International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 05 | May 2021 www.irjet.net p-ISSN: 2395-0072 © 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 116 IMPLEMENTING ROBUST SECURITY SYSTEM WITH SMTP PROTOCOL BASED MACHINE LEARNING ALGORITHM Mr. J. Subhash 1 , S. Mugilan 2 , T. Mugilan 3 , R. M. P. Mukhilan 4 , V. Prem Kumar 5 1 Assistant Professor, 2,3,4,5 UG Scholars, Department of Electronics and Communication Engineering, Adhiyamaan College of Engineering, Krishnagiri district, Tamilnadu, India subhash.ece@adhiyamaan.in 1 , mugilansdpi@gmail.com 2 , mugiltamil07@gmail.com 3 , rmpmugil@gmail.com 4 , premjack004@gmail.com 5 ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract.- Safety in the home has become a major concern for all people in the present. In this work an effort has been made to create a home system that is easily accessible, affordable and effective. The proposed system is based on a Remote Monitoring System that operates on an online verification and monitoring platform. The system is relatively inexpensive as it relies on existing network infrastructure. As viola jones are very popular and efficient facial recognition algorithm, it has been used in this work. Next to it the interface is designed for the purpose of connecting to a wireless security system via the Node MCU module. In line with this digital image processing system, automatic door movement controls have been implemented using machine-based door lock technology. This helps users to monitor real-time activities with web services. The web service contains any web browser command. The system establishes a connection between the system and the verified user. E-mail received by the system using the IMAP (internet message access protocol) from an unauthorized person will monitor and control real-time operation and locking of the door. The entire control system is verified using the ESP 8266 Wi-Fi device and tested for real use in the home environment. The result shows the validity of the proposed system test. Key Words: Nodemcu, Motor driver board, RPM motor, Gear motor 1.INTRODUCTION These days, the home security system is an important issue. Indeed, the program ensures that buildings and loved ones remain safe and secure. In the last few years, it has been important to have a strong home security system in place, which can be safe and secure. An important part of any home security system is an indication of a person entering and leaving the house. In the past, people used the traditional method of their home security system. The traditional security system relies on the use of external devices such as keys, passwords and ID cards to gain access. However, due to certain limitations, biometric is possible to deliver such a promising security system. Biometric is a unique parameter with a number of individual recognition. The biometric system requires the use of special hardware such as a fingerprint scanner, palm printer scanner, DNA analyzer and more. In addition, this particular device required that the target touch the hardware to obtain details of different human characteristics. Biometric technology is considered to be one of the most secure authentication systems available, providing a higher level of security than the standard method. Face recognition is the most popular method in biometric technology without fingerprint features. This is due to the increased stability as the face contains many features. Besides, it is considered a great protection as the face can be stolen, stolen or chosen to enter the house. Facial recognition is probably the most natural way to perform biometric authentication among humans. Face detection is the first step in a facial recognition program. Facial images can be captured remotely using a webcam. A person can be seen without physical contact on any special Hardware to see who he or she is. Facial recognition using an in-depth learning process. Deep learning is part of the process A broad group of machine learning methods based on the representation of learning data, unlike algorithms specific to a particular task. Learning can be managed, directed or supervised. With in-depth learning, the system is improved from time to time. Some user authorization images are used as the program database and the system will train face recognition automatically. Therefore, the accuracy is increased. Home Security is an example of Internet of Things (IoT) applications. IoT refers to a network of compatible body systems that can interact and trade information between them without the need for human intervention [5]. IoT is the technology of the future where devices and the internet are connected. It is different from the Internet because the Internet overrides the connection by allowing any embedded circuit to communicate with others using the current Internet infrastructure.