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 .
Status of Claims
The present application is being examined under the claims filed 05/20/2026.
Claims 1-8 and 10-20 are pending.
Response to Amendment
This Office Action is in response to Applicant’s communication filed 05/20/2026 in response to office action mailed 11/20/2025. The Applicant’s remarks and any amendments to the claims or specification have been considered with the results that follow.
Response to Arguments
Regarding 35 U.S.C. 101 rejections
In Remarks page 1, Argument 1
(Examiner summarizes Applicant’s arguments) Applicant argues various reasons why the rejections under 35 U.S.C. 101 should be withdrawn.
Examiner’s response to Argument 1
The rejections under 35 U.S.C. 101 are withdrawn thus rendering Applicant’s arguments moot.
Regarding art-based rejections:
In Remarks pages 6-9, Argument
(Examiner summarizes Applicant’s arguments) Applicant argues that Deshmukh does not teach certain limitations of the independent claims, as amended.
Examiner’s response to Argument
New rejections are made under 35 U.S.C. 103, where Deshmukh is no longer relied upon for the limitations argued by Applicant, rendering Applicant’s arguments moot. Due to new grounds of rejection herein, this office action is made non-final accordingly.
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.
Claims 1, 4-6, 8, 11-12., 15-17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Migdal et al. (PGPUB no. US20150193780A1) herein referred to as Migdal in view of Deshmukh et al. (PGPUB no. US20210217129A1) herein referred to as Deshmukh.
Regarding Claim 1
Migdal teaches:
A method comprising: capturing, by a scanner device comprising an image sensor, first image data representing at least a portion of a first item;
(paragraph [0041]) “The camera may be positioned to capture an image of the item being transacted over the barcode scanner. The image may be captured such that it includes the barcode and a surrounding of the barcode.”
determining a first item template associated with the first barcode,
(paragraph [0061]) “In one embodiment, the model visual signature may be obtained by collecting a group of visual signatures from the item. As the item is transacted multiple times over the checkout terminal in a period of time, the visual signatures from each of the transactions of the item may be collected. Once collected, a probabilistic model of the group of visual signatures may be calculated to obtain the model visual signature that can be compared against the visual signature of the item as the item is transacted post obtainment of the model visual signature.”
the first item template comprising first identifier data identifying the first item from among other items and first region-of-interest data specifying a first region-of-interest of the first item and representing at least one of a contextual or a geometric relationship between the first barcode represented in the first image data and the first region-of-interest of the first item;
(paragraph [0060]) “The similarity may be determined by comparing the visual signature from the image to the model visual signature linked to the item or the item identifier number[*Examiner notes: item template comprising first identifier data].”; (paragraph [0063]) “By way of a non-limiting example, a nonparametric probabilistic model can be constructed by collecting ten of the visual signatures from the most recent transactions of the item. The similarity of a new visual signature from a subsequent item can be determined by first comparing the new visual signature to each of the ten visual signatures within the nonparametric probabilistic model.”; (paragraph [0095]) “The detected barcode 1008 obtained from the image by either the camera or the optical-based scanner is identified. In the surrounding of the barcode 1009, a plurality of interesting points (1001 1002 1003 1004 1005 1006 1007) are detected[*Examiner notes: mapped to first region of interest] by the computer. In this exemplary embodiment, the visual signature comprises the plurality of interesting points, the barcode, and locations of each of the plurality of interesting points relative to the barcode[*Examiner notes: geometric or contextual relationship between barcode and region of interest].”
generating second image data comprising the first region-of-interest of the first image data;
(paragraph [0058]) “Further, the computer may obtain a visual signature from the image. In one embodiment, the interesting point may be automatically chosen by the interest operator[*Examiner notes: first region-of-interest]. The interest operator is an image processing functions that detect interesting locations within an image.”; [*Examiner notes: The first image data is the raw image taken by the capturing device. The second image data is the visual signature of the image captured.]
and generating first data indicating that the first barcode is matched with the first item.
(paragraph [0026]) “The change can be verified by comparing the item's visual features linked to the barcode with the item's visual features obtained during a transaction of such item at the checkout terminal. Once the barcode is switched to another item, the corresponding visual features are likely to be altered, thus the present invention provides a system and method that is capable of detecting such changes by verifying the visual features of the item in question. Each of the items being scanned over the checkout terminal may be severally verified[*Examiner notes: generating data indicating barcode is matched with item] by the system and method provided herein.”
Migdal does not explicitly teach:
decoding, by the scanner device, a first barcode represented in the first image data;
determining, by a first machine learning model, that the second image data corresponds to the first identifier data identifying the first item;
However, Deshmukh teaches:
decoding, by the scanner device, a first barcode represented in the first image data;
(paragraph [0058]) “It receives each code from the scanner, in response to the scanner decoding UPC and Digimarc Barcode data carrier during check-out. A processor in the scanner executes firmware instructions loaded from memory to perform these decoding operations.”
determining, by a first machine learning model, that the second image data corresponds to the first identifier data identifying the first item;
(paragraph [0201]) “The scanner may also include a recognition unit that implements an image recognition method[*Examiner notes: machine learning model] for identifying a product in a store's inventory as well as product labels, such as price change labels. In such a system, reference image feature sets of each product are stored in a database of the scanner's memory and linked to an item identifier for a product and/or particular label (e.g., price change label). The recognition unit extracts corresponding features from an image frame and matches them against the reference feature sets to detect a likely match. If the match criteria are satisfied, the recognition unit returns an item identifier to the controller[*Examiner notes: second image data corresponds to first identifier identifying first item].”
Migdal, Deshmukh, and the instant application are analogous because they are all directed to image classification and/or product scanner devices.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition as taught by Deshmukh because (Deshmukh paragraph [0056]) “Below, we describe approaches for scanner devices to identify items accurately and at higher speed while minimizing use of processing resources within the POS system or requiring manual intervention by the checker.”
Regarding Claim 4
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
And Migdal further teaches:
further comprising: determining, using an object detector, a first bounding box around the first barcode in the first image data;
(paragraph [0093]) “At 802, the affine transform is identified by first fitting the bounding box 603 around the barcode within the image to determine the size and shape of the barcode in the image.”
determining a first size of the first bounding box; determining a first orientation of the first bounding box; determining a second size of a second barcode associated with the first region-of-interest data of the first item template; and determining a ratio between the first size and the second size.
(paragraph [0093]) “In FIG. 8, the image 801 is distorted both with a scale distortion and a rotational distortion. The combination of the scale distortion[*Examiner notes: first size] and the rotational distortion[*Examiner notes: first orientation] results in the affine distortion. To correct the affine distortion, both rotation and scale, from the image, the affine transform can be applied to the image 801. At 802, the affine transform is identified by first fitting the bounding box 603 around the barcode within the image to determine the size and shape of the barcode in the image. Then the size and shape of the barcode in the image is compared[*Examiner notes: determining a ratio] to the predetermined reference size and shape[*Examiner notes: second size associated with template] of the barcode corresponding to the item identifier number to calculate the affine transform. The image at 803 shows the image with the affine distortion removed by applying the affine transform to the image 801.”; [*Examiner notes: The broadest reasonable interpretation of determining a ratio between sizes includes determining a transformation to resize one shape to the same size as another shape]; (Figure 8)
PNG
media_image1.png
503
476
media_image1.png
Greyscale
Regarding Claim 5
Migdal in view of Deshmukh teaches:
The method of claim 4
(see rejection of claim 4)
Deshmukh further teaches:
further comprising determining the first region-of-interest of the first image data based at least in part by: resizing a second bounding box corresponding to the first region-of-interest of the first item in the first item template using the ratio; and applying the re-sized second bounding box to the first image data.
(paragraph [0248]) “The minimum bounding box helps facilitate re-orientation 532 of the candidate contour to resolve image rotation and scale. For example, the bounding box (and its image contents) can be rotated such that one of its edges is horizontal to an image plane. And the image data within the candidate contour can be resized, e.g., according to the sizing of previously stored templates.”
It would have been further obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition of Migdal in view of Deshmukh by further resizing and applying the bounding box to the image data as taught by Deshmukh because (Deshmukh paragraph [0248]) “The minimum bounding box helps facilitate re-orientation 532 of the candidate contour to resolve image rotation and scale” and (Deshmukh paragraph [0258]) “This orientation process helps the icon matching be more rotation invariant relative to an un-rotated block. The block can then be resized 563 to match or approximate the size of the template(s).”
Regarding Claim 6
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Migdal further teaches:
further comprising: capturing, by the scanner device, third image data representing at least a portion of a second item;
(paragraph [0041]) “The camera may be positioned to capture an image of the item being transacted over the barcode scanner. The image may be captured such that it includes the barcode and a surrounding of the barcode.”
determining a second item template associated with the second barcode,
(paragraph [0061]) “In one embodiment, the model visual signature may be obtained by collecting a group of visual signatures from the item. As the item is transacted multiple times over the checkout terminal in a period of time, the visual signatures from each of the transactions of the item may be collected. Once collected, a probabilistic model of the group of visual signatures may be calculated to obtain the model visual signature that can be compared against the visual signature of the item as the item is transacted post obtainment of the model visual signature.”
the second item template comprising second identifier data identifying the second item from among other items and second region-of-interest data specifying a second region-of-interest of the second item that includes the second barcode and a second non-barcode portion of the second item;
(paragraph [0060]) “The similarity may be determined by comparing the visual signature from the image to the model visual signature linked to the item or the item identifier number[*Examiner notes: item template comprising identifier data].”; (paragraph [0063]) “By way of a non-limiting example, a nonparametric probabilistic model can be constructed by collecting ten of the visual signatures from the most recent transactions of the item. The similarity of a new visual signature from a subsequent item can be determined by first comparing the new visual signature to each of the ten visual signatures within the nonparametric probabilistic model.”; (paragraph [0095]) “The detected barcode 1008 obtained from the image by either the camera or the optical-based scanner is identified. In the surrounding of the barcode 1009, a plurality of interesting points (1001 1002 1003 1004 1005 1006 1007) are detected[*Examiner notes: mapped to region of interest having barcode and non-barcode portions] by the computer. In this exemplary embodiment, the visual signature comprises the plurality of interesting points, the barcode, and locations of each of the plurality of interesting points relative to the barcode.” (fig. 10)
PNG
media_image2.png
566
757
media_image2.png
Greyscale
generating fourth image data comprising the second region-of-interest of the third image data;
(paragraph [0058]) “Further, the computer may obtain a visual signature from the image. In one embodiment, the interesting point may be automatically chosen by the interest operator[*Examiner notes: first region-of-interest]. The interest operator is an image processing functions that detect interesting locations within an image.”; [*Examiner notes: The third image data is the raw image taken by the capturing device. The fourth image data is the visual signature information of the image captured.]
Deshmukh further teaches:
decoding, by the scanner device, a second barcode represented in the third image data;
(paragraph [0058]) “It receives each code from the scanner, in response to the scanner decoding UPC and Digimarc Barcode data carrier during check-out. A processor in the scanner executes firmware instructions loaded from memory to perform these decoding operations.”
determining, by the first machine learning model, that the fourth image data is mismatched with respect to the second barcode;
(para [0265]) - "If the number of remaining objects is equal to (or greater than) m, flow moves on to template correlation 566 and comparison with threshold 567 as discussed above with reference to FIG. 20C. If not, it is determined that the candidate does not match the target icon."; (see also paragraph [0072] and [0201])
and generating first output data indicating that the second barcode is mismatched with respect to the second item.
(paragraph [0215]) "To avoid false positives, a "no match" output is produced if the distance score for the best match is close- e.g., 25 %-to the distance score for the next-best match.”
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to combine Migdal with Deshmukh for the same reasons given in claim 1 above.
Regarding Claim 8
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Migdal further teaches:
wherein the first region-of-interest of the first item includes the first barcode and a non-barcode portion of the first item
(paragraph [0095]) “The detected barcode 1008 obtained from the image by either the camera or the optical-based scanner is identified. In the surrounding of the barcode 1009, a plurality of interesting points (1001 1002 1003 1004 1005 1006 1007) are detected[*Examiner notes: mapped to region of interest having barcode and non-barcode portions] by the computer.”; (Fig. 10)
PNG
media_image2.png
566
757
media_image2.png
Greyscale
Regarding Claim 11:
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Migdal further teaches:
wherein the first item template further comprises: a template image of the first region-of-interest of the first item; and at least one of coordinate data representing a location in the template image of the first barcode, orientation data representing an orientation in the template image of the first barcode, or size data representing a size of the first barcode in the template image.
(paragraph [0095]) “FIG. 10 illustrates an exemplary embodiment of the visual signature. The detected barcode 1008 obtained from the image[*Examiner notes: template image] by either the camera or the optical-based scanner is identified. In the surrounding of the barcode 1009 a plurality of interesting points (1001 1002 1003 1004 1005 1006 1007) are detected by the computer. In this exemplary embodiment, the visual signature comprises the plurality of interesting points, the barcode, and locations of each of the plurality of interesting points relative to the barcode[*Examiner notes: coordinate data],”; [*Examiner notes: The model visual signature is composed from an aggregation of collected visual signatures and thus also contains the data contained within its component visual signatures.]
Regarding Claim 12
Claim 12 is a computer system claim corresponding to method claim 1. The only differences are that claim 12 does not include the scanner device and does include a computer system:
Migdal teaches:
A system comprising: an image sensor; at least one processor; and non-transitory computer-readable memory storing instructions that, when executed by the at least one processor, are effective to
(paragraph [0036]) “The system for detecting a fraudulent activity at a checkout terminal is provided. The system may comprise a camera, a barcode scanner, a computer with one or more processors, and a storage unit accessible by the computer via a network.”
The remaining limitations of the claim are taught by the rejection of claim 1.
Regarding Claim 15
Migdal in view of Deshmukh teaches:
The system of claim 12
(see rejection of claim 12)
Migdal further teaches:
the non-transitory computer-readable memory storing further instructions that, when executed by the at least one processor, are further effective to: determine, using an object detector, a first bounding box around the first barcode in the first image data;
(paragraph [0080]) “In another embodiment, the size and shape of the barcode in the image may be determined by fitting a bounding box around the barcode within the image.”
determine a first orientation of the first bounding box; determine a second orientation of the barcode associated with the first region-of-interest data of the first item template;
(paragraph [0092]) “In FIG. 7, the image 701 is distorted with a rotational distortion. To correct the rotational distortion from the image, a rotational transform can be applied to the image 701. At 702, the rotational transform is identified by first fitting the bounding box 603 around the barcode within the image to determine the size and shape of the barcode in the image. Then the size and shape of the barcode in the image is compared to the predetermined reference size and shape of the barcode corresponding to the item identifier number to calculate the rotational transform. The image at 703 shows the image with the rotational distortion removed by applying the rotational transform to the image 701”; (Fig. 7)
PNG
media_image3.png
607
573
media_image3.png
Greyscale
and determine an amount of rotation between the first orientation and the second orientation.
(paragraph [0092]) “At 702, the rotational transform is identified by first fitting the bounding box 603 around the barcode within the image to determine the size and shape of the barcode in the image. Then the size and shape of the barcode in the image is compared to the predetermined reference size and shape of the barcode corresponding to the item identifier number to calculate the rotational transform.”
Regarding Claim 16
Migdal in view of Deshmukh teaches:
The system of claim 15
(see rejection of claim 15)
And Migdal further teaches:
the non-transitory computer-readable memory storing further instructions that, when executed by the at least one processor, are further effective to: re-orient a second bounding box corresponding to the first region-of-interest of the first item in the first item template based on the amount of rotation; and apply the re-oriented second bounding box to the first image data.
(paragraph [0092]) “The image at 703 shows the image with the rotational distortion removed by applying the rotational transform to the image 701”; (Fig. 7)
PNG
media_image3.png
607
573
media_image3.png
Greyscale
Regarding Claim 17
Claim 17 is a computer system claim corresponding to method claim 6. The difference is that claim 6 recites a computer system as taught in the rejection of claim 12 above. The remaining limitations of the claim are taught by the rejection of claim 6.
Regarding Claim 19
Claim 19 is a method claim corresponding to method claim 1. The only difference is that claim 19 recites receiving first image data instead of capturing, by a scanner device comprising an image sensor. The same rejection and rationale applies.
Claims 2, 7, 13, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Migdal, Deshmukh and further in view of Skaff et al. (PGPUB no. US 20190034864 A1) herein referred to as Skaff.
Regarding Claim 2
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Migdal in view of Deshmukh does not teach:
wherein the first machine learning model comprises a convolutional neural network classifier or visual transformer classifier trained to classify a given item based on an image of a predefined region-of-interest of the given item
However, Skaff teaches:
wherein the first machine learning model comprises a convolutional neural network classifier or visual transformer classifier trained to classify a given item based on an image of a predefined region-of-interest of the given item
(paragraph [0046]) “Segmentation can be improved by training classifiers on annotated training data sets, where bounding boxes are manually drawn around products. Training can be performed with supervised or unsupervised machine learning, deep learning, or hybrid machine and deep learning techniques, including but not limited to convolutional neural networks.”
Migdal, Deshmukh, Skaff, and the instant application are analogous because they are all directed to image classification.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition of Migdal in view of Deshmukh with the convolutional neural network of Skaff because (Skaff paragraph [0047]) “Segmentation can be improved by training classifiers on annotated training data sets, where bounding boxes are manually drawn around products. Training can be performed with supervised or unsupervised machine learning, deep learning, or hybrid machine and deep learning techniques, including but not limited to convolutional neural networks.”
Regarding Claim 7
Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Skaff teaches:
further comprising: generating third image data representing a second region-of-interest of a second item, the second region-of-interest representing a second barcode of the second item and at least a second non-barcode portion of the second item;
(paragraph [0045]) “Segmented images can assist in defining a product bounding box that putatively identifies a product facing.”; (paragraph [0098]) “Typically, high resolution images can capture bar codes[*Examiner notes: barcode portion], product names, or other identifiers printed and visible on the product[*Examiner notes: non-barcode portion] box or container.”
generating second identifier data identifying the second item from among other items;
(paragraph [0045]) “Segmented images can assist in defining a product bounding box that putatively identifies a product facing. This information is often necessary to develop a product library[*Examiner notes: identifying the item from among other items].”; (paragraph [0006]) “defining a product bounding box; associating the bounding box to a shelf label[*Examiner notes: identifier data] to build a training data set;”
generating a first training instance comprising the third image data and the second identifier data; and training the first machine learning model to classify items using a training dataset comprising the first training instance.
(paragraph [0006]) “associating the bounding box to a shelf label to build a training data set; and using the training data set to train a product classifier.”
Deshmukh, Skaff, and the instant application are analogous because they are all directed to image classification.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition of Deshmukh with the training taught by Skaff because (Skaff paragraph [0047]) “Segmentation can be improved by training classifiers on annotated training data sets, where bounding boxes are manually drawn around products. Training can be performed with supervised or unsupervised machine learning, deep learning, or hybrid machine and deep learning techniques, including but not limited to convolutional neural networks.”
Regarding Claim 13
Claim 13 is a computer system claim corresponding to method claim 2. The only difference is that claim 13 recites as taught in the rejection of claim 12 above. The remaining limitations of the claim are taught by the rejection of claim 2.
Regarding Claim 18
Claim 18 is a computer system claim corresponding to method claim 7. The only difference is that claim 18 recites as taught in the rejection of claim 12 above. The remaining limitations of the claim are taught by the rejection of claim 7.
Claims 3, 14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Migdal, Deshmukh and further in view of Srivastava et al. (PGPUB no. US 20240095709 A1).
Regarding Claim 3
Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
further comprising: generating, by the first machine learning model, a first vector representing the second image data;
(paragraph [0222]) "Such methods extract local features from patches of an image[*Examiner notes: second image data] (e.g., SIFT points), and automatically cluster the features into N groups (e.g., 168 groups)-each corresponding to a prototypical local feature. A vector of occurrence counts[*Examiner notes: first vector] of each of the groups (i.e., a histogram) is then determined, and serves as a reference signature for the image.
Deshmukh does not explicitly teach:
comparing the first vector to a plurality of item vectors stored in a data store; determining a second vector among the plurality of item vectors based at least in part on a first distance metric used to determine a distance between the first vector and the second vector;
However, Srivastava teaches:
comparing the first vector to a plurality of item vectors stored in a data store; determining a second vector among the plurality of item vectors based at least in part on a first distance metric used to determine a distance between the first vector and the second vector;
(paragraph [0140]) “Additionally or alternatively, determining the item identifier can include determining a distance or similarity score[*Examiner notes: based on distance metric] (e.g., similarity metric) between the unknown item's feature vectors (e.g., image and/or geometric feature vectors) and a set of reference feature vectors[*Examiner notes: plurality of item vectors] (e.g., image and/or geometric feature vectors) associated with a set of known item identifiers, and selecting the item identifier associated with the best distance or similarity score[*Examiner notes: second vector] (e.g., smallest distance, furthest distance, most similar, etc.)”; [*Examiner notes: The second vector is the vector with the best distance or similarity score and the item identifier is the associated identifier]
and determining that the second vector is associated with the first identifier data in the first item template, wherein the determination that the second image data corresponds to the first identifier data is made based at least in part on the second vector being associated with the first identifier data.
(paragraph [0140]) “Additionally or alternatively, determining the item identifier can include determining a distance or similarity score (e.g., similarity metric) between the unknown item's feature vectors (e.g., image and/or geometric feature vectors) and a set of reference feature vectors (e.g., image and/or geometric feature vectors) associated with a set of known item identifiers, and selecting the item identifier associated with the best distance or similarity score (e.g., smallest distance, furthest distance, most similar, etc.); an example is shown in FIG. 12 .”
Deshmukh, Srivastava, and the instant application are analogous because they are all directed to image classification.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition of Deshmukh with the vectors and distance comparisons taught by Srivastava because (Srivastava paragraph [0026]) “First, the method can improve item segmentation and identification accuracy by leveraging 3D visual data instead of processing only 2D data.”
Regarding Claim 14
Claim 14 is a computer system claim corresponding to method claim 3. The only difference is that claim 14 recites a computer as taught in the rejection of claim 12 above. The remaining limitations of the claim are taught by the rejection of claim 3.
Regarding Claim 20
Claim 20 is a method claim corresponding to method claim 3. The same rejection and rationale applies.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Migdal, Deshmukh, and further in view of NPL reference Zhao et al. “Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database” herein referred to as Zhao.
Regarding Claim 10
Migdal in view of Deshmukh teaches:
The method of claim 1
(see rejection of claim 1)
Migdal in view of Deshmukh does not explicitly teach:
wherein the first item template further comprises data representing a barcode type of the first barcode
However, Zhao teaches
wherein the first item template further comprises data representing a barcode type of the first barcode
(pages 3-4) “Note that, we overallly annotate these digital signs into 2 categories: Barcode and QR code , indicated as green and yellow mask as shown in Fig1”
Migdal, Deshmukh, Zhao, and the instant application are analogous because they are all directed to image classification and/or scanner devices.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the present invention to modify the barcode scanning and image recognition as taught by Migdal in view of Deshmukh by using the barcode type data as taught by Zhao because (Zhao page 1) “Barcode and QR code, the most widely appeared digital signs in common life, are employed in factories and supermarkets massively. Using computer vision algorithms to help accurately detect, segment and recognize these digital signs will greatly promote the development of automation in these industries.”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ezra J Baker whose telephone number is (703)756-1087. The examiner can normally be reached Monday - Friday 10:00 am - 8:00 pm ET.
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, David Yi can be reached at (571) 270-7519. 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.
/E.J.B./Examiner, Art Unit 2126
/DAVID YI/ Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights