An online real-time face recognition system for police purposes

In general, face recognition algorithms are often utilized in order to identify or authenticate a human through a camera feed. However, face recognition algorithms must adapt to real-life uncertainties and noisy environments. This work targets upon extending the existing work of facial recognition algorithms by proposing an online platform that can be used from the police forces towards effective real-time human recognition. The approach on facial recognition is to use and extend the Haar Cascade algorithm for real-time purposes, which is widely considered one for the most efficient and used algorithms for that cause. As for the criminal identification, it will made possible through image pattern recognition between the provided criminal’s image and snapshots of identified faces from the livestream feed. The platform will include a live feed section with different options for video filters, enabling the user to select the best filter, depending on relevant situation of the physical surroundings for better recognition.