BLUE EYE TECHNOLOGY

PRESENTED BY: M.SARANYAA P.PRIYANKA MUTHAYAMMAL ENGINEERING COLLEGE RASIPURAM EMAIL ID: Ponpriyanka1 !"#ai$.%o#

and to extract key information. (his information determine ABSTRACT: Is it possible to create a computer which can interact with us as we interact each other? For example imagine in a fine morning you walk on to your computer room and switch on your computer, and then it tells you Hey friend, good morning you seem to be a bad mood today. And then it opens your mailbox and shows you some of the mails and tries to cheer you. It seems to be a fiction, but it will be the life lead by !"# #$#%& in the 'ery near future. (he basic idea behind this technology is to gi'e the computer the human power. )e all ha'e some perceptual abilities. (hat is we can understand For each we others can feelings. example emotional, the user is the or then analy*ed to user+s physical, state, by

informational producti'e

which in turn can be used to help make more performing expected actions or by pro'iding expected information. For example, in future a lue #yes,enabled tele'ision could become acti'e when the user makes eye contact, at which point the user could then tell the tele'ision to -turn on-. (his paper is about the benefits and interconnection of 'arious parts in'ol'ed in the blue eye& technology.

understand ones emotional state by analy*ing his facial expression. If we add these perceptual abilities of human to computers would enable computers to work together with human beings as intimate partners. (he !"# #$#%& technology aims at creating computational machines that ha'e perceptual and sensory ability like those of human beings. lue #yes uses sensing technology to identify a user+s actions

add more capabilities to computers that will allow them to interact like humans, recogni*e human presents, . INTRODUCTION: !"# #$#% is a technology, which aims at creating computational machines that ha'e perceptual and sensory abilities like those of human beings. (he basic idea behind this technology is to gi'e computer human power. For example, we can understand humans. emotional state by his facial expressions. If we add these perceptual abilities to computers, we would enable them to work together with human beings as intimate partners. It pro'ides technical means for monitoring operator.s and recording human, condition. physiological #motions are important to the computing community. A non,in'asi'e way to obtain information about a user is through touch. 1eople use their computers to obtain, store and manipulate data. (he proposed method for obtaining user information through touch is 'ia a computer input de'ice, the mouse. (he computer determines the user+s emotional state by a simple touch. %ensors in the mouse sense physiological attributes, which are correlated to emotions using a correlation model. 2ouse is embedded with sensors that can sense the physiological attributes like (emperature ody 1ressure talk, listen, or e'en guess their feelings. EMOTION&COMPUTING:

It has the ability to gather information about you and interact with you through special techni/ues like facial recognition, speech recognition, etc. Human cognition depends primarily on the ability to percei'e, interpret, and integrate audio,'isuals and sensoring information. Adding extraordinary perceptual abilities to computers would enable computers to work together with human beings as intimate partners. 0esearchers are attempting to

1ulse 0ate (ouching %tyle etc.

through touch. :ne ob'ious place to put sensors is on the mouse. (hrough obser'ing normal surfing the web7, 4=> computer usage people of their spend total 3creating and editing documents and approximately de'ice.

(he computer determines the user.s emotional states from these inputs. 0osalind 1icard 345567 describes why emotions are important to the computing community. (here are two aspects of affecti'e computing8 gi'ing the computer the ability to detect emotions the and ability gi'ing to the computer express

computer time touching their input ecause of the incredible amount of time spent touching an input de'ice, we will explore the possibility of detecting emotion through touch. PAUL EKMAN'S (ACIAL

emotions. 9ot only are emotions crucial for rational decision making as 1icard describes, but emotion detection is an important step to an adapti'e computer system. An adapti'e, smart computer system has been dri'ing our efforts to detect a person.s emotional state. y matching a person.s emotional state and the context of the expressed emotion, o'er a period of time the person.s personality is being exhibited. (herefore, by gi'ing the computer a longitudinal understanding of the emotional state of its user, the computer could adapt a working style which fits with its user.s personality. (he result of this collaboration could increase producti'ity for the user. :ne way of gaining information from a user non,intrusi'ely is by 'ideo. ;ameras ha'e been used to detect a person.s emotional state 3<ohnson, 45557. )e ha'e explored gaining information In 1aul #kman.s Facial #xpression, we see a correlation between a person.s emotional state and a person.s physiological measurements. %elected works from #kman and others on measuring facial beha'iors describe #kman.s Facial Action ;oding %ystem 3#kman and 0osenberg, experiments measurements gal'anic skin 45567. :ne of his in'ol'ed participants pulse, 3?%07, E)PRESSION:

attached to de'ices to record certain including response

temperature, somatic mo'ement and

blood pressure. He then recorded the measurements as the participants were instructed to mimic facial expressions which corresponded to the six basic emotions. He defined the six basic emotions as anger, fear, sadness, disgust, @oy and surprise. %ix participants were trained to exhibit the facial expressions of the six basic emotions. exhibited )hile these each participant the expressions,

these four physiological measures are sufficient to determine reliably a person.s specific emotional state. ecause of our need to incorporate these measurements into a small, non, intrusi'e form, we will explore taking these measurements from the hand. (he amount of conducti'ity of the skin is be best as taken ob'ious that from or the fingers. )e the Howe'er, the other measures may not robust. in hypothesi*e changes

physiological changes associated with affect were assessed. (he measures taken were ?%0, heart rate, skin temperature and general somatic acti'ity 3?%A7. (hese data were then sub@ect to two analyses. For the first analysis, a multidimensional scaling 32A%7 procedure was used to

temperature of the finger are reliable for prediction of emotion. )e also hypothesi*e the ?%A can be measured by change in mo'ement in the computer mouse. MANUAL AND GA*E INPUT

determine the dimensionality of the data. (his analysis suggested that the physiological similarities and dissimilarities of the six emotional states fit within a four dimensional model. For the second analysis, a discriminant function analysis was used to determine the mathematic functions that would distinguish the six emotional 'ariables nonredundant states. made (his analysis significant, to the suggested that all four physiological contributions

CASCADED: A techni/ue in which pointing and selection were aided by ga*e tracking is designed. (he idea is to use ga*e to dynamically redefine 3warp7 the position of the pointing cursor to be at the 'icinity of the target. :nce it has been redefined, the user would need to make a small mo'ement to and click on the target, that is, achie'e 2anual Ac/uisition with ?a*e Initiated ;ursor 32A?I;7 pointing. (he beauty of 2A?I; is that it enables the hand and the eye to do what each does best. (he I 2+s

functions that distinguish the six states. 2oreo'er, these analyses indicate that

approach takes ad'antage of the eye to reduce the effort re/uired for manual pointing. (o the user, pointing is still done by the natural organ for manipulation, the hand. ut the cursor y

always appears in about at the right place needed, as if by magic. combining eye tracking and input technology, you get 2A?I; 1ointing. (wo specific 2A?I; pointing techni/ues are designed8 Li+,ra$ , )arps the cursor to e'ery new ob@ect the user looks at. ;ursor waits readily in the target area. (he user mo'es the cursor once he decides to ac/uire the target he is looking at. Con-,r.a/i.,, Aoes not wrap a cursor to a target until the manual input de'ice has been actuated. :nce it is actuated, the cursor is warped to the ga*e area. (he user would the steer the cursor manually towards the target to complete target ac/uisition. THE TECHNOLOGY: Artificial intelligence 3AI7 in'ol'es two basic ideas. First, it in'ol'es studying the thought processes of human beings. %econd, it deals with representing those processes 'ia machines 3like computers, robots, etc7. AI is beha'ior of a machine, which, if performed by a human being, would be called intelligent. It makes machines smarter and more useful, and is less

expensi'e than natural intelligence. 9atural language processing 39!17 refers to artificial intelligence methods of communicating with a computer in a natural language like #nglish. (he main ob@ecti'e of a 9!1 program is to understand input and initiate action. (he input words are scanned and matched against internally stored known words. Identification of a key word causes some action to be taken. In this way, one can communicate with the computer in one.s language. 9o special commands or computer language are re/uired. (here is no need to enter programs in special language forcreating,software. SPEECH&RECOGNITION:

which, in usedB a simple system may contain a minimum of three filters. (he more the number of filters used, the higher the probability of accurate recognition. capacitor 1resently, filters switched are used digital

because these can be custom,built in integrated circuit form. (hese are smaller and cheaper than acti'e filters using operational amplifiers. (he filter output is then fed to the AA; to translate the analogue signal into digital word. (he AA; samples the filter outputs many times a second. #ach sample represents different amplitude of the signal .#'enly spaced 'ertical lines represent the amplitude of the audio filter output at the instant of sampling. #ach 'alue is then con'erted to a binary number proportional to the amplitude of the sample. A central processor unit 3;1"7 controls the input circuits that are fed by the AA;%. A large 0A2 3random access memory7 stores all the digital 'alues in a buffer area. (his digital information, representing the spoken word, is now accessed by the ;1" to process it further. (he normal speech has a fre/uency range of CDD H* to 6 kH*. 0ecogni*ing a telephone call is more difficult as it has bandwidth limitation of >DD H* to>.> kH*. As explained earlier, the spoken words are

(he user speaks to the computer through a microphone,

processed by the filters and AA;s. (he binary representation of each of these words becomes a template or standard, against which the future words are compared. (hese templates are stored in the memory. :nce the storing process is completed, the system can go into its acti'e mode and is capable of identifying spoken words. As each word is spoken, it is con'erted into binary e/ui'alent and stored in 0A2. (he computer then starts searching and compares the binary input pattern with the templates. t is to be noted that e'en if the same speaker talks the same text, there are always slight 'ariations in amplitude or loudness of the signal, pitch, fre/uency difference, time gap, etc. Aue to this reason, there is ne'er a perfect match between the template and binary input word. (he 'alues of binary input words are subtracted from the corresponding 'alues in the templates. If both the 'alues are same, the difference is *ero and there is perfect match. If not, the subtraction produces some difference or error. (he smaller the error, the better the match. )hen the best match occurs, the word is identified and displayed on the screen or used in some other manner. (he search process takes a considerable amount of time, as the ;1" has to make many

comparisons before recognition occurs. (his necessitates use of 'ery high, speed processors. A large 0A2 is also re/uired as e'en though a spoken word may last only a few hundred milliseconds, but the same is translated into many thousands of digital words. It is important to note that alignment of words and templates are to be matched correctly in time, before computing the similarity score. (his process, termed as dynamic time warping, recogni*es that different speakers pronounce the same words at different speeds as well as elongate different parts of the same word. SIMPLE TRACKER (he %imple "ser Interest (racker or the %"I(:0 finds out the areas of interest of the user and pro'ides more information on these areas, which the user may access con'eniently. (he %"I(:0 monitors the user and keeps track of what document the user is reading and to which area in the document the ga*e is fixed. It then identifies the area and searches the entire computer for materials related to what the user is reading. )hen the user finishes reading the document he can find the USER INTEREST

additional information on his desktop, which he can access at his will.

parameters and an o'erall 'iew of the operating room are recorded. (his helps to reconstruct the course of operators. work and pro'ides data for long,term analysis. (his system consists of a mobile measuring de'ice and a central analytical system. (he mobile de'ice is integrated with luetooth module pro'iding wireless interface between sensors worn by the operator and the central unit. TOOLS&DE0ELOPED: In creating the hardware part of the AA" we built a de'elopment board, which enabled us to mount, connect and test 'arious peripheral de'ices cooperating with the the microcontroller. Auring

SYSTEM&O0ER0IE1: !"##$#% system pro'ides technical means for monitoring and recording important the operator.s is basic saccadic physiological parameters. (he most parameter acti'ity4, which enables the system to monitor the status of the operator.s 'isual attention of along the with 'isual head axis acceleration, which accompanies large displacement 3saccades larger than 4E degrees7. ;omplex industrial en'ironment can create a danger of exposing the operator to toxic substances, which can affect his cardiac, circulatory and pulmonary systems. (hus, on the grounds of lethysmographic signal taken from the forehead skin surface, the system computes heart beat rate and blood oxygenation. against abnormal (he or !"##$#% system checks abo'e parameters undesirable 'alues and triggers user, defined alarms when necessary. Fuite often in an emergency to situation themsel'es operators speak

implementation of the AA" we needed a piece of software to establish and test luetooth connections. )e therefore created a tool called lue Aentist. (he tool pro'ides support for controlling the currently connected managementGconnection management. (o test the possibilities and performance of the remaining parts of the 1ro@ect Hit 3computer, camera and database software7 we created lue;apture sources 3"% (he tool supports capturing 'ideo data from 'arious web,cam, industrial luetooth de'ice. Its functions are8 local de'ice

expressing their surprise or stating 'erbally the problem. (herefore, the operator.s 'oice, physiological

camera7 and storing the data in the 2% %F! %er'er database. Additionally, the application performs sound recording. After filtering and remo'ing insignificant fragments 3i.e. silence7 the audio data is stored in the database. Finally, the program plays the recorded audio'isual stream. )e used the software to measure database system performance and to optimi*e some of the %F! /ueries 3e.g. we replaced correlated %F! /ueries with cursor operations7. %ince all the components of the application ha'e been tested thoroughly they were reused in the final simple software, tool which for additionally <a** (he reduced testing time. )e also created a recording 2ultisensor measurements.

and

mouth

mo'ement.

)hen

monitoring pupils, the system uses a camera and two infrared light sources placed inside the product display. :ne light source is aligned with the camera+s focusB the other is slightly off axis. )hen the eye looks into the camera,aligned light, the pupil appears bright to the sensor, and the software registers the customer+s attention. (his is way it captures the person+s income and buying preferences. the leading retail lue #yes is outlets. y simply acti'ely been incorporated in some of C. lue #yes can be applied in the automobile industry. touching a computer input de'ice such as a mouse, the computer system is designed to be able to determine a person+s emotional state. For cars, it could be useful to help with critical decisions like8 -I know you want to get into the fast lane, but I+m afraid I can+t do that. $our too upset right now- and therefore assist in dri'ing safely. >. )e could see its use in 'ideo games where, it could gi'e indi'idual challenges to customers playing 'ideo games. (ypically targeting commercial business. (he integration of children+s toys, technologies and computers is enabling new play experiences that were not commercially feasible until recently. (he Intel 1lay FI>

program reads the data using a parallel port and writes it to a file.

APPLICATIONS: 4. lue #yes software makes

sense of what the cameras see to answer key /uestions for retailers, including, how many shoppers ignored a promotion? How many stopped? How long did they stay? Aid their faces register boredom or delight? How many reached for the item and put it in their shopping carts? lue #yes works by tracking pupil, eyebrow

;omputer 2icroscope, the 2eC;am with Fun Fair, and the ;omputer %ound 2orpher are commercially a'ailable smart toy products de'eloped by the Intel %mart (oy !ab in. :ne theme that is common across these 1;, connected toys is that users interact with them using a combination of 'isual, audible and tactile input G output modalities. J. (he familiar and useful come from things we recogni*e. 2any of our fa'orite things+ appearance communicate their useB they show the change in their 'alue though patina. As technologists we are now poised to imagine a world where computing ob@ects communicate with us in,situB where we are. )e use our looks, feelings, and actions to gi'e the computer the experience it needs to work with us. Heyboards and mice will not continue to dominate computer user interfaces. Heyboard input will be replaced in large measure by systems that know what we want and re/uire less explicit communication. %ensors are gaining fidelity and ubi/uity to record presence and actionsB sensors will notice when we enter a space, sit down, lie down, pump, iron, etc. E. ;urrent interfaces between computers and humans can present information 'i'idly, but ha'e no sense

of whether that information is e'er 'iewed or understood. In contrast, new real,time computer 'ision techni/ues for percei'ing people allows us to create -Face,responsi'e Aisplays- and -1ercepti'e #n'ironments-, which can sense and respond to users that 'iewing them. "sing stereo,'ision techni/ues, we are able to detect, track, and identify users robustly and in real time. (his information can make spoken language interface more robust, by selecting the acoustic information from a 'isually,locali*ed source. #n'ironments can become aware of how many people are present. CONCLUSION: !"# #$#% emphasi*es the foundations of the pro@ect , luetooth pro'ides communication mo'ements information. technology reliable whereas us (he !"# enable to and the mo'ements of the eyes. luetooth wireless the eye obtain #$#%

technology ensures a con'enient way of simplifying the life by pro'iding more delicate and user,friendly facilities in computing de'ices. 9ot only computational de'ices, in future, ordinary household de'ices , such as tele'ision, refrigerators, and o'ens , will do their @obs when we look at

them and speak to them. (he day is not far away that this technology will push its way into our household, making us more comfortable. (he sprit of science says 21, 3a., %on/in4,5 /o 5i-%o.,r an5 ,6p$or,7. (his process will ne'er end.