简介：Inthispaper,wepresentanefficientapproachforunsupervisedsegmentationofnaturalandtexturalimagesbasedontheextractionofimagefeaturesandafastactivecontoursegmentationmodel.Weaddresstheproblemoftextureswhereneitherthegray-levelinformationnortheboundaryinformationisadequateforobjectextraction.Thisisoftenthecaseofnaturalimagescomposedofbothhomogeneousandtexturedregions.Becausetheseimagescannotbeingeneraldirectlyprocessedbythegray-levelinformation,weproposeanewtexturedescriptorwhichintrinsicallydefinesthegeometryoftexturesusingsemi-localimageinformationandtoolsfromdifferentialgeometry.Then,weusethepopularKullback-Leiblerdistancetodesignanactivecontourmodelwhichdistinguishesthebackgroundandtexturesofinterest.Theexistenceofaminimizingsolutiontotheproposedsegmentationmodelisproven.Finally,atexturesegmentationalgorithmbasedontheSplit-Bregmanmethodisintroducedtoextractmeaningfulobjectsinafastway.Promisingsyntheticandreal-worldresultsforgray-scaleandcolorimagesarepresented.