Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896770027> ?p ?o ?g. }
- W2896770027 abstract "There are several biometric-based systems which rely on a single biometric modality, most of them focus on face, iris or fingerprint. Despite the good accuracies obtained with single modalities, these systems are more susceptible to attacks, i.e, spoofing attacks, and noises of all kinds, especially in non-cooperative (in-the-wild) environments. Since non-cooperative environments are becoming more and more common, new approaches involving multi-modal biometrics have received more attention. One challenge in multimodal biometric systems is how to integrate the data from different modalities. Initially, we propose a deep transfer learning optimized from a model trained for face recognition achieving outstanding representation for only iris modality. Our feature level fusion by means of features selection targets the use of the Particle Swarm Optimization (PSO) for such aims. In our pool, we have the proposed iris fine-tuned representation and a periocular one from previous work of us. We compare this approach for fusion in feature level against three basic function rules for matching at score level: sum, multi, and min. Results are reported for iris and periocular region (NICE.II competition database) and also in an open-world scenario. The experiments in the NICE.II competition databases showed that our transfer learning representation for iris modality achieved a new state-of-the-art, i.e., decidability of 2.22 and 14.56% of EER. We also yielded a new state-of-the-art result when the fusion at feature level by PSO is done on periocular and iris modalities, i.e., decidability of 3.45 and 5.55% of EER." @default.
- W2896770027 created "2018-10-26" @default.
- W2896770027 creator A5015111666 @default.
- W2896770027 creator A5015475283 @default.
- W2896770027 creator A5026966525 @default.
- W2896770027 creator A5033489756 @default.
- W2896770027 creator A5088231372 @default.
- W2896770027 date "2018-07-01" @default.
- W2896770027 modified "2023-09-27" @default.
- W2896770027 title "Multimodal Feature Level Fusion based on Particle Swarm Optimization with Deep Transfer Learning" @default.
- W2896770027 cites W1963882359 @default.
- W2896770027 cites W1998529975 @default.
- W2896770027 cites W2019464758 @default.
- W2896770027 cites W2024808535 @default.
- W2896770027 cites W2025546194 @default.
- W2896770027 cites W2055579676 @default.
- W2896770027 cites W2058991683 @default.
- W2896770027 cites W2061090695 @default.
- W2896770027 cites W2092545044 @default.
- W2896770027 cites W2102796633 @default.
- W2896770027 cites W2117690924 @default.
- W2896770027 cites W2117721235 @default.
- W2896770027 cites W2125213524 @default.
- W2896770027 cites W2134794961 @default.
- W2896770027 cites W2144148034 @default.
- W2896770027 cites W2145113795 @default.
- W2896770027 cites W2152413067 @default.
- W2896770027 cites W2161381512 @default.
- W2896770027 cites W2167075312 @default.
- W2896770027 cites W2169096120 @default.
- W2896770027 cites W2294763754 @default.
- W2896770027 cites W2767420072 @default.
- W2896770027 cites W3099206234 @default.
- W2896770027 doi "https://doi.org/10.1109/cec.2018.8477817" @default.
- W2896770027 hasPublicationYear "2018" @default.
- W2896770027 type Work @default.
- W2896770027 sameAs 2896770027 @default.
- W2896770027 citedByCount "22" @default.
- W2896770027 countsByYear W28967700272019 @default.
- W2896770027 countsByYear W28967700272020 @default.
- W2896770027 countsByYear W28967700272021 @default.
- W2896770027 countsByYear W28967700272022 @default.
- W2896770027 countsByYear W28967700272023 @default.
- W2896770027 crossrefType "proceedings-article" @default.
- W2896770027 hasAuthorship W2896770027A5015111666 @default.
- W2896770027 hasAuthorship W2896770027A5015475283 @default.
- W2896770027 hasAuthorship W2896770027A5026966525 @default.
- W2896770027 hasAuthorship W2896770027A5033489756 @default.
- W2896770027 hasAuthorship W2896770027A5088231372 @default.
- W2896770027 hasConcept C105795698 @default.
- W2896770027 hasConcept C108583219 @default.
- W2896770027 hasConcept C112356035 @default.
- W2896770027 hasConcept C119857082 @default.
- W2896770027 hasConcept C120665830 @default.
- W2896770027 hasConcept C121332964 @default.
- W2896770027 hasConcept C138885662 @default.
- W2896770027 hasConcept C144024400 @default.
- W2896770027 hasConcept C153180895 @default.
- W2896770027 hasConcept C154945302 @default.
- W2896770027 hasConcept C165064840 @default.
- W2896770027 hasConcept C184297639 @default.
- W2896770027 hasConcept C192209626 @default.
- W2896770027 hasConcept C2776401178 @default.
- W2896770027 hasConcept C2779304628 @default.
- W2896770027 hasConcept C2779503344 @default.
- W2896770027 hasConcept C2779903281 @default.
- W2896770027 hasConcept C2780226545 @default.
- W2896770027 hasConcept C33923547 @default.
- W2896770027 hasConcept C36289849 @default.
- W2896770027 hasConcept C41008148 @default.
- W2896770027 hasConcept C41895202 @default.
- W2896770027 hasConcept C59404180 @default.
- W2896770027 hasConcept C83665646 @default.
- W2896770027 hasConcept C85617194 @default.
- W2896770027 hasConceptScore W2896770027C105795698 @default.
- W2896770027 hasConceptScore W2896770027C108583219 @default.
- W2896770027 hasConceptScore W2896770027C112356035 @default.
- W2896770027 hasConceptScore W2896770027C119857082 @default.
- W2896770027 hasConceptScore W2896770027C120665830 @default.
- W2896770027 hasConceptScore W2896770027C121332964 @default.
- W2896770027 hasConceptScore W2896770027C138885662 @default.
- W2896770027 hasConceptScore W2896770027C144024400 @default.
- W2896770027 hasConceptScore W2896770027C153180895 @default.
- W2896770027 hasConceptScore W2896770027C154945302 @default.
- W2896770027 hasConceptScore W2896770027C165064840 @default.
- W2896770027 hasConceptScore W2896770027C184297639 @default.
- W2896770027 hasConceptScore W2896770027C192209626 @default.
- W2896770027 hasConceptScore W2896770027C2776401178 @default.
- W2896770027 hasConceptScore W2896770027C2779304628 @default.
- W2896770027 hasConceptScore W2896770027C2779503344 @default.
- W2896770027 hasConceptScore W2896770027C2779903281 @default.
- W2896770027 hasConceptScore W2896770027C2780226545 @default.
- W2896770027 hasConceptScore W2896770027C33923547 @default.
- W2896770027 hasConceptScore W2896770027C36289849 @default.
- W2896770027 hasConceptScore W2896770027C41008148 @default.
- W2896770027 hasConceptScore W2896770027C41895202 @default.
- W2896770027 hasConceptScore W2896770027C59404180 @default.
- W2896770027 hasConceptScore W2896770027C83665646 @default.
- W2896770027 hasConceptScore W2896770027C85617194 @default.
- W2896770027 hasLocation W28967700271 @default.