The conventional method of finding a missing person involves lodging an FIR in nearby police station and police will then circulate the person’s photo to all the nearby police stations. This process is very time consuming. The idea is to automate this process by using Facial Recognition. The purposed algorithm is implemented using enhanced KNN, dlib and OpenCV. The presented approach uses dlib to generate a total of 68 exclusive facial key features. 136 points are generated in total which are floating point numbers(point 10 precision). Thus, we have decided to use Enhanced KNN algorithm. We use this algorithm for matching faces. This form k groups using the cases that have been registered. The traditional KNN strategy has different deficiencies we propose to upgrade its precision utilizing these techniques. Need of qualities and best neighborhood size are considered to ascertain increasingly exact separation capacities and to get precise outcomes. Rather than basic democratic strategy we propose to utilize likelihood class estimation technique.

Keywords : Facial Recognition, Machine Learning, Enhanced KNN, DLIB, PyQt5, DCR, OpenCV.