Abstract-When we acquiring the Electrocardiogram (ECG) signal fro m the person, the signal amplitude (PQRST) and timing values are changes due to various artefacts. The different artefacts are Baseline wander, power line interference, muscle artefact, mot ion artefact and the channel noise also added sometimes during the transmission of the signal for diagnosis purpose. The adaptive filters play vital ro le fo r reduction of noise in the desired signals. In this paper we proposed, block based error normalized Recursive Least Square (RLS) adaptive algorith m and sign based RLS adaptive algorith m, wh ich are used for reduction of muscle artifact noise and base line wander noise in the ECG signal. Fro m the simulat ion result we analy zed that, co mparing to Least Mean Square algorith m, the proposed RLS algorith m gives fast convergence rate with high signal to noise ratio and less mean square error.Index Terms-RLS Adaptive algorithms, Signal to noise ratio, artifacts, mean square error, ECG signal.