As the word become moving towards the globalization in engineering techniques, the capacity and techniques establish an identity of individuals using face as a biometric has become a more important. This paper includes the face recognition using the Extended Principal Component Analysis (EPCA) algorithm. The proposed algorithm uses the concept of PCA and represents an extended version of PCA by using the LDA (Linear Discriminate Analysis) to deal with the problem of operating the multiple numbers of the training images in the database. The Extended version of PCA algorithm may be used in to the face identification for security purpose, criminal face recognition, surveillance authentication etc. The problems related to background, noise and occlusion, and finally speed requirements are also overcome by using this algorithm. This paper focuses on developing a face recognition system using an extended PCA algorithm. The proposed algorithm uses the concept of PCA and represents an improved version of PCA to deal with the problem of orientation and lightening conditions present in the original PCA. Never the less the PCA algorithm is outperforms correct and good result in the less amount of database.