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 .
Typographic Conventions
Throughout this office action, shorthand notation for referencing locations of elements in documents are utilized. The following is a brief summary of the shorthand utilized:
Sec. – is used to denote an associated section with a header in non-patent literature
¶ – is used to denote the number and location of a paragraph
col. – is used to denote a column number
ln. – is used to denote a line; if a line number is not demarcated in a document, the line number will be assumed to start at 1 for each paragraph.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Response to Arguments
Objections to the Drawings
Applicant’s arguments [Sec II – Specification and Drawings; pg. 15], filed 03/25/2026 with respect to objections to the drawings have been fully considered and persuasive. The examiner acknowledges the amendments to the specification correct the previously missing references to drawing elements. The objection to the drawings has been withdrawn.
Objections to the Disclosure:
Applicant’s arguments [Sec II – Specification and Drawings; pg. 15], filed 03/25/2026 with respect to objections to the Specification have been fully considered. The examiner acknowledges the amendments to the specification clarify most but not all of the previously indicated objections. The objection to the specification for all but the following are withdrawn:
The amendment to [¶0026; ln. 4-5] is reproduced as follows: “Although the dimension set may not be a part of the drawing but may contain all of the information of the drawing.” The following amendment still renders the quoted sentence incomplete. The examiner suggests either of the following amendments to correct the sentence syntax:
“Although the dimension set may not be a part of the drawing, it may contain all of the information of the drawing.”
The dimension set may not be a part of the drawing but may contain all of the information of the drawing.”
Rejections under 35 U.S.C. § 101:
Applicant’s arguments [Sec IV – Rejections under 35 U.S.C. § 101; pg. 15-36], filed 03/25/2026 with respect to the rejections made under 35 U.S.C. § 101 have been fully considered and are persuasive. Applicant argues that claims 1-14 not directed to non-statutory subject matter. More specifically, that the claims do not recite a judicial exception (Step 2A – Prong One), are integrated into a practical application (Step 2A – Prong Two), and amount to significantly more than an abstract idea (Step 2B). The examiner agrees that the claims indeed are integrated into a practical application and are thus not directed to a judicial exception and qualify as eligible subject matter under 35 U.S.C. § 101. The rejections under 35 U.S.C. § 101 have been withdrawn.
Rejections under 35 U.S.C. § 112(b):
Applicant’s arguments [Sec III – Rejections under 35 U.S.C. § 112(b); pg. 15], filed 03/25/2026 with respect to the rejections made under 35 U.S.C. § 101 have been fully considered and are persuasive. Specifically, applicant has amended claims 7 and 14 to depend on claims 6 and 13, respectively, to resolve the previously indicated lack of antecedent basis for the limitation “annotation data”. The rejections under 35 U.S.C. § 112(b) have been withdrawn.
Rejections under 35 U.S.C. § 102 & 103:
Applicant’s arguments [Sec V– Rejections under 35 U.S.C. § 102 & 103; pg. 36-44], filed 03/25/2026 with respect to the rejections made under 35 U.S.C. § 102 have been fully considered but are not persuasive. The specific reasons are explained below:
Argument 1
Applicant argues that Lai (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) fails to teach, disclose or otherwise suggest “clustering (1310) the plurality of arrowheads to obtain a plurality of set arrowheads;”. Applicant argues that the method disclosed by Lai fails to create or maintain arrowhead sets as independent entities, that the arrowhead grouping disclosed by Lai is merely incidental as a result of path traversal, and that Lai does not disclose a clustering of arrowheads into sets based on their relationships. The examiner respectfully disagrees. While the examiner notes that the processes detailed in Lai differ from those disclosed in the instant application, the claims, as they are currently constructed, are still anticipated by Lai.
The claim language does not necessitate that “clustering the plurality of arrowheads” be performed via a particular operation based on a defined criteria to obtain a set of arrowheads as independent entities. One of ordinary skill in the art can interpret the act of “clustering” under broadest the reasonable interpretation as “to collect a number of similar things together / to come together to form a group” (see Meriam-Webster’s Dictionary for the definition of the verb “cluster”).
The examiner acknowledges that the method disclosed by Lai does not independently group sets of arrowheads as a computationally distinct step as the disclosure of the instant application, however, the claim language as recited does not inherently necessitate this as an independent step. In fact, the claim language provides no particular indication of the order of operation needed, only that arrowheads are grouped together to form sets of arrowheads. Instead, Lai’s use of leader extraction and tracking ultimately result in obtaining pairs of arrowheads.
Similarly, while Lai does not explicitly disclose that arrowhead pairs are treated as distinct data units, the claim language has no explicit requirement for this distinction, only that arrowheads are grouped into sets, which Lai still accomplishes by identifying complete arrowhead pairs as exemplified in Fig. 3(d & f). Therefore, the applicant’s argument is not persuasive.
Argument 2
Applicant argues that Lai (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) fails to teach, disclose or otherwise suggest “mapping (1312) each of the plurality of set of arrowheads with the dimension value; and”. Applicant argues that method disclosed by Lai uses fundamentally different technical operations, wherein text corresponding to dimension values are associated to dimension lines, as opposed to the invention disclosed by the instant application that recites an independent step of mapping a specific dimension value to an already clustered set of arrowheads. While the examiner acknowledges the differences between the processes utilized by Lai and the instant application, the examiner disagrees with the conclusion that Lai does not anticipate the previously quoted claim language.
Mapping each set of arrowheads to an associated set of dimension values does not strictly necessitate that these arrowhead sets are clustered as distinct entities. Rather, mapping, understood through the broadest reasonable interpretation of one of ordinary skill in the art, in this context, only requires an association between a dimension value and a set of arrowheads. While Lai’s method uses run-length smearing to assign text blocks to their nearest leader pairs, these leader pairs are inherently associated with arrowhead pairs [Sec 3.2 – Extraction of Complete Leaders; ¶01]. The process of extracting complete leaders begins with detecting and tracking arrowheads, which results in every arrowhead or arrowhead pair being associated with a particular dimension value.
Applicant argues that Lai’s mapping to text regions fails to disclose a dimension value as a distinct data element. Examiner believes this is a misconstrued interpretation of the Lai’s method for associating text. These text regions represent a basic dimension illustrated in the engineering drawing, and inherently function as distinct data element in order for the frame extraction [Sec 3.6 – Frame Extraction; ¶01] to be performed.
Lastly, applicant further argues that Lai fails to teach a pre-conditioned mapping pipeline. The examiner reiterates that the claim language, as currently presented, does not limit prior art to perform the recited steps in an identical sequence as that of the disclosed invention of the instant application. Rather, the claim language simply recites a step of mapping, or associating, a set of dimension values to a set of arrowheads. Therefore, the applicant’s argument is not persuasive.
Argument 3
Applicant argues that Lai (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) fails to teach, disclose or otherwise suggest “extracting (1314) dimension data corresponding to each of the plurality of set of arrowheads, based on the mapping”. Applicant argues that the method disclosed by Lai fails to perform mapping-dependent extraction of dimension data, and that this dimension data is simply visually grouped and lacks structured output for downstream processing. Furthermore, applicant argues that Lai’s method is directed to text and frame-centric extraction, as opposed to arrowhead-centric extraction of the claimed invention. The examiner acknowledges the functional difference between Lai’s disclosure and the disclosed invention of the instant application, but disagrees with the applicant’s assessment of Lai’s disclosure not anticipating the claimed invention.
Lai first discloses that the dimension data extracted from text regions (described as feature control frames [Sec 3.6 – Frame Extraction; ¶01]) is first associated with particular dimensioning lines to result in a complete dimensioning set. The extraction performed in Lai is still based on the aforementioned association (or mapping) of text to dimension lines [Sec 3.5 – Association of Text with Dimensioning Lines; ¶01-02], which in turn correspond to the set of arrowheads identified [Sec 3.2 – Extraction of Complete Leaders; ¶01].
Furthermore, applicant argues that the output of the extraction performed by Lai is a simple visual depiction rather than structured data. Lai provides context that this extraction still treats data in text blocks as distinct entities, and further cites the use for integrating said extracted data for complete integration into CAD/CAM systems [Sec 5 – Summary & Conclusions; ¶01]. While Lai does not elaborate on downstream applications of the extracted values, or a particular conversion into a structured data element, the claim language does not necessitate such specifics in order to be anticipated by the cited prior art.
Applicant’s final argument is directed to Lai’s lack of disclosing an arrowhead-centric extraction of dimension values. While Lai’s method of extraction focuses on detection of text in association with dimension lines through run-length smearing, this still falls under the broadest reasonable interpretation that the extraction of dimension data merely “corresponds” to each of the plurality of set of arrowheads. Given that the frame extraction ultimately results in a complete dimension set comprising arrowhead pairs, dimension lines, and dimension values (extracted from text boxes), the dimension data, by association, “corresponds” to pairs of arrowheads. Therefore, the applicant’s argument is not persuasive.
Specification
The disclosure is objected to because of the following informalities:
As previously noted in “Response to Arguments”, The amendment to [¶0026; ln. 4-5] in the specification is still unclear and is reproduced as follows: “Although the dimension set may not be a part of the drawing but may contain all of the information of the drawing.” The following amendment still renders the quoted sentence incomplete. The examiner suggests either of the following amendments to correct the sentence syntax:
“Although the dimension set may not be a part of the drawing, it may contain all of the information of the drawing.”
The dimension set may not be a part of the drawing but may contain all of the information of the drawing.”
Claim Objections
Claims 1, 4, 8, and 11 are objected to because of the following informalities
Claims 1, 4, 8, 11 recite the phrase “set of arrowheads”. The examiner believes applicant intended to recite this as “sets of arrowheads”.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 4-6 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lai et al (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE).
Regarding claim 1, Lai et al teach A method of extracting dimension data from a document (method for extracting text from engineering drawings into complete dimension sets [Fig. 4]), the method comprising:
receiving (1302) the document comprising at least one two-dimensional figure and a plurality of dimension sets associated with the at least one two-dimensional figure (engineering drawings (depicted in Fig. 1 with a 2D orthographic view and associated dimension sets) are uploaded and digitized [Fig. 4]), wherein each of the plurality of dimension sets comprises:
a dimension value;
a set of extension lines associated with the dimension value; and
a set of arrowheads associated with the dimension value (dimension sets depicted in the engineering drawing of Fig. 1, wherein dimension values, extension lines (herein referred to as witness lines), and arrowheads demarcate distinct dimensional features of the orthographic view);
detecting (1304) the at least one two-dimensional figure in the document (object lines (the outlines of the two-dimensional figure) are extracted in the 2-D interpretation step of Fig. 4 [Sec 4 – Extraction of Object Lines] and are depicted in Fig. 14);
detecting (1306) the plurality of dimension sets distinctly from the at least one two-dimensional figure in the document (dimension sets detected and separated from graphical elements in the segmentation step of Fig. 4 [Sec. 2 – Separation of Text from Graphics, ¶ 01], more specifically, the disclosed algorithm detects arrowheads and then backtracks from the detected arrowheads to find other components of the dimension set [Sec. 2 – Detection of Dimensioning Lines, ¶ 02]);
upon (1308) detecting the plurality of dimension sets, identifying a plurality of arrowheads associated with the plurality of dimension sets (arrowheads are detected from the skeletonized image via arrowhead model matching [Sec. 3.1 – Arrowhead Detection, ¶ 01-04]; Fig. 8 & 9);
clustering (1310) the plurality of arrowheads to obtain a plurality of set of arrowheads (pair matching performed is performed by detecting arrows and backtracking to extract the complete leader and match arrowhead pairs [Sec. 3.2 – Extraction of Complete Leaders, ¶ 01-3; Figs. 3(d & f) & 10]);
mapping (1312) each of the plurality of set of arrowheads with the dimension value (text regions are enclosed in blocks and associated with their nearest dimensioning line following a set of matching rules outlined for different case scenarios in Fig. 3(a-g) [Sec. 3.5 – Association of Text with Dimensioning Lines, ¶ 01-02]); and
extracting (1314) dimension data corresponding to each of the plurality of set of arrowheads, based on the mapping (text within enclosed blocks are known as feature control frame, which upon detection, is extracted [Sec. 3.6 – Frame Extraction, ¶ 01; Fig. 13]).
Regarding claim 4, Lai et al teach the method of claim 1 (as previously described), wherein mapping (1312) each of the set of arrowheads with the dimension value comprises: capturing position data associated with the at least one two-dimensional figure (the remaining vectorized graphics (which provide coordinate information for each vectorized element) corresponding to object lines are extracted and corrected for any line breaks from the dimension set extraction [Sec. 4 – Extraction of Object Lines; results in Fig. 14]) and each of the plurality of dimension sets (a connected component generation algorithm was designed and used for segmenting the engineering drawing, wherein coordinates corresponding to textual elements are generated [Sec. 2 – Separation of Text from Graphics, ¶ 02; Fig. 5], for each arrowhead, coordinate data relating to the tip, back, and terminating point are recorded, as well as the orientation for each leader [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]); and
mapping each of the plurality of set of arrowheads with the dimension value based on the position data associated with the at least one two-dimensional figure and each of the plurality of dimension sets (dimension text is associated with dimension lines of arrowheads, with tails terminating at or near their associated two-dimensional figure elements [Sec. 3.5 – Association of Text with Dimensioning Lines, ¶ 01-02; Fig. 13], see also Fig. 5 which illustrates the positioning of dimension sets).
Regarding claim 5, Lai et al teach the method of claim 1 (as previously described), further comprising:
converting the at least one two-dimensional figure into a binary image (scanning the document involves a built-in binarization step [Sec. 1 – Introduction, ¶ 02; Segmentation of Fig. 4]).
Regarding claim 6, Lai et al teach the method of claim 1 (as previously described), further comprising:
upon identifying the plurality of arrowheads, annotating each of the plurality of identified arrowheads with annotation data (complete leaders (arrowheads and tails) are labeled in the leader pair detection process [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]), wherein the annotation data comprises:
an orientation of each of the plurality of arrowheads; and
a location of each of the plurality of arrowheads (for each arrowhead, coordinate data relating to the tip, back, and terminating point are recorded, as well as the orientation for each leader [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 8, 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over Lai et al (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) in view of Schaefer et al (US 2021/0073530).
Regarding claim 8, Lai et al teach a system for extracting dimension data from a document (a three-phase system for extracting text from engineering drawings into complete dimension sets [Sec 1 – Introduction, ¶ 04; Fig. 4]),
receive (1302) the document comprising at least one two-dimensional figure and a plurality of dimension sets associated with the at least one two-dimensional figure (engineering drawings (depicted in Fig. 1 with a 2D orthographic view and associated dimension sets) are uploaded and digitized [Fig. 4]), wherein each of the plurality of dimension sets comprises:
a dimension value;
a set of extension lines associated with the dimension value; and
a set of arrowheads associated with the dimension value (dimension sets depicted in the engineering drawing of Fig. 1, wherein dimension values, extension lines (herein referred to as witness lines), and arrowheads demarcate distinct dimensional features of the orthographic view);
detect (1304) the at least one two-dimensional figure in the document (object lines (the outlines of the two-dimensional figure) are extracted in the 2-D interpretation step of Fig. 4 [Sec 4 – Extraction of Object Lines] and are depicted in Fig. 14);
detect (1306) the plurality of dimension sets distinctly from the at least one two-dimensional figure in the document (dimension sets detected and separated from graphical elements in the segmentation step of Fig. 4 [Sec. 2 – Separation of Text from Graphics, ¶ 01], more specifically, the disclosed algorithm detects arrowheads and then backtracks from the detected arrowheads to find other components of the dimension set [Sec. 2 – Detection of Dimensioning Lines, ¶ 02]);
upon (1308) detecting the plurality of dimension sets, identify a plurality of arrowheads associated with the plurality of dimension sets (arrowheads are detected from the skeletonized image via arrowhead model matching [Sec. 3.1 – Arrowhead Detection, ¶ 01-04]; Fig. 8 & 9);
cluster (1310) the plurality of arrowheads to obtain a plurality of set of arrowheads (pair matching performed is performed by detecting arrows and backtracking to extract the complete leader and match arrowhead pairs [Sec. 3.2 – Extraction of Complete Leaders, ¶ 01-3; Figs. 3(d & f) & 10]);
map (1312) each of the plurality of set of arrowheads with the dimension value (text regions are enclosed in blocks and associated with their nearest dimensioning line following a set of matching rules outlined for different case scenarios in Fig. 3(a-g) [Sec. 3.5 – Association of Text with Dimensioning Lines, ¶ 01-02]); and
extract (1314) dimension data corresponding to each of the plurality of set of arrowheads, based on the mapping (text within enclosed blocks are known as feature control frame, which upon detection, is extracted [Sec. 3.6 – Frame Extraction, ¶ 01; Fig. 13]).
Lai however fails to specifically disclose the claimed processor and memory. Schaefer et al is analogous art pertinent to the technological problem addressed in this application and teaches the system comprising:
a processor (1702) (processing system 808 [Fig. 8]); and
a memory (1706) communicatively coupled to the processor (1702), wherein
the memory (1706) stores processor instructions, which, on execution, causes the processor (1702) to (read-only memory (ROM) 812 or random-access memory (RAM) 816 [Fig. 8]):
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al in view of Schaefer et al to utilize the processor(s) and memory disclosed in Schaefer to aid the implementation of the method outlined in Lai et al. This provides a technical advantage in automating the aforementioned dimension extraction method and allows for substantial time savings [Schaefer et al: ¶ 0012].
Regarding claim 11, Lai et al in view of Schaefer teach the system of claim 8, (as previously described). Lai et al further disclose wherein to map (1312) each of the set of arrowheads with the dimension value, the processor executable instructions further cause the processor to:
capture position data associated with the at least one two-dimensional figure (Lai et al: the remaining vectorized graphics (which provide coordinate information for each vectorized element) corresponding to object lines are extracted and corrected for any line breaks from the dimension set extraction [Sec. 4 – Extraction of Object Lines; results in Fig. 14]) and each of the plurality of dimension sets (Lai et al: a connected component generation algorithm was designed and used for segmenting the engineering drawing, wherein coordinates corresponding to textual elements are generated [Sec. 2 – Separation of Text from Graphics, ¶ 02; Fig. 5], for each arrowhead, coordinate data relating to the tip, back, and terminating point are recorded, as well as the orientation for each leader [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]); and
map each of the plurality of set of arrowheads with the dimension value based on the position data associated with the at least one two-dimensional figure and each of the plurality of dimension sets (Lai et al: dimension text is associated with dimension lines of arrowheads, with tails terminating at or near their associated two-dimensional figure elements [Sec. 3.5 – Association of Text with Dimensioning Lines, ¶ 01-02; Fig. 13], see also Fig. 5 which illustrates the positioning of dimension sets).
Regarding claim 12, Lai et al in view of Schaefer teach the system of claim 8, (as previously described). Lai et al further disclose wherein the processor executable instructions further cause the processor to:
convert the at least one two-dimensional figure into a binary image (Lai et al: scanning the document involves a built-in binarization step [Sec. 1 – Introduction, ¶ 02; Segmentation of Fig. 4]).
Regarding claim 13, Lai et al in view of Schaefer et al teach the system of claim 8, (as previously described). Lai et al further disclose wherein the processor executable instructions further cause the processor to:
upon identifying the plurality of arrowheads, annotate each of the plurality of identified arrowheads with annotation data (Lai et al: complete leaders (arrowheads and tails) are labeled in the leader pair detection process [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]), wherein the annotation data comprises:
an orientation of each of the plurality of arrowheads; and
a location of each of the plurality of arrowheads (Lai et al: for each arrowhead, coordinate data relating to the tip, back, and terminating point are recorded, as well as the orientation for each leader [Sec 3.2 – Extraction of Complete Leaders, ¶ 02]).
Claims 2 & 9 are rejected under 35 U.S.C. 103 as being unpatentable over Lai et al (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) in view of Schaefer et al (US 2021/0073530) further in view of Cinnamon et al (US 10210631 B1).
Regarding claim 2, Lai et al teach the method as claimed in claim 1 (as previously described), but does not teach using a machine learning model for identifying arrowheads.
Schaefer et al is analogous art pertinent to the technological problem addressed in this application and teaches wherein the plurality of arrowheads associated with the plurality of dimension sets are identified using a trained machine learning model, wherein the machine learning model is trained using a training image dataset (Schaefer et al: a machine learning component (112) receives a training dataset (106) [Fig. 1] which can include arrows [¶ 0024]), but does not teach training data comprised of true and false images.
Cinnamon et al is a pertinent to the technological problem addressed and teaches wherein the training image dataset comprises:
a set of images of unique true arrowheads;
and a set of images of false arrowheads (Cinnamon et al: the neural network (discriminator 404; Fig. 4) is trained on training data using images that are specified as either real or fake [¶ 80]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al in view of Schaefer et al further in view of Cinnamon et al to utilize machine learning for identifying arrowheads using true and false arrowhead training data. Utilizing a deep learning system for arrowhead recognition disclosed in Schaefer et al provides a technical advantage of streamlined automated workflows which can allow for substantial time saving [Schaefer et al: ¶ 0012]. By training the aforementioned deep learning system using both true and false image training data as described in in Cinnamon et al improves both the volume and quality of training data to improve overall identification accuracy [Cinnamon et al: ¶ 0014].
Regarding claim 9, Lai et al in view of Schaefer et al teach the system of claim 8, (as previously described). Schaefer et al further disclose wherein the plurality of arrowheads associated with the plurality of dimension sets are identified using a trained machine learning model, wherein the machine learning model is trained using a training image dataset (Schaefer et al: a machine learning component (112) receives a training dataset (106) [Fig. 1] which can include arrows [¶ 0024]), but does not teach training data comprised of true and false images.
Cinnamon et al teaches wherein the training image dataset comprises:
a set of images of unique true arrowheads;
and a set of images of false arrowheads (Cinnamon et al: the neural network (discriminator 404; Fig. 4) is trained on training data using images that are specified as either real or fake [¶ 80]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al in view of Schaefer et al further in view of Cinnamon et al to utilize machine learning for identifying arrowheads using true and false arrowhead training data. Utilizing a deep learning system for arrowhead recognition provides a technical advantage of streamlined automated workflows which can allow for substantial time saving [Schaefer et al: ¶ 0012]. By training the aforementioned deep learning system using both true and false image training data as described in in Cinnamon et al improves both the volume and quality of training data to improve overall identification accuracy [Cinnamon et al: ¶ 0014].
Claims 3 & 7 are rejected under 35 U.S.C. 103 as being unpatentable over Lai et al (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) in view of Das et al (“Recognition of Dimension Sets and Integration with Vectorized Engineering Drawings”, 1995, IEEE).
Regarding claim 3, Lai et al teach the method of claim 1 (as previously described), but does not teach segmenting the plurality of arrowheads via an image processing algorithm.
Das et al is analogous art pertinent to the technological problem addressed in this application and teaches:
wherein identifying (1308) the plurality of arrowheads comprises segmenting each of the plurality of arrowheads from the at least one two-dimensional figure via an image processing algorithm (Das et al: arrowheads are recognized via an image segmentation routine [Sec. 2.1 – Arrowhead recognition; Fig. 2]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al with the teachings of Das et at to segment the arrowheads in a two-dimensional figure to simplify the image representation and account for any errors introduced during scanning and vectorization [Das et al: Sec. 4 – Results, ¶ 01; Tables 1 & 2].
Regarding claim 7, Lai et al teach the method of claim 1 (as previously described), but does not teach classifying the plurality of arrowheads based on orientation information.
Das et al further teach wherein clustering (1310) the plurality of arrowheads comprising:
classifying each of the plurality of arrowheads into one of a plurality of orientation-based classifications based on the annotation data and a predefined rule (Das et al: dimension line information is used to obtain arrowhead orientation [Sec. 2.3 – Arrowhead orientation and grouping, ¶ 01]), wherein the plurality of orientation-based classifications comprises:
an upwards orientation;
a downward orientation;
a left orientation;
a right orientation;
a left-upwards orientation;
a left-downward orientation;
a right-upwards orientation;
and a right -downward orientation (Das et al: arrowhead orientation is classified as either horizontal, vertical, or oblique [Sec. 2.3 – Arrowhead orientation and grouping, ¶ 01]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al with the teachings of Das et al to classify arrowheads based on their orientation. Arrowhead classification by orientation provides additional contextual information which provides an added control for matching dimension sets to object features to minimize errors introduced during scanning and vectorization [Das et al: Sec. 4 – Results, ¶ 01; Tables 1 & 2].
Claims 10 & 14 is rejected under 35 U.S.C. 103 as being unpatentable over Lai et al (“Detection of Dimension Sets in Engineering Drawings”, 1993, IEEE) in view of Schaefer et al (US 2021/0073530) further in view of Das et al (“Recognition of Dimension Sets and Integration with Vectorized Engineering Drawings”, 1995, IEEE).
Regarding claim 10, Lai et al in view of Schaefer et al teach the system of claim 8, (as discussed previously), but does not teach segmenting the plurality of arrowheads via an image processing algorithm.
Das et al is analogous art pertinent to the technological problem addressed in this application and teaches wherein, to identify (1308) the plurality of arrowheads, the processor-executable instructions further cause the processor to segment each of the plurality of arrowheads from the at least one two-dimensional figure via an image processing algorithm (Das et al: arrowheads are recognized via an image segmentation routine [Sec. 2.1 – Arrowhead recognition; Fig. 2]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al with the teachings of Das et at to segment the arrowheads in a two-dimensional figure to simplify the image representation and account for any errors introduced during scanning and vectorization [Das et al: Sec. 4 – Results, ¶ 01; Tables 1 & 2].
Regarding claim 14, Lai et al in view of Schaefer teach the system of claim 8 (as previously described), but does not teach classifying the plurality of arrowheads based on orientation information.
Das et al further teach wherein, to cluster (1310) the plurality of arrowheads, the processor-executable instructions further cause the processor to:
classify each of the plurality of arrowheads into an orientation-based classification of a plurality of orientation-based classifications based on the annotation data and a pre-defined rule (Das et al: dimension line information is used to obtain arrowhead orientation [Sec. 2.3 – Arrowhead orientation and grouping, ¶ 01]), wherein the plurality of orientation-based classifications comprises:
an upwards orientation;
a downward orientation;
a left orientation;
a right orientation;
a left-upwards orientation;
a left-downward orientation;
a right-upwards orientation;
and a right -downward orientation (Das et al: arrowhead orientation is classified as either horizontal, vertical, or oblique [Sec. 2.3 – Arrowhead orientation and grouping, ¶ 01]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the teachings of Lai et al with the teachings of Das et al to classify arrowheads based on their orientation. Arrowhead classification by orientation provides additional contextual information which provides an added control for matching dimension sets to object features to minimize errors introduced during scanning and vectorization [Das et al: Sec. 4 – Results, ¶ 01; Tables 1 & 2].
Conclusion
THIS ACTION IS MADE FINAL. 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 Michael M. Sofroniou whose telephone number is (571)272-0287. The examiner can normally be reached M-F: 8:30 AM - 5:00 PM.
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, John M. Villecco can be reached at (571) 272-7319. 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.
/MICHAEL M SOFRONIOU/Examiner, Art Unit 2661
/JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661
Prosecution Insights