Pupil detection algorithm based on feature extraction for eye gaze

Exact real-time pupil tracking is an important step in a live eye gaze. Since pupil centre is a base point's reference, exact eye centre localization is essential for many applications, such as face recognition and eye gaze estimation. A new method proposed in this paper is to extract pupil eye features exactly within different intensity levels of eye images, mostly with localization of determined interest objects and where the human is looking. As application area, the eye localization in the frame of a video-sequence has been chosen with continuing in iris and pupil detection. This method is fast and has a high degree of accuracy to determine the eye gaze after the pupil is detected because it depends on the features in the human eye. The intensity increases in the centre of the eye, and these features are extracted using a multistage algorithm. Firstly, the feature-based algorithm detected the location of the face region and will be used to detect the pupil on the face. Secondly, use the pupil to determine where humans are looking. Proposed algorithm experiments results to the faces show that they are not only robust, but also relatively efficient. It has been tested on the Mackup database, which contains 500 images belonging to 108 females from the Asian region with different indoor illuminations. The image from a real-world indoor setting with lenses, and images from the Internet. The experiment results show 99%. This ratio shows very good robustness and accuracy.