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 .
Response to Amendment
In the previous Office Action issued 8-1-2025 (hereinafter “the previous Office Action”), claims 1-20 were pending.
This action is in response to the amendment and remarks filed 10-31-2025. In the amendment, claims 1, 9, 11, 12, and 20 were amended, no claims were canceled, and no claims were added. Thus, claims 1-20 are pending.
The objections of claims 1, 12, and 20, set forth in the previous Office Action have been withdrawn in view of Applicant’s amendments and remarks.
The rejections of claims 1-20 under 35 U.S.C. § 101, set forth in the previous Office Action, have been withdrawn in view of Applicant’s amendments.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 8-15-2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejection – 35 U.S.C. 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-5, 7, 10, 12-16, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (US 20230027514), hereinafter Ma, in view of Balthasar et al. (US 20230011383), hereinafter Balthasar.
Regarding Claim 1:
Ma discloses:
A system, comprising: a processor configured to:
Ma, [0186], “The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.”
[0183], “These computer programs (also known as programs, software, software applications or code) include machine instructions for a programmable processor, and can be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language.”
In para. 186, Ma discloses a computing system, and para. 186 further discloses a programmable processor.
obtain a machine learning model, wherein the machine learning model was trained using training data that was obtained by
Ma, [0089], “Segmented images can also be used by the computer system 130 or another system to generate input for one or more machine learning models. For example, the computer system 130 can generate input feature values from the pixel values for certain segmented regions and providing the input feature values to a machine learning model. For example, a machine learning model may be trained to classify an item or a set of items as recyclable or not based on the type of plastic and amount and types of additives and/or contamination present.”
Ma discloses training a machine learning model [obtain a machine learning model, wherein the machine learning model was trained] by inputting feature values [using training data…].
obtaining a set of vision sensor data of a set of objects from one or more vision sensors
Ma, [0048], “In the example of FIG. 1, the camera system 110 includes or is associated with a computer or other device that can communicate over a network 120 with a server system 130 that processes hyperspectral image data and returns segmented images or other data derived from the segmented images.”
[0080], “As an example application of the technique shown in FIG. 1 to recycling, the camera system 110 can be arranged to capture hyperspectral images of waste materials as the object 101 being imaged.”
As cited above in para. 89, Ma discloses using segmented images to generate input [obtaining a set of vision sensor data] for the machine learning models. Para. 48 further specifies that data derived from segmented images [set of vision sensor data] is obtained from a camera system 110 [one or more vision sensors]. Lastly, para. 80 discloses that the camera system captures images of objects [a set of objects from one or more vision sensors].
using the set of non-vision sensor data to determine respective material characteristics corresponding to the set of objects
Ma, [0070], “Some of the common functions that the system 130 can use the segmented hyperspectral image data to perform include characterizing the object 101 or specific portions of it, such as assigning scores for the composition, quality, size, shape, texture, or other properties.”
Ma discloses using hyperspectral image data [using the set of non-vision sensor data] to perform characterizing of the object [determine respective material characteristics corresponding to the set of objects].
annotating the set of vision sensor data with labels of the respective material characteristics corresponding to the set of objects at locations in which the set of objects appear within the set of vision sensor data
Ma, [0071], “The segmentation results 160, results of applying the segmentation to the hyperspectral image 115, and/or other information generated using them can be provided…For example, the boundaries of different region types determined through segmentation can be specified in annotation data that overlays the region boundaries and indicates region types for the hyperspectral image 115 or for a composite image or standard color (e.g., RGB) image of the object 101.”
Ma discloses annotation data [annotating the set of vision sensor data with labels of the respective material characteristics] that overlays region boundaries to indicate the region types for the images [corresponding to the set of objects at locations in which the set of objects appear within the set of vision sensor data].
obtain, from a vision sensor located in a sorting facility, a vision sensor signal corresponding to an object within the sorting facility
Ma, [0080], “As an example application of the technique shown in FIG. 1 to recycling, the camera system 110 can be arranged to capture hyperspectral images of waste materials as the object 101 being imaged. In some implementations, the camera system 110 is arranged to capture hyperspectral images of waste materials on a conveyor.”
[0022], “the system may be used to generate output that characterizes a collection of multiple items, such as a group of plastic items on a conveyor belt in a recycling facility.”
[0017], “Another application of the technology is to predict the chemical content of other materials, such as plastics. The technology can be used to assess the composition of waste materials to facilitate sorting and recycling of materials.”
In para. 80, Ma discloses using a camera system [a vision sensor] with respect to recycling to capture images of waste materials [obtain…a vision sensor signal corresponding to an object]. Para. 22 specifies with respect to recycling that there is a recycling facility, and para. 17 further specifies the recycling facility sorts and recycles waste materials [sorting facility].
use the machine learning model and the vision sensor signal to determine a material characteristic type associated with the object
Ma, [0082], “Using the techniques discussed above, the computer system 130 generates a profile for a material by processing various training examples 151 that include hyperspectral images of instances of the material to be profiled. The training examples can include examples showing a target material to be identified (e.g., PET) in the presence of various other different materials, including other waste materials such as other types of plastics.”
[0146], “As a result, the system 100 can use different bands of information to segment or identify regions in the hyperspectral image corresponding to different objects or materials. Similarly, the system can use different bands of information as input to estimate different chemical properties or to estimate the properties of different types of objects.”
Ma discloses training the model to identify target materials in the various materials using different bands of information to estimate properties of the object.
cause a sorting device in the sorting facility to perform a sorting operation on the object based at least in part on the material characteristic type associated with the object
Ma, [0074], “the results of machine learning models that classify an object 101 can be used to generate instructions sent to sorting equipment 180 (e.g., causing the sorting equipment 180 to physically move or group objects according to the characteristics indicated by the machine learning model results)…”
Ma discloses instructing sorting equipment to physically sort the objects [cause a sorting device in the sorting facility to perform a sorting operation on the object] according to the characteristics indicated by the machine learning model results [based at least in part on the material characteristic type associated with the object].
Ma does not explicitly disclose:
obtaining a set of non-vision sensor data of the set of objects from one or more non-vision sensors
However, in the same field, analogous art Balthasar teaches:
obtaining a set of non-vision sensor data of the set of objects from one or more non-vision sensors
Balthasar, [0146], “The capturing step 120 comprises capturing reflected radiation of the objects using at least one optical sensor. The optical sensor may be a near-infrared (NIR) scanner, an image sensor, a laser triangulator, a laser scanner, a pulsed LED emitter and/or an X-ray camera.”
[0130], “X-ray fluorescence allows the detection of existing elements in particles. The material will be excited by low-energy X-ray radiation and element specific fluorescence will be released. With an energy dispersive X-ray sensor, this fluorescence may be measured and represented as multi- or hyperspectral data. The result of the fluorescence is information about presence of elements and their concentration.”
In para. 146, Balthasar discloses using sensors such as a NIR sensor, a laser triangulator, a laser scanner, a pulsed LED emitter, or an X-ray sensor [one or more non-vision sensors] to measure radiation data of an object [obtaining a set of non-vision sensor data of the set of objects], which is represented as hyperspectral data.
Ma, Balthasar, and the instant application are analogous art because they are all directed to using machine learning to identify and sort objects.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma with Balthasar to using a sensor that can capture non-visual properties such as radiation in order to sort more items at once. “This is beneficial in that previous problems such as objects laying on top of each other, thus obstructing sensor data, may be identified and processed accordingly. The CNN with at least two convolutional layers may advantageously be trained to handle this type of multi- or hyperspectral data in an improved way compared to known sorting systems for bulk sorting” (Balthasar, [0009]). Balthasar discloses that objects may obstruct other objects when sorting in bulk, which obstructs the sensor data as well. However, the use of hyperspectral data allows these objects to be identified regardless of bulk quantity.
Regarding Claim 2:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, and Ma further discloses:
wherein the vision sensor data on the set of objects comprises image frames showing the set of objects
Ma at Fig. 2:
PNG
media_image1.png
544
728
media_image1.png
Greyscale
In this example, hyperspectral image 101 is a frame of a strawberry. However, hyperspectral image 101 can also be of plastics. See e.g. Ma at [0021], [0023], [0148], [0160].
Regarding Claim 3:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, and Ma further discloses:
wherein the non-vision sensor data comprises hyperspectral data corresponding to the set of objects
Ma, [0113], “For example, the technique can be used to train models to use information from hyperspectral image data to detect the presence of and predict the concentration of additives to plastics (e.g., phthalates, bromides, chlorates, surface coatings, etc.) and contaminants (e.g., oils or food residue on plastic items).”
Regarding Claim 4:
As discussed above, Ma in view of Balthasar teach [the] system of claim 3, and Ma further discloses:
wherein the hyperspectral data comprises reflectivity data corresponding to the set of objects
Ma, [0115], “Hyperspectral images also often include data for spectral bands that are not in the visible range, e.g., bands in the ultraviolet and/or infrared ranges, including potentially one or more bands for each of short-wave infrared (SWIR), mid-range infrared (MWIR), and long-wave infrared (LWIR). Different chemical compounds have different light reflectance and absorption properties for different spectral bands. In other words, different chemicals interact strongly with different wavelength bands depending on their chemical structure. As a result, the ability to assess the reflectance of a sample across many relatively narrow spectral bands using a hyperspectral image can help the system 130 identify the distinct interactions that are characteristic of chemicals of interest.”
Using reflectance of a sample is reflectivity data corresponding to the set of objects.
Regarding Claim 5:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, and Ma further discloses:
wherein to use the machine learning model and the vision sensor signal to determine the material characteristic type associated with the object comprises to input the vision sensor signal into the machine learning model
Ma, [0113], “As discussed further below for FIG. 5B, the technique can be used to predict properties of a plastic or other material for recycling and waste management. For example, the technique can be used to train models to use information from hyperspectral image data to detect the presence of and predict the concentration of additives to plastics (e.g., phthalates, bromides, chlorates, surface coatings, etc.) and contaminants (e.g., oils or food residue on plastic items). In some implementations, the same techniques can be used to train models to predict the type of base resin used (e.g., PE, PET, PVC, etc.) and to predict other properties of an object.”
The hyperspectral images, i.e., input the vision sensor signal, can be used to predict the base resin, i.e., material characteristic type, associated with the plastic, i.e., object.
wherein the machine learning model is configured to recognize a correlation between a visual characteristic associated with the object and a non-visual characteristic associated with the object in the vision sensor signal
Ma, [0111], “FIG. 5A is a block diagram of an example system 100 configured to predict the chemical content of an object by processing one or more images of the object using a machine learning model. The system 500 includes a computer system 130 that uses a machine learning model 170 to generate a prediction of a chemical content of a sample 101 based on a hyperspectral image 115 of the sample 101. The system 100 includes a camera system 110 for capturing an image of an object to be analyzed. The camera system 110 can be configured to obtain hyperspectral images, e.g., with pixel intensity values for each of multiple different spectral bands. In some implementations, the camera system 110 can obtain data using other imaging or scanning techniques, including X-ray fluorescence and laser-induced breakdown spectroscopy. The results from spectroscopy or other scanning techniques can be used in addition to or instead of hyperspectral imaging results, for segmentation, model training, predicting amounts and concentrations of chemicals, and so on.” See also Ma at [0015].
Regarding Claim 7:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, and Ma further discloses:
wherein the processor is further configured to determine a classification associated with the object based at least in part on the material characteristic type
Ma, [0115], “Hyperspectral images often include information for many different spectral bands (e.g., 5, 10, 15, 20, etc.). The bands are also typically narrower than RGB bands and may include more than three bands covering the region of spectrum that is covered by RGB data. Hyperspectral images also often include data for spectral bands that are not in the visible range, e.g., bands in the ultraviolet and/or infrared ranges, including potentially one or more bands for each of short-wave infrared (SWIR), mid-range infrared (MWIR), and long-wave infrared (LWIR). Different chemical compounds have different light reflectance and absorption properties for different spectral bands. In other words, different chemicals interact strongly with different wavelength bands depending on their chemical structure. As a result, the ability to assess the reflectance of a sample across many relatively narrow spectral bands using a hyperspectral image can help the system 130 identify the distinct interactions that are characteristic of chemicals of interest. It also helps distinguish between chemicals that have similar properties with respect to some spectral bandwidths but which may have different properties for interaction with other spectral bandwidths.” See also Ma at [0113].
The classification, such as type of resin, is based, in part, on material characteristics such as absorption of light.]
Regarding Claim 10:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, and Ma further discloses:
wherein to use the machine learning model and the vision sensor signal to determine the material characteristic type associated with the object comprises to omit inputting a non-vision sensor signal associated with the object into the machine learning model
Ma, [0113], “As discussed further below for FIG. 5B, the technique can be used to predict properties of a plastic or other material for recycling and waste management. For example, the technique can be used to train models to use information from hyperspectral image data to detect the presence of and predict the concentration of additives to plastics (e.g., phthalates, bromides, chlorates, surface coatings, etc.) and contaminants (e.g., oils or food residue on plastic items). In some implementations, the same techniques can be used to train models to predict the type of base resin used (e.g., PE, PET, PVC, etc.) and to predict other properties of an object. The information produced by the models can be used to characterize waste items or a stream of waste material.”
The machine learning model uses the hyperspectral image, i.e., vision sensor data, to determine plastic or other material properties of an object. The machine learning model does not use incorporate a non-vision sensor signal and therefore omits a non-vision sensor signal associated with the object into the machine learning model.
Regarding Claims 12-16 and 18:
Claims 12-16 and 18 are method claims corresponding to system claims 1-5 and 7 and are rejected for at least the same reasons as given in the rejections of claims 1-5 and 7. In particular, the corresponding claims are 12:1, 13:2, 14:3, 15:4, 16:5, 18:7.
Regarding Claim 20:
Claim 20 is a computer-program product claim corresponding to system claim 1 and is rejected for at least the same reasons as given in the rejection of claim 1, with the exception of the following limitations.
Ma discloses:
A computer program product, the computer program product being embodied in a non- transitory computer-readable storage medium and comprising computer instructions for
Ma, [0183], “As used herein, the terms ‘machine-readable medium’ ‘computer-readable medium’ refers to any computer program product, apparatus and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal.”
Claims 6, 8, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Balthasar as applied to claim 1 above, and further in view of Torek et al. (US 9785851), hereinafter Torek.
Regarding Claim 6:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, but do not explicitly disclose:
wherein the processor is further configured to query a database that stores mappings between material characteristic types and chemical compositions
However, in the same field, analogous art Torek teaches:
wherein the processor is further configured to query a database that stores mappings between material characteristic types and chemical compositions
Torek at cl. 10, ln. 7-16, “The image processor 130 or control unit 108 may use a matrix with cells and arrays of the matrix including [R, G, B] color channel data, and additional information regarding particle location, and particle properties as determined below. The image processor 130 or control unit 108 may alternatively use an imaging library processing tool, such as MATROX, to create a table or other database populated with pixel data for each particle including [R, G, B] values, boundary information, and other particle properties as determined below.”
See also Torek at cl. 12, ln. 4-16, “At step 216, the control unit 108 classifies the particle 104 into one of at least two classifications of a material as a function of the data vector by inputting the data vector into a machine learning algorithm. The control unit may use a Support Vector Machine (SVM), a Partial Least Squares Discriminant Analysis (PLSDA), a neural network, a random forest of decision trees, or another machine learning and classification technique to evaluate the data vector and classify the particle 104. In one example, a neural network is used to classify each of the scrap particles 104 as one of a preselected list of alloy families or other preselected list of materials based on elemental or chemical composition based on the analysis of spectral data and color input data.”
Ma, Balthasar, Torek, and the instant application are analogous art because they are all directed to using machine learning to analyze objects using imaging and hyperspectral data.
A person skilled in the art, before the filing date of the present application, would be motivated to modify Ma with Torek to recite to query a database that stores mappings between material characteristic types and chemical compositions with the motivation being “(cl. 15, ln. 39-44) [t]he fill fraction may be calculated as the percentage of pixels or cells of the particle that fall with the region 272. At step 282, the control unit 108 saves the calibration or look-up table with the predefined sets of discriminant pairs that are associated with a classification and are in defined region 272.”
Regarding Claim 8:
Regarding claim 8, claim 8 has substantially similar limitations as claim 6. Therefore, claim 8 is rejected under the same rationale as claim 6.
Regarding Claims 17 and 19:
Claims 17 and 19 are method claims corresponding to system claims 6 and 8 and are rejected for at least the same reasons as given in the rejections of claims 6 and 8. In particular, the corresponding claims are 17:6, 19:8.
Claims 9 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Balthasar as applied to claim 1 above, and further in view of Murphy et al. (US 20230062938), hereinafter Murphy.
Regarding Claim 9:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, but do not explicitly disclose:
wherein the processor is further configured to generate the training data including to:
determine bounding polygons corresponding to the set of objects appearing within the vision sensor data of the set of objects
associate the bounding polygons corresponding to the set of objects appearing within the vision sensor data of the objects to the labels of the respective material characteristics corresponding to the set of objects
However, in the same field, analogous art Murphy teaches:
wherein the processor is further configured to generate the training data including to:
Murphy, [0027], “The machine learning model(s) may have been generated or may be generated by training one or more neural networks on multiple spectral data points collected across a large integrated database of diverse spectral data. For example, the diverse spectral data can include spectra corresponding to two or more of: short-wavelength infrared (SWIR), middle-wavelength infrared (MWIR), near infrared (NIR), X-ray fluorescence, X-ray diffraction (XRD), millimeter-wave, Fourier-transform infrared. The large integrated database may further include chemical properties, physical properties, and/or meta data about the corresponding materials or objects. Such a training set may include tens of thousands of objects/samples). The machine learning models can be trained, configured, and/or used to correlate these spectra across a single object, such that when a similar object is scanned by lower resolution devices (such as a SWIR camera or MWIR camera), the higher resolution FTIR spectra were inferred using spectrum-inferring model.”
determine bounding polygons corresponding to the set of objects appearing within the vision sensor data of the set of objects
Murphy, [0026], “The bounding box can then be used to identify a region in physical space to be represented in the hypercube(s).”
[0029], “The hypercube includes the physical space dimensions, associated with an object.”
associate the bounding polygons corresponding to the set of objects appearing within the vision sensor data of the objects to the labels of the respective material characteristics corresponding to the set of objects
Murphy, [0030], “The machine learning model may be machine learning model 370 in FIG. 3. The hypercubes are fed into the machine learning model. The machine learning model predicts characteristics of the object based on the inputted hypercubes.”
[0072], “The spectral hypercube corresponding to MWIR wavelengths was extracted from the bounding box output from the segmentation model. This bounding box was broadcasted to the SWIR image and used to extract the spectral hypercube corresponding to the SWIR wavelengths. The hypercubes from both the sensor modalities (SWIR and MWIR) were concatenated and passed as input to a deep neural network trained to predict multiple outputs in parallel…s to (a) classify whether the plastic is black or not, (b) classify the base polymer category for example PE, PET, PVC, PP, etc., (c) classify the suitability of the plastic for chemical recycling in terms of polyolefin class…”
Ma, Balthasar, Murphy, and the instant application are analogous art because they are all directed to using machine learning to analyze objects using imaging and hyperspectral data.
A person skilled in the art, before the filing date of the present application, would be motivated to modify Ma with Murphy to recite wherein the processor is further configured to generate the training data including to: determine bounding polygons corresponding to the set of objects within the vision sensor s data of the objects; obtain the non-vision sensor data on the set of objects from a non-vision sensor; determine the material characteristic labels corresponding to the set of objects based at least in part on the non-vision sensor data on the set of objects; and associate the bounding polygons corresponding to the set of objects within the vision sensor data of the objects to the material characteristic labels corresponding to the set of objects with the motivation being “(0024) [t]he signals collected by the hyperspectral camera and at least one spectroscopy sensor can be collectively processed by one or more machine learning models to generate accurate predictions about the characteristics of (e.g., composition of and/or properties of) the material or object. For example, a prediction may predict whether a material or object includes a given additive, any of a class of additives, a given contaminant, any of a class of contaminants, a given base polymer, or any of a class of base polymers. As another example, a prediction may predict which (if any) additive, contaminant, or base polymer is within the material or object. As yet another example, a prediction can include a predicted spectrum that has a higher resolution, a higher signal-to-noise, and/or wider frequency bands as compared to spectra that were initially captured and/or input into the model(s) (e.g., so as to transform a short-wave infrared spectrum or a mid-wave infrared spectrum into a near-infrared spectrum). The machine learning model may be executed by a computer system 120. (See also 0025, 0026.)”
Regarding Claim 11:
As discussed above, Ma in view of Balthasar teach [the] system of claim 1, but do not explicitly disclose:
wherein the processor is further configured to: is receive a non-vision sensor signal
use the machine learning model, the vision sensor signal, and the non-vision sensor signal to determine the material characteristic type associated with the object
However, in the same field, analogous art Murphy teaches:
wherein the processor is further configured to: is receive a non-vision sensor signal
Murphy, [0024], “The signals collected by the hyperspectral camera and at least one spectroscopy sensor can be collectively processed…” See also Murphy at [0073]-[0074].
The non-vision sensor signal is the spectroscopy sensor.
use the machine learning model, the vision sensor signal, and the non-vision sensor signal to determine the material characteristic type associated with the object
Murphy, [0024], “The signals collected by the hyperspectral camera and at least one spectroscopy sensor can be collectively processed by one or more machine learning models to generate accurate predictions about the characteristics of (e.g., composition of and/or properties of) the material or object. For example, a prediction may predict whether a material or object includes a given additive, any of a class of additives, a given contaminant, any of a class of contaminants, a given base polymer, or any of a class of base polymers. As another example, a prediction may predict which (if any) additive, contaminant, or base polymer is within the material or object.”
Using one or more machine learning models, the hyperspectral image, i.e., the vision sensor signal, and spectroscopy sensor, i.e., the non-vision sensor signal, are used to determine a material characteristics associated with an object.
A person skilled in the art, before the filing date of the present application, would be motivated to modify Ma with Murphy to recite wherein the processor is further configured to: is receive a non-vision sensor signal; and use the machine learning model, the vision sensor signal, and the non-vision sensor signal to determine a material characteristic type associated with the object with the motivation being “(0024) [t]he signals collected by the hyperspectral camera and at least one spectroscopy sensor can be collectively processed by one or more machine learning models to generate accurate predictions about the characteristics of (e.g., composition of and/or properties of) the material or object. For example, a prediction may predict whether a material or object includes a given additive, any of a class of additives, a given contaminant, any of a class of contaminants, a given base polymer, or any of a class of base polymers. As another example, a prediction may predict which (if any) additive, contaminant, or base polymer is within the material or object. As yet another example, a prediction can include a predicted spectrum that has a higher resolution, a higher signal-to-noise, and/or wider frequency bands as compared to spectra that were initially captured and/or input into the model(s) (e.g., so as to transform a short-wave infrared spectrum or a mid-wave infrared spectrum into a near-infrared spectrum). The machine learning model may be executed by a computer system 120. (See also 0025, 0026.)” and that UV-Vis, X-ray, Infrared i.e., spectroscopy methods, can capture different spectral data points (see 0027).
Response to Arguments
Applicant's arguments filed 10-31-2025 (hereinafter “Remarks”) have been fully considered but they are not persuasive.
35 U.S.C. § 103:
Remarks, pg. 7-9. Applicant’s arguments with respect to amended claims 1, 12, and 20 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.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Xiang et al. (US 20170090068) recites a method for estimating soil properties, which include material and chemical properties, using a hyperspectral data including reflectivity data.
Kottenstette et al. (US 20170076438) recites a method for obtaining target geometric object properties, which can include material (see [0236]), using multiple sensors such as hyperspectral images and red-green-blue images, the training images can be multiple different image types (see [0139]).
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 KAMRAN AFSHAR whose telephone number is 571-272-7796. The examiner can normally be reached Monday-Thursday: 9:00AM-4:00PM 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.
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.
/KAMRAN AFSHAR/Supervisory Patent Examiner, Art Unit 2125