Automatic Eye Blink Tracking and Detection in an Image Sequence Tarun Dhar Diwan 1 ,Rajesh Tiwari 2 1 Computer Science & Engineering Dept. Dr.C.V.Raman University Bilaspur, C.G 2 Computer Science & Engineering Dept. Shri Shankaracharya College, of Engg. & Tech. Bhilai. C.G. Abstract-Human face, the most active and healthy part of human body and Eyes are one of the most complex features of it. It may be used to reduce some of their critical life complexities. Eye blinking is one of the prominent areas to solve many real world problems. The process of blink detection consists of two phases. These are eye tracking followed by detection of blink. The work that has been carried out for eye tracking only is not suitable for eye blink detection. Therefore some approaches had been proposed for eye tracking along with eyes blink detection. Keyword:- image sequence, facial signs, eyes movements, blink detection, template image, template accuracy, face size. 1. INTRODUCTION There has been a growing interest in the field of facial expression recognition especially in the last two decades. Human-Computer Interaction (HCI) systems may also be Enriched by a facial feature tracker. We propose a robust and accurate method of tracking the eye locations, detecting the eye states, and estimating the eye parameters for each frame in a sequence. Our purpose is to develop an eye tracker [4, 5] which is robust to blinking, and which accurately recovers the eye parameters. Initialized the eye template in the first frame, the eye’s inner corner can be tracked accurately by feature point tracking. We assume the outer corners of eyes are in the line connecting two inner corners of eyes. 2. CHALLENGES 1. Identifying and tracking the head location. 2. Identifying and tracking the location of the eyes. 3. Detecting blinks of the eyes. 4. Being able to process the information in real-time using a moderately priced processor that will be running other applications in the foreground. 3. PROPOSED METHODOLOGY To make an automatic eye blink detection system for a video, we require extracting and tracking the eyes movements in an image sequence. For making such type of system, we have included three distinct phases: First, eyes are detected in each frame of a video. Motion analysis[1,2] techniques are used in this stage, followed by online creation of a template of the open eye to be used for the subsequent tracking and template matching that is carried out at each frame. A flow chart depicting the main stages of the system is shown in Figure 1.1. Figure1.1: Overview of the main stages in the system. 3.1 Eye Tracking This measure is computed at each frame using the following formula: Where f(x, y) is the brightness of the video frame at the point (x, y), and fu, v are the average value of the video frame in the current search region, t(x, y) is the brightness of the template image at the point (x, y), and t is the average value of the template image[3,6].The result of this computation is a correlation score between -1 and 1 that indicates the similarity between the open eye template and all points in the search region of the video frame. Scores closer to 0 indicate a low level of similarity, while scores closer to 1 indicate a probable match for the open eye template. A B C D Figure1.2 : Motion analysis phase: (A) User at frame f. (B) User at frame f + 1, having just blinked. (C) Initial difference of the two frames f and f+1. (D) Difference image used to locate the eyes after performing the Opening operation. Tarun Dhar Diwan et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 2 (5) , 2011, 2348-2349 2348