Summary - In this article, the method used by facial recognition to access automated teller machines (ATMs). ATMs are used to perform banking functions, like checking balance, withdrawing cash, changing ID numbers, etc. ATM cards and identification numbers are used for security purposes. But this system uses a SIM card instead of ATM cards. To improve security, the system first authenticates the person if they are recognized and then it will ask them for the account password. This system used the Spartan 3 FPGA board to control the system. A buzzer is connected to the FPGA board which gives instructions to the user to access the account. If the person is not authenticated, the process is completed and the output is displayed on the FPGA board using LEDs. Key words: recognition, ATM, PCA, GSM, FPGA, Euclidean distance. INTRODUCTIONFacial recognition plays a very important role in security system [4]. The main goal of facial recognition is to recognize a person from images or videos using face databases. There are many variations and designing facial recognition is not an easy task [2]. Due to variations in lighting, facial expression, and poses, it is difficult to perform facial recognition [7]. A number of defense, security, and commercial applications require a real-time facial recognition system, particularly where other biometric techniques are not feasible [1]. In this article, the system uses facial recognition to access the ATM. Automated Teller Machines (ATMs) are used by users to carry out banking transactions such as withdrawing money, checking balance, etc. Nowadays, ATMs are very popular because they operate on all days of the week and provide 24-hour service. We can find ATMs anywhere in cities, railway stations, near companies, near restaurants...... middle of paper ......otani, Feifei Lee and Tadahiro Ohmi, “Facial recognition using self-organizing cards” www. intechopen.com[6] Rala M. Ebied, “Feature Extraction using PCA and Kernel-PCA for Face Recognition,” in 8th International Conference on Computer Science and Systems, Computational Intelligence and multimedia computer track, 2012, pp mm72-mm77[7] Mohammed Alwakeel, Zyad Shaaban, “Face recognition based on Haar wavelet transform and principal component analysis via Levenberg-Marquardt backpropagation neural network” in European Journal of Scientific Research, 2010 pp. 25-31[8] Kyungnam Kim, “Face recognition using Principal Component”, Analysis” www.google.com[9] Kyungnam Kim, “Face Recognition using Principal Component”, Analysis” www.google.com[10] Lindsay I Smith, “A Tutorial on Principal Component Analysis,” February 26, 2002 [11] www.mathwork.com[12] www.google.com