人脸识别英文文献

人脸识别英文文献

ID:39854481

大小:468.46 KB

页数:17页

时间:2019-07-13

人脸识别英文文献_第1页
人脸识别英文文献_第2页
人脸识别英文文献_第3页
人脸识别英文文献_第4页
人脸识别英文文献_第5页
资源描述:

《人脸识别英文文献》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、D.Bhattacharjee,M.K.Bhowmik,M.Nasipuri,D.K.Basu&M.KunduAParallelFrameworkforMultilayerPerceptronforHumanFaceRecognitionDebotoshBhattacharjeedebotosh@indiatimes.comReader,DepartmentofComputerScienceandEngineering,JadavpurUniversity,Kolkata-700032,India.MrinalKantiBhowmikmkb_c

2、se@yahoo.co.inLecturer,DepartmentofComputerScienceandEngineering,TripuraUniversity(ACentralUniversity),Suryamaninagar-799130,Tripura,India.MitaNasipurimitanasipuri@gmail.comProfessor,DepartmentofComputerScienceandEngineering,JadavpurUniversity,Kolkata-700032,India.DipakKumar

3、Basudipakkbasu@gmail.comProfessor,AICTEEmeritusFellow,DepartmentofComputerScienceandEngineering,JadavpurUniversity,Kolkata-700032,India.MahantapasKundumkundu@cse.jdvu.ac.inProfessor,DepartmentofComputerScienceandEngineering,JadavpurUniversity,Kolkata-700032,India.AbstractArt

4、ificialneuralnetworkshavealreadyshowntheirsuccessinfacerecognitionandsimilarcomplexpatternrecognitiontasks.However,amajordisadvantageofthetechniqueisthatitisextremelyslowduringtrainingforlargerclassesandhencenotsuitableforreal-timecomplexproblemssuchaspatternrecognition.This

5、isanattempttodevelopaparallelframeworkforthetrainingalgorithmofaperceptron.Inthispaper,twogeneralarchitecturesforaMultilayerPerceptron(MLP)havebeendemonstrated.ThefirstarchitectureisAll-Class-in-One-Network(ACON)wherealltheclassesareplacedinasinglenetworkandthesecondoneisOne

6、-Class-in-One-Network(OCON)whereanindividualsinglenetworkisresponsibleforeachandeveryclass.Capabilitiesofthesetwoarchitectureswerecomparedandverifiedinsolvinghumanfacerecognition,whichisacomplexpatternrecognitiontaskwhereseveralfactorsaffecttherecognitionperformancelikeposev

7、ariations,facialexpressionchanges,occlusions,andmostimportantlyilluminationchanges.BoththestructureswereInternationalJournalofComputerScienceandSecurity(IJCSS),Volume(3):Issue(6)1D.Bhattacharjee,M.K.Bhowmik,M.Nasipuri,D.K.Basu&M.Kunduimplementedandtestedforfacerecognitionpur

8、poseandexperimentalresultsshowthattheOCONstructureperformsbetterthanthegene

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。