Patent · US11363909B2 · B2 · US

Sensor device for providing control for a food processing system

(11) Publication number

US11363909B2

(21) Application number

16/848,936

(22) Filing date

2020-04-15

(30) Priority date

2020-04-15

(43) Publication date

2022-06-21

(45) Date of grant

2022-06-21

(51) IPC

A47J 37/04; G01J 5/00; G06N 3/04; G06V 10/764; G06V 20/20

(52) CPC

F25D Refrigerators; cold rooms; ice-boxes; cooling or freezing apparatus not otherwise provided for: 13/06, 13/067
A23B Preservation of foods, foodstuffs or non-alcoholic beverages; chemical ripening of fruit or vegetables: 2/88, 4/09
A47J Kitchen equipment; coffee mills; spice mills; apparatus for making beverages: 37/045
B65G Transport or storage devices, e.g. conveyors for loading or tipping, shop conveyor systems or pneumatic tube conveyors: 43/08
G01J Measurement of intensity, velocity, spectral content, polarisation, phase or pulse characteristics of infrared, visible or ultraviolet light; colorimetry; radiation pyrometry: 5/0022
G05B Control or regulating systems in general; functional elements of such systems; monitoring or testing arrangements for such systems or elements: 19/4183, 2219/31282
G06N Computing arrangements based on specific computational models: 3/04, 3/0464, 3/09
G06V Image or video recognition or understanding: 10/764, 10/82, 20/20, 20/52
H04N Pictorial communication, e.g. television: 7/181

(73) Assignee

AIR PROD & CHEM

(72) Inventors

HENDERSHOT REED JACOB; GUHA AVISHEK; HAUPT SHAWN; NAIK ANKIT; HIMES MICHAEL ROBERT; ARSLAN ERDEM

(54) Title

Sensor device for providing control for a food processing system

(57) Abstract

A processor of a sensor device receives a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of a food processing system. The processor processes one or more images, among the plurality of images, to detect one or more characteristics in the scene. Processing the one or more images includes detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene, and classifying the scene as having one or more characteristics among a predetermined set of characteristics. The sensor device provides characteristics information indicating the one or more characteristics detected in the scene to a controller. The characteristics information is to be used by the controller to control operation of one or both of the conveyor and the treatment area of the food processing system.

Full text

View on Google Patents

Claims (14)

A method of providing control for a food processing system, the method comprising: receiving, at a processor of a sensor device, a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time; processing, with the processor of the sensor device, one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; and providing, by the sensor device to a controller, characteristics information indicating the one or more characteristics detected in the scene, wherein the characteristics information is to be used by the controller to control operation of one or both of i) the conveyor and ii) ii) the treatment area of the food processing system; wherein receiving the plurality of images comprises receiving a plurality of infrared (IR) images captured by an IR camera; and wherein processing the one or more images among the plurality of images includes i) rendering an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, ii) processing the visible image to detect the one or more characteristics in the scene, iii) comparing values of respective pixels in an IR image, among the plurality of IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, iv) counting at least one of a) a first number of pixels having values that exceed the threshold temperature and b) a second number of pixels having values that do not exceed the threshold temperature, and v) determining at least one of the one or more characteristics of the scene based on a ratio of at least one of a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.
The method of claim 1, wherein processing the one or more images among the plurality of images includes using a neural network to classify the product detected in an image, among the one or more images, into one of a plurality of predetermined types of products.
The method of claim 1, wherein determining the one or more characteristics of the scene includes determining whether the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to i) a no-load constant or ii) is below the no-load constant, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to the no-load constant, determining that the conveyor is currently empty, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image is below the no-load constant, determining that the product is currently present on the conveyor.
The method of claim 1, wherein determining the one or more characteristics of the scene includes determining, based on the ratio of the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image, a degree of coverage of the at least the portion of the conveyor depicted in the scene by the product.
The method of claim 1, further comprising dynamically determining a value of the threshold temperature based on changing operating conditions of the conveyor.
The method of claim 1, wherein processing the one or more images among the plurality of images includes determining, based on at least one IR image among the plurality of IR images, distribution of the product on the conveyor, and determining, based on the distribution of the product on the conveyor, one or more control parameters for dispensing a cryogen substance in the treatment area of the food processing system such that the cryogen substance is dispensed in accordance with the distribution of the product on the conveyor.
The method of claim 1, wherein processing the one or more images among the plurality of images to detect the one or more characteristics of the scene includes determining, based on the one or more images among the plurality of images, one or more of i) a speed of the conveyor, ii) operating temperature across the conveyor, iii) a distribution of the product on the conveyor, iv) a degree of coverage of the conveyor by the product, and v) a maintenance condition of the conveyor.
A sensor device for providing control for a food processing system, the sensor device comprising at least one camera configured to capture a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time, and wherein the at least one camera includes an IR camera configured to capture a plurality of IR images capturing the scene that depicts at least the portion of the conveyer entering the treatment area of the food processing system; and a processor implemented on one or more integrated circuit devices configured to i) process one or more images, among the plurality of images, to detect one or more characteristics in the scene, including a) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and b) classifying the scene as having one or more characteristics among a predetermined set of characteristics; ii) provide characteristics information indicating the one or more characteristics detected in the scene to a controller, wherein the characteristics information is to be used by the controller to control operation of one or both of a) the conveyor and b) the treatment area of the food processing system; (iii) render an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, (iv) process the visible image to detect the one or more characteristics in the scene, (v) compare values of respective pixels in an IR image, among the one or more IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, (vi) count at least one of (a) a first number of pixels having values that exceed the threshold temperature and (b) a second number of pixels having values that do not exceed the threshold temperature, and (vii) determine at least one of the one or more characteristics based on a ratio of at least one of (a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and (b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.
The sensor device of claim 8, wherein the processor is configured to process the one or more images using a neural network to classify the product detected in the one or more images into one of a plurality of predetermined types of products.
The sensor device of claim 8, wherein the processor is configured to determine whether the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to i) a no-load constant or ii) is below the no-load constant, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to the no-load constant, determine that the conveyor is currently empty, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image is below the no-load constant, determine that the product is currently present on the conveyor.
The sensor device of claim 8, wherein the processor is configured to determine, based on the ratio of the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image, a degree of coverage of the at least the portion of the conveyor depicted in the scene by the product.
The sensor device of claim 8, wherein the at least one camera includes an infrared IR camera and a visible light camera, the sensor device further comprises a sensor configured to determine whether or not fog is present at the conveyor, and the processor is further configured to select an image to be processed, the processor being configured to i) when it is determined that fog is present at the conveyor, select an IR image captured by the IR camera and ii) when it is determined that fog is not present at the conveyor, select a visible light image captured by the visible light camera.
A tangible, non-transitory computer readable medium storing machine readable instructions that, when executed by a processor associated with a sensor device, cause the processor to: receive a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of a food processing system, wherein respective ones of the images capture the scene at respective points in time; process one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; and provide characteristics information indicating the one or more characteristics detected in the scene to a controller, wherein the characteristics information is to be used by the controller to control operation of one or both of a) the conveyor and b) the treatment area of the food processing system; wherein the machine readable instructions, when executed by the processor associated with the sensor device, cause the processor to i) receive a plurality of infrared (IR) images captured by an IR camera capturing the scene that depicts at least the portion of the conveyer entering the treatment area of the food processing system, ii) render an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, iii) process the visible image to detect the one or more characteristics in the scene. iv) compare values of respective pixels in an IR image, among the one or more IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, v) count at least one of a) a first number of pixels having values that exceed the threshold temperature and b) a second number of pixels having values that do not exceed the threshold temperature, and vi) determine at least one of the one or more characteristics based on a ratio of at least one of a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.
A method of providing control for a food processing system, the method comprising: receiving, at a processor of a sensor device, a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time; processing, with the processor of the sensor device, one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; providing, by the sensor device to a controller, characteristics information indicating the one or more characteristics detected in the scene, wherein the characteristics information is to be used by the controller to control operation of one or both of i) the conveyor and ii) the treatment area of the food processing system; detecting, with a sensor disposed in the sensor device, whether fog is present at the conveyor; and selecting an image to be processed by the processor, including i) when it is determined that fog is present in the scene, selecting an IR image captured by the IR camera and ii) when it is determined that fog is not present at the conveyor, selecting a visible light image captured by the visible light camera; wherein obtaining the plurality of images comprises obtaining one or both of a) one or more infrared (IR) image captured by an IR camera and b) one or more visible light images captured by a visible light camera.

Description

The present disclosure relates generally to sensor devices and, more particularly, to imaging sensor devices for providing control for freezing or chilling equipment.

Food industries often utilize various types of conveyor equipment for freezing or chilling products. For example, a food production or processing plant may utilize a conveyor freezer for freezing various types of food, such as fish, chicken, shrimp, meat patties, fruits, vegetables, etc. As another example, a food production or processing plant may utilize a conveyor cooler for quickly chilling products, such as eggs, cured meats, cheeses, etc. In such freezing or chilling equipment, the product is loaded onto a continuously moving conveyor that moves through a treatment area, which may be an enclosed area such as a tunnel. As the conveyor belt moves through the treatment area, a coolant is supplied to the product to bring the temperature of the product to a desired cooling or freezing temperature. Such typical freezing or chilling equipment does not monitor, in real-time, characteristics of the conveyor, and does not automatically control operating conditions of the freezing or chilling equipment based on real-time characteristics of the conveyor, which often results in inefficient use of the equipment and increased costs of operating the equipment.

The following introduces a selection of concepts in a simplified form in order to provide a foundational understanding of some aspects of the present disclosure.

Citations (13)

EP0667501A1
EP2998663A2
US2014230460A1
US2017138661A1
US2018338354A1
US2018365820A1
US2021112818A1
US2021201471A1
US2021204553A1
US6233966B1
WO2006073909A2
WO2016043925A1
WO2020003310A1

Record as JSON

{
  "publication_number": "US11363909B2",
  "country": "US",
  "kind": "B2",
  "title": "Sensor device for providing control for a food processing system",
  "abstract": "A processor of a sensor device receives a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of a food processing system. The processor processes one or more images, among the plurality of images, to detect one or more characteristics in the scene. Processing the one or more images includes detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene, and classifying the scene as having one or more characteristics among a predetermined set of characteristics. The sensor device provides characteristics information indicating the one or more characteristics detected in the scene to a controller. The characteristics information is to be used by the controller to control operation of one or both of the conveyor and the treatment area of the food processing system.",
  "claims": [
    "1. A method of providing control for a food processing system, the method comprising: receiving, at a processor of a sensor device, a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time; processing, with the processor of the sensor device, one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; and providing, by the sensor device to a controller, characteristics information indicating the one or more characteristics detected in the scene, wherein the characteristics information is to be used by the controller to control operation of one or both of i) the conveyor and ii) ii) the treatment area of the food processing system; wherein receiving the plurality of images comprises receiving a plurality of infrared (IR) images captured by an IR camera; and wherein processing the one or more images among the plurality of images includes i) rendering an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, ii) processing the visible image to detect the one or more characteristics in the scene, iii) comparing values of respective pixels in an IR image, among the plurality of IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, iv) counting at least one of a) a first number of pixels having values that exceed the threshold temperature and b) a second number of pixels having values that do not exceed the threshold temperature, and v) determining at least one of the one or more characteristics of the scene based on a ratio of at least one of a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.",
    "2. The method of claim 1, wherein processing the one or more images among the plurality of images includes using a neural network to classify the product detected in an image, among the one or more images, into one of a plurality of predetermined types of products.",
    "3. The method of claim 1, wherein determining the one or more characteristics of the scene includes determining whether the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to i) a no-load constant or ii) is below the no-load constant, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to the no-load constant, determining that the conveyor is currently empty, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image is below the no-load constant, determining that the product is currently present on the conveyor.",
    "4. The method of claim 1, wherein determining the one or more characteristics of the scene includes determining, based on the ratio of the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image, a degree of coverage of the at least the portion of the conveyor depicted in the scene by the product.",
    "5. The method of claim 1, further comprising dynamically determining a value of the threshold temperature based on changing operating conditions of the conveyor.",
    "6. The method of claim 1, wherein processing the one or more images among the plurality of images includes determining, based on at least one IR image among the plurality of IR images, distribution of the product on the conveyor, and determining, based on the distribution of the product on the conveyor, one or more control parameters for dispensing a cryogen substance in the treatment area of the food processing system such that the cryogen substance is dispensed in accordance with the distribution of the product on the conveyor.",
    "7. The method of claim 1, wherein processing the one or more images among the plurality of images to detect the one or more characteristics of the scene includes determining, based on the one or more images among the plurality of images, one or more of i) a speed of the conveyor, ii) operating temperature across the conveyor, iii) a distribution of the product on the conveyor, iv) a degree of coverage of the conveyor by the product, and v) a maintenance condition of the conveyor.",
    "8. A sensor device for providing control for a food processing system, the sensor device comprising at least one camera configured to capture a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time, and wherein the at least one camera includes an IR camera configured to capture a plurality of IR images capturing the scene that depicts at least the portion of the conveyer entering the treatment area of the food processing system; and a processor implemented on one or more integrated circuit devices configured to i) process one or more images, among the plurality of images, to detect one or more characteristics in the scene, including a) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and b) classifying the scene as having one or more characteristics among a predetermined set of characteristics; ii) provide characteristics information indicating the one or more characteristics detected in the scene to a controller, wherein the characteristics information is to be used by the controller to control operation of one or both of a) the conveyor and b) the treatment area of the food processing system; (iii) render an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, (iv) process the visible image to detect the one or more characteristics in the scene, (v) compare values of respective pixels in an IR image, among the one or more IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, (vi) count at least one of (a) a first number of pixels having values that exceed the threshold temperature and (b) a second number of pixels having values that do not exceed the threshold temperature, and (vii) determine at least one of the one or more characteristics based on a ratio of at least one of (a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and (b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.",
    "9. The sensor device of claim 8, wherein the processor is configured to process the one or more images using a neural network to classify the product detected in the one or more images into one of a plurality of predetermined types of products.",
    "10. The sensor device of claim 8, wherein the processor is configured to determine whether the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to i) a no-load constant or ii) is below the no-load constant, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image corresponds to the no-load constant, determine that the conveyor is currently empty, and in response to determining that the ratio of the first number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image is below the no-load constant, determine that the product is currently present on the conveyor.",
    "11. The sensor device of claim 8, wherein the processor is configured to determine, based on the ratio of the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image, a degree of coverage of the at least the portion of the conveyor depicted in the scene by the product.",
    "12. The sensor device of claim 8, wherein the at least one camera includes an infrared IR camera and a visible light camera, the sensor device further comprises a sensor configured to determine whether or not fog is present at the conveyor, and the processor is further configured to select an image to be processed, the processor being configured to i) when it is determined that fog is present at the conveyor, select an IR image captured by the IR camera and ii) when it is determined that fog is not present at the conveyor, select a visible light image captured by the visible light camera.",
    "13. A tangible, non-transitory computer readable medium storing machine readable instructions that, when executed by a processor associated with a sensor device, cause the processor to: receive a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of a food processing system, wherein respective ones of the images capture the scene at respective points in time; process one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; and provide characteristics information indicating the one or more characteristics detected in the scene to a controller, wherein the characteristics information is to be used by the controller to control operation of one or both of a) the conveyor and b) the treatment area of the food processing system; wherein the machine readable instructions, when executed by the processor associated with the sensor device, cause the processor to i) receive a plurality of infrared (IR) images captured by an IR camera capturing the scene that depicts at least the portion of the conveyer entering the treatment area of the food processing system, ii) render an IR image, among the plurality of IR images, as a visible image depicting the at least the portion of the conveyor in the scene, iii) process the visible image to detect the one or more characteristics in the scene. iv) compare values of respective pixels in an IR image, among the one or more IR images, to a threshold temperature, the threshold temperature being between a temperature of a surface of the conveyor and a temperature of the product on the conveyor, v) count at least one of a) a first number of pixels having values that exceed the threshold temperature and b) a second number of pixels having values that do not exceed the threshold temperature, and vi) determine at least one of the one or more characteristics based on a ratio of at least one of a) the first number of pixels having values that exceed the threshold temperature to a total number of the respective pixels in the IR image and b) the second number of pixels having values that do not exceed the threshold temperature to the total number of the respective pixels in the IR image.",
    "14. A method of providing control for a food processing system, the method comprising: receiving, at a processor of a sensor device, a plurality of images capturing a scene that depicts at least a portion of a conveyer entering a treatment area of the food processing system, wherein respective ones of the images capture the scene at respective points in time; processing, with the processor of the sensor device, one or more images, among the plurality of images, to detect one or more characteristics in the scene, including i) detecting presence or absence of a product on the at least the portion of the conveyor depicted in the scene and ii) classifying the scene as having one or more characteristics among a predetermined set of characteristics; providing, by the sensor device to a controller, characteristics information indicating the one or more characteristics detected in the scene, wherein the characteristics information is to be used by the controller to control operation of one or both of i) the conveyor and ii) the treatment area of the food processing system; detecting, with a sensor disposed in the sensor device, whether fog is present at the conveyor; and selecting an image to be processed by the processor, including i) when it is determined that fog is present in the scene, selecting an IR image captured by the IR camera and ii) when it is determined that fog is not present at the conveyor, selecting a visible light image captured by the visible light camera; wherein obtaining the plurality of images comprises obtaining one or both of a) one or more infrared (IR) image captured by an IR camera and b) one or more visible light images captured by a visible light camera."
  ],
  "description_excerpt": "The present disclosure relates generally to sensor devices and, more particularly, to imaging sensor devices for providing control for freezing or chilling equipment.\n\nFood industries often utilize various types of conveyor equipment for freezing or chilling products. For example, a food production or processing plant may utilize a conveyor freezer for freezing various types of food, such as fish, chicken, shrimp, meat patties, fruits, vegetables, etc. As another example, a food production or processing plant may utilize a conveyor cooler for quickly chilling products, such as eggs, cured meats, cheeses, etc. In such freezing or chilling equipment, the product is loaded onto a continuously moving conveyor that moves through a treatment area, which may be an enclosed area such as a tunnel. As the conveyor belt moves through the treatment area, a coolant is supplied to the product to bring the temperature of the product to a desired cooling or freezing temperature. Such typical freezing or chilling equipment does not monitor, in real-time, characteristics of the conveyor, and does not automatically control operating conditions of the freezing or chilling equipment based on real-time characteristics of the conveyor, which often results in inefficient use of the equipment and increased costs of operating the equipment.\n\nThe following introduces a selection of concepts in a simplified form in order to provide a foundational understanding of some aspects of the present disclosure.",
  "cpc": [
    "F25D 13/06",
    "A23B 2/88",
    "A23B 4/09",
    "A47J 37/045",
    "B65G 43/08",
    "F25D 13/067",
    "G01J 5/0022",
    "G05B 19/4183",
    "G05B 2219/31282",
    "G06N 3/04",
    "G06N 3/0464",
    "G06N 3/09",
    "G06V 10/764",
    "G06V 10/82",
    "G06V 20/20",
    "G06V 20/52",
    "H04N 7/181"
  ],
  "ipc": [
    "A47J 37/04",
    "G01J 5/00",
    "G06N 3/04",
    "G06V 10/764",
    "G06V 20/20"
  ],
  "assignees": [
    "AIR PROD & CHEM"
  ],
  "inventors": [
    "HENDERSHOT REED JACOB",
    "GUHA AVISHEK",
    "HAUPT SHAWN",
    "NAIK ANKIT",
    "HIMES MICHAEL ROBERT",
    "ARSLAN ERDEM"
  ],
  "filing_date": "2020-04-15",
  "publication_date": "2022-06-21",
  "grant_date": "2022-06-21",
  "priority_date": "2020-04-15",
  "application_number": "US-202016848936-A",
  "family_id": "75529784",
  "citations": [
    "EP0667501A1",
    "EP2998663A2",
    "US2014230460A1",
    "US2017138661A1",
    "US2018338354A1",
    "US2018365820A1",
    "US2021112818A1",
    "US2021201471A1",
    "US2021204553A1",
    "US6233966B1",
    "WO2006073909A2",
    "WO2016043925A1",
    "WO2020003310A1"
  ]
}

Record 465 of 5,000 in Patents full text (MLC-0201). Request the full dataset.