Fetal electrocardiogram (f-ECG) presents the electrical activity of a fetus heart. The f-ECG contains significant information about the physiological states of a developing child inside the mother's womb. It can even detect a fetus's pathologies including acidemia and hypoxia. However, the extraction of the f-ECG is a challenging task for both invasive and non-invasive methods because it is mixed with a high amplitude mother's ECG (m-ECG) signal and other random noises. This paper presents two blind source separation (BSS) algorithms to extract the f-ECG from the mixed signals. These algorithms are fast independent component analysis (FastICA) and principal component analysis with whitening (PCA-Whitening). The performances of these two algorithms are compared in this work. The results show that the FastICA algorithm outperforms PCA-Whitening algorithm by an improvement of signal to noise ratio (SNR) of 10 dB.