Page 1 of 10
`
`SAMSUNG EXHIBIT 1005
`Samsung v. Image Processing Techs.
`
`

`

`& IEEE Conference on
`INTELLIGENT
`TRANSPORTATION SYSTEMS
`
`GER RES finpany
`oER. REG. LIBRARY
`
`1] i oe
`tet
`:
`
`U.C. DAVIS
`
`
`
`Boston Park Plaza Hotel
`Boston, Massachusetts
`November 9-12, 1997
`
` 005
`
`Page 2 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 2 of 10
`
`

`

`97TH8331
`IEEE Catalog Number
`ISBN: 0-7803-4269-0 (Softbound)
`ISBN: 0-7803-4271-2 (Microfiche)
`ISBN: 0-7803-4271-2 (CD-Rom)
`Library of Congress:
`97-80147
`
`Copyright and Reprint Permission
`Abstracting is permitted with credit to the source.Libraries are permittedto photocopybey
`the limit of U.S. copyright law for private use of patrons those articles in this volume that cat ,
`a codeat the bottomofthefirst page, provided the per-copyfee indicated in the code is sai
`through Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923. For other . J
`ing, reprint or republication permission, write to IEEE Copyrights Manager, IEEE Service Center
`445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331.All rights reserved. Copyright ©199
`by the Institute of Electrical and Electronics Engineers, Inc,
`°
`’
`
`ond
`
`IEEE Catalog Number: 97TH833 1
`Library of Congress: 97-80147
`ISBN:0-7803-4269-0
`
`SAMSUNG EXHIBIT 1005
`Page 3 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 3 of 10
`
`

`

`Welcome from the Conference General Chair
`welcome to the 1997 IEEE Conference onIntelligent Transportation
`Systems (TSC'97).
`Hosted by 17 IEEE societies and supported by a number ofinterna-
`tional organizations, ITSC'97 ts thefirst of a newseries focusing on
`the broad technology aspects of Intelligent Transportation Systems
`(ITS). ITSC'97 incorporates the very successful Vehicle Navigation and
`Information System (VNIS) andIntelligent Vehicle Systems (IVS) con-
`ferencesthat bave been held by individual IEEEsocieties in past
`ars. In the technical program onthe following pages, you willfind
`that ITSC‘97 includes a broad range of important andtimely techni-
`cal topics now active in various ITS projects.
`The Conference Committee and the many additional individuals who
`pave arranged ITSC'97 are excited aboutthe technical papers that
`will be presented, All papers received in response to the I 996 Cailfor
`Papers have been peer-reviewed. We believe you will agree their quali-
`ty is excellent. These papers, plus several sessions arranged around
`invited papers, bave been organized into five parallel tracks of ses-
`sions running the full three days of the conference. One highlight ts
`a series of sessions devoted to the rapidly evolving area ofApplied
`ComputerVision.
`The conference also features three plenary sessions—one each on
`the three days of the technical program. In the opening plenary on
`Monday, Mr. Richard Weiland andMr. Peter Zuk, well-
`recognized leaders in current ITS programs, provide someof their
`perspectives on progress in developing critically needed ITS standards.
`Onthe secondday, four internationally knownspeakers will provide
`their perspectives on four keyITS technologies—navigation andposi-
`tion location, communication, automated vehicle control, and in-
`vebicle information systems. In the closing plenary on the third day,
`we invited Dr. Kan Chen, one of the early IVHS leadersto provide his
`views on the past, present and future of ITS. Our banquet speaker,
`Mr. Hans-Georg Metzler, Vice President of Research for Daimler
`Benz, comes to us from Stuttgart, Germany and promises an informa-
`tive presentation on evolving intelligent vebicle technology and relat-
`ed issues. We hope you won't miss any of these excellent presentations.
`Once again, welcome. We trust ITSC'97 will be a stimulating and tech-
`nically rewarding conference for you.
`
`IEEE Conference on Intelligent Transportation Systems
`
`a L
`
`yle Saxton
`Conference General Chair
`
`CJ
`
`IEEE
`
`SAMSUNG EXHIBIT 1005 iii
`Page 4 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 4 of 10
`
`

`

`EYE-TRACKING FOR DETECTION OF DRIVER FATIGUE
`
`Martin Eriksson
`
`Nikolaos P. Papanikolopoulos
`
`Artificial
`
`Intelligence, Robotics, and Vision Laboratory
`
`Department of Computer Science, University of Minnesota,
`
`Minneapolis, MN 55455
`
`E-mail: {eriksson, npapas}@cs.umn.edu
`
`Keywords: driver
`Abstract
`
`SAMSUNG EXHIBIT 1005
`0-7803-4267.898725 P1.00 © 1998
`
`template matching.
`fatigue, eye-tracking,
`[3]. There
`identification and database retrieval
`are
`also many
`real-time
`systems,
`being
`developed
`in order
`to
`track
`face
`features
`[15,13,17].<~These kinds of real-time systems
`generally consist of three components:
`a) Localization of the eyes (in the first frame),
`b) Tracking the eyes in the subsequent frames,
`c) Detection of failure in tracking.
`
`locates
`In this paper, we describe a system that
`and tracks the eyes of a driver. The purpose of
`such a systemis to perform detection of driver
`fatigue. By mounting a small camera inside the
`car, we can monitor the face of the driver and
`look for eye-movements which indicate that the
`driver is no longer in condition to drive. In such
`a case, a warning signal should be issued. This
`paper describes howto find and track the eyes.
`the
`Localization of the eyes involves looking at
`We also describe a method that can determine if
`entire image of the face and determining the
`the
`eyes are open or closed. The primary
`eye-envelopes
`(the
`areas
`around
`the
`eyes).
`criterion for
`the successful
`implementation of
`During
`tracking
`in
`subsequent
`frames,
`the
`this system is
`that
`it must be highly non-
`
`search-space the—areais reduced to
`
`
`
`intrusive. The system should start when the
`corresponding
`to
`the
`eye-envelopes
`in_
`the
`ignition is turned on without having the driver
`current
`frame. This tracking can be done at
`Initiate the system. Nor should the driver be
`relatively low computational effort,
`since the
`responsible for providing any feedback to the
`search-space is significantly reduced. In order to
`system. The system must also operate regardless
`detect failure in the tracking, general constraints
`of the texture and the color of the face. It must
`such as distance between the eyes and horizontal
`also be able to handle diverse conditions, such as
`alignment of the two eyes can be used.
`changesin light, shadows, reflections, etc.
`the next
`This paper is organized as follows: In
`section, we describe some of the previous work
`in
`this
`area. Afterwards, we describe
`the
`
`experimental how the=systemsetup, and
`
`
`INTRODUCTION
`operates. Then, we proceed to the description of
`the algorithm for
`the detection of
`fatigue.
`Driver fatigue is an important factor in a large
`Finally, we present results and future work,
`number of accidents. Lowering the number of
`fatigue-related accidents would not only save
`PREVIOUS WORK
`society a significant amount financially, but also
`for
`proposed
`Many methods
`have
`been
`reduce personal suffering. We believe that by
`
`
`localizing facial_—_features in images
`
`monitoring the eyes,
`the symptoms of driver
`[2,4,5,6,8,10,11,12,19]. These methods
`can
`fatigue in our proposed system can be detected
`roughly two_categories:be divided into
`
`
`
`
`early enough to avoid several of these accidents.
`Template-based matching and Feature-based
`Detection of
`fatigue involves
`a
`sequence of
`matching. These techniques are compared by
`images of
`a
`face, and observation of eye-
`Poggio and Brunelli [1]. One popular template-
`movements and blink patterns.
`matching
`technique
`for
`extraction
`of
`face
`The analysis of face images is a popular research
`features is to use deformable templates
`(5.16),
`area with applications such as face recognition,
`which are similar to the active snakes introduced
`virtual tools and handicap aids [9,14], human
`by Kass [7],
`in the sense that they apply energy
`
`
`
`
`SAMSUNG EXHIBIT 1005
`Page 5 of 10
`
`

`

`tracking, we also perform the detection of
`fatigue. At
`this point, we count consecutive
`frames during which the eyes are closed. If this
`numbergets too large, we issue a warning signal.
`Experimental setup
`a camera
`The final
`system will consist of
`pointing at
`the driver. The camera is to be
`mounted on the dashboard inside the vehicle.
`For the system we are developing, the camera is
`Stationary and will not adjust
`its position or
`zoom during operation. For experimentation, we
`are using a JVC color video camera, sending the
`frames
`to
`a Silicon Graphics
`Indigo. The
`grabbed frames are represented in RGB-space
`with 8-bit pixels (256 colors). We do not use any
`specialized hardware for image processing.
`
`Localization of the eyes
`We localize the eyes in a top-down manner,
`reducing the search-space at each step. The steps
`are:
`
`1. Localization of the face.
`2. Computation of the vertical
`eyes.
`3. Computation of the exact
`eyes,
`4. Estimation of the position of the iris.
`
`location of the
`
`location of
`
`the
`
`Localization of the face. Since the face of a
`driver is symmetric, we use a symmetry-based
`approach, similar to [18]. We found that in order
`for this method to work,
`it
`is enough to use a
`subsampled, gray-scale version of the image. A
`symmetry-value is
`then computed for every
`
`‘s
`
`segtrtts
`
`‘{
`7
`
`oa EE
`Ee
`cal
`Pe
`redtia
`
`eyes
`ers
`
`
`
`.
`on
`
`i
`rk
`
`|
`t
`
`‘
`
`Mk
`
`-
`
`cold
`
`.F
`
`“ar
`;
`
`P
`-
`,
`«(TD ips
`
`=.
`
`eye
`
`7
`als
`
`nice
`
`e
`.
`
`;
`Pas
`
`pe
`
`af
`hues
`
`een
`
`iS ae
`F ey
`a ca
`
`t
`
`=
`
`the computation of
`minimization based on
`image-forces.
`In feature-based matching,
`the
`system uses knowledge about some geometrical
`constraints. For example, a face has two eyes,
`one mouth and one nose in specific relative
`locations.
`
`Oneinteresting application for face recognition
`was developed by Stringa [12]. He used the
`observation that the eyes are regions of rapidly
`changing intensity. We use a similar approach
`on a reduced version of
`the image. Another
`approach, developed by Steifelhagen et al. [13]
`uses connected regions in order to extract
`the
`dark disks corresponding to the pupils. Rather
`than looking for the pupils, we used the fact that
`the entire eye-regions
`are darker
`than their
`surroundings,
`again allowing us
`to use
`the
`reduced image in order to extract these rough
`regions at a reduced computational cost. The
`systems described in [15] and [13] use color
`information in order to extract the head from
`the background.
`In order to avoid dependence
`on a fairly colorless background, we decided to
`again use the reduced image and localize the
`symmetry axis [18]. Since the driver will be
`looking almost straight ahead,
`there will be a
`well defined vertical symmetry line between the
`eyes,
`
`templates have been described
`Many different
`for finding the shape of an eye. Xie et al. [16]
`developed a deformable template consisting of
`10 cost equations, based on image intensity,
`image gradient
`and
`internal
`forces of
`the
`template. Since we are greatly concerned about
`computational speed, we decided to use only the
`two cost equations dealing with image intensity.
`Once the eyes are found, the search-space in the
`subsequent
`frames
`is
`limited
`to
`the
`area
`surrounding
`the
`found
`eye-regions.
`In the
`system by Stiefelhagen et al., the darkest pixel
`(whichis likely to be a pixel inside the pupil) is
`used for tracking, allowing high computational
`speed. Another approach [5] is to perform edge-
`detection on the region of interest and then track
`the region with a high concentration of edges.
`
`THE SYSTEM
`Whenthe system starts, frames are continuously
`fed from the camera to the computer. We use the
`initial
`frame
`in order
`to
`localize
`the eye-
`positions. Once the eyes are localized, we start
`the tracking process by using information in
`previous frames in order to achieve localization
`in subsequent frames. During tracking, error-
`detection is performed in order to recover from
`possible tracking failure. When a tracking failure
`is detected,
`the eyes are relocalized. During
`
`Figure 1. The symmetry histogram.
`
`SAMSUNG EXHIBIT 1005 315
`Page 6 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 6 of 10
`
`

`

` LU
`
`t
`
`S(x) = y >[abs(U(x.y ~—w)~I(x,y+ w))].
`
`wel
`
`y=l
`
`Figure 2. The original image, the edges and the histogram of projected edges.
`In
`Find the exact
`location of the eyes.
`pixel-column in the reduced image. If the image
`the
`order
`to
`find
`the
`eye-regions
`given
`is represented as
`/(x,y) then the symmetry-
`that
`proceeding processing, we rely on the fact
`value for a pixel-column is given by
`the eyes correspond to intensity-valleys in the
`ysize
`image. Given that, we can threshold the image
`and then extract the connected regions. We used
`a raster-scan algorithm on the reduced image in
`order to extract
`these regions.
`In general, our
`raster-scan algorithm found 4-5
`regions.
`In
`order
`to
`resolve which
`of
`these
`regions
`correspond to the eyes, we use the information
`in H(y). We try to find a peak corresponding to
`a row in the image with two connected regions
`on. The three best peaks in A(y) are considered.
`Wealso use general constraints, such that both
`eyes must be located "fairly close" to the center
`of the face,
`
`where k
`S(x) is computed for x €[k,xsize—k]
`is the maximum distance from the pixel-column
`that symmetry is measured, and xsize
`is
`the
`width of the image. The x corresponding to the
`lowest value of S(x) is the center of the face. The
`result from this process is shown in Figure 1.
`The search-space is now limited to the area
`around this line, which reduces the probability
`of having distracting features in the background.
`Computation of the vertical
`location of
`the eyes. As suggested by Stringa [12], we use
`the observation that eye-regions correspond to
`regions of high spatial frequency. Again weare
`working with the reduced image. Wecreate the
`gradient-map, G(x,y), by
`applying
`an
`edge
`detection algorithm on the reduced image. Any
`edge-detection method
`could
`be
`used. We
`choose to use a very simple and fast method
`called pixel-differentiation, that assigns G(x,y) =
`(x,y) - I(x-1,y). We selected this method since it
`does not
`involve any convolution. G(x,y) will
`now reveal areas of high spatial frequency. By
`projecting G(x,y) onto its vertical axis, we get a
`histogram A(y):
`Wize
`
`H(y) = .GGy).
`
`Since both eyes are likely to be positioned at the
`same row, H(y) will have a strong peak on that
`row. However,
`in order
`to reduce the risk of
`error, we consider the best three peaks in H(y)
`for further search rather than just the maximum.
`This process is illustrated in Figure 2.
`
`to find a
`The difficulty with this method is
`threshold that will generate the correct eye-
`regions. We used a method called adaptive
`thresholding [13]
`that
`starts out with a low
`threshold. If two good eye-regions are found,
`that threshold is stored, and used the next
`time
`the eyes have to be localized. If no good eye-
`regions are
`found,
`the
`system automatically
`attempts with a higher
`threshold,
`until
`the
`regions are found.
`Estimation of the position of the iris. Once
`the eye-regions are localized, we can apply a
`very simple template in orderto localize the iris.
`
`al
`
`Figure 3. The eye-template.
`two
`We constructed a template consisting of
`circles, one inside the other. A good match
`
`SAMSUNG EXHIBIT 1005
`Page 7 of 10
`
`A
`
`SAMSUNG EXHIBIT 1005
`Page 7 of 10
`
`

`

`
`
`Figure 4, Snapshots from the system during tracking. Note that in the second image, the system
`missed tracking of one eye.
`
`in many dark pixels in the area
`would result
`inside the inner circle, and many bright pixels in
`the area between the twocircles. The template is
`shown in Figure 3. This match occurs when the
`inner circle is centered on the iris and the
`outside circle covers the sclera.
`
`The match M(al,a2) is computed as
`M(al,a2)= Si l(p.q)- Si 1(p,4).
`(p,q)eal
`(p.q)ea2
`
`A low value for M(al,a2) corresponds to a good
`match. The template is matched across
`the
`predicted eye-region, and the best match is
`reported.
`
`Tracking the eyes
`the darkest
`We track the eye by looking for
`In order to
`pixel in the predicted region [13].
`recover from tracking errors, we make sure that
`none of the geometrical constraints are violated.
`If they are, we relocalize the eyes in the next
`frame. To find the best match for
`the eye-
`template, we initially center
`it at
`the darkest
`
`in
`pixel, and then perform a gradient descent
`order to find a local minimum. In Figure 4, we
`show a few snapshots during tracking.
`
`DETECTION OF FATIGUE
`Asthe driver becomes more fatigued, we expect
`the
`eye-blinks to last
`longer. We
`count
`the
`number of consecutive frames that the eyes are
`closed in order to decide the condition of the
`driver. For
`this, we need a robust way to
`determine if the eyes are open or closed; so we
`developed a method that looks at the horizontal
`histogram across the pupil.
`During initialization (the first frames after the
`driver has settled down), an average match over a
`numberof frames is calculated. When the match
`in a frame is
`“significantly” lower than the
`average, we call that frame a closed frame. If the
`match is close to the average, we call
`that an
`open frame. After C consecutive closed frames,
`we issue a warning signal, where Cis the
`number
`of
`frames
`corresponding
`to
`approximately 2 to 2.5 seconds (the time when
`the eyes have been closed for too long).
`
`SAMSUNG EXHIBIT 1005
`Page 8 of 10
`angeeeeee
`
`SAMSUNG EXHIBIT 1005
`Page 8 of 10
`
`

`

`
`
`
`PerTa[SagesCa[1DeoCa
`30 Degrees Down
`
`
`
`eee
`non
`
`e
`
`I. Results fromthe tests.
`
`10
`
`Ta
`
`10
`
`0
`
`the
`
`histogram across
`
`Horizontal
`pupil
`We use the characteristic curve generated by
`plotting the image-intensities along the
`line
`going through the pupil from left
`to right, as
`shown in Figure 5. The pupil
`is always the
`darkest point. Surrounding the pupil, we have
`the iris, which is also very dark. To the right and
`left of the iris is the white sclera. In Figure 5 we
`show two curves, one corresponding to an open
`eye, and one corresponding to a closed eye.
`Note that the curve corresponding to the closed
`eye is very flat.
`We compute the matching function M(x,y) as
`
`M(x, y) = I(x, y)/min{I(x —r,y), I(x +r,y)}
`
`is the computed center of the pupil
`where (x,y)
`and r is the radius ofthe iris. /(x,y)
`is the image
`intensity at (x,y). When the eye is open,
`the
`valley in the intensity-curve corresponding to
`the pupil will be surrounded by two large peaks
`corresponding to the sclera. When the eye is
`closed,
`this curve is usually
`very flat
`in the
`center. However,
`in the latter case there is no
`pupil to center the curve on, which can lead to a
`very unpredictable shape. In order to minimize
`the risk of having one big peak nearby (due to
`noise), we always use the minimum peak at the
`distance r
`from the pupil. This will lead to a
`good match when the eye is open, and very
`likely to a bad match when the eyeis closed.
`
`RESULTS AND FUTURE WORK
`We simulated three
`‘“test-drives” where we
`
` IMl
`
`Figure 5, Histograms corresponding to an
`open and a closed eye, respectively.
`
`
`
`ene
`———
`
`the detection of
`measured the accuracy of
`opened/closed
`eyes.
`In
`each
`test-drive, we
`simulated 10 long eye-blinks, and recorded how
`many were computed by the system.
`In each
`test-drive, the driver had the head turned in a
`different angle. The results are shown in Table
`
`For this test, we did not allow for any rapid head
`movements,
`since we wanted to simulate the
`situation when the driver is tired. For small head-
`movements, the system rarely loses track of the
`eyes, as we can see from the results. We can also
`see that when the head is
`turned too much
`sideways, we had some false alarms. However, in
`the case where the head is tilted forward (which
`is the most
`likely posture when the driver
`is
`tired), the system operated perfectly.
`When weperform the detection of driver fatigue,
`we operate on frames of size 640 by 320. This
`frame-size allows us to operate at approximately
`5 frames per second. In order to track the eyes,
`without detecting fatigue,
`it is enough to use
`frames of size 320 by 160, which allows a
`frame-rate of approximately 15 frames / second.
`At this point, the system has problems localizing
`eyes whenthe person is wearing glasses, or has a
`large amount of facial hair. We believe that by
`using a small set of face templates, similar to
`[15], we will be able to avoid this problem,
`without losing anything in performance. Also,
`we are not using any color-information in the
`image. By using techniques described in [13],
`we can further enhance robustness.
`
`Currently, we do not adjust zoom or direction of
`the camera during operation. Future work may
`be to automatically zoom in on the eyes, once
`they are localized. This would avoid the trade-
`off between having a wide field of view in order
`to locate the eyes, and a narrow field of view in
`order to detect fatigue.
`
`of
`number
`the
`at
`looking
`only
`are
`We
`consecutive frames where the eyes are closed. At
`that point, it may be too late to issue the signal.
`By study the eye-movement patterns, we are
`hoping to find a method to generate the alert
`signal at an earlier stage.
`
`318
`
`SAMSUNG EXHIBIT 1005
`Page 9 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 9 of 10
`
`

`

`
`
`hs
`
`CONCLUSIONS
`localizes and
`We have developed a system that
`tracks the eyes of a driver in order to detect
`fatigue. The system uses
`a combination of
`template-based matching
`and
`feature-based
`matching in order to localize the eyes. During
`tracking, the system is able to decide if the eyes
`are open or closed. When the eyes have been
`closed too long,
`a warning signal
`is
`issued.
`Several experimental results are presented.
`
`ACKNOWLEDGMENTS
`This work has been supported by the ITS
`Institute at
`the University of Minnesota,
`the
`Minnesota
`Department
`of
`Transportation
`through
`Contracts
`#71789-72983-169
`and
`#71789-72447-159,
`the National
`Science
`Foundation through Contracts #IRI-9410003
`and
`#IRI-9502245,
`and
`the Center
`for
`Transportation Studies.
`
`REFERENCES
`
`[3]
`
`[4]
`
`“Face
`Poggio,
`T.
`and
`Brunelli
`[1] R.
`recognition: Features versus Templates,”
`IEEE Transactions on Pattern Analysis and
`Machine Intelligence, Vol. 15, No. 10, pp.
`1042-1052, 1993.
`[2] G. Chow and X. Li, “Towards a System for
`Automatic
`Feature Detection,”
`Pattern
`Recognition, Vol. 26, No. 12, pp. 1739-
`1755, 1993,
`IJ. Cox, J. Ghosn, P.N. Yianilos, "Feature-
`Based
`Recognition
`Using Mixture-
`Distance,"
`NEC
`Research
`Institute,
`Technical Report 95 - 09, 1995.
`I. Craw, H. Ellis
`and
`J.R. Lishman,
`“Automatic Extraction of Face-Features,”
`Pattern Recognition Letters, 5, pp. 183-187,
`1987.
`[5] L.C. De Silva, K. Aizawa and M. Hatori,
`“Detection and Tracking of Facial Features
`by Using Edge
`Pixel Counting
`and
`Deformable Circular Template Matching, ”
`IEICE Transaction on
`Information and
`Systems, Vol. E78-D No. 9, pp. 1195-1207,
`September 1995.
`[6] C. Huang and C. Chen, “Human Facial
`Feature Extraction for Face Interpretation
`and Recognition,” Pattern Recognition,
`Vol. 25, No. 12 pp. 1435-1444, 1992.
`[7] M. Kass, A. Witkin and D. Terzopoulos,
`“Snakes:
`Active
`Contour Models,”
`
`International Journal of Computer Vision,
`pp. 321-331, 1988.
`“Face Contour
`[8] X. Li and N. Roeder,
`Extraction
`from Front-View
`Images,”
`Pattern Recognition, Vol. 28, No. 8, pp.
`1167-1179, 1995.
`J.M.
`and
`[9] K.P. White, T.E. Hutchinson
`Carley, “Spatially Dynamic Calibration of
`an
`Eye-Tracking
`System,”
`IEEE
`Transactions
`on
`Systems, Man,
`and
`Cybernetics, Vol. 23, No. 4, pp. 1162-1168,
`1993.
`“Accuracy
`and Xiabo Li,
`[10] N. Roeder
`Analysis
`for Facial Feature Detection,”
`Pattern Recognition, Vol. 29, No.
`1, pp.
`143-157, 1996.
`Sakai, T. Endoh, K.
`[11] Y. Segawa, H.
`Murakami, T. Toriu and H. Koshimizu,
`“Face
`Recognition
`Through
`Hough
`Transform for
`Irises
`Extraction
`and
`Projection
`Procedures
`for
`Parts
`Localization,”
`Pacific Rim International
`Conference on Artificial
`Intelligence, pp.
`625-636, 1996.
`Face
`for
`[12] L. Stringa,
`“Eyes Detection
`Artificial
`Recognition,”
`Applied
`Intelligence, No. 7, pp. 365-382, 1993.
`[13] R. Stiefelhagen, J. Yang and A. Waibel, “ A
`Model-Based
`Gaze-Tracking
`System,”
`International
`IEEE Joint Symposia
`on
`Intelligence
`and Systems,
`pp.
`304-310,
`1996.
`[14] E.R. Tello, “Between Man and Machine,”
`BYTE, September, pp. 288-293, 1983.
`and
`[15] D. Tock and
`I. Craw, “Tracking
`Measuring Drivers Eyes,”
`Real-Time
`Computer Vision, pp. 71-89, 1995.
`[16] X. Xie, R. Sudhakar and H. Zhuang, “On
`Improving Eye Features Extraction Using
`Deformable
`Templates,”
`Pattern
`Recognition, Vol. 27, No. 6, pp. 791-799,
`1994.
`[17] X. Xie, R. Sudhakar and H. Zhuang, "Real-
`Time Eye Feature Tracking from a Video
`Image Sequence Using Kalman
`Filter,"
`IEEE Transactions on Systems, Man, and
`Cybernetics, Vol. 25, No.
`12, pp.
`1568-
`1577, 1995.
`[18] T. Yoo and I. Oh, "Extraction of Face
`Region and Features Based on Chromatic
`Properties of Human Faces," Pacific Rim
`International Conference
`on Artificial
`Intelligence, pp. 637-645, 1996.
`[19] H. Wu, Q. Chen, and M. Yachida, "Facial
`Feature Extraction and Face Verification,"
`International
`Conference
`on
`Pattern
`Recognition, pp. 484-488, 1996.
`
`SAMSUNG EXHIBIT 1005 319
`Page 10 of 10
`
`SAMSUNG EXHIBIT 1005
`Page 10 of 10
`
`