Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981731957> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2981731957 abstract "Biometrics authentication has been very useful and necessary nowadays due to the great developments in technology and the transaction of huge amounts of sensitive data on a daily basis. Traditionally, access to some data or service is achieved by means of some documents or a password. However, these methods are not very convenient. Alternatively, typical biometric systems can be employed that use fingerprint, iris, voice, face recognition or a combination of them. This project focuses on the task of face recognition from still images and investigates how different algorithms for face verification perform under various adverse conditions modelled by blur, salt-and-pepper noise and changes in illumination. Conventional pattern recognition algorithms are first presented. Pixel intensities, Gabor features, Local Binary Patterns (LBP) and 2D-DCT coefficients are considered as features while for classification the nearest neighbor (NNC), nearest mean (NMC), SVM classifiers, and Likelihood Ratio Tests (LRT) with Gaussian Mixture Models (GMM) are examined. Out of all these methods, Gabor features combined with the linear SVM classifier are shown to produce best results across all degradations giving an average Equal Error Rate (EER) of 0:97% using the ORL face dataset. Then, emphasis is placed on deep learning and Convolutional Neural Networks (CNN). Specically, VGG-Face with triplet loss training for face verification is suggested. VGG-Face achieves an average EER of 2:63% when both test images of a query image pair are drawn from the same degradation conditions and an average EER of 3:80% when only one image in the given pair is degraded and the other one is derived from the clean ORL dataset. We also experimented with the extracted VGG-Face features and NNC, linear SVM and Gaussian SVM and it is seen that a linear SVM gives an average EER of 1:10% by macro-averaging the Detection Error Tradeoff (DET) curves." @default.
- W2981731957 created "2019-11-01" @default.
- W2981731957 creator A5070875480 @default.
- W2981731957 date "2019-01-01" @default.
- W2981731957 modified "2023-09-27" @default.
- W2981731957 title "Face recognition using traditional machine learning algorithms and deep neural networks with application to face verification" @default.
- W2981731957 hasPublicationYear "2019" @default.
- W2981731957 type Work @default.
- W2981731957 sameAs 2981731957 @default.
- W2981731957 citedByCount "0" @default.
- W2981731957 crossrefType "journal-article" @default.
- W2981731957 hasAuthorship W2981731957A5070875480 @default.
- W2981731957 hasConcept C115961682 @default.
- W2981731957 hasConcept C12267149 @default.
- W2981731957 hasConcept C144024400 @default.
- W2981731957 hasConcept C153180895 @default.
- W2981731957 hasConcept C154945302 @default.
- W2981731957 hasConcept C184297639 @default.
- W2981731957 hasConcept C2221639 @default.
- W2981731957 hasConcept C2779304628 @default.
- W2981731957 hasConcept C31510193 @default.
- W2981731957 hasConcept C36289849 @default.
- W2981731957 hasConcept C40969351 @default.
- W2981731957 hasConcept C41008148 @default.
- W2981731957 hasConcept C50644808 @default.
- W2981731957 hasConcept C81363708 @default.
- W2981731957 hasConceptScore W2981731957C115961682 @default.
- W2981731957 hasConceptScore W2981731957C12267149 @default.
- W2981731957 hasConceptScore W2981731957C144024400 @default.
- W2981731957 hasConceptScore W2981731957C153180895 @default.
- W2981731957 hasConceptScore W2981731957C154945302 @default.
- W2981731957 hasConceptScore W2981731957C184297639 @default.
- W2981731957 hasConceptScore W2981731957C2221639 @default.
- W2981731957 hasConceptScore W2981731957C2779304628 @default.
- W2981731957 hasConceptScore W2981731957C31510193 @default.
- W2981731957 hasConceptScore W2981731957C36289849 @default.
- W2981731957 hasConceptScore W2981731957C40969351 @default.
- W2981731957 hasConceptScore W2981731957C41008148 @default.
- W2981731957 hasConceptScore W2981731957C50644808 @default.
- W2981731957 hasConceptScore W2981731957C81363708 @default.
- W2981731957 hasLocation W29817319571 @default.
- W2981731957 hasOpenAccess W2981731957 @default.
- W2981731957 hasPrimaryLocation W29817319571 @default.
- W2981731957 hasRelatedWork W1036701977 @default.
- W2981731957 hasRelatedWork W2038957684 @default.
- W2981731957 hasRelatedWork W2071654404 @default.
- W2981731957 hasRelatedWork W2182302476 @default.
- W2981731957 hasRelatedWork W2247193073 @default.
- W2981731957 hasRelatedWork W2292946401 @default.
- W2981731957 hasRelatedWork W2385578336 @default.
- W2981731957 hasRelatedWork W2469962374 @default.
- W2981731957 hasRelatedWork W2625252215 @default.
- W2981731957 hasRelatedWork W2733985683 @default.
- W2981731957 hasRelatedWork W2796152502 @default.
- W2981731957 hasRelatedWork W2796827446 @default.
- W2981731957 hasRelatedWork W2902346218 @default.
- W2981731957 hasRelatedWork W2951312798 @default.
- W2981731957 hasRelatedWork W2990067746 @default.
- W2981731957 hasRelatedWork W3003111497 @default.
- W2981731957 hasRelatedWork W3026742379 @default.
- W2981731957 hasRelatedWork W3137168991 @default.
- W2981731957 hasRelatedWork W3183345461 @default.
- W2981731957 hasRelatedWork W82976258 @default.
- W2981731957 isParatext "false" @default.
- W2981731957 isRetracted "false" @default.
- W2981731957 magId "2981731957" @default.
- W2981731957 workType "article" @default.