This　paper　addresses　the　problem　of　fetal　electrocardiogram　(FECG)　extracion　using　recursive　least　squares　(RLS)　and　normalized　least　mean　squares　(NLMS)　adaptive　algorithms　based　adaptive　noise　canceling　(ANC)　approach.　The　simulation　results　are　compared　with　the　classical　adaptive　filters,　such　as　RLS,　NLMS　and　LMS　algorithms,　for　eliminating　the　maternal　electrocardiogram　(MECG)　and　hence　to　extract　the　FECG.　The　comparative　study　has　been　carried　out　to　show　that　the　performance　and　accuracy　of　the　recursive　least　squares　adaptive　noise　cancelling(RLS-ANC)　approach　is　more　effective　than　the　normalized　least　mean　squares　(NLMS)　algorithm　in　an　adaptive　manner,　and　it　is　found　to　converge　faster　than　NLMS　algorithm　in　ANC.　©　2011　IEEE.