Published Paper Details:

Intruder attack and burglary are a serious issue now a days. Currently many systems are using sensors and motion detection devices but these systems cannot be reliable as they can be triggered with little change in climate like heat. The proposed system has solved this problem with the help of computer vision and OpenCV. The system can detect and recognize person from the previously provided data. The proposed system is capable for face detection and reorganization of person for identifying whether a person in the frame is a known person or an intruder. For face detection Haar-cascade models are used in order to detect human as well as pet animal. This detected section of face is the given to face recognition model which is trained on LBPH. The model returns the probability of the recognition for each person in the frame. In addition to this, the system can trigger an alarm once it finds some Intruder with respect to human or pet.