`
`
`
`UNITED STATES PATENT AND TRADEMARK OFFICE
`______________________________________________
`
`BEFORE THE PATENT TRIAL AND APPEAL BOARD
`______________________________________________
`
`Samsung Electronics Co., Ltd., and
`Samsung Electronics America, Inc.,
`Petitioners
`
`v.
`
`Image Processing Technologies, LLC,
`Patent Owner.
`
`
`
`PETITION FOR INTER PARTES REVIEW
`OF U.S. PATENT NO. 6,959,293
`
`

`

`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`TABLE OF CONTENTS
`
`
`Introduction ..................................................................................................... 1
`I.
`II. Grounds for Standing, Mandatory Notices, and Fee Authorization ............... 1
`III. Summary of Challenges .................................................................................. 3
`IV. This Petition Is Not Cumulative ..................................................................... 4
`V. Overview of The Relevant Technology and ’293 Patent ............................... 5
`VI. The Invalidating Prior Art .............................................................................. 9
`A.
`International Patent Publication WO 99/36893 (“Pirim”) ................... 9
`B. U.S. Patent No. 5,239,594 (“Yoda”) .................................................. 15
`C.
`International Patent Publication WO 99/35606 (“Qian”) .................. 16
`D.
`Eriksson et al., “Eye-Tracking for Detection of Drive Fatigue,”
`(IEEE 1998) (“Eriksson”) .................................................................. 20
`VII. Level of Ordinary Skill In The Art ............................................................... 21
`VIII. Claim Construction ....................................................................................... 22
`IX. Specific Explanation Of Grounds For Invalidity.......................................... 22
`A. Ground 1: Claims 3-17 are rendered obvious under 35 U.S.C. §
`103 by the combination of Pirim and Yoda ....................................... 22
`1.
`Reasons to Combine Pirim and Yoda ...................................... 22
`2.
`Claim 3 ..................................................................................... 23
`3.
`Claim 4 ..................................................................................... 43
`4.
`Claim 5 ..................................................................................... 46
`5.
`Claim 6 ..................................................................................... 47
`6.
`Claim 7 ..................................................................................... 49
`7.
`Claim 8 ..................................................................................... 51
`8.
`Claim 9 ..................................................................................... 52
`9.
`Claim 10 ................................................................................... 52
`10. Claim 11 ................................................................................... 53
`11. Claim 12 ................................................................................... 56
`12. Claims 13-16 ............................................................................ 57
`
`
`
`

`

`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`
`
`13. Claim 17 ................................................................................... 58
`B. Ground 2: Claims 20-21 are rendered obvious under 35 U.S.C.
`§ 103 by the combination of Pirim and Eriksson ............................... 60
`1.
`Reasons to Combine Pirim and Eriksson ................................. 60
`2.
`Claim 20 ................................................................................... 62
`3.
`Claim 21 ................................................................................... 67
`C. Ground 3: Claims 2, 23, and 28 are rendered obvious under 35
`U.S.C. § 103 by Pirim ........................................................................ 68
`1.
`Claim 2 ..................................................................................... 69
`2.
`Claim 23 ................................................................................... 73
`3.
`Claim 28 ................................................................................... 77
`D. Ground 4: Claims 24-27 are rendered obvious under 35 U.S.C.
`§ 103 by the combination of Pirim and Qian ..................................... 79
`1.
`Reasons to Combine Pirim and Qian ....................................... 79
`2.
`Claim 24 ................................................................................... 80
`3.
`Claim 25 ................................................................................... 82
`4.
`Claim 26 ................................................................................... 83
`5.
`Claim 27 ................................................................................... 83
`Conclusion .................................................................................................... 83
`X.
`Certification of Word Count ................................................................................... 84
`
`ii
`
`
`
`
`
`

`

`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`LIST OF EXHIBITS
`
`iii
`
`
`
`1008
`
`1009
`
`1010
`
`
`
`
`Exhibit No. Description
`1001
`U.S. Patent No. 6,959,293
`1002
`Declaration of Dr. John C. Hart
`1003
`Curriculum Vitae of Dr. John C. Hart
`1004
`Prosecution File History of U.S. Patent No. 6,959,293
`1005
`WO 99/36893, Patrick Pirim and Thomas Binford, “Method and
`Apparatus for Detection of Drowsiness,” published July 22, 1999
`U.S. Patent No. 5,239,594 to Yoda, issued August 24, 1993
`WO 99/35606, Richard Jungiang Qian, “System for Human Face
`Tracking,” published July 15, 1999
`Martin Eriksson and Nikoalaos P. Papanikolopoulos, “Eye-Tracking
`for Detection of Drive Fatigue,” 0-7803-4269-0/97 (IEEE 1998)
`Hennessy and Patterson, “Computer Architecture: A Quantitative
`Approach,” Morgan-Kaufman (1990) (excerpts)
`Declaration of Umit Ozguner (establishing publication of Ex. 1008)
`
`1006
`1007
`
`

`

`
`I.
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`INTRODUCTION
`Pursuant to 37 C.F.R. § 42.100, et seq., Samsung Electronics Co., Ltd.
`
`(“Petitioner” or “Samsung”) hereby petitions the United States Patent and
`
`Trademark Office (the “Office”) to institute an inter partes review of claims 2-17,
`
`20-21, and 23-28 of U.S. Patent No. 6,959,293 (“the ’293 Patent”). The ’293
`
`Patent, attached as Ex. 1001, is assigned to Image Processing Technologies, LLC
`
`(“Patent Owner”). As set forth below, claims 2-17, 20-21, and 23-28 of the ’293
`
`Patent are invalid as obvious over the prior art. Petitioner has also challenged
`
`claims 1, 18-19, 22, and 29 of the 293 Patent in co-pending case No. IPR2017-
`
`00336, in which an institution decision has not yet issued.
`
`This petition presents non-cumulative grounds of invalidity based on
`
`combinations of prior art that were not relied upon by the Office during
`
`prosecution. Each ground presented is reasonably likely to prevail, and this
`
`petition should be granted on all grounds.
`
`II. GROUNDS FOR STANDING, MANDATORY NOTICES, AND FEE
`AUTHORIZATION
`Grounds for Standing: Petitioner certifies that the ’293 patent is available
`
`for inter partes review and that Petitioner is not barred or estopped from requesting
`
`an inter partes review challenging the patent claims on the grounds identified in
`
`this petition.
`
`1
`
`

`

`Real Party-In-Interest: Samsung Electronics Co., Ltd.; and Samsung
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`
`
`Electronics America, Inc.
`
`Notice of Related Matters: Patent Owner has asserted the ’293 patent
`
`against Petitioner in Image Processing Techs., LLC v. Samsung Electronics Co.,
`
`Ltd., et al., Case No. 2:16-cv-00505-JRG (E.D. Tex., filed May 13, 2016).
`
`Patent Owner has also asserted infringement of U.S. Patents Nos. 8,989,445;
`
`8,893,134; 8,805,001; 7,650,015; and 6,717,518 in this same litigation. Petitioner
`
`previously filed the following related IPR petitions:
`
`IPR2017-00336 against the ’293 Patent,
`
`IPR2017-00357 against U.S. Patent 8,989,445,
`
`IPR2017-00355 against U.S. Patent 7,650,015,
`
`IPR2017-00347 against U.S. Patent 8,805,001, and
`
`IPR2017-00353 against U.S. Patent 8,983,134.
`
`Petitioner is concurrently filing additional IPR petitions challenging U.S.
`
`Patent 8,989,445, U.S. Patent 7,650,015, U.S. Patent 8,805,001, U.S. Patent No.
`
`6,717,518, and U.S. Patent 8,983,134.
`
`Lead and Back-Up Counsel:
`
`• Lead Counsel: John Kappos (Reg. No. 37,861), O’Melveny & Myers
`
`LLP, 610 Newport Center Drive, 17th Floor, Newport Beach, California
`
`92660. (Telephone: 949-823-6900; Fax: 949-823-6994; Email:
`
`2
`
`

`

`
`
`jkappos@omm.com.)
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`• Backup Counsel: Nick Whilt (Reg. No. 72,081), Brian M. Cook (Reg.
`
`No. 59,356), O’Melveny & Myers LLP, 400 S. Hope Street, Los
`
`Angeles, CA 90071. (Telephone: 213-430-6000; Fax: 213-430-6407;
`
`Email: nwhilt@omm.com, bcook@omm.com.
`
`Service Information: Samsung consents to electronic service by email to
`
`IPTSAMSUNGOMM@omm.com. Please address all postal and hand-delivery
`
`correspondence to lead counsel at O’Melveny & Myers LLP, 610 Newport Center
`
`Drive, 17th Floor, Newport Beach, California 92660, with courtesy copies to the
`
`email address identified above.
`
`Fee Authorization: The Office is authorized to charge an amount in the
`
`sum of $27,400 to Deposit Account No. 50-2862 for the fee set forth in 37 CFR §
`
`42.15(a), and any additional fees that might be due in connection with this Petition.
`
`III. SUMMARY OF CHALLENGES
`Petitioner respectfully requests cancellation of claims 2-17, 20-21, and 23-28
`
`on the following grounds:
`
`• Ground 1: Claims 3-17 are rendered obvious under 35 U.S.C. § 103 by the
`
`combination of International Patent Publication WO 99/36893 (“Pirim”) and
`
`U.S. Patent No. 5,239,594 (“Yoda”);
`
`• Ground 2: Claims 20-21 are rendered obvious under 35 U.S.C. § 103 by the
`
`3
`
`

`

`
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`combination of Pirim and Eriksson et. al, “Eye-Tracking for Detection of
`
`Drive Fatigue,” (IEEE 1998) (“Eriksson”);
`
`• Ground 3: Claims 2, 23, and 28 are rendered obvious under 35 U.S.C. §
`
`103 by Pirim; and
`
`• Ground 4: Claims 24-27 are rendered obvious under 35 U.S.C. § 103 by
`
`the combination of Pirim and International Patent Publication WO 99/35606
`
`(“Qian”).
`
`IV. THIS PETITION IS NOT CUMULATIVE
`This Petition is not cumulative of IPR2017-00336 (“the ’336 Petition”)
`
`challenging the ’293 Patent and is necessary because in the EDTX litigation, Patent
`
`Owner amended its infringement contentions after Samsung filed the ’336 Petition
`
`to assert additional claims that were not challenged in the ’336 Petition. See, e.g.,
`
`Microsoft Corp. v. Proxyconn, Inc., Case No. IPR2013-00109, slip op., 3 (P.T.A.B.
`
`Feb. 25, 2014) (Paper 15) (instituting IPR because additional claims had been
`
`asserted against the petitioner in concurrent district court litigation). In this
`
`Petition, Samsung has challenged all remaining claims in case IPT asserts
`
`additional claims in the concurrent litigation. See Silicon Labs. Inc. v. Cresta
`
`Tech. Corp., Case No. IPR2015-00615, slip op. 24 (P.T.A.B. Aug. 14, 2015)
`
`(Paper 9) (instituting where petitioner filed petition to “challenge the remaining
`
`claims that the Patent Owner may likely assert in the district court case”).
`
`4
`
`

`

`Second, this petition raises new arguments not raised in the ’336 Petition and
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`
`
`does not challenge any claim previously challenged in the ’336 Petition. See, e.g.,
`
`Cepheid v. Roche Molecular Sys., Inc., Case No. IPR2015-00881 (P.T.A.B. Sept.
`
`17, 2015) (Paper 9). This Petition raises new arguments to address new
`
`limitations, applying new combinations of prior art that were not presented in the
`
`’336 Petition. Facebook, Inc. v. TLI Commc’ns, LLC, Case No. IPR2015-00778,
`
`Paper 17, 26-27 (P.T.A.B. Aug. 28, 2015) (instituting new petitions not
`
`substantially similar to previous petitions).
`
`V. OVERVIEW OF THE RELEVANT TECHNOLOGY AND ’293
`PATENT
`
`The ’293 patent to Patrick Pirim was filed on February 23, 2001 and claims
`
`priority to a foreign application filed February 24, 2000. Ex. 1001 at 1, 50. It is
`
`directed to using histograms for image processing, which was well known for
`
`decades before its priority date. Ex. 1002, Hart Decl. ¶¶19-26. It claims a device
`
`and method for processing a scene by acquiring one or more histograms of
`
`parameters associated with a digitized picture element or “pixel.” See, e.g., Ex.
`
`1001, ’293 Patent, at claims 3, 23, 28. For example, an input video signal S(t)
`
`comprises a succession of frames, each made up of pixels: “[t]his signal S(t)
`
`carries a value aij of the parameter A for each pixel (i, j).” Id. at 7:59-60.
`
`“Parameter A” refers to a property of a pixel, such as its speed, shape, color, etc.
`
`5
`
`

`

`
`Id. at 1:18-20, 29-31. The values of A for the pixels of a given frame are analyzed
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`using a histogram processor, such as depicted in Figure 3, annotated below:
`
`
`
`Digital DATA(A), corresponding to parameter A, flows through input
`
`multiplexer 105 (shaded green) to the address input of histogram memory 100
`
`(shaded red). If each DATA(A) were an 8-bit value representing pixel brightness
`
`(ranging from 0 to 255) for a pixel in the frame, the histogram memory would
`
`increment the value stored at the address representing the brightness value for that
`
`pixel. In other words, once the frame is processed, the histogram memory would
`
`6
`
`

`

`
`contain a value at each of 256 memory addresses representing the number of pixels
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`having the brightness value corresponding to that address. See id. at 8:45-64. Ex.
`
`1002, Hart Decl. ¶¶27-28.
`
`Figure 3 depicts a “classifier unit” 101 (shaded blue) that compares
`
`DATA(A) values to a particular condition, for example, brightness equal to 203.
`
`Ex. 1001 at 9:31-34. The output of the classifier indicating whether or not the
`
`condition is met is sent to coincidence bus 111 (shaded yellow). Id. at 9:36-42.
`
`Output signals from the classifiers associated with other histogram units (B, C, D,
`
`E . . .) are also present on coincidence bus 111 and are sent to coincidence unit 102
`
`(shaded purple). Id. at 10:34-40. Ex. 1002, Hart Decl. ¶30.
`
`The coincidence unit 102 (shaded purple) determines whether a pixel will be
`
`added to the histogram memory 100 (shaded red) based on selected classification
`
`conditions. Ex. 1001 at Fig. 3 (validation signal). For example, validation logic
`
`might enable the histogram memory for those pixels having both brightness greater
`
`than 100 and color equal to red. See id. at 9:36-50. Ex. 1002, Hart Decl. ¶30.
`
`The classification criterion as described above is a fixed value. However,
`
`the classification condition may also be set automatically during a “learning mode”
`
`in which statistics about the scene are used to update the classification criteria. See
`
`id. at 11:9-29; 18:23-28. For example, in Figure 13a, annotated below, the
`
`classifier 119 (shaded blue) evaluates whether data P is greater than condition Q,
`
`7
`
`

`

`
`where Q derived from statistics such as RMAX (shaded red), the number of counts
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`in the highest bin, or NBPTS (shaded orange), the number of pixels in the
`
`histogram. Id. at 10:7-31.
`
`
`
`The ’293 patent states:
`
`Generally, the classifier may be achieved according to numerous
`
`embodiments, the essential being that it allows to place the parameter
`
`DATA(A) with respect to values or limits statistically determined
`
`over a set of former data DATA(A).
`
`Id. at 13:32-36. For example, the processor might determine the maximum
`
`brightness of the pixels in a frame and set a classifier condition for subsequent
`
`frames based on that statistic, such as implementing a classifier that selects pixels
`
`having a brightness less than 80% of the maximum brightness. This classifier, in
`
`8
`
`

`

`
`conjunction with the validation logic, would then ensure that only those pixels
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`satisfying this condition are included in the histogram. Ex. 1002, Hart Decl. ¶¶31-
`
`35.
`
`The ’293 patent also describes an “anticipation” function for predicting the
`
`future value of a parameter based on statistics about that parameter at earlier times:
`
`“the histogram processing unit 1 is configured to perform an anticipation
`
`function.” Ex. 1001 at 13:61-14:4. For example, a variable called “POSMOY”
`
`may be calculated, which is defined as “the value of a parameter, e.g., DATA(A),
`
`in relation to which, in a given frame, the parameter has a value greater than or
`
`equal to half the enabled points in the frame.” Id. at 14:13-18. Thus, POSMOY is
`
`the well-known “median” statistic. Ex. 1002, Hart Decl. ¶171. The anticipation
`
`circuit may use the shift in the median (POSMOY) from a prior frame to the
`
`current frame (POSMOY0 - POSMOY1) to predict the value of a parameter in the
`
`next frame. Ex. 1001 at 14:46-15:6.
`
`VI. THE INVALIDATING PRIOR ART
`A.
`International Patent Publication WO 99/36893 (“Pirim”)
`Pirim, Ex. 1005, was published on July 22, 1999, based on an international
`
`application filed January 15, 1999, designating the U.S. and qualifies as prior art
`
`under at least pre-AIA 35 U.S.C. §§ 102(a), 102(b), and § 119 (“but no patent shall
`
`be granted… for an invention which had been… described in a printed publication
`
`9
`
`

`

`
`in any country more than one year before the date of the actual filing of the
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`application in this country.”). Pirim names one inventor in common with the
`
`challenged ’293 patent but has a different inventive entity. Ex. 1005 at 1. Pirim is
`
`of record in the prosecution history but was never discussed or used in a rejection
`
`by the examiner. Ex. 1004, Prosecution History at 110, 201-231; 237-242.
`
`Pirim discloses a system for detecting whether a driver is falling asleep by
`
`acquiring pictures of the driver and forming histograms to analyze opening and
`
`closing of the driver’s eyes. Ex. 1005, Pirim at 3. Pirim’s image processing
`
`system “receives a digital video signal S originating from a video camera or other
`
`imaging device 13 which monitors a scene 13a.” Id. at 10. “Signal S(PI)
`
`represents signal S composed of pixels PI.” Id. at 11. Each video frame comprises
`
`horizontal scanned lines, each including “a succession of pixels or image points PI,
`
`e.g., a1.1, a1.2, and a1.3 for line l1.1.” Id.
`
`Figure 14 (annotated below) discloses a histogram unit having a memory
`
`100 (shaded red). Data(V), representing pixel parameter V, proceeds through input
`
`multiplexer 104 (shaded green) to the address input of memory 100. Id. at 27. Just
`
`as in the ’293 patent, a value stored at the address corresponding to the value of the
`
`input data parameter is incremented to accumulate a histogram of the parameter.
`
`Id.
`
`Pirim discloses a “classifier 25b” (shaded blue) that compares data(V) to a
`
`10
`
`

`

`
`“register 106 that enables the classification criteria to be set by the user, or by a
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`separate computer program.” Id. at 27-28.
`
`
`
`The output of classifier 25b proceeds to bus 23 (shaded yellow), which also
`
`carries the output of other classifiers in the system. Id. at 29. These signals
`
`proceed to validation unit 31 (shaded purple). “Each validation unit generates a
`
`validation signal which is communicated to its associated histogram formation
`
`11
`
`

`

`
`block 24-29. The validation signal determines, for each incoming pixel, whether
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`the histogram formation block will utilize that pixel in forming it histogram.” Id.
`
`at 30. The operation is summarized as follows:
`
`Thus, using the classifiers in combination with validation units 30-35,
`
`the system may select for processing only data points in any selected
`
`classes within any selected domains. For example, the system may be
`
`used to detect only data points having speed 2, direction 4, and
`
`luminance 125 by setting each of the following registers to “1”: the
`
`registers in the validation units for speed, direction, and luminance,
`
`register 2 in the speed classifier, register 4 in the direction classifier,
`
`and register 125 in the luminance classifier. In order to form those
`
`pixels into a block, the registers in the validation units for the x and y
`
`directions would be set to “1” as well.
`
`Id. at 29.
`
`Pirim also calculates and stores statistical characteristics of the histogram in
`
`memory unit112, including “the minimum (MIN) of the histogram, the maximum
`
`(MAX) of the histogram, the number of points (NBPTS) in the histogram, the
`
`position (POSRMAX) of the maximum of the histogram.” Id. at 30. The controller
`
`can read these statistics and can also execute a program to update the classification
`
`criteria in the classifiers (among other parameters in the system):
`
`12
`
`

`

`
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`Controller 42 is in communication with data bus 23, which allows
`
`controller 42 to run a program to control various parameters that may
`
`be set in the system and to analyze the results. In order to select the
`
`criteria of pixels to be tracked, controller 42 may also directly control
`
`the following: i) content of each register in classifiers 25b, ii) the
`
`content of each register in validation units 31… Controller 42 may
`
`also retrieve i) the content of each memory 100 and ii) the content of
`
`registers 112, in order to analyze the results of the histogram
`
`formation process.”
`
`Pirim, Ex. 1005 at 38-39; Ex. 1002, Hart Decl. ¶¶42-46. Pirim’s controller may
`
`adjust these classification thresholds dynamically to automatically adapt the system
`
`to the observed scene:
`
`Controller 42 constantly adapts operation of the system, especially in
`
`varying lighting levels. Controller 42 may detect varying lighting
`
`conditions by periodically monitoring the luminance histogram and
`
`adapting the gain bias of the sensor to maintain as broad a luminance
`
`spectrum as possible. Controller 42 may also adjust the thresholds that
`
`are used to determine shadowing, etc. to better distinguish eye and
`
`nostril shadowing from noise, e. g. shadowing on the side of the nose,
`
`and may also adjust the sensor gain to minimize this effect. If desired
`
`13
`
`

`

`
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`controller 42 may cause the histogram formation units to form a
`
`histogram of the iris. This histogram may also be monitored for
`
`consistency, and the various thresholds used in the system adjusted as
`
`necessary.
`
`Ex. 1005, Pirim at 57.
`
`Pirim also discloses an anticipation function for predicting the future value
`
`of a parameter based on statistics about the parameter in prior frames:
`
`As discussed above, the system of the invention may be used to search
`
`for objects within a bounded area defined by XMIN, XMAX, YMIN
`
`and YMAX. Because moving object may leave the bounded area the
`
`system preferably includes an anticipation function which enables
`
`XMIN, XMAX, YMIN and YMAX to be automatically modified by
`
`the system to compensate for the speed and direction of the target.
`
`This
`
`is accomplished by determining values
`
`for O-MVT,
`
`corresponding to orientation (direction) of movement of the target
`
`within the bounded area using the direction histogram, and I-MVT,
`
`corresponding to the intensity (velocity) of movement. Using these
`
`parameters, controller 42 may modify the values of XMIN, XMAX,
`
`YMIN and YMAX on a frame-by-frame basis to ensure that the target
`
`remains in the bounded box being searched.
`
`14
`
`

`

`
`Id. at 37-38 (emphasis added); Ex. 1002, Hart Decl. ¶¶47-48.
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`B. U.S. Patent No. 5,239,594 (“Yoda”)
`Yoda, Ex. 1006, issued on August 24, 1993 and qualifies as prior art under
`
`at least pre-AIA 35 U.S.C. §102(b). Yoda discloses a system of “self-organizing
`
`classifiers” for analyzing images on the basis of multiple characteristics. For
`
`example, Yoda states that classifying on a single feature, such as brightness, is not
`
`always sufficient:
`
`FIG. 4 provides an example wherein a single feature is used. In
`
`particular, it shows the distributions 13 and 14 of brightness features
`
`F1 for ash wood and birch wood, respectively… In Fig. 4 there is a
`
`large overlapping area in the brightness feature F1 of the ash wood 13
`
`and the birch wood 14. As such it is impossible to make correct
`
`classification using only the brightness feature F1. However, as
`
`shown in Fig. 5, by using both the brightness feature F1 and the grain
`
`prominence feature F2, it is possible to classify these two objects
`
`correctly.
`
`Ex. 1006, Yoda at 2:27-43; Figs. 4, 5.
`
`
`
`15
`
`

`

`Yoda discloses that modifications to the weighting vector defining the
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`
`
`operation of the classifiers are made during a “learning mode” in in which training
`
`values representing typical classes are loaded into the classifiers:
`
`The neural network system operates in either a classification mode
`
`wherein pattern signals are classified or a learning mode wherein the
`
`weighting vectors stored in the self-organizing classifiers 17 are
`
`modified.
`
`Id. at 4:44-47. The classifier operates in the same way during learning mode but
`
`with different inputs:
`
`In the learning mode, a classification result P 21 is determined in the
`
`same way as in the as in the classification mode. As Fig. 6 shows, the
`
`classification result P 21 is then transferred to the learning trigger 19,
`
`wherein whether a correct class signal L 23 is transferred to the self-
`
`organizing classifiers 17 is determined based on the classification
`
`result P 21 and a training signal Tr 22 which is externally supplied by
`
`the user.
`
`Id. at 5:29-36; Ex. 1002, Hart Decl. ¶¶49-50.
`
`
`International Patent Publication WO 99/35606 (“Qian”)
`
`C.
`Qian, Ex. 1007, was published on July 15, 1999, based on an international
`
`application filed January 6, 1999, designating the U.S. and qualifies as prior art
`
`16
`
`

`

`
`under at least pre-AIA 35 U.S.C. §§ 102(a), 102(b), and § 119. Qian describes a
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`system that uses histograms of regions of an image representing skin-tone to
`
`identify and track a face. Ex. 1007, Qian at Abstract. Qian states:
`
`Referring to Fig. 1, a face detection and tracking system 6 includes an
`
`image acquisition device 8, such as a still camera or video camera. A
`
`frame grabber 9 captures individual frames from the acquisition
`
`decide for face detection and tracking.
`
`Ex. 1007, Qian at 5.
`
`Figure 6, reproduced below, is described as follows: “Fig. 6 is a pair of
`
`histograms of the binary image of Fig. 5 together with the medians and variances
`
`for each histogram.”
`
`17
`
`

`

`
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`
`
`Qian uses the median or mean of the histograms to track face position:
`
`Referring to FIG. 6, the mean of the distribution of the l's (skin-tones)
`
`is calculated in both the x and y directions. The distribution is a
`
`histogram of the number of l's in each direction. The mean may be
`
`calculated by μ=(l/N)Σxi. The approximate central location 38 of the
`
`face is determined by projecting the x-mean 30 and the y-mean 32
`
`onto the binary image 14.
`
`Id. at 9. Qian refers to the mean and to the median when discussing Figure 6 and
`
`further states:
`
`18
`
`

`

`
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`The system may alternatively use other suitable statistical techniques
`
`on the binary image 14 in the x and y direction to determine a location
`
`indicative of the central portion of the facial feature and/or its size, if
`
`desired.
`
`Id. Qian looks at the change in the mean or median location of the face from frame
`
`to frame to track its velocity and anticipate its value in subsequent frames:
`
`The estimated face location may also be used for tracking the face
`
`between frames of a video. For simplicity the face motion may be
`
`modeled as a piece-wise constant two-dimensional translation within
`
`the image plane. A linear Kalman filter may be used to predict and
`
`correct the estimation of the two-dimensional translation velocity
`
`vector. The estimated (filtered) velocity may then also be used to
`
`determine the tracked positions of faces.
`
`The preferred system model for tracking the motion is:
`
`x(k+l)=F(k)x(k)+w(k)
`
`z(k+l)=H(k+l)x(k+l)+v(k+l)
`
`where x(k) is the true velocity vector to be estimated, z(k) is the
`
`observed instantaneous velocity vector, w(k), v(k) are white noise,
`
`and F(k)=I, H(k)=I for piece-wise constant motion.
`
`Id. at 10. Since velocity of the current frame, x(k), is derived from the change in
`
`19
`
`

`

`
`the median location of the object divided by the time between frames (Ex. 1002,
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`Hart Decl. ¶171), velocity is directly proportional to the difference between the
`
`medians of frame 0 and frame 1. Thus, Qian anticipates motion by evaluating a
`
`function based on the difference of the median values from one frame to the next.
`
`Ex. 1002, Hart Decl. ¶¶51-54.
`
`D. Eriksson et al., “Eye-Tracking for Detection of Drive Fatigue,”
`(IEEE 1998) (“Eriksson”)
`
`Eriksson, Ex. 1008, was published at least as early as November 12, 1997
`
`and qualifies as prior art under at least pre-AIA 35 U.S.C. § 102(b). See Ex. 1010,
`
`Ozguner Decl. Eriksson describes an eye-tracking system that uses histograms to
`
`identify and track eye movement. Ex. 1008, Eriksson at Abstract. Eriksson
`
`acquires an image of a driver’s face and forms a histogram of detected edges,
`
`based on the assumption that “eye-regions correspond to regions of high spatial
`
`frequency.” Ex. 1008, Eriksson at 316; see also Fig. 2, reproduced below:
`
`Eriksson locates the eyes using a threshold classifier. Id. The classification
`
`
`
`20
`
`

`

`
`threshold is adjusted automatically based on measured performance:
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`The difficulty with this method is to find a 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.
`
`Id.; Ex. 1002, Hart Decl. ¶¶55-56.
`
`VII. LEVEL OF ORDINARY SKILL IN THE ART
`The level of ordinary skill in the art is evidenced by the challenged patent
`
`and the prior art described above. Specifically, one of ordinary skill in the art the
`
`time of the alleged invention of the ’293 patent would have had either (1) a
`
`Master’s Degree in Electrical Engineering or Computer Science or the equivalent
`
`plus at least a year of experience in the field of image processing, image
`
`recognition, machine vision, or a related field or (2) a Bachelor’s Degree in
`
`Electrical Engineering or Computer Science or the equivalent plus at least three
`
`years of experience in the field of image processing, image recognition, machine
`
`vision, or a related field. Additional education could substitute for work
`
`experience and vice versa. Ex. 1002, Hart Decl. ¶¶38-40.
`
`21
`
`

`

`
`VIII. CLAIM CONSTRUCTION
`In an inter partes review, “[a] claim in an unexpired patent shall be given its
`
`U.S. Patent No. 6,959,293
`Petition for Inter Partes Review
`
`broadest reasonable construction in light of the specification of the patent in which
`
`it appears.” 37 C.F.R. § 42.100(b). The ’293 patent will not expire before a final
`
`written decision issues, and its claims should be given their broadest reasonable
`
`interpretation.1 Petitioner submits that for purposes of this petition, no special
`
`definition applies to any term of the ’293 patent, and the claim terms should be
`
`i