基于分形維數(shù)的眼睛檢測算法研究.pdf

1、南京理工大學(xué)碩士學(xué)位論文基于分形維數(shù)的眼睛檢測算法研究姓名：張曉燕申請學(xué)位級別：碩士專業(yè)：應(yīng)用數(shù)學(xué)指導(dǎo)教師：張正軍20090601Abstract碩士論文AbstractFacedetectionandrecognitiontechnologyisthefieldofartificialintelligenceandmachinevisioninthemostchallengingoneoftheresearchtopicLetthec

2、omputerautomaticallyrecognizehumanfacesthefieldofcomputervisionisanimportantresearchtopic，acompletefacerecognitionsystemconsistsoffacedetection，faceimagepreprocessing，facefeatureextraction，imagesimilaritycalculationbetwe

3、enfunctionalmodules，suchasFacialfeatureextractionistheautomaticfacerecognitionsysteminaveryimportantComparedtootherfacialfeatures，eyestheexactlocationhasauniquevalue，Itistherealizationofhumanfaceimagesnormalizedgeometryo

4、fthenecessaryconditionsforfullyautomaticfacerecognitionhasbecomeaverycrucialaspectofthispaperonthecomputerinthefacedetectionanalysisofanumberofissuesatthesametime，forthefacerecognitionsystemThetllirdimportantaspectFacede

5、tectionfeatureextractionmethodsintheeyesofanindepthstudy，basedonfractaldimensionofdetectionmethodsInthispaper，thestandardfacedatabaseinthemainorgansoftheface(suchaseyes，eyebrows，nose，mouth)forthefractaldimensionanalysis，

6、thestatisticsoftheabove—mentionedfractaldimensionoftheorgandistributionandorgan、Ⅳitllanimageofthefractaldimensionafewontherelationshipbetweentheffactaldimensionbasedonthenumberofeyestoidentifymodel(BasedonFractalDimensio

7、ntecognitioneyes，BFD)，andmodeltheuseofBFDlibraryMIT—FacedetectioninimagesBFDInthispaperexperimentalresultsshowthattheeyedetectionmethodisreasonable，withatheoreticalvalueandpracticalvalueKeywords：fractal，boxdimension，eyed