This paper presents novel technique for recognizing faces. From the last two decades, face recognition is playing an important and vital role especially in the field of commercial, banking, social and law enforcement area. It is an interesting application of pattern recognition and hence received significant attention. The complete process of face recognition covers in three stages, face detection, feature extraction and recognition. Various techniques are then needed for these three stages. Also these techniques vary from various other surrounding factors such as face orientation, expression, lighting and background. The Self-Organizing Map (SOM) Neural Network has been used for training of database and simulation of FR system. In this paper the feature extraction methods discrete wavelet transform (DWT), discrete cosine transform (DCT) simulated in MATLAB are explained.