Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897188355> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2897188355 abstract "Previous works have shown that face recognition with high accurate 3D data is more reliable and insensitive to pose and illumination variations. Recently, low-cost and portable 3D acquisition techniques like ToF(Time of Flight) and DoE based structured light systems enable us to access 3D data easily, e.g., via a mobile phone. However, such devices only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly. In this paper, we aim at achieving high-performance face recognition for devices equipped with such modules which is very meaningful in practice as such devices will be very popular. We propose a framework to perform face recognition by fusing a sequence of low-quality 3D data. As 3D data are sparse and noisy which can not be well handled by conventional methods like the ICP algorithm, we design a PointNet-like Deep Registration Network(DRNet) which works with ordered 3D point coordinates while preserving the ability of mining local structures via convolution. Meanwhile we develop a novel loss function to optimize our DRNet based on the quaternion expression which obviously outperforms other widely used functions. For face recognition, we design a deep convolutional network which takes the fused 3D depth-map as input based on AMSoftmax model. Experiments show that our DRNet can achieve rotation error 0.95{deg} and translation error 0.28mm for registration. The face recognition on fused data also achieves rank-1 accuracy 99.2% , FAR-0.001 97.5% on Bosphorus dataset which is comparable with state-of-the-art high-quality data based recognition performance." @default.
- W2897188355 created "2018-10-26" @default.
- W2897188355 creator A5003152439 @default.
- W2897188355 creator A5028960242 @default.
- W2897188355 creator A5050118501 @default.
- W2897188355 creator A5061525421 @default.
- W2897188355 creator A5070483282 @default.
- W2897188355 date "2018-10-23" @default.
- W2897188355 modified "2023-09-23" @default.
- W2897188355 title "Face Recognition from Sequential Sparse 3D Data via Deep Registration" @default.
- W2897188355 cites W1819285909 @default.
- W2897188355 cites W1820849028 @default.
- W2897188355 cites W1972394471 @default.
- W2897188355 cites W1980257741 @default.
- W2897188355 cites W1981660604 @default.
- W2897188355 cites W1982755836 @default.
- W2897188355 cites W2070870580 @default.
- W2897188355 cites W2081528579 @default.
- W2897188355 cites W2121644888 @default.
- W2897188355 cites W2130571344 @default.
- W2897188355 cites W2133131023 @default.
- W2897188355 cites W2145287260 @default.
- W2897188355 cites W2157364958 @default.
- W2897188355 cites W2166335841 @default.
- W2897188355 cites W2194775991 @default.
- W2897188355 cites W2200124539 @default.
- W2897188355 cites W2207409364 @default.
- W2897188355 cites W2237250383 @default.
- W2897188355 cites W2434421859 @default.
- W2897188355 cites W2560609797 @default.
- W2897188355 cites W2605111497 @default.
- W2897188355 cites W2612733445 @default.
- W2897188355 cites W2963858339 @default.
- W2897188355 cites W2963865528 @default.
- W2897188355 cites W2964121744 @default.
- W2897188355 cites W2964171387 @default.
- W2897188355 cites W3099206234 @default.
- W2897188355 cites W3103152812 @default.
- W2897188355 doi "https://doi.org/10.48550/arxiv.1810.09658" @default.
- W2897188355 hasPublicationYear "2018" @default.
- W2897188355 type Work @default.
- W2897188355 sameAs 2897188355 @default.
- W2897188355 citedByCount "0" @default.
- W2897188355 crossrefType "posted-content" @default.
- W2897188355 hasAuthorship W2897188355A5003152439 @default.
- W2897188355 hasAuthorship W2897188355A5028960242 @default.
- W2897188355 hasAuthorship W2897188355A5050118501 @default.
- W2897188355 hasAuthorship W2897188355A5061525421 @default.
- W2897188355 hasAuthorship W2897188355A5070483282 @default.
- W2897188355 hasBestOaLocation W28971883551 @default.
- W2897188355 hasConcept C104317684 @default.
- W2897188355 hasConcept C105580179 @default.
- W2897188355 hasConcept C108583219 @default.
- W2897188355 hasConcept C144024400 @default.
- W2897188355 hasConcept C149364088 @default.
- W2897188355 hasConcept C153180895 @default.
- W2897188355 hasConcept C154945302 @default.
- W2897188355 hasConcept C185592680 @default.
- W2897188355 hasConcept C2779304628 @default.
- W2897188355 hasConcept C31510193 @default.
- W2897188355 hasConcept C31972630 @default.
- W2897188355 hasConcept C36289849 @default.
- W2897188355 hasConcept C41008148 @default.
- W2897188355 hasConcept C55493867 @default.
- W2897188355 hasConceptScore W2897188355C104317684 @default.
- W2897188355 hasConceptScore W2897188355C105580179 @default.
- W2897188355 hasConceptScore W2897188355C108583219 @default.
- W2897188355 hasConceptScore W2897188355C144024400 @default.
- W2897188355 hasConceptScore W2897188355C149364088 @default.
- W2897188355 hasConceptScore W2897188355C153180895 @default.
- W2897188355 hasConceptScore W2897188355C154945302 @default.
- W2897188355 hasConceptScore W2897188355C185592680 @default.
- W2897188355 hasConceptScore W2897188355C2779304628 @default.
- W2897188355 hasConceptScore W2897188355C31510193 @default.
- W2897188355 hasConceptScore W2897188355C31972630 @default.
- W2897188355 hasConceptScore W2897188355C36289849 @default.
- W2897188355 hasConceptScore W2897188355C41008148 @default.
- W2897188355 hasConceptScore W2897188355C55493867 @default.
- W2897188355 hasLocation W28971883551 @default.
- W2897188355 hasOpenAccess W2897188355 @default.
- W2897188355 hasPrimaryLocation W28971883551 @default.
- W2897188355 hasRelatedWork W1942434842 @default.
- W2897188355 hasRelatedWork W1985878399 @default.
- W2897188355 hasRelatedWork W1987584713 @default.
- W2897188355 hasRelatedWork W1989039360 @default.
- W2897188355 hasRelatedWork W2124026597 @default.
- W2897188355 hasRelatedWork W2136499149 @default.
- W2897188355 hasRelatedWork W2248182120 @default.
- W2897188355 hasRelatedWork W2764781308 @default.
- W2897188355 hasRelatedWork W2807287270 @default.
- W2897188355 hasRelatedWork W2908959303 @default.
- W2897188355 isParatext "false" @default.
- W2897188355 isRetracted "false" @default.
- W2897188355 magId "2897188355" @default.
- W2897188355 workType "article" @default.