Joseph Maria Angelo. Djugash

Patent Trials and Appeals Board

Aug 30, 2019

13706809 - (D) (P.T.A.B. Aug. 30, 2019)

UNITED STATES PATENT AND TRADEMARK OFFICE
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
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
13/706,809 12/06/2012 Joseph Maria Angelo Djugash 22562-748/2012-126 2052
96411 7590 08/30/2019
Dinsmore & Shohl LLP
255 East Fifth Street, Suite 1900
Cincinnati, OH 45202
EXAMINER
BALI, VIKKRAM
ART UNIT PAPER NUMBER
2663
MAIL DATE DELIVERY MODE
08/30/2019 PAPER
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.
PTOL-90A (Rev. 04/07)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
____________

Ex parte JOSEPH MARIA ANGELO DJUGASH
________________

Appeal 2016-004355
Application 13/706,8091
Technology Center 2600
____________

Before JEREMY J. CURCURI, KARA L. SZPONDOWSKI,
and MATTHEW J. McNEILL, Administrative Patent Judges.

McNEILL, Administrative Patent Judge.

DECISION ON APPEAL

Appellant appeals under 35 U.S.C. § 134(a) from the Examiner’s
rejection of claims 1‒20, which are all the claims pending in this application.
An oral hearing was held August 1, 2019, and a transcript of that hearing
will be made of record in due course. We have jurisdiction under 35 U.S.C.
§ 6(b).
We reverse.

1 According to Appellant, the real party in interest is the Applicant, Toyota
Motor Engineering & Manufacturing North America, Inc. App. Br. 2.
Appeal 2016-004355
Application 13/706,809

2
STATEMENT OF THE CASE
Introduction
Appellant’s application relates to an object recognition module that
adjusts object recognition parameters in response to a pose estimation error.
Spec. ¶ 5. Claim 1 illustrates the appealed subject matter and reads as
follows:
1. A method for adjusting at least one object recognition
parameter comprising:
receiving digital image data;
automatically recognizing an object with an object
recognition module based on the digital image data, wherein the
object recognition module includes at least one object
recognition parameter;
determining whether a pose estimation error has
occurred; and
adjusting the at least one object recognition parameter
when the pose estimation error has occurred.

The Examiner’s Rejections
Claims 1‒12, 14, and 15 stand rejected under pre-AIA 35 U.S.C.
§ 103(a) as being unpatentable over Hyun Oh Song et al., Visual Grasp
Affordances From Appearance-Based Cues, 2011 IEEE International
Conference on Computer Vision Workshops (2011) (“Song”), and Fujimura
(US 7,206,435 B2; Apr. 17, 2007). Final Act. 4‒7.
Claims 13 and 16‒20 stand rejected under pre-AIA 35 U.S.C. § 103(a)
as being unpatentable over Song, Fujimura, and Nagatsuka (US
2008/0301072 A1; Dec. 4, 2008). Final Act. 8‒9.

Appeal 2016-004355
Application 13/706,809

3
ANALYSIS
The Examiner finds the combination of Song and Fujimura teaches or
suggests “determining whether a pose estimation error has occurred” and
“adjusting the at least one object recognition parameter when the pose
estimation error has occurred,” as recited in claim 1. See Final Act. 4‒5;
Ans. 8. In particular, the Examiner finds Fujimura teaches detecting an eye
in an image, which the Examiner finds corresponds to the “pose estimation
error” limitation. Final Act. 4 (citing Fujimura 5:44‒49). The Examiner
further finds Fujimura teaches adjusting the camera focus when an eye is not
found, which the Examiner finds corresponds to “adjusting the at least one
object recognition parameter when the pose estimation error has occurred.”
Id.
Appellant argues the Examiner erred because adjusting parameters
when a subject’s eyes are not found does not teach or suggest “determining
whether a pose estimation error has occurred” and “adjusting the at least one
object recognition parameter when the pose estimation error has occurred.”
App. Br. 17‒18.
We agree with Appellant. Fujimura teaches a process that includes an
eye detection step. Fujimura 5:44‒45. If a subject’s eyes are not found, the
eye detection step is repeated, potentially with adjusted parameters, such as
camera focus. Id. at 5:45‒47. We agree with Appellant that the Examiner
has failed to establish that Fujimura teaches or suggests “determining
whether a pose estimation error has occurred” because these teachings relate
to detecting an object, not detecting the pose of the object or determining
whether an error in the pose estimation has occurred.
Appeal 2016-004355
Application 13/706,809

4
For these reasons, Appellant has persuaded us the Examiner erred in
rejecting claim 1 as unpatentable over Song and Fujimura. We, therefore, do
not sustain the rejection of claim 1. We also do not sustain the rejection of
independent claims 17 and 20, which recite commensurate limitations, or
dependent claims 2‒16, 18, and 19.

DECISION
We reverse the Examiner’s decision rejecting claims 1‒20.

REVERSED