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 .
Prior arts cited in this office action:
Bhatt et al. (US 20220122347 A1, hereinafter “Bhatt”)
McEntire et al. (US 11715024 B1, hereinafter “McEntire”)
Bainbridge et al. (WO 2021255458 A1, hereinafter “Bainbridge”)
Response to Arguments
Applicant's arguments filed on 08/03/2026 have been fully considered but they are moot in view of the new ground of rejection set forth below.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-5, 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over Bhatt et al. (US 20220122347 A1, hereinafter “Bhatt”) and in view of Bainbridge et al. (WO 2021255458 A1, hereinafter “Bainbridge”).
Regarding claim 1:
Bhat teaches a system for crop monitoring (Bhatt [0003], where Bhatt teaches an automated yet a generalized system that performs a start to end monitoring of various crops from sowing to harvest) comprising:
a memory comprising a crop monitoring application (Bhatt [0003], [0005], [0033], [0035] where Bhatt teaches one or more data storage devices or memory 102 operatively coupled to the one or more processors 104. The one or more processors 104 that are hardware processors can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, graphics controllers, logic circuitries, and/or any devices that manipulate signals based on operational instructions); and
a processor (Bhatt [0005], [0033] where Bhatt teaches a processor implemented method comprising the steps of: receiving an image from a temporal set of images of at least a portion of one or more crops being monitored for a pre-defined event; detecting one or more Regions Of Interest (ROIs) as localized bounding boxes in the received image based on the pre-defined event using one or more context sensitive pre-trained models associated with the pre-defined event for the one or more crops being monitored),
wherein the crop monitoring application, when executed on the processor, configures the
processor to:
receive one or more images of a crop area (Bhatt [0003], [0005], [0033], [0035], where Bhatt teaches receiving an image from a temporal set of images of at least a portion of one or more crops being monitored for a pre-defined event; detecting one or more Regions Of Interest (ROIs) as localized bounding boxes in the received image based on the pre-defined event using one or more context sensitive pre-trained models associated with the pre-defined event for the one or more crops being monitored, wherein the one or more ROIs correspond to a detected event);
process the one or more image to generate processed image data (Bhatt [0003], [0005], [0033], [0035], [0038]- [0039], where Bhatt teaches the images may need to be preprocessed for brightness correction…. Receiving an image from a temporal set of images of at least a portion of one or more crops being monitored for a pre-defined event; detecting one or more Regions Of Interest (ROIs) as localized bounding boxes in the received image based on the pre-defined event using one or more context sensitive pre-trained models associated with the pre-defined event for the one or more crops being monitored, wherein the one or more ROIs correspond to a detected event);
extract one or more features form the processed image (Bhatt [0011], where Bhat teaches In accordance with an embodiment of the present disclosure, the step of performing unsupervised segmentation of the one or more ROIs comprises: computing features in the one or more ROIs, by the CNN, based on properties including color, edges, texture and the spatial continuity of the pixels comprised therein; labeling the pixels in the one or more ROIs based on the computed features such that (i) pixels with identical features are assigned a common label, (ii) spatially continuous pixels are assigned a common label; and (iii) a pre-defined number of potential unique labels is selected to account for each segment of the one or more ROIs; and obtaining the segmentation map having one or more segments, wherein each of the one or more segments being assigned a unique label);
input the one or more features into a disease classifier model (Bhatt [0003], [0023], where Bhat teaches Existing applications in the literature target classification and detection of certain diseases or pests on a particular crop with custom-developed models; The methods and systems of the present disclosure may find practical application in identifying and localizing plants and parts of a plant in an image, classifying parts and plants into their type as well as possible health state and growth stage. Such detected plants, plant parts and occurrences of events on the plant can be counted. An extent (such as severity) of manifestation of an event (such as a disease), size of the event (such as fruit size) as well as temporal change of these events may be estimated in terms of percentage of pixels );
input the processed image data into one or more crop models (Bhatt [0003], [0023], [0038]-[0040], where Bhatt teaches for instance, the ROIs may depend on an event like detecting a disease affected area in the crop or a pest affecting the crop. In accordance with the present disclosure, the one or more pre-trained models are comprised in a model library, wherein each of the one or more pre-trained models is associated with a corresponding architecture definition. There may be a common architecture definition for several pre-trained models even though they represent say, different diseases. Likewise, a same disease may be represented by pre-trained models having different architecture definitions); and
identify one or more plant diseases associated with the one or more images based on an output from the disease classifier model (Bhatt [0003], [0023], [0038]-[0040], [0045] where Bhatt teaches for instance, the ROIs may depend on an event like detecting a disease affected area in the crop or a pest affecting the crop. In accordance with the present disclosure, the one or more pre-trained models are comprised in a model library, wherein each of the one or more pre-trained models is associated with a corresponding architecture definition. There may be a common architecture definition for several pre-trained models even though they represent say, different diseases. Likewise, a same disease may be represented by pre-trained models having different architecture definitions).
Bhat fails to explicitly teach wherein the disease classifier model is a supervised learning model trained on the labeled image data.
However, Bhat teaches When the neural network is trained to learn xn and ƒ for a fixed and known set of labels ln, it is a supervised classification. In accordance with the present disclosure, an unknown segmentation map is predicted while iteratively updating the function ƒ and the features x.sub.n. Effectively, a joint optimization is achieved as given below (Bhatt [0028]). Bhatt also teaches Widely used methods of image segmentation that are fully supervised i.e. they need a training data that is labeled at pixel level (Bhatt [0003]). One can see that the technique of using a supervised classifier model trained on labeled data is taught by Bhatt because the system of Bhatt is an improvement of that system because the labeled data is few. Furthermore, Bainbridge teaches the method may comprise labelling a sub-set of identified crop features with the one or more crop feature attributes. The method may comprise storing the labelled classified crop features in a database as a training data set for the machine learning model. In this context, hyperspectral mean that each pixel of each image contains a large number of narrow spectral bands (i.e. a spectrum) covering a wide spectral range e.g. visible to NIR, as opposed to multi-spectral images that contain a relatively low number of broad spectral bands or colour channels such as red (R), green (G), and blue (B). The machine learning model may be used for the crop monitoring method of the first aspect. The images of crops may be the images of crops of the first aspect. The method advantageously produces training data adapted or adaptable for the specific imaging device or field camera used in the field for crop monitoring, as described in the first aspect. Classification of crop features and attributes is sensitive to the image resolution and spectral response of the field images input to the machine learning model and the training data is was trained on (Bainbridge pages 9-15).
Therefore, taking the teachings of Bhatt and Bainbridge as a whole, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to use supervised disease classifier model trained on labeled image data when sufficient labeled image data is available, since using labeled data provide better result when sufficient training labeled data is present.
Regarding claims 2 and 11:
Bhatt in view of Bainbridge teaches where the images are of plants (Bhatt [0003], where Bhatt teaches Apart from detection of an event (e.g. disease manifestation, flowering, change in the plant) it is important to know the growth stage of the crops or the severity of the disease in the detected area).
Regarding claims 3 and 12:
Bhatt in view of Bainbridge teaches wherein processing the one or more image comprises at least one selected from the following: sizing the one or more image, normalizing the one or more image, and setting a color flag for the one or more image (Bhatt [0009], where Bhatt teaches the one or more ROIs in the received image is preceded by preprocessing of the received image, wherein the preprocessing comprises one or more of normalization of image data, resizing, Principal Components Analysis (PCA) whitening, brightness correction, histogram equalization, contrast stretching, de-correlation stretching and denoising).
Regarding claims 4 and 13:
Bhatt in view of Bainbridge teaches wherein the one or more crop models comprise at least one selected from the following: a crop damage estimation model, a plant disease identification model, a plant disease severity estimation model, and a weed identification model (Bhatt [0037]-[0039], where Bhatt teaches for instance, the ROIs may depend on an event like detecting a disease affected area in the crop or a pest affecting the crop. In accordance with the present disclosure, the one or more pre-trained models are comprised in a model library, wherein each of the one or more pre-trained models is associated with a corresponding architecture definition. There may be a common architecture definition for several pre-trained models even though they represent say, different diseases. Likewise, a same disease may be represented by pre-trained models having different architecture).
Regarding claims 5 and 14:
Bhatt in view of Bainbridge teaches further comprising: training the one or more crop models (Bhatt [0037]-[0039], where Bhatt teaches for instance, the ROIs may depend on an event like detecting a disease affected area in the crop or a pest affecting the crop. In accordance with the present disclosure, the one or more pre-trained models are comprised in a model library, wherein each of the one or more pre-trained models is associated with a corresponding architecture definition. There may be a common architecture definition for several pre-trained models even though they represent say, different diseases. Likewise, a same disease may be represented by pre-trained models having different architecture).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 6-9, 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bhatt et al. (US 20220122347 A1, hereinafter “Bhatt”) in view of Bainbridge et al. (WO 2021255458 A1, hereinafter “Bainbridge”) and in view of McEntire et al. (US 11715024 B1, hereinafter “McEntire”).
Regarding claims 6 and 15:
Bhatt in view of Bainbridge fails to explicitly teach where the processor is further configured to:
receive location information comprising a boundary of a crop area;
calculate a distance along the boundary;
generate a grid for the crop area; and
initiate and image collection of the one or more images along a pattern within the grid.
However, McEntire teaches method and system for estimating soil chemistry at different crop field locations wherein some additional information may include actual farm boundaries, field boundaries, cover crop activities… Yield data may also include additional geometry information such as a field boundary, a field size, and a location of each sub-field within the field… The samples may be collected at grid points within a field, and the grid may roughly form a rectangle or may have no fixed geometry constraints.
Therefore, taking the Bhat, Bainbridge and McEntire as a whole, it would have been obvious to one of ordinary skill in the art before the effective filing date to obtain information such as location and area to take the image to analyze such each area can be divided and analyzed separately in order to make the system more efficient and more focused on the regions of interest without using unnecessary data.
Regarding claims 7 and 16:
Bhatt in Bainbridge and in view of McEntire teaches where the processor is further configured to:
extract the one or more features from an image of the one or more images of the crop area;
use the one or more features in the disease classifier model; and identify one or more plant diseases associated with the image based on the output of the disease classifier model (Bhatt [0003], [0023], where Bhat teaches Existing applications in the literature target classification and detection of certain diseases or pests on a particular crop with custom-developed models) .
Regarding claims 8 and 17:
Bhatt in Bainbridge and in view of McEntire teaches where the processor is further configured to:
extract the image of a leaf in the image; determine an area of the leaf; determine an area of damage on the leaf; and determine a severity of a disease using the area of the leaf and the area of damage on the leaf (Bhatt [0045], where Bhatt teaches for instance, if there is any temporal information in the images received from a stationary camera, emergence of a new segment itself may be an indication of an event like flowering or a disease manifestation. In an image, if a segment has a different feature or characteristic like color, texture, etc. yellow, brown or black pixels inside a leaf, the leaf has a high probability of being disease/pest affected. If the kind of crop and possible diseases are already known, the properties of a particular disease manifestation can be compared with the resulting segments. Instead of presence of a certain feature like color or texture, the absence of the same may also flag a change. For example, absence of a particular hue or chromaticity of pixel values on the segment corresponding to a leaf, flags occurrence of some deficiency or disease e.g. light green color of leaves due to lack of fertilizer. Alternatively, absence of certain amount of density of required green pixels in the segment may indicate slower growth of a plant).
Regarding claims 9 and 18:
Bhatt in Bainbridge and in view of McEntire teaches where the processor is further configured to:
extract an image of a plant in the image; determine a type of plant from the image of the plant; and determine a type of pesticide for treating the crop area based on the type of plant (Bhatt [0023], [0046], The methods and systems of the present disclosure may find practical application in identifying and localizing plants and parts of a plant in an image, classifying parts and plants into their type as well as possible health state and growth stage. Such detected plants, plant parts and occurrences of events on the plant can be counted. An extent (such as severity) of manifestation of an event (such as a disease), size of the event (such as fruit size) as well as temporal change of these events may be estimated in terms of percentage of pixels… Measuring the diseased region out of the image gives an idea of severity and hence the quantity of the pesticide) .
Regarding claim 19:
Bhatt in view of Bainbridge and in view of McEntire teaches further comprising taking action on the crop area based on identified one or more properties of a crop plant (Bhatt [0023], [0046]).
Regarding claim 20:
Bhatt in view of Bainbridge and in view of McEntire teaches further comprising providing to the at least one processor the one or more images of the crop area from one or more cameras (Bhatt [0003]).
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 WEDNEL CADEAU whose telephone number is (571)270-7843. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, Chieh Fan can be reached at 571-272-3042. 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.
/WEDNEL CADEAU/Primary Examiner, Art Unit 2632 September 15, 2026
Prosecution Insights