Person Re-identification via Deep Metric Learning

Now a day's everyone are facing a wide range and variety of threats, ranging from robbery, kidnapping, and terrorism to murder. To avoid these threats, it is necessary for the authorities to collect real time information on what is happening in and around the city. Therefore, to make the cities safer and risk free, new technologies are being developed. Here we built a reliable system that recognizes the person from any angle from a captured image. We can get the input to the systems through CCTV cameras installed in public places where these kinds of life-threatening events take place. It is easy to install these cameras at public places and more easy to monitor and store the data. The developed system uses deep metric learning and the machine learning platform, tenser flow and keras. It is a type of machine learning where system iteratively performs computations to know the patterns. The system processes captured images and compares with existing dataset images to recognize the person. The comparison is done based on certain selected features. The results are more accurate (98.18%) compared to existing systems.