“…Ageneralgaitrecognitionframeworkconsistsofseveralsubstepssuchaspreprocessing,ROI detection,featureextractionandrecognition.Thepreprocessingstephasmuchimportanceforobtaining highrecognitionratebecausetherawinputvideoshaveacomplexbackgroundandlowcontrast.The lowcontrastvideosaffectROIdetectionwhichlaterondegradestherecognitionaccuracy.Therefore, preprocessingisamajorstepforimprovingthecontrastofinputvideoandalsoremovesextranoise suchaschangeinbackground,variationsandhumanchange.Ingaitrecognition,differentsegmentation methods have been introduced for ROI detection such as background subtraction, thresholding, watershed and few more (Piccardi, 2004;Gupta, Dixit et al, 2014). There are several types of featureswhichexistincomputervisionsuchastexture,color,geometric,shape,Gaborandwavelet transform.Thesefeaturesarehighinnumberofdimensions;therefore,theyreducetheaccuracy.This kindofproblemisresolvedbyseveralresearchersbytheimplementationofreductiontechniques.…”