The current crises due to terrorism has led to a number of youngsters being brainwashed to fight for groups such as ISIS that spread terrorism. Capitalising on this growth, ISIS and various terror outfits are now increasingly fighting an online cyber war, with the use of slick videos, images and are creating a new generation of cyber terrorists. Indeed, the group has actively been using social media sites such as Twitter, Facebook and YouTube to recruit individuals as new members. This is being done through images and the streaming of violent online viral videos filmed and professionally edited that are targeting young and impressionable people. The Internet therefore is becoming the virtual playground for extremist views to be reinforced and act as an echo chamber. In this paper we demonstrate how object detection algorithms can be efficient in detecting terror elements in a video and also reporting such terror elements through email to appropriate authorities using SMTP Library.In addition to this a UI has also been provided to interact with the system using Tkinter Library.
The detection phase of the proposed system is that mainly a window of the target size is moved over the input image, and for each subsection of the image the Haar like feature is calculated. This difference is then compared to a learned threshold that separates non objects from objects. The biggest advantage of this method is the calculation speed. Due to the use of integral images that quickly and efficiently generates the sum of values in a rectangular subset of a grid, henceforth a Haar like feature of any size can be calculated in constant time (approximately 60 microprocessor instructions for a 2 rectangle feature). The next step involves training using the set of positive images and negative images after training an xml file is generated and this xml file is used with OpenCV commands to detect the desired object.
Results: https://user-images.githubusercontent.com/19201530/37863712-f14df9fc-2f88-11e8-96e9-62348817f323.PNG
