Ex Parte Zouridakis

Patent Trial and Appeal Board

Dec 14, 2018

13852672 (P.T.A.B. Dec. 14, 2018)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
13/852,672 03/28/2013
27851 7590 12/18/2018
BENJAMIN A. ADLER
8011 CANDLE LANE
HOUSTON, TX 77071
FIRST NAMED INVENTOR
George Zouridakis
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www .uspto.gov
ATTORNEY DOCKET NO. CONFIRMATION NO.
D7099 7785
EXAMINER
LIMA, FABIO S
ART UNIT PAPER NUMBER
2486
NOTIFICATION DATE DELIVERY MODE
12/18/2018 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
Ben@adlerandassociates.com
Colleen@adlerandassociates.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte GEORGE ZOURIDAKIS
Appeal2018-005726
Application 13/852,672 1
Technology Center 2400
Before ROBERT E. NAPPI, ERIC S. FRAHM, and MICHAEL T. CYGAN,
Administrative Patent Judges.
CYGAN, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF CASE
Introduction
Appellant appeals under 35 U.S.C. § 134(a) from the Examiner's
Final Rejection of claims 1, 2, 7-15, 18, 19, 21-25, 27, and 28 We have
jurisdiction under 35 U.S.C. § 6(b).
We affirm.
1 According to Appellant, the real party in interest is the University of
Houston System. App. Br. 3.
Appeal2018-005726
Application 13/852,672
Disclosed Invention and Exemplary Claim
The disclosed invention is a handheld imaging device ( claim 1)
having algorithms to identify an object of interest present on a body, a
method ( claim 10), of using the handheld imaging device of claim 1 to
identify an object of interest, a digital processor-implemented system ( claim
14) and method (claim 22) for classifying an object of interest on a body,
and a non-transitory computer-readable medium storing a library of
algorithms to classify an object of interest on a body (Spec. ,r,r 8-13; claims
1, 10, 14, 22, 25). Independent claim 1 is exemplary of the disclosed
invention, and reads as follows ( with key limitations of the claim
emphasized):
1. A portable imaging system, comprising:
a hand-held imaging device having a digital camera, a
display, a memory, a processor and a network connection; and
a library of algorithms tangibly stored in the memory and
executable by the processor, said algorithms configured for
identification of an object of interest present on a body via
processor-executable instructions that function to:
segment the imaged object to detect a border of the object
via steps to:
determine an initial contour of the imaged object;
classify pixels as contained within the initial contour as
foreground, as contained without the initial contour as
background or as remaining pixels if they are not classified as
foreground pixels or background pixels; and
apply a supervised classifier to the remaining pixels for
classification as foreground or background;
extract features from the segmented object image via steps
to:
divide the segmented object image into regions based on
saliency values calculated for at least one patch within the
segmented object;
2
Appeal2018-005726
Application 13/852,672
divide the regions into two regions of higher or lower
intensity based on average intensity values thereof; and
extract feature representations from a sampling of patches
within the intensity regions based on sampling percentages
determined for the regions;
classify the object based on the extracted features via steps
to: input the extracted feature representations into a support
vector machine trained with manually segmented objects; and
classify the object based on a comparison of the inputted
extracted features with those in the trained support vector
machine.
Remaining independent claims 14 and 25 recite limitations
commensurate with the above-emphasized limitations recited in claim
1.
Examiner's Rejections
(1) The Examiner rejected claims 1, 2, 7-15, 18, 21-25, and 27
under 35 U.S.C. § I03(a) as being obvious over the combination Zouridakis
et al. (US 2008/0226151 Al; published September 18, 2008), Guyon et al.
(US 2012/0008838 Al; published January 12, 2012), and Wilensky et al.,
(US 2008/0095429 Al; published April 24, 2008). Final Act. 4--12; Ans. 2-
6.
(2) The Examiner rejected claims 19 and 28 under 35 U.S.C.
§ I03(a) as being obvious over the combination of Zouridakis, Guyon,
Wilensky, and Hattery et al., (US 2005/0273011 Al; published December 8,
2005). Final Act. 12-14; Ans. 6.
Appellant's Contentions
As to independent claims 1, 14, and 25, Appellant contends, inter alia
(see generally App. Br. 8-14) the following:
3
Appeal2018-005726
Application 13/852,672
(1) the incorporation of the Guyon and/or Wilensky algorithms into
Zouridakis' device would result in a device performing a step of merging
regions into small clusters that is not required by Appellant's claimed
invention (App. Br. 1-13);
(2) the incorporation of the Guyon and/or Wilensky algorithms into
Zouridakis' device would result in a device that classifies pixels based on a
foreground or background color, instead of classifying pixels into
foreground, background or remaining pixels as required by Appellant's
claimed invention (App. Br. 13); and
(3) the combination of Zouridakis, Wilensky, and Guyon would result
in a user-controlled extraction and classification of pixels, instead of the
claimed invention's use of an algorithm to extract and classify the pixels
(App. Br. at 13-14).
Appellant relies on these contentions as to the patentability for claims
1, 2, 7-15, 18, 21-25, and 27. Based upon Appellant's contentions, and
because claims 1, 2, 7-15, 18, 21-25, and 27 contain commensurate
limitations, we select claim 1 as representative of claims 1, 2, 7-15, 18, 21-
25, and 27 rejected over the base combination of Zouridakis, Guyon, and
Wilensky.
Issues on Appeal
The primary issue on appeal is whether the Examiner erred in
rejecting claims 1-2, 7-15, 18, 21-25, and 27 under 35 U.S.C. § 103(a) over
the base combination of Zouridakis, Guyon, and Wilensky, because the base
combination fails to teach or suggest the following limitation (italicized
4
Appeal2018-005726
Application 13/852,672
below) recited in independent claim 1 (and as commensurately recited in
remaining independent claims 14 and 25):
... algorithms configured for identification of an object of
interest present on a body via processor-executable instructions
that function to:
segment the imaged object to detect a border of the object
via steps to:
determine an initial contour of the imaged object;
classify pixels as contained within the initial contour as
foreground, as contained without the initial contour as
background or as remaining pixels if they are not classified as
foreground pixels or background pixels . ..
Claim 1 ( emphasis added).
ANALYSIS
We have reviewed the Examiner's rejections (Final Act. 4--14) in light
of Appellant's contentions in the Appeal Brief that the Examiner has erred
(App. Br. 8-17). We disagree with Appellant's arguments. With regard to
representative claim 1, we adopt as our own (1) the findings and reasons set
forth by the Examiner in the action from which this appeal is taken (Final
Act. 6-10), and (2) the reasons set forth by the Examiner in the Examiner's
Answer (Ans. 3-7) in response to Appellant's Appeal Brief. We concur
with the findings and conclusions reached by the Examiner as to the
obviousness rejection of claim 1.
Appellant first contends that the incorporation of the Guyon and/ or
Wilensky algorithms into Zouridakis' device would result in a device
performing a step of merging regions into small clusters that is not required
by Appellant's claimed invention (App. Br. 1-13). However, this contention
5
Appeal2018-005726
Application 13/852,672
is unpersuasive as failing to be commensurate in scope with the language of
representative claim 1. See In re Hiniker Co., 150 F.3d 1362, 1369 (Fed.
Cir. 1998) ("[The] proffered facts ... are not commensurate with the claim
scope and are therefore unpersuasive."); In re Self, 671 F.2d 1344, 1348
(CCPA 1982) (limitations not appearing in the claims cannot be relied upon
for patentability). The language of claim 1 recites a step of determining an
initial contour of the imaged object, but does not limit the manner of its
performance such that it cannot be performed through merging regions into
small clusters to determine the initial contour.
As explained by the Examiner, the use of an algorithm based upon
finding a curve to segment an image into two regions based on intensity
within those regions, and more particularly, the use of the Chan-Vese model
in such segmentation, is common both to Appellant's disclosure and to the
teachings of Zouridakis. Ex. Ans. at 3. The Examiner thus concludes that
Zouridakis teaches or suggests the claimed "segment the imaged object to
detect a border of the object via steps to[] determine an initial contour of the
imaged object." Id. Although the claim does not require regions to be
merged into small clusters during the segmentation, no negative limitation
exists in the claims that would exclude merging regions into small clusters in
performance of the step of determining the initial contour of the imaged
object. 2
2 It is further noted that independent claims 15 and 25 do not require any
step of determining the initial contour of the imaged object; similarly, those
claims lack limitation that would exclude merging regions into small
clusters.
6
Appeal2018-005726
Application 13/852,672
Appellant next contends that the incorporation of the Guyon and/or
Wilensky algorithms into Zouridakis' device would result in a device that
classifies pixels based on a foreground or background color, instead of
classifying pixels into foreground, background or remaining pixels as
required by Appellant's claimed invention (App. Br. 13). However, this
contention is unpersuasive because, as explained by the Examiner, Wilensky
teaches segmentation of the image into three separate regions: foreground,
uncertain, and background. Final Act. 6; Ex. Ans. 4.
The test for obviousness is "what the combined teachings of the
references would have suggested to those of ordinary skill in the art." In re
Keller, 642 F.2d 413,425 (CCPA 1981). Here, Appellant asserts that the
combination would result in a device that classifies pixels based on a
foreground or background color, but does not provide reasoning to explain
that bare assertion. App. Br. 13. In view of the facts and reasoning
presented, we find that one having ordinary skill in the art would find the
that the combination of the Zouridakis, Guyon, and Wilensky references
teach or suggest the claimed classification of pixels into foreground,
background, or remaining pixels.
Appellant also contends that the teaching of Wilensky is for user-
performed operation rather than the claimed algorithm-performed operation,
stating, "the claimed invention requires that the algorithm extracts and
classifies the foreground, background, and remaining pixels." App. Br. 13-
14. However, as noted by the Examiner, Wilensky teaches "[t]he algorithm
then segments the entire image or a portion of the image bounding the
selection into three separate regions: foreground, uncertain, and
background." Wilensky Jr 52; Ex. Ans. 5.
7
Appeal2018-005726
Application 13/852,672
Appellant's contention is unpersuasive as failing to be commensurate
in scope with the language of representative claim 1. See In re Hiniker Co.,
150 F.3d 1362, 1369 (Fed. Cir. 1998) ("[The] proffered facts ... are not
commensurate with the claim scope and are therefore unpersuasive."); In re
Self, 671 F.2d 1344, 1348 (CCPA 1982) (limitations not appearing in the
claims cannot be relied upon for patentability). The language of claim 1
requires that the algorithm, via processor-executable instructions, classify
pixels as foreground, background, or as remaining pixels. Claim 1 does not
contain any language excluding user input in the instructions of the
algorithms in any of the recited steps, including the step of classifying the
pixels. Nor does claim 1 contain any language concerning the "extract[ion ]"
of pixels as contended by Appellant. In this light, Appellant's contention
that Wilensky fails to teach or suggest an algorithm having processor-
executable instructions that function to segment than imaged object via steps
to determine an initial contour of the imaged object and to classify pixels
therein is unpersuasive.
In view of the foregoing, we sustain the Examiner's obviousness
rejection of claim 1, as well as claims 2, 7-15, 18, 21-25, and 27 grouped
therewith.
As to the rejection of dependent claims 19 and 28 as being obvious
over the combination of Zouridakis, Wilensky, Guyon, and Hattery,
Appellant's brief presents the same arguments presented concerning the
rejection of the respective independent claims 15 and 25 as being obvious
over the combination of Zouridakis, Wilensky, and Guyon. We decide the
outcome of claims 19 and 28 on the same basis as claims 15 and 25 from
which claims 19 and 28 depend, which in tum we decide on the basis of
8
Appeal2018-005726
Application 13/852,672
representative claim 1. Therefore, Appellant has not shown that the
Examiner erred in rejecting claims 19 and 28. See 37 C.F.R.
§ 41.37( C )(1 )(iv).
CONCLUSIONS
( 1) We conclude that the Examiner did not err in rejecting claims 1, 2,
7-15, 18, 21-25, and 27 under 35 U.S.C. § 103(a) over the base combination
of Zouridakis, Wilensky, and Guyon.
(2) We conclude that Appellant has not shown that the Examiner has
erred in rejecting claims 19 and 28 under 35 U.S.C. § 103(a) as being
obvious over the combination of Zouridakis, Wilensky, Guyon, and Hattery.
DECISION
We affirm the Examiner's rejections of claims 1, 2, 7-15, 18, 19, 21-
25, 27, and 28 under 35 U.S.C. § 103(a).
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a)(l )(iv).
AFFIRMED
9