Design for Smart Security System using Face Recognition

This research designs face detection and recognition systems for smart home security application. This system is used for door lock system to open or close door using face recognition. The design is implemented using NodeMCU, Servo Motor and programmed using Arduino IDE. The connection between the camera and NodeMCU controlled Servo Motor is on a wi-fi network. The image of a person is acquired via webcam connected to a device at door. Door is accessed by servo motor through Thingspeak API when face is identified. The face detection system is built based on the histogram analysis, while the face recognition is based on the Local Binary Patterns Histograms (LBPH). The testing is done to examine the performance of the face detection in various change of distance, light intensity, light position angles. The face detection module has good performance in some conditions as distance between the person and the camera is less than 100 cm, person doesn’t use accessories that cover part of face, person doesn’t use shirt with color similar to skin color, and background color is difference from skin color. While the face recognition system has 80% of accuracy when it is tested using real time image.