Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
Red.S.Sędziwy,SchedaeInformaticae,Vol.17/18December2009
Kraków2009,ISSN0860-0295,©byUJ
SCHEDAEINFORMATICAE
VOLUME17/18
2009
AnalysisoftheStage
KarolJaworowski
InstituteofComputerScience,JagiellonianUniversity,
Prof.StanisławaŁojasiewicza6,30-348Kraków,Poland
e-mail:karol.jaworowski@gmail.com
Abstract.Theprimaryobjectiveofthispaperistodesignamethodofde-
tectingroadedgeswithoutusingcomplexalgorithmstoidentifyandanalyze
images.Instead,neuralnetworksareused,whichallowstoenhanceandfacil-
itatethisprocess.Thepaperdescribesaprogramthatrecognizestheroadina
picturewiththeuseofaneuralnetworktrainedon500samples.Thesamples
containoriginalphotosandimageswithaselectedroad.Inthecourseofthe
researchtwosolutionsarose.ThefirstsolutionistouseasinglePerceptron
torecognizetheroad.Thesecondsolutionistoclassifythephotosusinga
Kohonennetworkandestablishaseparatenetworkforeachclass.
Keywords:neuralnetwork,imagerecognition.
1.Introduction
Artificialvisionsystemsareextremelyusefulinourlife.Theycouldhelpdrivers
bycontrollingtrafficlights.Physicianscouldusethemtodetectdiseasesandthey
canalsobeusedinthemanufacturingprocessinafactory.Oneapplicationof
artificialvisionsystems,whichmayproveespeciallyuseful,isdetectingtheroad
infrontofacar.Notonlycanitimprovethecomfortofdriving,butalsoincrease
safetyoftheroadusers.Thisisaveryinterestingquestionbecauseifacomputeris
abletoidentifytheroadandthelocationofthevehicleontheroaditwillbeable
todrivebyitself.Andcertainlyitwouldbehelpfulinkeepingthevehicleonthe
