FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804967795> ?p ?o ?g. }

• W2804967795 endingPage "2348" @default.
• W2804967795 startingPage "2336" @default.
• W2804967795 abstract "In this paper, we present a novel approach for 3D dental model segmentation via deep Convolutional Neural Networks (CNNs). Traditional geometry-based methods tend to receive undesirable results due to the complex appearance of human teeth (e.g., missing/rotten teeth, feature-less regions, crowding teeth, extra medical attachments, etc.). Furthermore, labeling of individual tooth is hardly enabled in traditional tooth segmentation methods. To address these issues, we propose to learn a generic and robust segmentation model by exploiting deep Neural Networks, namely NNs. The segmentation task is achieved by labeling each mesh face. We extract a set of geometry features as face feature representations. In the training step, the network is fed with those features, and produces a probability vector, of which each element indicates the probability a face belonging to the corresponding model part. To this end, we extensively experiment with various network structures, and eventually arrive at a 2-level hierarchical CNNs structure for tooth segmentation: one for teeth-gingiva labeling and the other for inter-teeth labeling. Further, we propose a novel boundary-aware tooth simplification method to significantly improve efficiency in the stage of feature extraction. After CNNs prediction, we do graph-based label optimization and further refine the boundary with an improved version of fuzzy clustering. The accuracy of our mesh labeling method exceeds that of the state-of-art geometry-based methods, reaching 99.06 percent measured by area which is directly applicable in orthodontic CAD systems. It is also robust to any possible foreign matters on model surface, e.g., air bubbles, dental accessories, and many more." @default.
• W2804967795 created "2018-06-01" @default.
• W2804967795 creator A5008766810 @default.
• W2804967795 creator A5014874717 @default.
• W2804967795 creator A5016956683 @default.
• W2804967795 date "2019-07-01" @default.
• W2804967795 modified "2023-10-17" @default.
• W2804967795 title "3D Tooth Segmentation and Labeling Using Deep Convolutional Neural Networks" @default.
• W2804967795 cites W1542610831 @default.
• W2804967795 cites W1593557558 @default.
• W2804967795 cites W1972891214 @default.
• W2804967795 cites W1973414297 @default.
• W2804967795 cites W1973947322 @default.
• W2804967795 cites W1974782679 @default.
• W2804967795 cites W1976638067 @default.
• W2804967795 cites W1989540182 @default.
• W2804967795 cites W1991337803 @default.
• W2804967795 cites W1995748618 @default.
• W2804967795 cites W1996576430 @default.
• W2804967795 cites W2001565680 @default.
• W2804967795 cites W2003940193 @default.
• W2804967795 cites W2010209818 @default.
• W2804967795 cites W2022508996 @default.
• W2804967795 cites W2022922662 @default.
• W2804967795 cites W2023056405 @default.
• W2804967795 cites W2023808821 @default.
• W2804967795 cites W2027069615 @default.
• W2804967795 cites W2031209446 @default.
• W2804967795 cites W2031449486 @default.
• W2804967795 cites W2031760064 @default.
• W2804967795 cites W2041306713 @default.
• W2804967795 cites W2047161559 @default.
• W2804967795 cites W2049308602 @default.
• W2804967795 cites W2053008628 @default.
• W2804967795 cites W2053935658 @default.
• W2804967795 cites W2054969885 @default.
• W2804967795 cites W2057175746 @default.
• W2804967795 cites W2064058834 @default.
• W2804967795 cites W2068337491 @default.
• W2804967795 cites W2086331119 @default.
• W2804967795 cites W2086470495 @default.
• W2804967795 cites W2093227155 @default.
• W2804967795 cites W2099606917 @default.
• W2804967795 cites W2099789128 @default.
• W2804967795 cites W2099854727 @default.
• W2804967795 cites W2106210044 @default.
• W2804967795 cites W2106723645 @default.
• W2804967795 cites W2106874266 @default.
• W2804967795 cites W2112482836 @default.
• W2804967795 cites W2112796928 @default.
• W2804967795 cites W2113169414 @default.
• W2804967795 cites W2116282199 @default.
• W2804967795 cites W2116707521 @default.
• W2804967795 cites W2117015441 @default.
• W2804967795 cites W2118503838 @default.
• W2804967795 cites W2120971756 @default.
• W2804967795 cites W2121717885 @default.
• W2804967795 cites W2122888827 @default.
• W2804967795 cites W2132582440 @default.
• W2804967795 cites W2140055783 @default.
• W2804967795 cites W2142873256 @default.
• W2804967795 cites W2143516773 @default.
• W2804967795 cites W2144012927 @default.
• W2804967795 cites W2153483943 @default.
• W2804967795 cites W2155893237 @default.
• W2804967795 cites W2156061717 @default.
• W2804967795 cites W2169008480 @default.
• W2804967795 cites W2172156083 @default.
• W2804967795 cites W2173758409 @default.
• W2804967795 cites W2254644702 @default.
• W2804967795 cites W2285190206 @default.
• W2804967795 cites W2293404936 @default.
• W2804967795 cites W2395611524 @default.
• W2804967795 cites W2734426270 @default.
• W2804967795 cites W2737081152 @default.
• W2804967795 cites W2999893964 @default.
• W2804967795 cites W3104141662 @default.
• W2804967795 cites W4210478798 @default.
• W2804967795 cites W4231109964 @default.
• W2804967795 cites W4234143236 @default.
• W2804967795 cites W4252055280 @default.
• W2804967795 doi "https://doi.org/10.1109/tvcg.2018.2839685" @default.
• W2804967795 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29994311" @default.
• W2804967795 hasPublicationYear "2019" @default.
• W2804967795 type Work @default.
• W2804967795 sameAs 2804967795 @default.
• W2804967795 citedByCount "106" @default.
• W2804967795 countsByYear W28049677952019 @default.
• W2804967795 countsByYear W28049677952020 @default.
• W2804967795 countsByYear W28049677952021 @default.
• W2804967795 countsByYear W28049677952022 @default.
• W2804967795 countsByYear W28049677952023 @default.
• W2804967795 crossrefType "journal-article" @default.
• W2804967795 hasAuthorship W2804967795A5008766810 @default.
• W2804967795 hasAuthorship W2804967795A5014874717 @default.
• W2804967795 hasAuthorship W2804967795A5016956683 @default.
• W2804967795 hasConcept C108583219 @default.
• W2804967795 hasConcept C124504099 @default.

• next