Skip to content

Latest commit

 

History

History
58 lines (35 loc) · 1.46 KB

README.md

File metadata and controls

58 lines (35 loc) · 1.46 KB

Person Recognition

Designed and implemented Person Recognition System as Person Attendance Tracker using face recognition methods to track and record person’s identities in the videos captured from security cameras. Achieved more than 90% tracking and recognition accuracy in non-occluded and more than 80% in occluded areas

Dataset:

chokepoint dataset dataset

Results:

Tested on 6 sequences of trackings and results in terms of tracking and recognition accuracy.

seq
tracking accuracy = 100%, recognition accuracy = 96%

seq
tracking accuracy = 100%, recognition accuracy = 96%

seq
tracking accuracy = 100%, recognition accuracy = 80%

seq
tracking accuracy = 100%, recognition accuracy = 91%

seq
tracking accuracy = 100%, recognition accuracy = 76%

seq
tracking accuracy = 84%, recognition accuracy = 76%