DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is in response to the Amendment filed on 1/27/2026.
Claims 1, 6, 8-10 are pending. Claim 2-5, 7 have been amended.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 8, 9, 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lloyd et al. (EP2843590B1, hereafter Lloyd) in view of Taguchi et al. (US 9208609 B2, hereinafter Taguchi).
Regarding Claim 1, Lloyd teaches a dimension measurement device comprising: a processor; and memory, wherein using the memory, the processor: (Lloyd, Paragraph [0013]-[0014], "a package-dimensioning system ... the processing of the image that is acquired by the image capturing subsystem is performed by a computer, which typically has a central processing unit (CPU) and a memory"), obtains a three-dimensional model of a target object (Lloyd, Paragraph [0015], "the image-capturing subsystem includes an imaging device (e.g., camera, stereo camera, range camera 110A, lidar) ... the image-capturing system is configured to generate a point cloud ... The point cloud usually contains information regarding the positioning of points in a three-dimensional space (e.g., X, Y, Z coordinates) ... including points on the surface of the object <read on target object>"), [[determines, from a plurality of types, a type of the target object based on image recognition carried out on an image of the target object, the plurality of types each being associated in advance with one of a plurality of basic shapes]],
selects, from the plurality of basic shapes, the one of the plurality of basic shapes that is associated in advance with the type determined (Lloyd, Paragraph [0018], "the classification module 130 categorizes the object's shape ... the domain of shipped objects 112 is generally limited, with the vast majority of shipped objects 112 being cuboids, cylinders, or prisms ... the classification module 130 is typically limited to a relatively small (e.g., between about 4 and 8) number of shape categories <read on plurality of basic shapes associated in advance>" , [0019],"the shape-estimation module 140 would utilize the shape-specific submodule 145 adapted for estimating the dimensions of rectangular boxes <read on selects the one of the plurality of basic shapes>"), [[fits the basic shape selected to the three-dimensional model]], measures a dimension of the target object using the basic shape that has been fitted (Lloyd, Paragraph [0019], "the shape-estimation module 140 would utilize the shape-specific submodule 145 adapted for estimating the dimensions of rectangular boxes ... output an estimate of the dimensions (e.g., length, width, and height) of the rectangular box object <read on measures a dimension of the target object using the basic shape that has been fitted>").
But Lloyd does not explicitly disclose determines, from a plurality of types, a type of the target object based on image recognition carried out on an image of the target object, the plurality of types each being associated in advance with one of a plurality of basic shapes; and fits the basic shape selected to the three-dimensional model.
However, Taguchi teaches determines, from a plurality of types, a type of the target object based on image recognition carried out on an image of the target object, the plurality of types each being associated in advance with one of a plurality of basic shapes (Taguchi, Column 1, Lines 8–9, "This invention relates generally processing three-dimensional (3D) data, and more particularly to fitting primitive shapes to 3D data <read on image recognition carried out on an image of the target object>"; Column 2, Lines 1–6, "The 3D point cloud is converted 105 to a distance field 102. The distance field is used in a RANSAC-based primitive shape fitting process 110, where a set of two or more candidate shapes 100 are hypothesized 111 by using a minimal number of points required to determine parameters of a corresponding shape <read on plurality of types each being a corresponding candidate>"; Column 3, Lines 28–35, " we use the RANSAC framework for primitive shape fitting. We hypothesize a set oftwo or more candidate primitive shapes, determine their scores, and select the best candidate with the minimal score. In the preferred embodiments, we use infinite planes segments, spheres, cylinders, and cuboids as the primitive shapes <read on plurality of types each being associated in advance with one of a plurality of basic shapes>"),
fits the basic shape selected to the three-dimensional model (Taguchi, Column 2, Lines 1–15, "The 3D point cloud is converted 105 to a distance field 102 ... A score 121 is determined for each shape ... The method selects 120 the best candidate primitive shape that has a minimal score among the candidates ... Optionally, the parameters of the best primitive shape can be refined 130 using a gradient-decent procedure <read on fits the basic shape selected to the three-dimensional model>").
Taguchi and Lloyd are analogous since both deal with extracting dimensional measurements from physical objects using 3D scan data, and both rely on selecting among a predefined set of primitive geometric shapes to characterize the scanned object's form before estimating its dimensions. Lloyd provided a way of classifying an object's shape from a feature set derived from a 3D point cloud, constraining the classification to a small set of known shape categories tied to a deployment context (e.g., shipping packages), and then routing to a shape-specific submodule for dimension estimation. Taguchi provided a way of determining the best-fitting primitive shape from among a pre-defined set of candidate primitive shapes by converting the 3D point cloud to a distance field, scoring each candidate shape against the field, and then fitting and refining the selected primitive shape's parameters to the 3D data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the type-to-shape association and primitive shape fitting process taught by Taguchi into the shape classification and estimation system of Lloyd, such that the processor first determines from a plurality of pre-associated object types which type the target object belongs to (based on image recognition of the 3D scan data), uses that determined type to select the corresponding pre-associated basic shape, and then explicitly fits that selected basic shape to the three-dimensional model prior to dimension measurement. The motivation is to improve measurement accuracy and reliability by ensuring the selected shape is precisely fit and refined to the captured 3D model before dimensions are extracted, as discussed by Taguchi at Column 2, Lines 12–15, where refinement using gradient descent is described as an optional but beneficial step for improving the accuracy of the fitted primitive shape parameters.
Regarding claim 8. The combination of Lloyd and Taguchi teaches the invention in Claim 1.
The combination further teaches wherein the processor: determines posture of the target object (Lloyd, Paragraph [0016]-[0018], "Object information relating to an image of a cylinder lying flat will have ... a continuous range of orientation with respect to the ground ( e.g., 0 = [O, n]) <read on posture>" "The classification module 130 may be configured to categorize an object's shape as ... a right circular cylinder lying flat, [a] right circular cylinder standing vertically” "orientation θ relative to the ground plane <read on posture>);
Lloyd does not explicitly disclose but Taguchi teaches and fits the three-dimensional model to the basic shape selected, using the posture determined (Taguchi, Column 2, Lines 27-31, "Let R be a 3x3 rotation matrix, t a 3 x 1 translation vector, and s be a scale factor ... Then, the ith 3D point p, in the point cloud is transformed to the coordinate system of the distance field as q,=s(Rp,+t) <read on posture/orientation>" Column 4, Line 42-45,, "points ... that define the axis and radius of the cylinder. The direction of the axis is defined as na = n1 x nz <read on posture>" Column 5, Lines 48-56 "We optionally refine the parameters of the best primitive shape using a gradient-descent procedure ... determine a Jacobian matrix with respect to each parameter of the primitive shape for refining the parameters").
Taguchi and Lloyd are analogous since both fit canonical shapes to observed data. Lloyd provided a way of determining posture (lying flat/standing vertically). Taguchi provided a way of refining the selected shape's parameters during fitting, consistent with using the determined posture. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate fitting the selected shape taught by Taguchi into the modified invention of Lloyd such that system will be able to use the posture of the properly fit into the modeling data in order to create more reliable modeling result.
Regarding Claim 9, it recites limitations similar in scope to the limitations of Claim 1 but as a method and the combination of Lloyd and Taguchi teaches all the limitations as of Claim 1. Therefore is rejected under the same rationale.
Regarding claim 10. The combination of Lloyd and Taguchi teaches the invention in Claim 9.
The combination further teaches a non-transitory computer-readable recording medium having recorded thereon a program for causing a computer to execute the dimension measurement method according to claim 9 (Lloyd, Paragraph [0014], “The package-dimensioning system” “Typically, the processing of the image that is acquired by the image capturing subsystem is performed by a computer, which typically has a central processing unit (CPU) and a memory).
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lloyd et al. (EP2843590B1, hereafter Lloyd) in view of Taguchi et al. (US 9208609 B2, hereinafter Taguchi) and further in view of Abe et al. (US 20200125066 A1, hereinafter Abe).
Regarding claim 6. Lloyd teaches a dimension measurement device comprising: a processor and memory (Lloyd, Paragraph [0013]-[0014], "a package-dimensioning system ... the processing of the image that is acquired by the image capturing subsystem is performed by a computer, which typically has a central processing unit (CPU) and a memory"); wherein using the memory, the processor: obtains a three-dimensional model of a target object (Lloyd, Paragraph [0015], "the image-capturing subsystem includes an imaging device (e.g., camera, stereo camera, range camera 110A, lidar)… the image-capturing system is configured to generate a point cloud…The point cloud usually contains information regarding the positioning of points in a three-dimensional space (e.g., X, Y, Z coordinates)… including points on the surface of the object <read on target object>"); [[ determines, from a plurality of locations, a location where the target object or the dimension measurement device is present, the plurality of locations each being associated in advance with one of a plurality of basic shapes ]]; selects, from the plurality of basic shapes, the one of the basic shapes that is associated in advance with the location determined (Lloyd, Paragraph [0018], "the domain of shipped objects 112 is generally limited, with the vast majority of shipped objects 112 being cuboids, cylinders, or prisms … the classification module 130 is typically limited to a relatively small (e.g., between about 4 and 8) number of shape categories" <read on selects, from the plurality of basic shapes>); [[ fits the basic shape selected to the three-dimensional model ]]; and measures a dimension of the target object using the basic shape that has been fitted (Lloyd, Paragraph [0019], "the shape-estimation module 140 would utilize the shape-specific submodule 145 adapted for estimating the dimensions of rectangular boxes … output an estimate of the dimensions (e.g., length, width, and height) of the rectangular box object"). Lloyd does not explicitly disclose but Taguchi teaches fits the basic shape selected to the three-dimensional model (Taguchi, Column 2, Lines 1-15, "The 3D point cloud is converted 105 to a distance field 102. The distance field is used in a RANSAC-based primitive shape fitting process 110, where a set of two or more candidate shapes 100 are hypothesized 111 by using a minimal number of points required to determine parameters of a corresponding shape" "The method selects 120 the best candidate primitive shape that has a minimal score among the candidates" "Optionally, the parameters of the best primitive shape can be refined 130 using a gradient-decent procedure");
Taguchi and Lloyd are analogous since both deal with extracting dimensional measurements from physical objects using 3D scan data, and both rely on selecting among a predefined set of primitive geometric shapes to characterize the scanned object's form before estimating its dimensions. Lloyd provided a way of classifying an object's shape from a feature set derived from a 3D point cloud, constraining the classification to a small set of known shape categories tied to a deployment context (e.g., shipping packages), and then routing to a shape-specific submodule for dimension estimation. Taguchi provided a way of determining the best-fitting primitive shape from among a pre-defined set of candidate primitive shapes by converting the 3D point cloud to a distance field, scoring each candidate shape against the field, and then fitting and refining the selected primitive shape's parameters to the 3D data. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the type-to-shape association and primitive shape fitting process taught by Taguchi into the shape classification and estimation system of Lloyd, such that the processor first determines from a plurality of pre-associated object types which type the target object belongs to (based on image recognition of the 3D scan data), uses that determined type to select the corresponding pre-associated basic shape, and then explicitly fits that selected basic shape to the three-dimensional model prior to dimension measurement. The motivation is to improve measurement accuracy and reliability by ensuring the selected shape is precisely fit and refined to the captured 3D model before dimensions are extracted, as discussed by Taguchi at Column 2, Lines 12–15, where refinement using gradient descent is described as an optional but beneficial step for improving the accuracy of the fitted primitive shape parameters.
But the combination of Lloyd and Taguchi does not explicitly disclose determines, from a plurality of locations, a location where the target object or the dimension measurement device is present, the plurality of locations each being associated in advance with one of a plurality of basic shapes.
However, Abe teaches determines, from a plurality of locations, a location where the target object or the dimension measurement device is present (Abe, Paragraph [0011], "the detecting unit may acquire the position and orientation of the object" <read on determines a location where the target object or the dimension measurement device is present>; [0054], "the measurement program selection assisting apparatus 1 acquires the shape of the object W placed on the stage 112 by the camera 55 or the three-dimensional sensor of the detecting unit 50" <read on determines a location where the target object or the dimension measurement device is present>), the plurality of locations each being associated in advance with one of a plurality of basic shapes (Abe, Paragraph [0047], " arrangement information for measurement indicating the position and orientation of the object W suitable for measuring the object W by the measurement program is stored in advance in association with the measurement program of the object W" <read on the plurality of locations each being associated in advance>; [0038], "the measurement program database 10 stores the measurement program related to measurement of the object W and superimposed display information corresponding to the three-dimensional shape of the object W in association with each other" <read on one of a plurality of basic shapes>), and selects, from the plurality of basic shapes, the one of the basic shapes that is associated in advance with the location determined (Abe, Paragraph [0046], "the measurement program specifying unit 70 refers to the measurement program database 10 for the shape of the object W recognized by the detecting unit 50, and specifies a measurement program corresponding to the object W" <read on selects, from the plurality of basic shapes, the one of the basic shapes that is associated in advance with the location determined>; [0048], "the measurement program correcting unit 80 calculates an error of the position and orientation of the object W acquired by the detecting unit 50 from the arrangement information for measurement corresponding to the measurement program specified by the measurement program specifying unit 70" <read on the one of the basic shapes that is associated in advance with the location determined>).
Abe and Lloyd are analogous since both are directed to automated object measurement systems that use sensor-acquired data to identify an object and automatically select a pre-configured measurement routine suited for that object based on stored associations. Lloyd provided a way of capturing a 3D point cloud of an object at a known operational setting (e.g., a retail shipping station) and routing to a shape-specific submodule based on the object's classification. Abe provided a way of acquiring the position and orientation of an object via a detecting unit and looking up pre-stored arrangement information that associating object locations and orientations in advance with corresponding measurement programs that encode the appropriate geometric shape, thereby automatically selecting the measurement approach tied to where and how the object is situated. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the location-based, pre-association and selection mechanism taught by Abe into the modified combination of Lloyd and Taguchi, such that the processor determines the location where the target object or device is present from among a plurality of locations each pre-associated with a basic shape, and selects the basic shape pre-associated with that determined location, which will improve measurement efficiency and reduce misclassification errors by restricting the candidate shape to the one known to be appropriate for the operating environment or station in which the object is found.
Response to Arguments
Applicant’s arguments with respect to claim 1, 9, 10, filed on 1/27/2026, with respect to rejection under 35 USC § 103 have been considered but is not persuasive.
Applicant asserts that the cited combination of Lloyd and Taguchi does not teach or suggest the feature of amended claim 1 which recites that the processor "determines, from a plurality of types, a type of the target object based on image recognition carried out on an image of the target object, the plurality of types each being associated in advance with one of a plurality of basic shapes." Specifically, Applicant contends that while Lloyd discloses the ability to categorize an object into one of a plurality of shape categories, the amended claim requires that the "types" are distinct from the "basic shapes," and that the plurality of types must each be "associated in advance" with one of the plurality of basic shapes. Applicant further contends that Taguchi does not cure this alleged deficiency.
In response to the argument, applicant's argument is premised on a distinction between "types" and "basic shapes" as if these are necessarily separate and independently managed entities in the claim. However, the claim language does not require that "types" and "basic shapes" be entirely unrelated or managed by wholly distinct systems. The claim requires only that (1) a type is determined from a plurality of types via image recognition on an image of the target object, and (2) each of the plurality of types is associated in advance with one of the plurality of basic shapes. Lloyd clearly discloses both requirements when properly read: Lloyd's classification module 130 determines the type of the target object — for example, categorizing the object as "a rectangular box, a right circular cylinder lying flat, a right circular cylinder standing vertically, a right regular prism with triangular bases lying flat, or a right regular prism with triangular bases standing vertically", by analyzing a feature set derived from image data, "the image-capturing subsystem includes an imaging device... the image-capturing system is configured to generate a point cloud" and "features-computation module 120... compiles a feature set... curvature c and orientation θ relative to the ground plane"). These classifications — rectangular box, cylinder lying flat, cylinder standing vertically, etc. — are precisely the "types" recited in claim 1, and each such type is inherently and necessarily "associated in advance" with the corresponding shape-specific submodule (i.e., the basic shape) in Lloyd's shape-estimation module : "the shape-estimation module 140... includes a plurality of shape-specific submodules 145 adapted for estimating the dimensions of particular shapes... the shape-estimation module... utilize the shape-specific submodule... adapted for estimating the dimensions of rectangular boxes").
Applicant's argument that "types" and "basic shapes" must be different things therefore does not distinguish the claim from Lloyd. In Lloyd, the classification result (the "type") directly and pre-deterministically selects which shape-specific submodule (the "basic shape") is invoked. This is precisely the pre-association recited in claim 1. The fact that Lloyd uses a single classification step that outputs both the type and the corresponding basic shape simultaneously does not negate the teaching — it is the functional relationship of pre-association between the type and the basic shape that matters, and that relationship is plainly present in Lloyd.
Moreover, to the extent Applicant argues that Lloyd's feature set analysis based on curvature and orientation of the point cloud does not constitute "image recognition carried out on an image of the target object," this argument is also unpersuasive. Lloyd expressly discloses that the image-capturing subsystem acquires information about the object using an imaging device (e.g., a range camera) that generates a range image, and that this image data is processed to identify and classify the object's shape. The classification based on the image data of the target object therefore constitutes "image recognition carried out on an image of the target object" as broadly recited in claim 1.
Accordingly, Applicant's arguments have been considered but are not persuasive, and the rejection of claim 1 is maintained. For the same reasons, claim 8, which depends from claim 1, and claims 9 and 10, which recite corresponding method limitations, are also maintained.
Applicant’s arguments with respect to claim 6, filed on 1/27/2026, with respect to rejection under 35 USC § 103 in regard to prior art does not teaches the limitation(s) “interactive computer simulation environment" have been considered but are moot in view of the new ground(s) of rejection. it has now been taught by the combination of prior arts Lloyd, Taguchi and Abe.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20170262999 A1 INFORMATION PROCESSING APPARATUS, COMPUTER-READABLE STORAGE MEDIUM, INFORMATION PROCESSING METHOD
US 20200167936 A1 TRUE SPACE TRACKING OF AXISYMMETRIC OBJECT FLIGHT USING DIAMETER MEASUREMENT
US 20210349627 A1 INTERACTING WITH HANDWRITTEN CONTENT ON AN ELECTRONIC DEVICE
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YUJANG TSWEI whose telephone number is (571)272-6669. The examiner can normally be reached 8:30am-5:30pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kent Chang can be reached at (571)272-7667. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/YuJang Tswei/Primary Examiner, Art Unit 2614
Prosecution Insights