Unconstrained Face Detection of Multiple Humans Present in the Video

Abstract

To capture a stable picture through the digital camera is a challenging task in computer vision. The While identifying facial features such as misalignment, a parasitic light effect and a change in object position are the errors found in image processing. These errors get aggregated with images and cumulatively create distortion in the output video, which makes facial feature recognition more complicated in the video. In this paper, a solutions for unconstrained facial detection from digital image processing has been proposed, which fulfilled two requirements; first is a reliable method to extract the facial feature of the humans from a video and second is the estimation of 3D-image of human from the motion video. To meet these requirements, we develop a hybrid estimation method that combines the feature selection and extraction of facial features of the human from the video. Here we have extended the estimation of 2D to 3D unconstrained facial feature recognition. In the results, we found that the object in images is detected and we are able to develop the 3D sketch of human from the video. Further to validate the robustness of the proposed method, we have performed comprehensive testing on the huge dataset. The output of testing shows that the proposed method would be better to identify multiple facial features.