Matches in SemOpenAlex for { <https://semopenalex.org/work/W2739038498> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2739038498 endingPage "619" @default.
- W2739038498 startingPage "613" @default.
- W2739038498 abstract "The authors propose TripNet as method for calculating similarities between striated toolmark images. The objective for this system is detecting and comparing characteristics of the tools while being invariant to varying parameters like angle of attack, substrate material, and lighting conditions. Instead of designing a handcrafted feature extractor customised for this task, the authors propose the use of a convolutional neural network. With the proposed system, one‐dimensional profiles extracted from images of striated toolmarks are mapped into an embedding. The system is trained by minimising a triplet loss function, so that a similarity measure is defined by the distance in this embedding. The performance is evaluated on the NFI Toolmark database containing 300 striated toolmarks of screwdrivers published by the Netherlands Forensic Institute. The system proposed is able to adapt to a large range of angles of attack, achieving a mean average precision of 0.95 for toolmark comparisons with differences in angle of attack of – . Furthermore, four different triplet selection approaches are proposed and their effect on the retrieval of toolmarks from a database of unseen tools is evaluated in detail." @default.
- W2739038498 created "2017-07-31" @default.
- W2739038498 creator A5019162549 @default.
- W2739038498 creator A5054354886 @default.
- W2739038498 date "2017-08-22" @default.
- W2739038498 modified "2023-09-26" @default.
- W2739038498 title "Retrieval of striated toolmarks using convolutional neural networks" @default.
- W2739038498 cites W1650090063 @default.
- W2739038498 cites W1955055330 @default.
- W2739038498 cites W1983947329 @default.
- W2739038498 cites W2008347226 @default.
- W2739038498 cites W2057441605 @default.
- W2739038498 cites W2104646003 @default.
- W2739038498 cites W2112796928 @default.
- W2739038498 cites W2127194650 @default.
- W2739038498 cites W2165168736 @default.
- W2739038498 cites W2169457609 @default.
- W2739038498 cites W2214041299 @default.
- W2739038498 cites W2269595609 @default.
- W2739038498 cites W2325939864 @default.
- W2739038498 cites W2963775347 @default.
- W2739038498 cites W3099206234 @default.
- W2739038498 cites W4213009331 @default.
- W2739038498 doi "https://doi.org/10.1049/iet-cvi.2017.0161" @default.
- W2739038498 hasPublicationYear "2017" @default.
- W2739038498 type Work @default.
- W2739038498 sameAs 2739038498 @default.
- W2739038498 citedByCount "2" @default.
- W2739038498 countsByYear W27390384982019 @default.
- W2739038498 countsByYear W27390384982020 @default.
- W2739038498 crossrefType "journal-article" @default.
- W2739038498 hasAuthorship W2739038498A5019162549 @default.
- W2739038498 hasAuthorship W2739038498A5054354886 @default.
- W2739038498 hasConcept C103278499 @default.
- W2739038498 hasConcept C115961682 @default.
- W2739038498 hasConcept C117978034 @default.
- W2739038498 hasConcept C127413603 @default.
- W2739038498 hasConcept C138885662 @default.
- W2739038498 hasConcept C153180895 @default.
- W2739038498 hasConcept C154945302 @default.
- W2739038498 hasConcept C1667742 @default.
- W2739038498 hasConcept C190470478 @default.
- W2739038498 hasConcept C21880701 @default.
- W2739038498 hasConcept C2776401178 @default.
- W2739038498 hasConcept C31972630 @default.
- W2739038498 hasConcept C33923547 @default.
- W2739038498 hasConcept C37914503 @default.
- W2739038498 hasConcept C41008148 @default.
- W2739038498 hasConcept C41608201 @default.
- W2739038498 hasConcept C41895202 @default.
- W2739038498 hasConcept C50644808 @default.
- W2739038498 hasConcept C81363708 @default.
- W2739038498 hasConceptScore W2739038498C103278499 @default.
- W2739038498 hasConceptScore W2739038498C115961682 @default.
- W2739038498 hasConceptScore W2739038498C117978034 @default.
- W2739038498 hasConceptScore W2739038498C127413603 @default.
- W2739038498 hasConceptScore W2739038498C138885662 @default.
- W2739038498 hasConceptScore W2739038498C153180895 @default.
- W2739038498 hasConceptScore W2739038498C154945302 @default.
- W2739038498 hasConceptScore W2739038498C1667742 @default.
- W2739038498 hasConceptScore W2739038498C190470478 @default.
- W2739038498 hasConceptScore W2739038498C21880701 @default.
- W2739038498 hasConceptScore W2739038498C2776401178 @default.
- W2739038498 hasConceptScore W2739038498C31972630 @default.
- W2739038498 hasConceptScore W2739038498C33923547 @default.
- W2739038498 hasConceptScore W2739038498C37914503 @default.
- W2739038498 hasConceptScore W2739038498C41008148 @default.
- W2739038498 hasConceptScore W2739038498C41608201 @default.
- W2739038498 hasConceptScore W2739038498C41895202 @default.
- W2739038498 hasConceptScore W2739038498C50644808 @default.
- W2739038498 hasConceptScore W2739038498C81363708 @default.
- W2739038498 hasIssue "7" @default.
- W2739038498 hasLocation W27390384981 @default.
- W2739038498 hasOpenAccess W2739038498 @default.
- W2739038498 hasPrimaryLocation W27390384981 @default.
- W2739038498 hasRelatedWork W1504288058 @default.
- W2739038498 hasRelatedWork W2017205855 @default.
- W2739038498 hasRelatedWork W2048505601 @default.
- W2739038498 hasRelatedWork W2167293474 @default.
- W2739038498 hasRelatedWork W2331674254 @default.
- W2739038498 hasRelatedWork W2358403311 @default.
- W2739038498 hasRelatedWork W2767651786 @default.
- W2739038498 hasRelatedWork W2912288872 @default.
- W2739038498 hasRelatedWork W2979079341 @default.
- W2739038498 hasRelatedWork W3042897387 @default.
- W2739038498 hasVolume "11" @default.
- W2739038498 isParatext "false" @default.
- W2739038498 isRetracted "false" @default.
- W2739038498 magId "2739038498" @default.
- W2739038498 workType "article" @default.