Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313648144> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4313648144 abstract "Abstract Biometric systems have been used extensively in the identification and verification of persons. Fingerprint biometrics stands out as the most effective due to their characteristics of Permanence, uniqueness, ergonomics, throughput, low cost, and lifelong usability. By reducing the number of comparisons, biometric recognition systems can effectively deal with large‐scale databases. Fingerprint classification is an important task used to reduce the number of comparisons by dividing fingerprints into classes. Deep learning models have demonstrated impressive classification performance in fingerprint classification tasks. The high‐level features of deep learning models can affect the transfer learning in deep learning models. Furthermore, the high‐level features involve high computational costs that can render difficulty in the deployment of the applications. This work proposes an improved system for fingerprint classification through the truncation of layers and transfer learning. Our approach modifies the ResNet50 model to improve its network inference speed and performance in fingerprint classification by removing some deep convolutional layers. We then finetune the modified model and train it using a fingerprint dataset. The results show that the finetuned modified model improves classification accuracy at a reduced computational cost. At only 5.1M parameters, our model obtained a classification accuracy of 93.3% and precision of 93.4% performing better than previous studies based on its size‐performance ratio." @default.
- W4313648144 created "2023-01-07" @default.
- W4313648144 creator A5018693051 @default.
- W4313648144 creator A5022240412 @default.
- W4313648144 creator A5038171683 @default.
- W4313648144 creator A5051388166 @default.
- W4313648144 creator A5071357744 @default.
- W4313648144 date "2023-01-05" @default.
- W4313648144 modified "2023-09-26" @default.
- W4313648144 title "Accelerating deep learning inference via layer truncation and transfer learning for fingerprint classification" @default.
- W4313648144 cites W1984020445 @default.
- W4313648144 cites W2019761615 @default.
- W4313648144 cites W2097117768 @default.
- W4313648144 cites W2128603616 @default.
- W4313648144 cites W2142692934 @default.
- W4313648144 cites W2149407554 @default.
- W4313648144 cites W2194775991 @default.
- W4313648144 cites W2330219538 @default.
- W4313648144 cites W2584050167 @default.
- W4313648144 cites W2625817666 @default.
- W4313648144 cites W2730497260 @default.
- W4313648144 cites W2735377425 @default.
- W4313648144 cites W2752782242 @default.
- W4313648144 cites W2898529688 @default.
- W4313648144 cites W2910505567 @default.
- W4313648144 cites W2912819642 @default.
- W4313648144 cites W2963446712 @default.
- W4313648144 cites W2977945624 @default.
- W4313648144 cites W2986379325 @default.
- W4313648144 cites W3000592047 @default.
- W4313648144 cites W3010909809 @default.
- W4313648144 cites W3014714734 @default.
- W4313648144 cites W3015083589 @default.
- W4313648144 cites W3037662149 @default.
- W4313648144 cites W3043256287 @default.
- W4313648144 cites W3092360750 @default.
- W4313648144 cites W3094477106 @default.
- W4313648144 cites W3108357504 @default.
- W4313648144 cites W3115642521 @default.
- W4313648144 cites W3159611211 @default.
- W4313648144 cites W3169822846 @default.
- W4313648144 cites W3189237734 @default.
- W4313648144 cites W3196289623 @default.
- W4313648144 cites W3197217317 @default.
- W4313648144 cites W3203640873 @default.
- W4313648144 cites W4211116959 @default.
- W4313648144 cites W4242121546 @default.
- W4313648144 doi "https://doi.org/10.1002/cpe.7619" @default.
- W4313648144 hasPublicationYear "2023" @default.
- W4313648144 type Work @default.
- W4313648144 citedByCount "0" @default.
- W4313648144 crossrefType "journal-article" @default.
- W4313648144 hasAuthorship W4313648144A5018693051 @default.
- W4313648144 hasAuthorship W4313648144A5022240412 @default.
- W4313648144 hasAuthorship W4313648144A5038171683 @default.
- W4313648144 hasAuthorship W4313648144A5051388166 @default.
- W4313648144 hasAuthorship W4313648144A5071357744 @default.
- W4313648144 hasConcept C107457646 @default.
- W4313648144 hasConcept C108583219 @default.
- W4313648144 hasConcept C119857082 @default.
- W4313648144 hasConcept C150899416 @default.
- W4313648144 hasConcept C153180895 @default.
- W4313648144 hasConcept C154945302 @default.
- W4313648144 hasConcept C170130773 @default.
- W4313648144 hasConcept C184297639 @default.
- W4313648144 hasConcept C2776214188 @default.
- W4313648144 hasConcept C2777826928 @default.
- W4313648144 hasConcept C41008148 @default.
- W4313648144 hasConceptScore W4313648144C107457646 @default.
- W4313648144 hasConceptScore W4313648144C108583219 @default.
- W4313648144 hasConceptScore W4313648144C119857082 @default.
- W4313648144 hasConceptScore W4313648144C150899416 @default.
- W4313648144 hasConceptScore W4313648144C153180895 @default.
- W4313648144 hasConceptScore W4313648144C154945302 @default.
- W4313648144 hasConceptScore W4313648144C170130773 @default.
- W4313648144 hasConceptScore W4313648144C184297639 @default.
- W4313648144 hasConceptScore W4313648144C2776214188 @default.
- W4313648144 hasConceptScore W4313648144C2777826928 @default.
- W4313648144 hasConceptScore W4313648144C41008148 @default.
- W4313648144 hasIssue "8" @default.
- W4313648144 hasLocation W43136481441 @default.
- W4313648144 hasOpenAccess W4313648144 @default.
- W4313648144 hasPrimaryLocation W43136481441 @default.
- W4313648144 hasRelatedWork W2017324411 @default.
- W4313648144 hasRelatedWork W2889705046 @default.
- W4313648144 hasRelatedWork W2960456850 @default.
- W4313648144 hasRelatedWork W3192840557 @default.
- W4313648144 hasRelatedWork W4223943233 @default.
- W4313648144 hasRelatedWork W4312200629 @default.
- W4313648144 hasRelatedWork W4317565044 @default.
- W4313648144 hasRelatedWork W4380075502 @default.
- W4313648144 hasRelatedWork W4382286161 @default.
- W4313648144 hasRelatedWork W4386213806 @default.
- W4313648144 hasVolume "35" @default.
- W4313648144 isParatext "false" @default.
- W4313648144 isRetracted "false" @default.
- W4313648144 workType "article" @default.