Rule-based Classifiers for Suspect Detection from CCTV Footages

Abstract

Background: A significant work has been presented to identify suspects, gathering information and examining any videos from the CCTV Footage. This exploration work expects to recognize suspicious exercises, i.e., object trade, the passage of another individual, peeping into other's answer sheet and individual trade from the video caught by a reconnaissance camera amid examinations. This requires the procedure of face acknowledgment, hand acknowledgment and distinguishing the contact between the face and hands of a similar individual and that among various people. Methods: Segmented frames have been given as input to obtain a foreground image with the help of Gaussian filtering and background modeling method. Such foreground images have been given to Activity Recognition model to detect normal activity or suspicious activity. Result: Accuracy rate, Precision and Recall are calculated for activities detection, contact detection for Best Case, Average Case and Worst Case. Simulation results are compared with performance parameter such as Material Exchange, Position Exchange, and Introduction of a new person, Face and Hand Detection and Multi Person Scenario. Conclusion: In this paper, a framework is prepared for suspect detection. This framework will absolutely realize an unrest in the field of security observation in the training area.