Palmprints are of long practical and cultural interest.Palmprint principal lines,also called primary palmar lines,are one of the most dominant palmprint features and do not change over the lifespan.The existing method...Palmprints are of long practical and cultural interest.Palmprint principal lines,also called primary palmar lines,are one of the most dominant palmprint features and do not change over the lifespan.The existing methods utilize filters and edge detection operators to get the principal lines from the palm region of interest(ROI),but can not distinguish the principal lines from fine wrinkles.This paper proposes a novel deep-learning architecture to extract palmprint principal lines,which could greatly reduce the influence of fine wrinkles,and classify palmprint phenotypes further from 2D palmprint images.This architecture includes three modules,ROI extraction module(REM)using pre-trained hand key point location model,principal line extraction module(PLEM)using deep edge detection model,and phenotype classifier(PC)based on ResNet34 network.Compared with the current ROI extraction method,our extraction is competitive with a success rate of 95.2%.For principal line extraction,the similarity score between our extracted lines and ground truth palmprint lines achieves 0.813.And the proposed architecture achieves a phenotype classification accuracy of 95.7%based on our self-built palmprint dataset CAS_Palm.展开更多
To the Editor:Hearing loss is the most common sensory disorder in humans.There is one case of congenital deafness among every 1000 newborns,and in 50%of cases,the deafness is hereditary.Deafness exhibits high genetic ...To the Editor:Hearing loss is the most common sensory disorder in humans.There is one case of congenital deafness among every 1000 newborns,and in 50%of cases,the deafness is hereditary.Deafness exhibits high genetic heterogeneity.To date,over 110 non-syndromic deafness genes have been identified(https://hereditaryhearingloss.org/).Lots of those genes can cause both autosomaldominant hearing loss(ADNSHL)and autosomal-recessive non-syndromic hearing loss(ARNSHL)andTMC1(encoding the transmembrane channel-like 1)is one of them.TMC1(OMIM:606706)is a member of the TMC family located at 9q21.13.The protein contains 760 amino acids and has six transmembrane regions.TMC1 is expressed in the inner and outer hair cells of the cochlea.A TMC1 mutation was first shown to cause deafness in 2002.[1]The prevalence of TMC1 variants ranged from 3.4%(19/557)among Pakistani ARNSHL families to 8.1%(7/86)in Turkish families.To date,around 20 hearing loss families associated withTMC1 variants have been reported in China.展开更多
基金We would like to thank the participants of the CAS_palm set who consented to participate in research.This project was funded by the Shanghai Municipal Science and Technology Major Project 2017SHZDZX01(S.W.)National Natural Science Foundation of China Grant 61831015(G.Z.)China Postdoctoral Science Foundation Grant 2019M651351(J.L.).
文摘Palmprints are of long practical and cultural interest.Palmprint principal lines,also called primary palmar lines,are one of the most dominant palmprint features and do not change over the lifespan.The existing methods utilize filters and edge detection operators to get the principal lines from the palm region of interest(ROI),but can not distinguish the principal lines from fine wrinkles.This paper proposes a novel deep-learning architecture to extract palmprint principal lines,which could greatly reduce the influence of fine wrinkles,and classify palmprint phenotypes further from 2D palmprint images.This architecture includes three modules,ROI extraction module(REM)using pre-trained hand key point location model,principal line extraction module(PLEM)using deep edge detection model,and phenotype classifier(PC)based on ResNet34 network.Compared with the current ROI extraction method,our extraction is competitive with a success rate of 95.2%.For principal line extraction,the similarity score between our extracted lines and ground truth palmprint lines achieves 0.813.And the proposed architecture achieves a phenotype classification accuracy of 95.7%based on our self-built palmprint dataset CAS_Palm.
基金Collaborative Innovation Project of Zhengzhou (Zhengzhou University)(No. 18XTZX12004)
文摘To the Editor:Hearing loss is the most common sensory disorder in humans.There is one case of congenital deafness among every 1000 newborns,and in 50%of cases,the deafness is hereditary.Deafness exhibits high genetic heterogeneity.To date,over 110 non-syndromic deafness genes have been identified(https://hereditaryhearingloss.org/).Lots of those genes can cause both autosomaldominant hearing loss(ADNSHL)and autosomal-recessive non-syndromic hearing loss(ARNSHL)andTMC1(encoding the transmembrane channel-like 1)is one of them.TMC1(OMIM:606706)is a member of the TMC family located at 9q21.13.The protein contains 760 amino acids and has six transmembrane regions.TMC1 is expressed in the inner and outer hair cells of the cochlea.A TMC1 mutation was first shown to cause deafness in 2002.[1]The prevalence of TMC1 variants ranged from 3.4%(19/557)among Pakistani ARNSHL families to 8.1%(7/86)in Turkish families.To date,around 20 hearing loss families associated withTMC1 variants have been reported in China.
