Tracking of Criminal Through CCTV Using Face Detection
In our social life, face is the primitive center for consideration, which plays an important task for identification. Live Face Recognition has attained enormous consideration in security systems, because of its non-intrusiveness, accurate and fast results etc. Under this project the execution of identification of facial features is done in two parts viz. Facial features detection and recollection. Facial features detection part is done using viola-jones algorithm along with Scale Invariant feature transform due to its high precision and high real time permit rate which is deployed in OpenCV by python language. In Face recognition two categories are considered: training phase and evaluation phase. Training phase is achieved by iterating the algorithm with image samples that are to be learnt & retained and In estimation phase, the test image is compared among all the trained samples in the dataset.The facial features are extracted with the detected faces from live stream by Local Binary Patterns Histogram (LBPH). On detection of the criminal face the timestamp and the location of the corresponding camera is sent as an alert message continuously ,thus the criminal is tracked.