Abstract:Eye-Writer is an Eye Tracking device and a custom software. It is anapplication of eye tracking. Eye Tracking is a sensor technology to know whereyour eyes are focused. Individualssuffering from paralysis cannot move their bodies but they can still move theireyes. So Eye-Writer is an application which will help them to draw or writewithout using the rest of the body.
The original Eye-Writer was meant for amotionless head. The Eye-Writer which we have designed has a LED and cameramounted away from the head which allows slight motion.I.INTRODUCTION The Eye-Writer project is an ongoing, opensource, collaborative research effort to empower people who are suffering fromneuromuscular disorder and injury with creative technology.
The Eye-Writeritself is a pair of low-costeye-tracking glasses and custom software that allows artists and graffitiwriters with paralysis resulting from Amyotrophic Lateral Sclerosis, as well asother neuromuscular disorders and injuries, to draw using only their eyes. The original design featured a pair ofglasses, but we have a new design, which we’ve called “eye-writer2.0” which improves the accuracy of the device, and allows people whoseheads are moving slightly to also use an eye tracker. The original eye-writer,designed for a paralyzed Graffiti artist TEMPT1, was designed to be worn on acompletely motionless head. The 2.0 design, which uses a camera and LED systemmounted away from the head, can be used by people whose heads are movingslightly, such as MS patients, and people who wear glasses, etc. Eye tracking is the process of measuring either the point of gaze(where one is looking) or the motion of an eye relative to the head.
An eye tracker is a device for measuring eye positions and eye movement. Most modern eyetrackers utilize near-infrared technology along with a high-resolution camera(or other optical sensor) to track gaze direction. The underlying concept,commonly referred to as PCCR involves thecamera tracking the pupil center, and where light reflects from thecornea. Keywords-: PCCR-Pupil center corneal reflection II.LITERATURE SURVEY Edmund Huey builtan early eye tracker, using a sort of contact lens with a hole for the pupil.
The lens was connected to analuminium pointer that moved in response to the movement of the eye. Hueystudied and quantified regressions (only a small proportion of saccades areregressions), and show that some words in a sentence are not fixated. 1 The first non-intrusive eyetrackers were built by Guy Thomas Buswell in Chicago, using beams of light thatwere reflected on the eye and then recording them on film. Buswell madesystematic studies into reading andpicture viewing. 3 In the 1950s, Alfred L. Yarbus did important eye tracking researchand his 1967 book is very highly quoted. He showed the task given to a subjecthas a very large influence on the subject’s eye movement.
He also wrote aboutthe relation between fixations and interest. 5 In the 1970s, eye trackingresearch expanded rapidly, particularly reading research. A good overview ofthe research in this period is given by Rayner. 1 In 1980, Just and Carpenterformulated the influential Strongeye-mind Hypothesis, the hypothesis that “there is no appreciable lagbetween what is fixated and what is processed”.
If this hypothesis iscorrect, then when a subject looks at a word or object, he or she also thinksabout (process cognitively), and for exactly as long as the recorded fixation.The hypothesis is often taken for granted by beginning eye tracker researchers.2 During the 1980s, theeye-mind hypothesis was often questioned in light of covert attention, theattention to something that one is not looking at, which people often do. Ifcovert attention is common during eye tracking recordings, the resulting scanpath and fixation patterns would often show not where our attention has been,but only where the eye has been looking, and so eye tracking would not indicatecognitive processing. According to Hoffman, currentconsensus is that visual attention is always slightly (100 to 250 ms) ahead ofthe eye.
But as soon as attention moves to a new position, the eyes will wantto follow. 3 We still cannot infer specific cognitiveprocesses directly from a fixation on a particular object in a scene. For instance, a fixation on a face ina picture may indicate recognition, liking, dislike, puzzlement etc. Thereforeeye tracking is often coupled with other methodologies, such as introspectiveverbal protocols. 5 III.
EYE TRACKING The term eye tracking here as it is use here means estimation of direction of users gaze. In most casesestimation of gaze direction means identification of the object upon which thegaze falls. Theaccuracy of eye movement measurement heavily relies on a clear demarcation ofthe pupil and detection of corneal reflection. The visible spectrum is likelyto generate uncontrolled specular reflection, while illuminating the eye withinfrared light – which is not perceivable by the human eye – renders thedemarcation of the pupil and the iris an easy task – while the light directlyenters the pupil, it just reflects from the iris.
This means that a clearreflection is generated (with little noise) and can, therefore be followed withease. Near-infrared light isdirected toward the center of the eyes (the pupils) causing visible reflectionsin the cornea (the outer-most optical element of the eye), which are tracked bya camera.Tracker Types Eyetrackers measure rotations of the eye in one of several ways, but principallythey fall into three categories: a special contact lens with an embedded mirroror magnetic field sensor. video based eye tracker: optical method for measuringeye motion(IR rays). Video camera senses these rays.
(Non-invasive and lesscost). electric potentials measured with electrodes placed around the eyes.This steady electric potential field, which can also be detected in totaldarkness and if the eyes are closed. In this third method, electric signal that can be derived using twopairs of contact electrodes placed on the skin around one eye iscalled Electro oculogram (EOG). Analysing the changes in the eye movementby reading the EOG.
Horizontal and vertical movement components. Due topotential drifts and variable relations between the EOG signal amplitudes andthe saccade sizes make it challenging to use EOG for measuring slow eyemovement and detecting gaze direction. Technologies andtechniques Technologies andtechniques: The most widely used current designs are video-based eye trackers.Most modern eye-trackers use contrast to locate the center of the pupil anduse infrared and near-infrared non-collimated light tocreate a corneal reflection.
Two general types of eye tracking techniques areused based on the location of the illumination source with respect to theoptics: Bright Pupil Dark Pupil. Bright pupil iseffective in the indoors where there is a little IR interference duringmonitoring. Eye movement is typically divided into fixations and saccades ,when the eye gaze pauses in a certain position, and when it moves to anotherposition, respectively.
The resulting series of fixations and saccades iscalled a scanpath . Most information fromthe eye is made available during a fixation, but not during a saccade.Scanpaths are useful for analyzing cognitive intent, interest, and salience.
Other biological factors (some as simple as gender) may affect the scanpath. IV.PARAMETERSi) Pupilsize / dilation An increasein pupil size is referred to as pupil dilation, and a decrease in size iscalled pupil constriction. Pupil size primarily responds to changes in light(ambient light) or stimulus material (e.g. video stimulus). ii) Distanceto the screenAlong with pupil size, eye trackers also measure thedistance to the screen and the relative position of the respondent.
Leaningforwards or backwards in front of a remote device is tracked directly and canreflect approach-avoidancebehavior.iii)Ocular VergenceMost eye trackers measure the positions of the leftand right eyes independently. This allows the extraction of vergence,i.
e., whether left and right eyes move together or apart from each other. Thisphenomenon is just a natural consequence of focusing near and far. Divergenceoften happens when our mind drifts away, when losing focus or concentration.iv) BlinksEye tracking can also provide essential informationon cognitive workload bymonitoring blinks. Cognitively demanding tasks can be associated with delays inblinks, the so-called attentional blink.
However, manyother insights can be derived from blinks. A very low frequency of blinks, forexample, is usually associated with higher levels of concentration. A ratherhigh frequency is indicative of drowsiness and lower levels of focus and concentration.V.
LEARNING AN END-TO-END MODEL Working of the model is divided into threebasic steps. First, making LED illuminators for the sides of the screen and thecenter. From a technical perspective, the system works by strobing 3 IR illuminators every frame. On even frames,it uses the center illuminator (located around the camera lens) and on oddframes it uses the 2 side illuminators. On even frames, the pupil appearsbright, since the IR light is actually bouncing off the back of your eye, likered eye effect. On odd frames, our pupil appears dark.
The difference betweenthe two allows us to isolate and track the pupil in realtime. Additionally, theglints (reflections of the IR illuminators) of the dark frame are tracked, andthese, plus the info on the pupil, is calibrated to screen position using aleast squares fitting process for an equation that provides a mapping ofglint/pupil position to screen position. In particular, an infrared light sourceilluminating the eye of a wearer at a relatively high intensity may generatespecular reflections off the wearer’s cornea, also called ‘glints’. The glintscan be imaged with an infrared camera. When the infrared light sources areilluminated at a relatively lower intensity, determination of the pupillocation is possible. Glints, in combination with the pupil location, may beused to accurately determine the gaze direction and eye rotation.
Thedetermined gaze direction could be used in various eye-tracking applications.By controlling the light sources to change intensity levels and by combiningmultiple images of the eye to incorporate multiple glint locations with thepupil location, eye tracking can be performed with better accuracy and withfewer light sources. Second, hacking the PS3 eye camera toget the vertical sync (when the frame of video is being taken) and to make itsensitive to IR. Third, programming and building thearduino / circuit to control the blinking. Finally, setting up the base for thesystem and go through the basics of the software. VI.
RESULTAIR LED BSoftware Results i) Using EyeWriter Software -Catch MeIt is one partof the EyeWriter project. When the person stares at the box called as the’Catch Me Box’, the box will turn green. When the box is fully green then thebox is caught and it will appear somewhere else. We can keep catching the boxesto test the eye-tracking calibration.
. ii)Using EyeWriter Software- Typing Avirtual keyboard is visible on the screen. We can stare at whichever key thatwe wish to press. After staring, the key colour will turn green and then flashblue. When the key flashes blue, it has been pressed.
Whatever is typed can beseen at the top of the screen. VII. FUTURE SCOPE The project will inspire the formation ofsocial networks, broadening the scope of research into its potency not only asa tool for expression by drawing, but also in the fields of medicine andwelfare.Anyonecan build and use the Eye-Writer by utilizing a combination of computers andother familiar instruments, and installing software that is available for free.It is probably the most versatile device for drawing with the eyes. VIII.
CONCLUSIONThus Eye-Writer is aboon to the disabled people suffering from neuromuscular diseases. It’s cost islow which is affordable even to the common man. It improves the accuracy of the device and allowspeople whose heads are moving even slightly to use an Eye-Writer, unlike theprevious version where eye tracking glasses were used. Itis not a bulky setup as the person using Eye-Writer will not have to wear theglasses. IX.
REFERENCES 1T. Baltrusaitis, P. Robinson, and L.-P. Morency. Constrained local neuralfields for robust facial landmark detection in the wild. In Com-puter VisionWorkshops(ICCVW),2013IEEE InternationalConfer- ence on, pages 354–361. IEEE,2013.
2A.Vetrivel et al, International Journal of Computer Science andMobile Computing, Vol.5 Issue.3, pg. 423-430 , March- 2016 3 D. Beymer,D. Russell and P.
Orton An eye tracking study ofhow font size and type influence online reading, Proceedings of the 22ndBritish HCI Group Annual Conference on People and Computers: Culture,Creativity, Interaction – Volume 2, Pages 15-18, 2008. 4Z Hao, and Q Lei, “Vision-based Interface: Using Face and Eye Blinking Trackingwith Camara”, Second International Symposium on Intelligent Information Technology Applications, pp 306-310., 2008.5N H Cuong, and H T Hoang, “Eye Gaze Detection with a Single WebCAM Based on Geometry Features Extraction”, 2010 11th International Conferenceon Control, Automation, Robotics and vision, Singapore, pp 2507-2512., 7-10thDecember, 2010.6L Lu, Y Yang, L Wang, and B Tang, “Eye Location Based on Gray Projection”, 2009 Third International Symposium on Intelligent InformationTechnologyApplication, pp58-60, 2009.
7 Z Hao, and Q Lei, “Vision-based Interface: Using Face and Eye BlinkingTracking with Camara”, Second International Symposium on Intelligent Information Technology Applications, pp 306-310, 2008.8 Hari Singh and Dr. Jaswinder Singh, “Human Eye Tracking and RelatedIssues: A Review”, International Journal ofScientific and Research Publications, Volume 2, Issue 9, ISSN 2250-3153, September 2012 9 A. Vetriveland T.
Pandiyavathi, “Tracking Eye Movement by characterizing a sequencethrough hierarchical clustering”, A.Vetrivel et al, International Journal of Computer Science and Mobile Computing, Vol.5 Issue.3, pg. 423-430, March- 2016