Object Recognition and Selection Method by Gaze Tracking and SURF Algorithm

The goal of this research is to make a robust camera vision system which can help those with disabilities of their hands and feet to select and control home appliances. The proposed method operates by object recognition and awareness of interest by gaze tracking. Our research is novel in the following three ways compared to previous research. First, in order to track the gaze position accurately, we designed a wearable eyeglasses type device for capturing the eye image using a near-infrared (NIR) camera and illuminators. Second, in order to achieve object recognition in the frontal view, which represents the facial gaze position in the real world, an additional wide view camera is attached to the wearable device. Third, for the rapid feature extraction of the objects in the wide view camera, we use the speeded-up robust features (SURF) algorithm, which is robust to deformations such as image rotation, scale changes, and occlusions. The experimental results showed that we obtained a gaze tracking error of only 1.98 degrees and successful matching results of object recognition.