Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
Red.S.Sędziwy,SchedaeInformaticae,Vol.17/18December2009
Kraków2009,ISSN0860-0295,©byUJ
14
pixelsarepixels,whichthenetworkincorrectlyclassifiedastheroadandpixels,
whichshouldhavebeenclassifiedasaroadbuttheywerenot.InFig.4blackpoints
makeupacorrectly-detectedroad,thegreenonesarethepixelswhicharetheroad
butthenetworkhasnotidentifiedthemasaroadandtheredpixelsareincorrectly
classifiedasaroad.
Fig.4.Blackpoints–correctlydetectedroad,greenpoints–notdetectedroad,redpoints
–incorrectlydetectedroad
TheerrorinFig.4equals3,125%,itisthesumofredandgreenpixels(33+15)
dividedbythenumberoftestedpixels(1536)multipliedby100.
•Errorofroadrecognitionforpicturesonwhichthenetworkhasbeentrained.
Thehighestestimationerroroftheroadidentificationprocesswas14.9%,thelowest
0.19%,whiletheaverageerrorofroadrecognitioninthissolutionwasequalto
2.9%.Theresultsofthesystemperformanceincaseofthehighestandthelowest
errorarepresentedinTab.1.
•Errorofroadrecognitionforpicturespreviouslyunknowntothenetwork.