preview

Gaze Estimation Using A Low Cost Webcam

Good Essays

GAZE ESTIMATION USING A LOW COST WEBCAM Abhishek Kuntal and Tanya Jha New York University Abstract In this project we develop an integrated vision system which reliably detects Human Gaze using a low cost webcam. We detect the user face using Haar-Like features and then use neural networks to estimate the gaze point. KEYWORDS Computer Vision, tracking, head pose, gaze tracking, neural networks. 1. INTRODUCTION Object recognition is a process for identifying a specific object in a digital image or video. Object recognition algorithms rely on matching, learning, or pattern recognition algorithms using appearance-based or feature-based techniques. Visual Perception according to Wikipedia is the ability to understand and interpret the surrounding environment by processing information that is contained in visible light. Visual recognition services like IBM Watson Visual Recognition Service etc. allows users to understand the contents of an image or video frame and to give user the answer of the question “What is in this image?” thereby improving our visual perception of the scene. There has been rapid development in the field for eye tracking. The traditional methods in eye tracking required systems to be intrusive, i.e. they require the user’s head to be fixed or mounted on an equipment to restrict movement but now systems are evolved to the point where the user can freely move. In our method we implement gaze tracking using a simple webcam. The simplest application of gaze

Get Access