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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 02/06/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
Amendments to claims filed 07/21/2026 have been acknowledged.
Claims 1 and claim 84 have been amended.
Response to Arguments
Applicant’s arguments with respect to claim 1 and all depending claims have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitations are: “artificial intelligence (AI) module” , and “analysis module“, in claim 1 as well as claim 1’s dependent claims, “artificial intelligence (AI) module” in claim 41 and its dependent claims , “recalibration module” in claim 77 and “artificial intelligence (AI) module” in claim 84.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 and 84 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim 1 recites …”an artificial intelligence (Al) module, trained to identify, directly within multi- dimensional image data corresponding to images of objects, wavelength patterns…” Examiner is uncertain what is objectively meant by “directly” in claim 1. Does “directly” mean there is exclusion of all preprocessing of the image? Does “directly” mean that exclusively raw data is put into the AI module? Without further elaboration of what the word “directly” is pointed to within the claim language, claim 1 is deemed indefinite.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim 1-3, 41, 46 and 54 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”)
As per claim 1
Qiao teaches A system, comprising: an imager configured to acquire images of a sample ( 5. Experiment results and Analysis: “Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5.”) an artificial intelligence (Al) module, trained to identify, directly within multi- dimensional image data corresponding to images of objects (Figure 4, Introduction: “Hyperspectral imaging integrates image processing and spectroscopic techniques to obtain the hyperspectral 3Dcube data (hypercube)… It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information. For example, a 256 × 256RGB image, its actual data storage size is 256 × 256 × 3, where 3 represents its three RGB components. If these 3components are extended to hundreds or thousands of continuous bands, such as 100 continuous bands, the data of the image will be expanded to 256 × 256 × 100, and this 100 is the expansion of the spectrum, which makes the image add rich spectral information. The x and y of a hyperspectral image represent its image in the pixel dimension.” ) Introduction: “The contributions of this article are summarized as follows:(1) An improved Deep Residual 3D Convolutional Neural Network is proposed. input image of the model is the original hyperspectral image, no dimensionality reduction method is needed, and the image space and spectral characteristics are retained…Rich spectral and spatial features can be rapidly extracted from samples of complete hyper spectral images using our proposed network” Qiao’s methodology does not collapse the hyperspectral cube before AI processing. Original/raw image is supplied to the 3D CNN with no dimensionality reduction and preserves the spectral dimension. The AI operates directly within the multidimensional hyperspectral image.) wavelength patterns corresponding to one or more defects within the objects; (5. Experient results and analysis: “the spectral reflectance of the blueberry mildew area in the visible band (450–760 nm) is slightly higher than that of the sound area. In the near infrared band (760–1000 nm), the spectral reflectance of the sound region is higher than that of the mildew region” Qiao identifies the wavelength dependent spectral patterns that directly correlate to defective blueberry tissue. Qiao then states “. The reason for the difference of spectral reflectance between the blueberry mildew area and sound area is that the color of the blueberry mildew area is slightly different from that of sound area, and the main components and physical and chemical properties of the blueberry mildew area are changed due to the decay of blueberry disease so that the spectral reflectance is changed )Therefore, the spectral data of 450–1000 nm range were used to establish a training and testing dataset so as to detect the mildewed blueberry. The Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5.” Qiao says their 3D CNN “performs convolution operations in both spatial and spectral dimensions to extract the features of the “spectral “combination of hyperspectral images. It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information.” In the Deep Residual 3D Convolutional Neural Network section. Qiao’s describes the network input as “3D data matrix in 3D-CNN,which is obtained by taking a pixel in the original image as the center and its size as S × S × L, where L is the number of hyperspectral image channels and S is the size of plane dimension.” Figure 4 shows an input of 7 X 7 X L region extraction where L is the number of channels of the original hyperspectral image. Qiao describes this as “the basic structure of feature extraction is our improved 3D residual convolution structure, and its schematic diagram is shown in Figure 4. The TPE algorithm is adopted to optimize hyperparameters, which can realize end-to-end hyperspectral “spectrum “feature extraction.” Qiao is disclosing that decayed blueberry tissue exhibits distinct wavelength spectral patterns that’s distinguishable from good tissue. That very same spectral data is used to train the AI. Qiao’s 3D CNN directly processes the spectral dimension of the original spectral image to extract spectral features. Therefore, the trained AI identifies wavelength patterns corresponding to blueberry decay within the multidimensional image data.) and an analysis module configured to detect, using the Al module, one or more defects in the sample. (Figure 3, See section 5. Experiment Results and Analysis. Qiao’s classification and detection processing corresponds to the claimed analysis module. It uses the trained 3D CNN to detect and classify decay defects in the blueberry sample)
As per claim 2
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao teaches wherein the analysis module is configured to classify and/or map the detected defect. (Tables 1-3, Figure 3)
As per claim 3
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao teaches The system according to claim 1, wherein the imager comprises a multi- dimensional imager (Figure 5. “The Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5”)
As per claim 41
Qiao teaches A method, comprising: acquiring images of a sample with an imager ( 5. Experiment results and Analysis: “Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5.”) detecting, using an artificial intelligence (Al) module, one or more defects in the sample, the Al module having been trained to identify, within multi-dimensional image data corresponding to images of objects (Figure 4, Introduction: “Hyperspectral imaging integrates image processing and spectroscopic techniques to obtain the hyperspectral 3Dcube data (hypercube)… It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information. For example, a 256 × 256RGB image, its actual data storage size is 256 × 256 × 3, where 3 represents its three RGB components. If these 3components are extended to hundreds or thousands of continuous bands, such as 100 continuous bands, the data of the image will be expanded to 256 × 256 × 100, and this 100 is the expansion of the spectrum, which makes the image add rich spectral information. The x and y of a hyperspectral image represent its image in the pixel dimension.” ) Introduction: “The contributions of this article are summarized as follows:(1) An improved Deep Residual 3D Convolutional Neural Network is proposed. input image of the model is the original hyperspectral image, no dimensionality reduction method is needed, and the image space and spectral characteristics are retained…Rich spectral and spatial features can be rapidly extracted from samples of complete hyper spectral images using our proposed network” Qiao’s methodology does not collapse the hyperspectral cube before AI processing. Original/raw image is supplied to the 3D CNN with no dimensionality reduction and preserves the spectral dimension. The AI operates directly within the multidimensional hyperspectral image.) wavelength patterns corresponding to one or more defects within the objects; (5. Experient results and analysis: “the spectral reflectance of the blueberry mildew area in the visible band (450–760 nm) is slightly higher than that of the sound area. In the near infrared band(760–1000 nm), the spectral reflectance of the sound region is higher than that of the mildew region” Qiao identifies the wavelength dependent spectral patterns that directly correlate to defective blueberry tissue. Qiao then states “. The reason for the difference of spectral reflectance between the blueberry mildew area and sound area is that the color of the blueberry mildew area is slightly different from that of sound area, and the main components and physical and chemical properties of the blueberry mildew area are changed due to the decay of blueberry disease so that the spectral reflectance is changed )Therefore, the spectral data of 450–1000 nm range were used to establish a training and testing dataset so as to detect the mildewed blueberry. The Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5.” Qiao says their 3D CNN “performs convolution operations in both spatial and spectral dimensions to extract the features of the “spectral “combination of hyperspectral images. It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information.” In the Deep Residual 3D Convolutional Neural Network section. Qiaos describes the network input as “3D data matrix in 3D-CNN,which is obtained by taking a pixel in the original image as the center and its size as S × S × L, where L is the number of hyperspectral image channels and S is the size of plane dimension.” Figure 4 shows an input of 7 X 7 X L region extraction where L is the number of channels of the original hyperspectral image. Qiao describes this as “the basic structure of feature extraction is our improved 3D residual convolution structure, and its schematic diagram is shown in Figure 4. The TPE algorithm is adopted to optimize hyperparameters, which can realize end-to-end hyperspectral “spectrum “feature extraction.” Qiao is disclosing that decayed blueberry tissue exhibits distinct wavelength spectral patterns that’s distinguishable from good tissue. That very same spectral data is used to train the AI. Qiao’s 3D CNN directly processes the spectral dimension of the original spectral image to extract spectral features. Therefore the trained AI identifies wavelength patterns corresponding to blueberry decay within the multidimensional image data.)
As per claim 46
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches wherein the step of acquiring images of a sample comprises collecting multi-dimensional data associated with the sample using a multi- dimensional imager. (Figure 4, Figure 5 “The input of the network is a 3D data matrix in 3D-CNN, which is obtained by taking a pixel in the original image as the center and its size as S×S×L, where L is the number of hyperspectral image channels and S is the size of plane dimension.” )
As per claim 54
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches wherein the artificial intelligence module is trained with a training set of multi-dimensional images processed to classify spatio-spectral signatures for the defects. (5. Experiment Results and Analysis “Therefore, the spectral data of 450–1000nm range were used to establish a training and testing dataset so as to detect the mildewed blueberry. The Hyperspectral Imaging System is used to collect spectral images and is showing in figure 5.” “Finally, the image is reshaped to the same size 256 ×256. These images are divided into the training set and the testing set, whose number is shown in Table 1.” “The input of the network is a 3D data matrix with the size of S ×S×L, where L is the number of hyperspectral image channels and S is the field of view… The time taken to train 10 epochs and the time spent on testing with different input sizes are shown in Figure 6. It can be found that the larger the size of input, the longer the training time spends. Since the input of larger size converges faster than the input of smaller size, it also requires more training and testing time. ) Therefore, according to the tradeoff between the recognition performance and calculation efficiency, the input size of the hyperspectral image is fixed as to 7 ×7×L.” “When the sound blueberry hyperspectral images are input into the network for recognition after the network training is completed, more than 50% blueberries are classified as sound and more than 40%are classified as decayed blueberries,” Also see Section 5.6 Generalization Performance)
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 14, 57 and 64 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of Rao et al (Rao hereinafter “Quaternion Based Neural Network for Hyperspectral Image Classification”)
As per claim 14
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao does not teach wherein the Al module comprises a hypercomplex neural network.
Rao wherein the Al module comprises a hypercomplex neural network. (Figure 2 Figure 3, Abstract : “The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels” “Introduction: “a novel quaternion hyperspectral image classification network (QHIC Net), which represents the hyperspectral data in the quaternion domain, is proposed.”)
In a combined teaching, Qiao teaches the system of claim 1 including directly supplying original multidimensional hyperspectral image data into a trained 3D-CNN while retaining its spatial and spectral characteristics to detect defects. Rao teaches implementing hyperspectral image classification using a quaternion based neutral network capable of modeling dependencies between spectral channels. The combined teaching provides Qiao’s direct multidimensional hyperspectral defect detection system utilizing Rao’s quaternion based neural network architecture for processing the spectral information.
Accordingly a person of ordinary skill in the art at the time this invention was effectively filed would have found it obvious to modify Qiao’s methodology with Rao’s concept of using a hypercomplex complex neural network in order to evaluate hyperspectral imaging. Both references address neural network processing and classification of multidimensional hyperspectral imagery and both seek to exploit the relationships elucidated from spectral information. Qiao preserves the spectral dimension of the raw hyperspectral image and performs neural network processing over spectral and spatial dimension. Rao specifically teaches that QHIC can model “local dependencies between spectral channels” while also modeling over all relationships between groups of pixel. Rao states that “CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper” Therefore a person of ordinary skill in the art would have had reason to apply Rao’s quaternion architecture to Qiao’s hyperspectral classification network to efficiently model the interdependent spectral information that Qiao preserves and supplies to their neural network. This modification jointly models relationships among hyperspectral wavelength channels while reducing the number of neural network parameters. This in turn provides efficient spectral spatial feature learning for classification. Rao reports similar classification performance to traditional CNN methods with fewer parameters (See table 6)
As per claim 57
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Rao wherein the Al module comprises a hypercomplex neural network. (Figure 2 Figure 3, Abstract : “The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels” “Introduction: “a novel quaternion hyperspectral image classification network (QHIC Net), which represents the hyperspectral data in the quaternion domain, is proposed.”)
As per claim 64
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches the step of reducing a number of dimensions of the multi-dimensional data. (Although Qiao establishes that the input data is the original multidimensional hyperspectral image (See claim 1 mapping) Qiao later states that after the input “The network input first is proposed by a convolution layer with the convolution kernel of l×l×7 and the step size of l×l×2 and a maximum pooling layer with the kernel of l×l×3 and the step size of l ×l×2 The purpose is to reduce the number of channels and improve the operation efficiency.” This can be seen in figure 4. The original hyperspectral data is inputted directly to the 3D CNN and after the max pooling and convolution it reduces the number of spectral channels. Reducing the channels on the spectral dimension reads on “reducing a number of dimensions of the multi-dimensional data. “ under broadest reasonable interpretation)
Claims 20, 23 and 66 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of Kang et al (Kang hereinafter “Single-cell classification of foodborne pathogens using hyperspectral microscope imaging coupled with deep learning frameworks⋆” )
As per claim 20
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao teaches wherein the defects comprise pathogens (Figure 1, Introduction “Spectral spatial-based residual network introduces the residual structure into the 3D-CNN network and uses two 3D convolution kernels of spectral and spatial features to extract deep features, which can improve the recognition accuracy for mildew blueberries” Section 2. Blueberry and Its Hyperspectral Imaging Features: “In the process of transportation, storage, and sales, they are also prone to rot and disease.” Section 5. Experiment Results and Analysis “When the sound blueberry hyperspectral images are input into the network for recognition after the network training is completed, more than 50% blueberries are classified as sound and more than 40% are classified as decayed blueberries” )
Qiao does not teach the wavelength patterns each correspond to a particular pathogen.
Kang teaches wherein the defects comprise pathogens (Abstract “A high-throughput hyperspectral microscope imaging (HMI) technology with hybrid deep learning (DL) framework defined as “Fusion-Net” was proposed for rapid classification of foodborne bacteria at single-cell level. HMI technology is useful in single-cell characterization, providing spatial, spectral and combined spatial-spectral profiles with high resolution… HMI data were decomposed into three parts as morphological features, intensity images, and spectral profiles. Multiple advanced DL frameworks including long-short term memory (LSTM) network, deep residual network …Taking advantage of fusion strategy, individual DL framework was stacked to form “Fusion-Net” that processed these features simultaneously with improved classification accuracy of up to 98.4 %. Our study demonstrated the ability of DL frameworks to assist HMI technology in single-cell classification as a diagnostic tool for rapid detection of foodborne pathogens) the wavelength patterns each correspond to a particular pathogen (Figure 3, Introduction “In addition, the integrated hyperspectral spectrometer provided spectral information of every pixel from the bacterial cell images, thereby becoming a powerful tool for live single-cell classification.” Introduction: “Besides aforementioned spatial (morphological features) and spectral features (spectral pro files), recent study showed that intensity image (i.e., intensity distribution of spectral image) at the key wavelength provides additional spatial-spectral mapping information for bacterial classification” Kang discloses foodborne pathogens as the defects of interest and teaches particular pathogens possess distinguishable spectral profiles/signatures obtained from hyperspectral wavelength information. Kangs Deep learning classifiers process spectral profiles with the spatial information to distinguish particular pathogens.)
In a combined teaching Qiao teaches direct processing of multidimensional hyper spectral image data using a neural network to identify spectral characteristics corresponding to defects in a sample. Kang teaches using hyperspectral profiles and signatures with trained deep learning classifiers to distinguish particular pathogens. The combined teaching enables Qiao’s system to be applied to pathogens, wherein wavelength dependent spectral patterns correspond to and permit identification of particular pathogens on a blueberry not just the decay of tissue caused by mildew.
Accordingly a person of ordinary skill in the art, at the time this invention was effectively filed would have found it obvious to modify Qiao’s methodology with Kang’s teaching of detection and distinguishment of pathogenic defects using hyperspectral imaging. This is because both references use hyperspectral information and neural network processing to classify biological samples according to their spectral characteristics. Qiao already preserves and analyzes spectral information within multidimensional hyperspectral imagery for detecting defects. Kang teaches that hyperspectral imagining provides distinguishable spectral profiles of foodborne pathogens and that those spectral features can be processed using deep learning classifiers for pathogen identification. Kang gives a practical reason for doing this. Kang states “Routine pathogen testing methods such as culture-based methods using selective media are still “gold standard”, but confirmation of the results requires extra days for sample incubation [3]. Currently, nucleic acid-based polymerase chain reaction (PCR) methods are widely used to detect target pathogens, but high recurring cost of such methods is inescapable issue [4]. Therefore, it is necessary to seek robust, cost-effective, rapid, and reliable early detection methods for foodborne pathogens.” A person of ordinary skill in the art would see this modification enables Qiao’s hyperspectral AI system to rapidly detect and distinguish particular foodborne pathogens based on their respective spectral characteristics, not just the tissue decay itself. This is an extension of Qiao’s system that allows for food safety inspection that provides automated high accuracy classification which can benefit from Kangs reported “98.4% classification accuracy”
As per claim 23
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao in view of Kang teach wherein the sample comprises food (Qiao: Figure 1) and the defects comprises pathogens the defects comprises pathogens. (Qiao: “Figure 1(b) shows the mildewed blueberry.” Kang (Figure3))
As per claim 66
Qiao teaches all previously rejected claim limitations of claim 41 in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao in view of Kang teach wherein the sample comprises food (Qiao: Figure 1) and the defects comprises pathogens the defects comprises pathogens. (Qiao: “Figure 1(b) shows the mildewed blueberry.” Kang (Figure3))
Claims 24, 33, 67 and 76 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of McQuilkin et al (McQuilkin hereinafter US 9551616 B2)
As per claim 24
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
Qiao teaches defects comprise pathogens. (Figure 1(b) shows the mildewed blueberry.”)
Qiao does not teach wherein the sample is an abiotic object
McQuilkin teaches wherein the sample is an abiotic object and the defects comprise pathogens. (Paragraph (119) “System 200 is aimed so that the spectral imaging elements 204 have a cumulative field of view 211 that encompasses surface 212 with multi-wavelength light 207 reflecting from the surface into spectral filter “ Paragraph (188) “Throughout the normalization and calibration process it is desirable to account for variations in intensity such that the relative spectral amplitudes at various wavelengths are maintained.” Paragraph (189) “Advantageously, the present invention may be used in reflectance and/or transmission modes. In reflectance mode the light reflects from the target surface and is detected by the system component…For example, spectral peaks in a transmission spectrum may be at different wavelengths and/or have different amplitudes than spectral peaks in a reflectance spectrum” Paragraph (243) “Biofilms may form on living and non-living surfaces and can be prevalent in many environments, such as, natural, industrial, agricultural and hospital settings” Paragraph (245) “the present invention relates to a method to detect a target substance that is a specific biofilm on a surface…such as E. Coli or Salmonella. In this application a characteristic spectrum of the specific biofilm is obtained by conventional hyperspectral imaging methods or other spectral means. Then specific selected wavelengths are determined that identify the desired spectra. Filter elements passing the selected wavelengths are incorporated into the elements of the spectral filter array.” Paragraph (246) “In the above manner, the present invention may be used as part of a sanitation process for inanimate surfaces to identify the presence of biofilms” Paragraph (477) “Food processing equipment, food preparation surfaces, cooking surfaces, cooking equipment, countertops, vats, beverage containers, storage containers, fermentation containers, stirring vats, pipes, conveyor belts, test equipment, inspection equipment, meat processing equipment, ovens, utensils, vacuum equipment, and bottling equipment.” )
Accordingly, a person of ordinary skill in the art, at the time this invention was effectively filed would have found it obvious to apply Qiao’s hyperspectral defect detection technique to the inanimate surfaces as taught by McQuilkin. A person of ordinary skill in the art would do this because McQuilkin identifies microbial biofilm contamination on food processing surfaces as a target for spectral inspection and teaches that a biofilms characteristic spectrum and selected wavelengths can bee used to detect its presence. Qiao already provides the trained hyperspectral AI architecture for identification of defects from spectral characteristics. McQuilkin allows that pathogenic microbial contamination on abiotic surfaces is another known defect having spectrally detectable characteristics. Applying Qiao’s known hyperspectral classification technique to McQuilkin’s known spectrally distinguishable defects on abiotic surfaces would have been predictable application of hyperspectral defect detection on a known inspection target. A person of ordinary skill in the art can see that this modification gives noninvasive detection of pathogenic microbial contamination on abiotic surfaces. This allows contaminated surfaces in a food processing space to be identified during sanitation inspection. McQuilkin recognizes that contaminants such as biofilms remain after cleaning and may not be visible to the naked eye and that spectral imaging to detect and locate such contamination is useful.
As per claim 33
Qiao teaches all previously rejected claim limitations of claim 1 in claim 1’s 102 rejection. See claim 1’s 102 rejection.
McQuilkin teaches wherein the imager further comprises a hyperspectral array imager comprising an array of unique wavelength filter lenses. (Figure 4, Figure 9, Figure 13 Paragraph (118) A filter array 206 comprising filter elements 208 is incorporated into system 200. The filter array 206 includes a filter element 208 for each spectral imaging element 204.. “Paragraph (119) “System 200 is aimed so that the spectral imaging elements 204 have a cumulative field of view 211 that encompasses surface 212 with multi-wavelength light 207 reflecting from the surface into spectral filter 206.” Paragraph (125) “The ability to capture and evaluate selected wavelengths for different target substances is incorporated into the system via filter elements 244 of the spectral filter array included in card 240 and a custom target algorithm that evaluates captured image information” Paragraph (142) FIG. 13 shows an example of a spectral imaging system 350 whose detection capabilities are easily configured to detect a wide range of target substances. System 350 includes multi-camera array 351 and spectral filter array 358. Multi-camera array 351 includes a lens array of lens elements 352 and corresponding sensor array of sensors 354.”)
As per claim 67
Qiao teaches all previously rejected claim limitations of claim 41 in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches defects comprise pathogens. (Figure 1(b) shows the mildewed blueberry.”)
Qiao does not teach wherein the sample is an abiotic object
McQuilkin teaches wherein the sample is an abiotic object and the defects comprise pathogens. (Paragraph (119) “System 200 is aimed so that the spectral imaging elements 204 have a cumulative field of view 211 that encompasses surface 212 with multi-wavelength light 207 reflecting from the surface into spectral filter “ Paragraph (188) “Throughout the normalization and calibration process it is desirable to account for variations in intensity such that the relative spectral amplitudes at various wavelengths are maintained.” Paragraph (189) “Advantageously, the present invention may be used in reflectance and/or transmission modes. In reflectance mode the light reflects from the target surface and is detected by the system component…For example, spectral peaks in a transmission spectrum may be at different wavelengths and/or have different amplitudes than spectral peaks in a reflectance spectrum” Paragraph (243) “Biofilms may form on living and non-living surfaces and can be prevalent in many environments, such as, natural, industrial, agricultural and hospital settings” Paragraph (245) “the present invention relates to a method to detect a target substance that is a specific biofilm on a surface…such as E. Coli or Salmonella. In this application a characteristic spectrum of the specific biofilm is obtained by conventional hyperspectral imaging methods or other spectral means. Then specific selected wavelengths are determined that identify the desired spectra. Filter elements passing the selected wavelengths are incorporated into the elements of the spectral filter array.” Paragraph (246) “In the above manner, the present invention may be used as part of a sanitation process for inanimate surfaces to identify the presence of biofilms” Paragraph (477) “Food processing equipment, food preparation surfaces, cooking surfaces, cooking equipment, countertops, vats, beverage containers, storage containers, fermentation containers, stirring vats, pipes, conveyor belts, test equipment, inspection equipment, meat processing equipment, ovens, utensils, vacuum equipment, and bottling equipment.” )
As per claim 76
Qiao teaches all previously rejected claim limitations of claim 41 in claim 41’s 102 rejection. See claim 41’s 102 rejection.
McQuilkin teaches wherein the imager further comprises a hyperspectral array imager comprising an array of unique wavelength filter lenses. (Figure 4, Figure 9, Figure 13 Paragraph (118) A filter array 206 comprising filter elements 208 is incorporated into system 200. The filter array 206 includes a filter element 208 for each spectral imaging element 204.. “ Paragraph (119) “System 200 is aimed so that the spectral imaging elements 204 have a cumulative field of view 211 that encompasses surface 212 with multi-wavelength light 207 reflecting from the surface into spectral filter 206.” Paragraph (125) “The ability to capture and evaluate selected wavelengths for different target substances is incorporated into the system via filter elements 244 of the spectral filter array included in card 240 and a custom target algorithm that evaluates captured image information” Paragraph (142) FIG. 13 shows an example of a spectral imaging system 350 whose detection capabilities are easily configured to detect a wide range of target substances. System 350 includes multi-camera array 351 and spectral filter array 358. Multi-camera array 351 includes a lens array of lens elements 352 and corresponding sensor array of sensors 354.”)
Claims 43 and 84 are rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of Ni et al (Ni hereinafter CN 111753121 A).
As per claim 43
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches wherein the classifying and/or mapping comprises per-pixel processing (Section 4. Detection and Classification Based on 3D Deep Residual Mode: “The input of the network is a 3D data matrix in 3D-CNN,which is obtained by taking a pixel in the original image as the center and its size as S × S × L, where L is the number of hyperspectral image channels and S is the size of plane dimension” “For pixel-level classification in hyperspectral images, the overall steps can be divided into 3 steps: Step 1: a patch region with a size of 7 × 7 × L from the hyperspectral image is extracted as the network input, and the class label of the central pixel is extracted as the object class, where L is the number of channels of the original hyperspectral image” )
Qiao does not teach sub-pixel-level material classification
Ni teaches sub-pixel-level material classification (Ni states within the Content of Invention section that “The technical solution provided by the invention can be seen, on the one hand, using the spectrum segment vector on the dictionary vector set of projection, namely the linear representation of the dictionary vector (sparse representation of spectral segment vector), realizing the mixed pixel of sub-pixel decomposition, so as to realize accurate interpretation and target identification…”. Ni Further states within the Specific implementation examples section “Those skilled in the art will understand that …the existence of the mixed image element will increase the difficulty of classification identification,” and the solution within “…the embodiment of the invention, learning based on spectral vector dictionary, establishing a unified mathematical model of multi-hyperspectral remote sensing image sub-pixel interpretation, using efficient dictionary learning algorithm as means, realizing high precision interpretation of the multi-hyperspectral remote sensing image and identification of the fuzzy micro target.”. Ni explains that the hyperspectral pixels often contain mixed spectral signals and the method decomposes those signals to identify targets within the pixel. Therefore Ni teaches decomposing mixed hyperspectral pixels according to their spectral information to perform identification at the sub pixel level. This resolves spectral information that conventional pixel level classification may combine within a singular mixed pixel.
In a combined teaching, Qiao teaches pixel level classification of the imagery while retaining the original spectral channels for each processes pixel centered region. Ni teaches extending hyperspectral classification and identification below pixel level by spectrally decomposing mixed pixels to identify targets.
Accordingly a person of ordinary skill in the art , at the time this invention was effectively filed, would have found it obvious to modify Qiao’s methodology with Ni’s concept of sub pixel decomposition. A single hyperspectral may contain spectral contributions from multiple targets, a person of ordinary skill in the art recognizes this. These contributions can reduce the accuracy of assigning a single class to a pixel. Qiao already retains the spectral channels associated with their spectral pixels and then performs classification using that information. Ni recognizes that “existence of the mixed image element will increase the difficulty of classification identification” and teaches spectral decomposition of mixed pixels to improve identification of targets. A person of ordinary skill in the art would have done this to resolve mixed spectral info within individual pixels rather than treating each mixed pixel as representing only a single target. A person of ordinary skill in the art sees the advantage of a more precise classification and mapping where an individual hyperspectral pixel contains multiple spectral data. This improves identification of mixed pixels that cant be accurately portrayed at the pixel level itself.
As per claim 84
Qiao teaches a method comprising acquiring images of a sample with an imager ( 5. Experiment results and Analysis: “Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5 detecting, using an artificial intelligence (AI) module, one or more defects in the sample by identifying wavelength patterns corresponding to the one or more defects, wherein the AI module has been trained to identify, directly within multi-dimensional image data corresponding to images of objects, wavelength patterns corresponding to one or more defects within the objects. (Figure 4, Introduction: “Hyperspectral imaging integrates image processing and spectroscopic techniques to obtain the hyperspectral 3Dcube data (hypercube)… It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information. For example, a 256 × 256RGB image, its actual data storage size is 256 × 256 × 3, where 3 represents its three RGB components. If these 3components are extended to hundreds or thousands of continuous bands, such as 100 continuous bands, the data of the image will be expanded to 256 × 256 × 100, and this 100 is the expansion of the spectrum, which makes the image add rich spectral information. The x and y of a hyperspectral image represent its image in the pixel dimension.” ) Introduction: “The contributions of this article are summarized as follows:(1) An improved Deep Residual 3D Convolutional Neural Network is proposed. input image of the model is the original hyperspectral image, no dimensionality reduction method is needed, and the image space and spectral characteristics are retained…Rich spectral and spatial features can be rapidly extracted from samples of complete hyper spectral images using our proposed network” Qiao’s methodology does not collapse the hyperspectral cube before AI processing. Original/raw image is supplied to the 3D CNN with no dimensionality reduction and preserves the spectral dimension. The AI operates directly within the multidimensional hyperspectral image. 5. Experient results and analysis: “the spectral reflectance of the blueberry mildew area in the visible band (450–760 nm) is slightly higher than that of the sound area. In the near infrared band(760–1000 nm), the spectral reflectance of the sound region is higher than that of the mildew region” Qiao identifies the wavelength dependent spectral patterns that directly correlate to defective blueberry tissue. Qiao then states “. The reason for the difference of spectral reflectance between the blueberry mildew area and sound area is that the color of the blueberry mildew area is slightly different from that of sound area, and the main components and physical and chemical properties of the blueberry mildew area are changed due to the decay of blueberry disease so that the spectral reflectance is changed Therefore, the spectral data of 450–1000 nm range were used to establish a training and testing dataset so as to detect the mildewed blueberry. The Hyperspectral Imaging System issued to collect spectral images and is shown in Figure 5.” Qiao says their 3D CNN “performs convolution operations in both spatial and spectral dimensions to extract the features of the “spectral “combination of hyperspectral images. It makes full use of spectral and spatial 3D correlation information instead of just their separate and independent feature information.” In the Deep Residual 3D Convolutional Neural Network section. Qiao’s describes the network input as “3D data matrix in 3D-CNN, which is obtained by taking a pixel in the original image as the center and its size as S × S × L, where L is the number of hyperspectral image channels and S is the size of plane dimension.” Figure 4 shows an input of 7 X 7 X L region extraction where L is the number of channels of the original hyperspectral image. Qiao describes this as “the basic structure of feature extraction is our improved 3D residual convolution structure, and its schematic diagram is shown in Figure 4. The TPE algorithm is adopted to optimize hyperparameters, which can realize end-to-end hyperspectral “spectrum “feature extraction.” Qiao is disclosing that decayed blueberry tissue exhibits distinct wavelength spectral patterns that’s distinguishable from good tissue. That very same spectral data is used to train the AI. Qiao’s 3D CNN directly processes the spectral dimension of the original spectral image to extract spectral features. Therefore, the trained AI identifies wavelength patterns corresponding to blueberry decay within the multidimensional image data. Figure 3, See section 5. Experiment Results and Analysis. Qiao’s classification and detection processing corresponds to the claimed analysis module. It uses the trained 3D CNN to detect and classify decay defects in the blueberry sample)
Ni teaches A system comprising:(A) one or more processors a non-transitory computer readable medium operatively connected to the one or more processors having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors (Contents of Invention: “ Based on this understanding, the technical solution of the embodiment can be embodied in the form of software product, the software product can be stored in a non-volatile storage medium (can be CD-ROM, U disk, mobile hard disk and so on). comprising a plurality of instructions for causing a computer device (can be a personal computer, a server, or a network device and so on) executing the method of each embodiment of the invention.”)
Claim 77 is rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of Qiu et al (Qiu hereinafter CN 112733659 A High-spectrum Image Classification Method Based On Self-paced Learning Double-flow Multi-scale Dense Connection Network).
As per claim 77
Qiao teaches all claim limitations previously rejected in claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao does not teach further including employing a feature recalibration module for enhancing content of interest in the images of the object.
Qiu teaches employing a feature recalibration module for enhancing content of interest in the images of the object (Contents of invention: “In the invention, the local space spectrum feature extraction branch comprises an image block and a multilayer Ghost residual network, wherein the input of the multi-layer Ghost residual network is the image block in the training sample set I1, outputting the local space spectrum characteristic f1; the multi-layer Ghost residual network is composed of a plurality of Ghost residual units; SE attention module (Hu J, Shen L, Sun G. Squeeze-and-the IEEE conference on the computer vision and pattern: 2018: 7132-7141), 1 * 1 convolutional layer and average pool layer.” An SE attention module is used to recalibrate features channel wise by focusing on the similarities and dependencies between channels; suppressing less informative features and enhancing important ones)
Accordingly a person of ordinary skill in the art, at the time this invention was filed would have found it obvious to incorporate Qiu’s SE attention based feature recalibration into Qiao’s hyperspectral neural network because Qiao processes a large number of spectral features across the hyperspectral channel while Qiu provides a known attention mechanism for adaptively emphasizing the more useful channel features during the spatial/spectral feature extraction. Qiao already performs convolution in the dimensions to extract discriminative features from the hyperspectral data. Qiu’s SE attention would predictably enable the network to assign higher priority to channels features and suppress less useful information. This improves discrimination of the hyperspectral classification. A person of ordinary skill in the art see’s that this modification enhances spectral/spatial features while suppressing less useful channel features which in turn improves classification.
Claim 44 is rejected under 35 U.S.C. 103 as being unpatentable over Qiao et al (Qiao hereinafter “Detection and Classification of Early Decay on Blueberry Based on Improved Deep Residual 3D Convolutional Neural Network in Hyperspectral Images”) in view of Grassucci et al (A QUATERNION-VALUED VARIATIONAL AUTOENCODER).
As per claim 44
Qiao covers all claim limitations previously rejected with claim 41’s 102 rejection. See claim 41’s 102 rejection.
Qiao teaches the underlying classification mapping pipeline on hyperspectral data but does not classifying and/mapping comprises Deep Hypercomplex based Reversible DR (DHRDR) processing for classification.
Grassucci teaches deep hypercomplex based reversible data reduction (3.2 Network architecture: “For the scope of the paper, here we use a rather simple architecture in order to prove the benefits of the variational inference in the quaternion domain. Thus, we consider an encoder network composed of quaternion convolutional layers”) in regards to reducing data (Conclusion: “Moreover, the QVAE involves the quaternion convolutional layers in both the encoder and the decoder networks, which lead to an impressive reduction of the overall number of network parameters.” Note that Variational Autoencoders themselves reduce dimensions/compress data and a QVAE does so on a hypercomplex quaternion algebra level. ) In regards to “reversibility” Grassucci states the in the Abstract that the “variational autoencoders (VAEs) have proved their ability in modeling a generative process by learning a latent representation of the input” and in the Conclusion section that “the proposed proper QVAE is able to learn latent representations in the quaternion domain by leveraging the augmented second-order statistics of the quaternion-valued input.” The latent representation is used in a VAE generative reconstruction framework so the reduced representation encapsulates the original input data rather than discarding it allowing for reversibility criteria. The encoder performs the data reduction and the decoder reconstructs original signal from reduced representation. Thus, the latent representation is a reversible reduced representation of the input data.).
Accordingly, a person of ordinary skill in the art would have been motivated to incorporate the quaternion domain latent representation processing of Grassuci into the hyperspectral classification pipeline of Qiao. Benouis shows deep learning model classification of defect related hyperspectral image data while Grassuci teaches a deep hypercomplex model that learns a latent representation of the input and does so in a way that preserves critical (and or as needed) informational content needed for reconstruction and or generative recovery. Using Grassuci’s quaternion latent representation processing as an added front end or intermediate stage in Qiao’s pipeline would have provided a deep hypercomplex data reduction before classification workflow. This would allow preservation of original content within the reduced features supporting a reversible data reduction criterion processing for classification in a task agnostic manner.
Conclusion
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 SHANE WRENSFORD CODRINGTON whose telephone number is (571)272-8130. The examiner can normally be reached 8:00am-5pm.
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, Matthew Bella can be reached at (571) 272-7778. 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.
/SHANE WRENSFORD CODRINGTON/ Examiner, Art Unit 2667
/MATTHEW C BELLA/ Supervisory Patent Examiner, Art Unit 2667
Prosecution Insights