IJARCCE ISSN (Online) 2278-1021 ISSN (Print) 2319 5940 International Journal of Advanced Research in Computer and Communication Engineering ISO 3297:2007 Certified Vol. 6, Issue 4, April 2017 Copyright to IJARCCE DOI10.17148/IJARCCE.2017.6414 70 Face Detection and Face Recognition Using Raspberry Pi Shrutika V. Deshmukh 1 , Prof Dr. U. A. Kshirsagar 2 P.G Student, Electronics and Telecommunication Department, HVPM’s College of Engineering and Technology Amravati, India 1 Professor and HOD, Electronics and Telecommunication Dept, HVPM’s College of Engineering and Technology, Amravati, India 2 Abstract: Nowadays the number of thefts and identity fraud has become a serious issue. In order to avoid these thefts and identity fraud, a face recognition system must be established. The scope of this project is to develop a security access control application based on face recognition. The haar-like features is used for face detection and HOG +SVM algorithm is used for face recognition. In order to achieve a higher accuracy and effectiveness we use OpenCV libraries and python computer language. Training and identification is done in embedded device known as Raspberry Pi. Keywords: Face detection, Face recognition, raspberry pi, security. I. INTRODUCTION In this current time a lot of incident occurs like robbery, stealing unwanted entrance happens abruptly. So the security does matters in this daily life. People always remain busy in their day to day work also wants to ensure their safety of their beloved things. Sometimes they forget to look after their necessary things like keys, wallet, credit cards etc. Without these, they are unable to access their home or any place they want.Traditional security system require the user a key, a security password, an RFID card, or ID card to have access to the system. However, these security systems have deficiencies; for example, they can be forgotten or stolen from unauthorized people. As a result, there is a need to develop software that guarantees a higher security level is a template. One of the unique features of our brain is that it can think only in images not in words. Once you may forget to keep your Car’s key but you will never forget to bring a face with you.God has given everyone a unique face. Face is the most important part of our body, so that it can reflect many emotions of a person. From a long year ago, we are using non-living thing (smart cards, plastic cards, PINS, tokens, keys) for authentication and to get grant access in restricted areas like ISRO, NASA, and DRDO etc. There are two types of biometric as physiological characteristics (face, fingerprint, finger geometry, hand geometry, palm, iris, ear and voice) and behavioural characteristics (gait, signature and keystroke dynamics). Sometimes your behavioural traits may changes because of illness, fear, hunger etc. Face detection and recognition system is more cheap, simple, accurate and non-intrusive process as compare to other biometrics. The system will fall into two categories as face detection (1:1) and face recognition(1:N).In the face detection we have to classify between face versus non face region while in recognition process we have to compare that single face image with multiple images from the input image. In This work uses BCM2835 processor, popularly known as Raspberry pi Board. The core of the board is the above processor. It is a RISC processor based on ARM11. The board has special features like camera interface and touch screen that make it suitable for real time image processing Open cv consists of huge number of inbuilt functions for image processing. It is under BSD license and hence libraries are free of proprietary cost. The full-fledged library functions simplify the complex mathematical operations. II. RASPBERRY PI To implement such a project, the main and most important step was finding the hardware to use for the device. We have chosen a Raspberry Pi model B3 to use in our device. We have done a lot of research, and compared elements in different microcontrollers, like, cost, processing, and user friendliness. The main reasons why we have chosen this specific element are the high processing capacity, relatively low price, and its ability to adapt in different programming modes.The device uses Linux as an operating system, which has access to a large number of libraries and applications compatible with it. Raspberry Pi has an Ethernet port allowing us a network connection, as long as we are in the same subnet with the device we want to access and manage, 4 USB ports used to connect devices like a keyboard, mouse, camera, and other devices that connect through a USB port, and an HDMI port giving us access to the interface of the operating system installed, and can also be used the first time while installing the devices.It has 40 pins that allow us to