Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149802657> ?p ?o ?g. }
- W3149802657 endingPage "5618" @default.
- W3149802657 startingPage "5607" @default.
- W3149802657 abstract "This work investigates the problem of undersampled face recognition (i.e., insufficient training data) encountered in practical Internet-of-Things (IoT) applications. Insufficient and uncertain samples captured by IoT devices may include background and facial disguise that makes face recognition more challenging than that with sufficient and reliable images. Many models work well in face recognition on a big data set, but when training data are insufficient, they achieve unsatisfactory performance. This work proposes a novel method named sparse common feature-based representation (SCFR) that provides a unique and stable result and completely avoids very time-consuming training required by a deep learning model. Specially, it constructs a common feature dictionary using both training and test images. Thereinto, a common feature is based on a discriminative common vector and learned by a Gaussian mixture model for both training and test images in a semisupervised learninig manner, which would reduce the difference among samples in each class. In the optimization, the latent indicator of test data is initialized by the estimated label. This can avoid learning invalid information and lead to good prototype images. A new variation dictionary characterizes variables that can be shared by different classes. Finally, this work adopts minimum reconstruction residuals to recognize test images, thus bringing about a substantial improvement in SCFR's performance. Extensive results on benchmark face databases demonstrate that the proposed method is better than the state-of-the-art methods handling undersampled face recognition." @default.
- W3149802657 created "2021-04-13" @default.
- W3149802657 creator A5023734401 @default.
- W3149802657 creator A5036563779 @default.
- W3149802657 creator A5081318069 @default.
- W3149802657 creator A5091130234 @default.
- W3149802657 date "2021-04-01" @default.
- W3149802657 modified "2023-10-15" @default.
- W3149802657 title "Sparse Common Feature Representation for Undersampled Face Recognition" @default.
- W3149802657 cites W1834627138 @default.
- W3149802657 cites W1963932623 @default.
- W3149802657 cites W1967180011 @default.
- W3149802657 cites W1970038279 @default.
- W3149802657 cites W1975815261 @default.
- W3149802657 cites W2038165640 @default.
- W3149802657 cites W2050551672 @default.
- W3149802657 cites W2069959554 @default.
- W3149802657 cites W2084716923 @default.
- W3149802657 cites W2085400714 @default.
- W3149802657 cites W2090504921 @default.
- W3149802657 cites W2093922090 @default.
- W3149802657 cites W2095189186 @default.
- W3149802657 cites W2100240926 @default.
- W3149802657 cites W2108598243 @default.
- W3149802657 cites W2108767394 @default.
- W3149802657 cites W2108840547 @default.
- W3149802657 cites W2116551122 @default.
- W3149802657 cites W2120100419 @default.
- W3149802657 cites W2125874614 @default.
- W3149802657 cites W2129812935 @default.
- W3149802657 cites W2137823674 @default.
- W3149802657 cites W2142470670 @default.
- W3149802657 cites W2144583419 @default.
- W3149802657 cites W2155759509 @default.
- W3149802657 cites W2157785665 @default.
- W3149802657 cites W2183341477 @default.
- W3149802657 cites W2194775991 @default.
- W3149802657 cites W2295151578 @default.
- W3149802657 cites W2324450140 @default.
- W3149802657 cites W2361128240 @default.
- W3149802657 cites W2520742745 @default.
- W3149802657 cites W2561743383 @default.
- W3149802657 cites W2581688519 @default.
- W3149802657 cites W2604462068 @default.
- W3149802657 cites W2609211153 @default.
- W3149802657 cites W2747472841 @default.
- W3149802657 cites W2807005919 @default.
- W3149802657 cites W2809242293 @default.
- W3149802657 cites W2922482186 @default.
- W3149802657 cites W2941914178 @default.
- W3149802657 cites W2947587845 @default.
- W3149802657 cites W2954875347 @default.
- W3149802657 cites W2994621558 @default.
- W3149802657 cites W3085615344 @default.
- W3149802657 cites W3099206234 @default.
- W3149802657 cites W3100830527 @default.
- W3149802657 cites W3106375245 @default.
- W3149802657 cites W4210997624 @default.
- W3149802657 doi "https://doi.org/10.1109/jiot.2020.3031390" @default.
- W3149802657 hasPublicationYear "2021" @default.
- W3149802657 type Work @default.
- W3149802657 sameAs 3149802657 @default.
- W3149802657 citedByCount "15" @default.
- W3149802657 countsByYear W31498026572021 @default.
- W3149802657 countsByYear W31498026572022 @default.
- W3149802657 countsByYear W31498026572023 @default.
- W3149802657 crossrefType "journal-article" @default.
- W3149802657 hasAuthorship W3149802657A5023734401 @default.
- W3149802657 hasAuthorship W3149802657A5036563779 @default.
- W3149802657 hasAuthorship W3149802657A5081318069 @default.
- W3149802657 hasAuthorship W3149802657A5091130234 @default.
- W3149802657 hasConcept C115961682 @default.
- W3149802657 hasConcept C119857082 @default.
- W3149802657 hasConcept C124066611 @default.
- W3149802657 hasConcept C13280743 @default.
- W3149802657 hasConcept C138885662 @default.
- W3149802657 hasConcept C144024400 @default.
- W3149802657 hasConcept C153180895 @default.
- W3149802657 hasConcept C154945302 @default.
- W3149802657 hasConcept C16910744 @default.
- W3149802657 hasConcept C180462255 @default.
- W3149802657 hasConcept C185798385 @default.
- W3149802657 hasConcept C199360897 @default.
- W3149802657 hasConcept C205649164 @default.
- W3149802657 hasConcept C2776401178 @default.
- W3149802657 hasConcept C2779304628 @default.
- W3149802657 hasConcept C31510193 @default.
- W3149802657 hasConcept C36289849 @default.
- W3149802657 hasConcept C41008148 @default.
- W3149802657 hasConcept C41895202 @default.
- W3149802657 hasConcept C52622490 @default.
- W3149802657 hasConcept C83665646 @default.
- W3149802657 hasConcept C9417928 @default.
- W3149802657 hasConcept C97931131 @default.
- W3149802657 hasConceptScore W3149802657C115961682 @default.
- W3149802657 hasConceptScore W3149802657C119857082 @default.
- W3149802657 hasConceptScore W3149802657C124066611 @default.
- W3149802657 hasConceptScore W3149802657C13280743 @default.