Comparison of Viola-Jones and Kanade-Lucas-Tomasi Face Detection Algorithms

Face detection technologies are used in a large variety of applications like advertising, entertainment, video coding, digital cameras, CCTV surveillance and even in military use. It is especially crucial in face recognition systems. You can’t recognise faces that you can’t detect, right? But a single face detection algorithm won’t work in the same way in every situation. It all comes down to how the algorithm works. For example, the Kanade-Lucas-Tomasi algorithm makes use of spatial common intensity transformation to direct the deep search for the position that shows the best match. It is much faster than other traditional techniques for checking far fewer potential matches between pictures. Similarly, another common face detection algorithm is the Viola-Jones algorithm that is the most widely used face detection algorithm. It is used in most digital cameras and mobile phones to detect faces. It uses cascades to detect edges like the nose, the ears etc. However, if there is a group of people and their faces are close to each other, the algorithm might not work that well as edges tend to overlap in a crowd. It might not detect individual faces. Therefore, in this work, we test both the Viola-Jones and the Kanade-Lucas-Tomasi algorithm for each image to find out which algorithm works best in which scenario.