.
- W2247447165 hasConceptScore W2247447165C45942800 @default.
- W2247447165 hasConceptScore W2247447165C52622490 @default.
- W2247447165 hasConceptScore W2247447165C61265191 @default.
- W2247447165 hasConceptScore W2247447165C95623464 @default.
- W2247447165 hasLocation W22474471651 @default.
- W2247447165 hasLocation W22474471652 @default.
- W2247447165 hasOpenAccess W2247447165 @default.
- W2247447165 hasPrimaryLocation W22474471651 @default.
- W2247447165 hasRelatedWork W1775397219 @default.
- W2247447165 hasRelatedWork W2017517155 @default.
- W2247447165 hasRelatedWork W2022942246 @default.
- W2247447165 hasRelatedWork W2042348617 @default.
- W2247447165 hasRelatedWork W2060029454 @default.
- W2247447165 hasRelatedWork W2147083459 @default.
- W2247447165 hasRelatedWork W2216174977 @default.