Matches in SemOpenAlex for { <https://semopenalex.org/work/W2102852560> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2102852560 abstract "Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult. We present a hybrid neural network solution which compares favorably with other methods. The system combines local image sampling, a self-organizing map neural network, and a convolutional neural network. The self-organizing map provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for partial invariance to translation, rotation, scale, and deformation. The method is capable of rapid classification, requires only fast, approximate normalization and preprocessing, and consistently exhibits better classification performance than the eigenfaces approach on the database considered as the number of images per person in the training database is varied from 1 to 5. With 5 images per person the proposed method and eigenfaces result in 3.8% and 10.5% error respectively. The recognizer provides a measure of confidence in its output and classification error approaches zero when rejecting as few as 10% of the examples. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details." @default.
- W2102852560 created "2016-06-24" @default.
- W2102852560 creator A5001294898 @default.
- W2102852560 creator A5043733219 @default.
- W2102852560 creator A5077581403 @default.
- W2102852560 date "1996-01-01" @default.
- W2102852560 modified "2023-09-25" @default.
- W2102852560 title "Convolutional neural networks for face recognition" @default.
- W2102852560 cites W1480865305 @default.
- W2102852560 cites W1508371546 @default.
- W2102852560 cites W1538131130 @default.
- W2102852560 cites W1973436000 @default.
- W2102852560 cites W2103560185 @default.
- W2102852560 cites W2111123712 @default.
- W2102852560 cites W2113341759 @default.
- W2102852560 cites W2115689562 @default.
- W2102852560 cites W2116360511 @default.
- W2102852560 cites W2127770870 @default.
- W2102852560 cites W2137983211 @default.
- W2102852560 cites W2138451337 @default.
- W2102852560 cites W2139314678 @default.
- W2102852560 doi "https://doi.org/10.1109/cvpr.1996.517077" @default.
- W2102852560 hasPublicationYear "1996" @default.
- W2102852560 type Work @default.
- W2102852560 sameAs 2102852560 @default.
- W2102852560 citedByCount "23" @default.
- W2102852560 countsByYear W21028525602014 @default.
- W2102852560 countsByYear W21028525602015 @default.
- W2102852560 countsByYear W21028525602018 @default.
- W2102852560 countsByYear W21028525602019 @default.
- W2102852560 countsByYear W21028525602020 @default.
- W2102852560 countsByYear W21028525602021 @default.
- W2102852560 crossrefType "proceedings-article" @default.
- W2102852560 hasAuthorship W2102852560A5001294898 @default.
- W2102852560 hasAuthorship W2102852560A5043733219 @default.
- W2102852560 hasAuthorship W2102852560A5077581403 @default.
- W2102852560 hasConcept C104906051 @default.
- W2102852560 hasConcept C115961682 @default.
- W2102852560 hasConcept C136886441 @default.
- W2102852560 hasConcept C144024400 @default.
- W2102852560 hasConcept C153180895 @default.
- W2102852560 hasConcept C154945302 @default.
- W2102852560 hasConcept C19165224 @default.
- W2102852560 hasConcept C28855332 @default.
- W2102852560 hasConcept C31510193 @default.
- W2102852560 hasConcept C31972630 @default.
- W2102852560 hasConcept C34736171 @default.
- W2102852560 hasConcept C41008148 @default.
- W2102852560 hasConcept C50644808 @default.
- W2102852560 hasConcept C70518039 @default.
- W2102852560 hasConcept C75294576 @default.
- W2102852560 hasConcept C81363708 @default.
- W2102852560 hasConceptScore W2102852560C104906051 @default.
- W2102852560 hasConceptScore W2102852560C115961682 @default.
- W2102852560 hasConceptScore W2102852560C136886441 @default.
- W2102852560 hasConceptScore W2102852560C144024400 @default.
- W2102852560 hasConceptScore W2102852560C153180895 @default.
- W2102852560 hasConceptScore W2102852560C154945302 @default.
- W2102852560 hasConceptScore W2102852560C19165224 @default.
- W2102852560 hasConceptScore W2102852560C28855332 @default.
- W2102852560 hasConceptScore W2102852560C31510193 @default.
- W2102852560 hasConceptScore W2102852560C31972630 @default.
- W2102852560 hasConceptScore W2102852560C34736171 @default.
- W2102852560 hasConceptScore W2102852560C41008148 @default.
- W2102852560 hasConceptScore W2102852560C50644808 @default.
- W2102852560 hasConceptScore W2102852560C70518039 @default.
- W2102852560 hasConceptScore W2102852560C75294576 @default.
- W2102852560 hasConceptScore W2102852560C81363708 @default.
- W2102852560 hasLocation W21028525601 @default.
- W2102852560 hasOpenAccess W2102852560 @default.
- W2102852560 hasPrimaryLocation W21028525601 @default.
- W2102852560 hasRelatedWork W1501769554 @default.
- W2102852560 hasRelatedWork W1591965711 @default.
- W2102852560 hasRelatedWork W1991269640 @default.
- W2102852560 hasRelatedWork W2066259560 @default.
- W2102852560 hasRelatedWork W2071846378 @default.
- W2102852560 hasRelatedWork W2483947148 @default.
- W2102852560 hasRelatedWork W2562832125 @default.
- W2102852560 hasRelatedWork W2576960802 @default.
- W2102852560 hasRelatedWork W2977314777 @default.
- W2102852560 hasRelatedWork W2983491485 @default.
- W2102852560 isParatext "false" @default.
- W2102852560 isRetracted "false" @default.
- W2102852560 magId "2102852560" @default.
- W2102852560 workType "article" @default.