WO2019238130A1 - 谷物评估方法、装置和存储介质 - Google Patents

谷物评估方法、装置和存储介质 Download PDF

Info

Publication number
WO2019238130A1
WO2019238130A1 PCT/CN2019/091399 CN2019091399W WO2019238130A1 WO 2019238130 A1 WO2019238130 A1 WO 2019238130A1 CN 2019091399 W CN2019091399 W CN 2019091399W WO 2019238130 A1 WO2019238130 A1 WO 2019238130A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
feature
grain
evaluated
data
Prior art date
Application number
PCT/CN2019/091399
Other languages
English (en)
French (fr)
Inventor
陈必东
Original Assignee
佛山市顺德区美的电热电器制造有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 佛山市顺德区美的电热电器制造有限公司 filed Critical 佛山市顺德区美的电热电器制造有限公司
Priority to JP2020569744A priority Critical patent/JP2021526646A/ja
Priority to KR1020217000926A priority patent/KR102453207B1/ko
Publication of WO2019238130A1 publication Critical patent/WO2019238130A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects

Definitions

  • the present application relates to image recognition technology, and in particular, to a method, device, and computer-readable storage medium for grain evaluation.
  • artificial intelligence is a very challenging subject, including a very wide range of sciences. It consists of different fields, such as machine learning, computer vision, biological sciences, neural network science, energy technology, genetic engineering, etc., artificial intelligence research.
  • the main purpose is to let machines perform complex tasks that require human intelligence to complete.
  • the name is food, and every day you eat, so cooking becomes an important thing.
  • Rice cookers can cook, and different functions and different prices of cooking equipment make different meals.
  • the cooking equipment is required to modify the effect of cereal cooking. . Before optimizing the cooking equipment, it is necessary to grasp what kind of rice meets the dietary habits of most users. Therefore, it is necessary to provide a method that can evaluate the quality and taste of the grain.
  • embodiments of the present application provide a method, a device, and a computer-readable storage medium for evaluating grains.
  • An embodiment of the present application provides a method for evaluating cereals.
  • the method includes:
  • the method further includes: performing feature enhancement processing on the first image data to obtain feature enhanced image data corresponding to the first image data;
  • obtaining the first recognition result based on the first image data and the first recognition model includes: obtaining the first recognition result based on the feature-enhanced image data corresponding to the first image data and the first recognition model.
  • the performing feature enhancement processing on the first image data to obtain the feature enhanced image data corresponding to the first image data includes:
  • the feature-enhanced image data corresponding to the first image data is obtained based on the contrast-enhanced image data of the first image data and the edge detection image data.
  • the method further includes:
  • the second image information includes second image data and corresponding label data;
  • the label data represents a category to which the grain belongs;
  • performing the data enhancement processing on the feature enhanced image data corresponding to the second image data to obtain the data enhanced image data includes:
  • the image data generating data enhances the image data.
  • the evaluating the cereal to be evaluated according to an evaluation strategy corresponding to the first image data and the category of the cereal to be evaluated includes:
  • the grain to be evaluated is evaluated according to the evaluation strategy and the feature enhanced image data corresponding to the first image data.
  • An embodiment of the present application further provides a grain evaluation device, where the device includes: an obtaining module and a processing module;
  • the acquisition module is configured to acquire first image data including a grain to be evaluated
  • the processing module is configured to obtain a first recognition result based on the first image data and a first recognition model, the first recognition result characterizing a category of the grain to be evaluated;
  • the processing module is further configured to perform feature enhancement processing on the first image data to obtain feature enhanced image data corresponding to the first image data; based on the first The feature-enhanced image data corresponding to an image data and the first recognition model obtain a first recognition result.
  • the processing module is configured to convert the first image data into a grayscale image, perform contrast enhancement processing on the grayscale image, and obtain the first image data.
  • the contrast-enhanced image data of the first image data; performing edge detection on the first image data to obtain edge-detected image data; and obtaining the first image data corresponding to the first image data based on the contrast-enhanced image data of the first image data and the edge detection image data Features enhanced image data.
  • the processing module is further configured to obtain a plurality of second image information; the second image information includes second image data and corresponding label data; and the label data is characterized The category to which the grain belongs; performing feature enhancement processing on the second image data to obtain feature enhancement image data corresponding to the second image data; performing data enhancement processing on feature enhancement image data corresponding to the second image data to obtain data Enhanced image data; learning and training based on the feature enhanced image data and / or the data enhanced image data and corresponding label data to obtain the first recognition model.
  • the processing module is configured to rotate and / or flip the feature enhanced image data corresponding to the second image data to obtain a flip corresponding to the feature enhanced image data.
  • Image data and / or rotated image data, and data enhanced image data is generated based on the flipped image data and / or rotated image data.
  • the processing module is configured to obtain a corresponding evaluation strategy according to the category of the grain to be evaluated; and enhance the image according to the evaluation strategy and a feature corresponding to the first image data.
  • the data evaluate the cereals to be evaluated.
  • An embodiment of the present application further provides a grain evaluation device.
  • the device includes: a processor and a memory for storing a computer program capable of running on the processor; wherein, when the processor is used for running the computer program, Perform the steps of any of the methods of grain assessment described above.
  • An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored.
  • a computer program is stored on which a computer program is stored.
  • the grain evaluation method, device, and computer-readable storage medium obtained in the embodiments of the present application obtain first image data including grains to be evaluated, and obtain a first recognition result based on the first image data and a first recognition model.
  • the first recognition result characterizes the category of the grain to be evaluated; and evaluates the grain to be evaluated according to an evaluation strategy corresponding to the first image data and the category of the grain to be evaluated to obtain an evaluation result.
  • an image of grain is collected and feature enhancement processing is performed, and the grain is accurately identified according to the image after the feature enhancement processing, and the assessment is performed according to the grain recognition result and the enhanced processing image to obtain an evaluation result of the grain.
  • the evaluation result reflects the quality and taste of the grain, so that the cooking curve of the cooking equipment can be modified according to the evaluation result, and the grain with a better exit feeling is cooked for the user.
  • FIG. 1 is a schematic flowchart of a cereal evaluation method according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of another cereal evaluation method according to an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a grain evaluation device according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of another cereal evaluation device according to an embodiment of the present application.
  • first image data including grains to be evaluated is obtained; a first recognition result is obtained based on the first image data and a first recognition model, and the first recognition result characterizes the to-be-evaluated The type of the cereal; and evaluating the cereal to be evaluated according to an evaluation strategy corresponding to the first image data and the type of the cereal to be evaluated to obtain an evaluation result.
  • FIG. 1 is a schematic flowchart of a cereal evaluation method according to an embodiment of the present application. As shown in FIG. 1, the method includes:
  • Step 101 Obtain first image data including a grain to be evaluated
  • Step 102 Obtain a first recognition result based on the first image data and a first recognition model, where the first recognition result characterizes a category of the grain to be evaluated;
  • Step 103 Evaluate the cereal to be evaluated according to an evaluation strategy corresponding to the first image data and the category of the cereal to be evaluated to obtain an evaluation result.
  • the first image data includes cereals to be evaluated, such as rice, millet, and the like.
  • the grain evaluation method may be applied to a device; as a first embodiment, the device may be a cooking device, the cooking device is provided with an image acquisition component (such as a camera), and the image data is collected by the image acquisition component, and the collected image data is Perform analysis and identification to determine the category of the cereal to be evaluated.
  • the device may be a cooking device.
  • the cooking device does not have an image acquisition function.
  • the cooking device may communicate with another device that has an image acquisition component.
  • the image acquisition component of the device collects image data, and the cooking device obtains the image data collected by the other device through the communication link with the other device, analyzes and identifies the collected image data, and determines the category to which the grain to be evaluated belongs; as
  • the device may be an electronic device.
  • the electronic device may be a mobile device, such as a mobile phone or a tablet computer.
  • the electronic device collects image data, analyzes and identifies the collected image data, and determines the category of the cereal to be evaluated.
  • the cooking device may be a kitchen heating device such as an electric rice cooker or an electric pressure cooker.
  • the grain evaluation method further includes: performing feature enhancement processing on the first image data to obtain feature enhanced image data corresponding to the first image data; and correspondingly, based on the first image
  • Obtaining the first recognition result by using the data and the first recognition model includes: obtaining the first recognition result based on the feature enhanced image data corresponding to the first image data and the first recognition model.
  • the image data obtained after processing has almost no color information, that is, after the first image data is converted into a grayscale image, the grain
  • the morphological features are not very obvious, and the classification effect is not good. Therefore, in the embodiment of the present application, feature enhancement is performed on the grayscale image after the first image data is converted, mainly to enhance the contrast of the grayscale image. deal with.
  • the contrast indicates the measurement of different brightness levels between the brightest pixel point and the darkest pixel point in the image data. A larger difference range indicates a larger contrast, and a smaller difference range indicates a smaller contrast.
  • a contrast enhancement algorithm can be used to enhance the contrast of the image data, especially when the contrast of useful data of the image data is quite close.
  • the difference between different rice grains is more obvious, and it can reflect the light transmittance of different rice grains.
  • the contrast enhancement algorithm includes, but is not limited to, at least one of the following algorithms: a linear transformation algorithm, an exponential change algorithm, a logarithmic change algorithm, a histogram algorithm, and the like.
  • performing the feature enhancement processing on the first image data to obtain the feature enhanced image data corresponding to the first image data includes: converting the first image data A grayscale image, performing contrast enhancement processing on the grayscale image to obtain contrast enhanced image data of the first image data; performing edge detection on the first image data to obtain edge detection image data; and based on the first The contrast-enhanced image data of the image data and the edge-detected image data obtain feature-enhanced image data corresponding to the first image data.
  • the contour information of the grain can be better obtained through edge detection, so that the difference between different rice grains is more obvious, and the light transmittance of different rice grains can be reflected.
  • the edge detection algorithm used includes but is not limited to at least one of the following algorithms: Roberts edge detection algorithm, Sobel edge detection algorithm, Prewitt edge detection algorithm, Canny edge detection algorithm, Laplacian edge detection algorithm, Log edge detection algorithm, and Operator detection methods such as second-order directional derivatives.
  • the first recognition model is obtained by a manufacturer of a cooking device by using a training method in advance and stored in the device.
  • the grain evaluation method may further include: obtaining a first recognition model through a method of learning and training, and specifically obtaining the first recognition model may include:
  • Step 001 Obtain a plurality of second image information; the second image information includes second image data and corresponding label data; and the label data represents a category to which the grain belongs.
  • Step 002 Perform feature enhancement processing on the second image data to obtain feature enhanced image data corresponding to the second image data.
  • Step 003 Perform data enhancement processing on the feature enhanced image data corresponding to the second image data to obtain data enhanced image data.
  • Step 004 Perform learning and training based on the feature-enhanced image data and / or the data-enhanced image data and corresponding label data to obtain the first recognition model.
  • performing the feature enhancement processing on the second image data to obtain the feature enhanced image data may include: converting the second image data into a grayscale image, and performing Performing contrast enhancement processing on the grayscale image to obtain contrast enhanced image data of the second image data; performing edge detection on the second image data to obtain edge detection image data; and contrast enhanced image based on the second image data Data and the edge detection image data to obtain feature enhanced image data corresponding to the second image data.
  • performing the data enhancement processing on the feature enhanced image data corresponding to the second image data to obtain the data enhanced image data may include: inverting the feature enhanced image data corresponding to the second image data And / or rotation to obtain inverted image data and / or rotated image data corresponding to the feature enhanced image data, and generate data enhanced image data based on the inverted image data and / or rotated image data.
  • the rotation angle may be a first preset angle, and the first preset angle is one of the following angles: 90 degrees, 180 degrees, and 270 degrees;
  • the feature enhanced image data After performing the flip the feature-enhanced image data after the flip is further rotated, and the rotation angle may be a second preset angle, and the second preset angle is one of the following angles: 90 degrees, 180 degrees, and 270 degrees.
  • the device stores in advance an evaluation strategy corresponding to at least one cereal category
  • the evaluating the grain to be evaluated according to an evaluation strategy corresponding to the category of the grain to be evaluated and obtaining an evaluation result includes: obtaining a corresponding assessment strategy according to the category of the grain to be evaluated; The evaluation strategy and the feature enhanced image data corresponding to the first image data evaluate the grain to be evaluated, and determine an evaluation result of the grain to be evaluated.
  • the evaluation strategy is set in advance by the manufacturer of the cooking equipment and stored in the equipment, and the evaluation strategy can evaluate the quality, taste, and score of different types of cereals.
  • FIG. 2 is a schematic flowchart of another cereal evaluation method according to an embodiment of the present application; as shown in FIG. 2, the method includes:
  • Step 201 Acquire first image data including a grain to be evaluated.
  • the cereal to be evaluated refers to cereals after cooking, such as cooked rice.
  • Step 202 Pre-process the first image data.
  • the preprocessing the first image data includes: converting the first image data into a grayscale image, and performing contrast enhancement processing on the grayscale image.
  • Step 203 Use a deep learning image classifier to identify the grain category.
  • the using the deep learning image classifier to identify the cereal category includes: obtaining a first recognition result based on the feature-enhanced image data corresponding to the first image data and a first recognition model, The first identification result characterizes a category of the grain to be evaluated.
  • Step 204 Grain evaluation is performed according to the grain type and the pre-processed image.
  • the performing cereal evaluation according to a cereal category and a pre-processed image includes: obtaining a corresponding evaluation strategy according to the category of the cereal to be evaluated; and according to the evaluation strategy and the The feature-enhanced image data corresponding to the first image data evaluates the discreteness of the grain to be evaluated, the density between the grains, glossiness, etc., so as to obtain an evaluation result for the quality, taste, and score of the grain to be evaluated.
  • Step 205 Obtain an evaluation result of the grain.
  • an image of grain is collected and feature enhancement processing is performed, and the grain is accurately identified according to the image after the feature enhancement processing, and the assessment is performed according to the grain recognition result and the enhanced processing image to obtain an evaluation result of the grain.
  • the evaluation result reflects the quality and taste of the grain, so that the cooking curve of the cooking equipment can be modified according to the evaluation result, and the grain with a better exit feeling is cooked for the user.
  • FIG. 3 is a schematic structural diagram of a grain evaluation device according to an embodiment of the present application. As shown in FIG. 3, the device includes: an obtaining module 301 and a processing module 302;
  • the obtaining module 301 is configured to obtain first image data including a grain to be evaluated
  • the processing module 302 is configured to obtain a first recognition result based on the first image data and a first recognition model, where the first recognition result represents a category of the grain to be evaluated;
  • the evaluation strategy corresponding to the category of the cereal to be evaluated evaluates the cereal to be evaluated to obtain an evaluation result.
  • the processing module 302 is further configured to perform feature enhancement processing on the first image data to obtain feature enhanced image data corresponding to the first image data; based on the The feature-enhanced image data corresponding to the first image data and the first recognition model obtain a first recognition result.
  • the processing module 302 is configured to convert the first image data into a grayscale image, perform contrast enhancement processing on the grayscale image, and obtain the first image. Contrast-enhanced image data of the data; performing edge detection on the first image data to obtain edge-detected image data; obtaining the first image data based on the contrast-enhanced image data of the first image data and the edge-detected image data Corresponding feature enhancement image data.
  • the processing module 302 is further configured to obtain a plurality of second image information; the second image information includes second image data and corresponding label data; and the label data Characterize the category to which the grain belongs; perform feature enhancement processing on the second image data to obtain feature enhanced image data corresponding to the second image data; perform data enhancement processing on feature enhanced image data corresponding to the second image data to obtain Data-enhanced image data; learning and training based on the feature-enhanced image data and / or the data-enhanced image data and corresponding label data to obtain a first recognition model.
  • the processing module 302 is configured to rotate and / or flip the feature-enhanced image data corresponding to the second image data to obtain a feature-enhanced image data corresponding to the feature-enhanced image data. Flip image data and / or rotated image data, and generate data-enhanced image data based on the flip image data and / or rotated image data.
  • the rotation angle may be a first preset angle, and the first preset angle is one of the following angles: 90 degrees, 180 degrees, and 270 degrees;
  • the feature enhanced image data After performing the flip the feature-enhanced image data after the flip is further rotated, and the rotation angle may be a second preset angle, and the second preset angle is one of the following angles: 90 degrees, 180 degrees, and 270 degrees.
  • the processing module 302 is configured to obtain a corresponding evaluation strategy according to the category of the grain to be evaluated; and enhance the features corresponding to the evaluation strategy and the first image data.
  • the image data evaluates the grain to be evaluated and determines an evaluation result of the grain to be evaluated.
  • the acquisition module 301 and the processing module 302 in the device may be implemented by a central processing unit (CPU, Central Processing Unit), a digital signal processor (DSP, Digital Signal) in the terminal in practical applications. Processor), Microcontroller Unit (MCU, Microcontroller Unit) or Programmable Gate Array (FPGA, Field-Programmable Gate Array).
  • CPU Central Processing Unit
  • DSP Digital Signal
  • MCU Microcontroller Unit
  • FPGA Programmable Gate Array
  • the grain evaluation device provided in the foregoing embodiment only uses the division of the above-mentioned program modules as an example for the grain evaluation.
  • the above processing may be allocated by different program modules as required. That is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above.
  • the grain evaluation device provided by the foregoing embodiment belongs to the same concept as the grain evaluation method embodiment, and its specific implementation process is described in the method embodiment in detail, and is not repeated here.
  • the embodiment of the present application provides another cereal evaluation device, which is set on a cooking device or a mobile terminal.
  • the device 40 includes:
  • the processor 401 When the processor 401 is used to run the computer program, executing: acquiring first image data including grains to be evaluated; obtaining a first recognition result based on the first image data and a first recognition model, the first recognition The result characterizes the category of the grain to be evaluated; and evaluates the grain to be evaluated according to an evaluation strategy corresponding to the first image data and the category of the grain to be evaluated to obtain an evaluation result.
  • the processor 401 when the processor 401 is configured to run the computer program, execute: performing feature enhancement processing on the first image data to obtain feature enhanced image data corresponding to the first image data; based on the The feature-enhanced image data corresponding to the first image data and the first recognition model obtain a first recognition result.
  • the processor 401 when the processor 401 is used to run the computer program, executing: converting the first image data into a grayscale image, and performing contrast enhancement processing on the grayscale image to obtain the first Contrast-enhanced image data of an image data; performing edge detection on the first image data to obtain edge-detected image data; obtaining the first image based on the contrast-enhanced image data of the first image data and the edge-detected image data The feature-enhanced image data corresponding to the image data.
  • the processor 401 when the processor 401 is used to run the computer program, executing: obtaining a plurality of second image information; the second image information includes second image data and corresponding label data; the label The data represents the category to which the grain belongs; performing feature enhancement processing on the second image data to obtain feature enhanced image data corresponding to the second image data; and performing data enhancement processing on the feature enhanced image data corresponding to the second image data, Obtain data-enhanced image data; perform learning and training based on the feature-enhanced image data and / or the data-enhanced image data and corresponding label data to obtain a first recognition model.
  • the processor 401 when the processor 401 is configured to run the computer program, performing: rotating and / or flipping the feature enhanced image data corresponding to the second image data to obtain the feature enhanced image data.
  • Corresponding inverted image data and / or rotated image data, and data enhanced image data is generated based on the inverted image data and / or rotated image data.
  • the processor 401 when the processor 401 is used to run the computer program, the processor 401 executes: obtaining a corresponding evaluation strategy according to the category of the grain to be evaluated; and according to the evaluation strategy and the first image data, The feature enhanced image data evaluates the grain to be evaluated, and determines an evaluation result of the grain to be evaluated.
  • the device 40 may further include: at least one network interface 403.
  • the various components in the grain evaluation device 40 are coupled together via a bus system 404.
  • the bus system 404 is used to implement connection and communication between these components.
  • the bus system 404 includes a power bus, a control bus, and a status signal bus in addition to the data bus.
  • various buses are marked as the bus system 404 in FIG. 4.
  • the number of the processors 401 may be at least one.
  • the network interface 403 is used for wired or wireless communication between the grain evaluation device 40 and other devices.
  • the memory 402 in the embodiment of the present application is used to store various types of data to support the operation of the device 40.
  • the method disclosed in the embodiments of the present application may be applied to the processor 401, or implemented by the processor 401.
  • the processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 401 or an instruction in the form of software.
  • the processor 401 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like.
  • DSP Digital Signal Processor
  • the processor 401 may implement or execute various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.
  • a general-purpose processor may be a microprocessor or any conventional processor.
  • the steps may be directly implemented by a hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module may be located in a storage medium.
  • the storage medium is located in the memory 402.
  • the processor 401 reads the information in the memory 402 and completes the steps of the foregoing method in combination with its hardware.
  • the memory 402 may be implemented by any type of volatile or non-volatile storage device, or a combination thereof.
  • the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), or an erasable programmable read-only memory (EPROM, Erasable Programmable Read- Only Memory), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Flash Surface Memory , Compact disc, or read-only compact disc (CD-ROM, Compact Disc-Read-Only Memory);
  • the magnetic surface memory can be a disk memory or a tape memory.
  • the volatile memory may be a random access memory (RAM, Random Access Memory), which is used as an external cache.
  • RAM random access memory
  • RAM Random Access Memory
  • many forms of RAM are available, such as Static Random Access Memory (SRAM, Static Random Access Memory), Synchronous Static Random Access Memory (SSRAM, Static Random Access, Memory), Dynamic Random Access DRAM (Dynamic Random Access Memory), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Double Data Rate Rate Synchronous Dynamic Access Random Access Memory, Enhanced Type Synchronous Dynamic Random Access Memory (ESDRAM, Enhanced Synchronous Random Access Memory), Synchronous Link Dynamic Random Access Memory (SLDRAM, SyncLink Dynamic Access Random Access Memory), Direct Memory Bus Random Access Memory (DRRAM, Direct Rambus Random Access Memory ).
  • the memory 402 described in the embodiments of the present invention is intended to include, but not limited to, these and any other suitable types of memory.
  • the grain evaluation device 40 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), and complex programmable logic Device (CPLD, Complex Programmable Logic Device), Field Programmable Gate Array (FPGA, Field-Programmable Gate Array), general-purpose processor, controller, microcontroller (MCU, MicroController), microprocessor (Microprocessor), Or other electronic components for performing the foregoing method.
  • ASICs Application Specific Integrated Circuits
  • DSPs Programmable Logic Devices
  • CPLD Complex Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • MCU microcontroller
  • Microcontroller Microcontroller
  • Microprocessor Microprocessor
  • an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the steps of the method described in the embodiment of the present application are performed.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division.
  • there may be another division manner such as multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed components are coupled, or directly coupled, or communicated with each other through some interfaces.
  • the indirect coupling or communications of the device or unit may be electrical, mechanical, or other forms. of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, which may be located in one place or distributed across multiple network units; Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.
  • the functional units in the embodiments of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration
  • the unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the foregoing program may be stored in a computer-readable storage medium.
  • the program is executed, the program is executed.
  • the foregoing storage medium includes: a mobile storage device, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, etc.
  • ROM read-only memory
  • RAM random access memory
  • magnetic disk or an optical disk etc.
  • the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
  • the computer software product is stored in a storage medium and includes several instructions for A computer device (which may be a personal computer, a server, or a network device) is caused to execute all or part of the methods described in the embodiments of the present application.
  • the foregoing storage media include: various types of media that can store program codes, such as a mobile storage device, a ROM, a RAM, a magnetic disk, or an optical disc.

Abstract

本申请实施例公开了一种谷物评估方法，包括：获取包括待评估谷物的第一图像数据；基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。本申请实施例还公开了一种谷物评估装置和存储介质。

Description

谷物评估方法、装置和存储介质
相关申请的交叉引用
本申请基于申请号为201810621682.6、申请日为2018年6月15日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本申请。
技术领域
本申请涉及图像识别技术，尤其涉及一种谷物评估方法、装置和计算机可读存储介质。
背景技术
目前人工智能是一门极富有挑战性的学科，包括十分广泛的科学，它由不同领域组成，如机器学习、计算机视觉、生物科学、神经网络科学、能源技术、基因工程等，人工智能研究的主要目的是让机器执行需要人类智能才能完成的复杂工作。随着人们的生活质量不断提高，对饮食起居要求也自然而然的提高。名以食为天，每天都要吃饭，因此做饭成为重要的事情，电饭煲能够做饭，不同功能、不同价格的烹饪设备做的饭口感也不同，对烹饪设备提出了修正谷物烹饪效果的要求。而在对烹饪设备进行优化之前，首先需要掌握到什么样的米饭符合绝大多数用户的饮食习惯，因此，需要提供一种能够评估谷物的质量与口感的方法。
发明内容
为解决现有存在的技术问题，本申请实施例提供一种谷物评估方法、装置和计算机可读存储介质。
本申请的技术方案是这样实现的：
本申请实施例提供了一种谷物评估方法，所述方法包括：
获取包括待评估谷物的第一图像数据；
基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；
根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
在本申请的一种可选实施例中，所述方法还包括：对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；
相应的，所述基于所述第一图像数据和第一识别模型获得第一识别结果，包括：基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
在本申请的一种可选实施例中，所述对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据，包括：
将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；
基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
在本申请的一种可选实施例中，所述方法还包括：
获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；
对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；
对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获 得数据增强图像数据；
基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得所述第一识别模型。
在本申请的一种可选实施例中，所述对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据，包括：
对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
在本申请的一种可选实施例中，所述根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，包括：
根据所述待评估谷物的类别获取对应的评估策略；
根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物。
本申请实施例还提供了一种谷物评估装置，所述装置包括：获取模块和处理模块；其中，
所述获取模块，配置为获取包括待评估谷物的第一图像数据；
所述处理模块，配置为基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；
根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
在本申请的一种可选实施例中，所述处理模块，还配置为对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
在本申请的一种可选实施例中，所述处理模块，配置为将所述第一图 像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
在本申请的一种可选实施例中，所述处理模块，还配置为获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据；基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得所述第一识别模型。
在本申请的一种可选实施例中，所述处理模块，配置为对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
在本申请的一种可选实施例中，所述处理模块，配置为根据所述待评估谷物的类别获取对应的评估策略；根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物。
本申请实施例还提供了一种谷物评估装置，所述装置包括：处理器和用于存储能够在处理器上运行的计算机程序的存储器；其中，所述处理器用于运行所述计算机程序时，执行以上任一所述谷物评估方法的步骤。
本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现以上任一所述谷物评估方法的步骤。
本申请实施例所提供的谷物评估方法、装置、计算机可读存储介质， 获取包括待评估谷物的第一图像数据；基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。本申请实施例的方案中，采集谷物的图像并进行特征增强处理，根据特征增强处理后的图像准确识别谷物，根据谷物识别结果和增强处理后的图像进行评估，获得所述谷物的评估结果，所述评估结果反映出谷物的质量和口感，从而根据评估结果可修正烹饪设备的烹饪曲线，为用户烹饪出口感更好的谷物。
附图说明
图1为本申请实施例提供的一种谷物评估方法的流程示意图；
图2为本申请实施例提供的另一种谷物评估方法的流程示意图；
图3为本申请实施例提供的一种谷物评估装置的结构示意图；
图4为本申请实施例提供的另一种谷物评估装置的结构示意图。
具体实施方式
在本申请的各种实施例中，获取包括待评估谷物的第一图像数据；基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
下面结合实施例对本申请再作进一步详细的说明。
图1为本申请实施例提供的一种谷物评估方法的流程示意图；如图1所示，所述方法包括：
步骤101、获取包括待评估谷物的第一图像数据；
步骤102、基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；
步骤103、根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
本实施例中，所述第一图像数据中包括待评估谷物，所述待评估谷物例如大米、小米等。
所述谷物评估方法可应用于设备中；作为第一种实施方式，该设备可以是烹饪设备，烹饪设备设置有图像采集组件(如摄像头)，通过图像采集组件采集图像数据，对采集的图像数据进行分析识别，确定待评估谷物所属类别；作为第二种实施方式，设备可以是烹饪设备，该烹饪设备不具有图像采集功能，烹饪设备可与具有图像采集组件的另一设备通信，通过另一设备的图像采集组件采集图像数据，烹饪设备通过与所述另一设备的通信链路获得所述另一设备采集的图像数据，对采集的图像数据进行分析识别，确定待评估谷物所属类别；作为第三种实施方式，设备可以是电子设备，该电子设备可以是移动设备，例如手机、平板电脑等设备，通过电子设备采集图像数据，对采集的图像数据进行分析识别，确定待评估谷物所属类别。实际应用中，所述烹饪设备可以是电饭煲、电压力锅等厨房加热设备。
本实施例中，所述谷物评估方法还包括：对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；相应的，所述基于所述第一图像数据和第一识别模型获得第一识别结果，包括：基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
本实施例中，区别于其他的物体识别任务，考虑到谷物的图像数据的色彩空间较为特殊，经过处理获得的图像数据几乎没有彩色信息，即：第一图像数据转换为灰度图像后，谷物的形态特征也不是很明显，分类效果不佳，因此，本申请实施例中对所述第一图像数据转换后的灰度图像进行 特征增强，主要是将对所述灰度图像的对比度进行增强处理。所述对比度表示图像数据中的最亮的像素点和最暗的像素点之间不同亮度层级的测量，差异范围越大表示对比度越大，差异范围越小表示对比度越小。这里，可以采用对比度增强算法，加强图像数据的对比度，尤其当图像数据的有用数据的对比度相当接近的情况。使不同米粒之间的区别更加明显，可以反映出不同米粒的透光程度。所述对比度增强算法包括但不限于以下算法的至少一个：线性变换算法、指数变化算法、对数变化算法、直方图算法等。
在本申请的一种可选实施例中，所述对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据，包括：将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
本实施例中，通过边缘检测，能够更好的获得谷物的轮廓信息，使不同米粒之间的区别更加明显，可以反映出不同米粒的透光程度。采用的边缘检测算法包括但不限于以下算法的至少之一：Roberts边缘检测算法，索贝尔(Sobel)边缘检测算法，Prewitt边缘检测算法，Canny边缘检测算法，Laplacian边缘检测算法，Log边缘检测算法以及二阶方向导数等算子检测法。
本实施例中，所述第一识别模型由烹饪设备的制造厂商预先运用学习训练的方法获得并保存在设备中。
在本申请的一种可选实施例中，所述谷物评估方法还可以包括：通过学习训练的方法获得第一识别模型，所述第一识别模型的获得方式具体可 以包括：
步骤001：获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别。
步骤002：对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据。
步骤003：对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据。
步骤004：基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得所述第一识别模型。
在本申请的一种可选实施例中，所述对所述第二图像数据进行特征增强处理，获得特征增强图像数据，可以包括：将所述第二图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第二图像数据的对比度增强图像数据；对所述第二图像数据进行边缘检测，获得边缘检测图像数据；基于所述第二图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第二图像数据对应的特征增强图像数据。
在一实施例中，所述对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据，可以包括：对所述第二图像数据对应的特征增强图像数据进行翻转和/或旋转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
其中，对特征增强图像数据进行旋转，旋转的角度可为第一预设角度，所述第一预设角度为以下角度的其中之一：90度、180度、270度；对特征增强图像数据进行翻转，翻转后的特征增强图像数据进一步进行旋转，旋转的角度可为第二预设角度，所述第二预设角度为以下角度的其中之一：90度、180度、270度。
本实施例中，所述设备预先保存有至少一种谷物类别对应的评估策略；
所述根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果，包括：根据所述待评估谷物的类别获取对应的评估策略；根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物，确定所述待评估谷物的评估结果。
这里，所述评估策略由烹饪设备的制造厂商预先设定并保存在设备中，所述评估策略可以针对不同类别的谷物进行质量、口感和评分等进行评估。
图2为本申请实施例提供的另一种谷物评估方法的流程示意图；如图2所示，所述方法包括：
步骤201、获取包括待评估谷物的第一图像数据。
这里，所述待评估谷物指烹饪之后的谷物，如煮熟后的米饭。
步骤202、对所述第一图像数据进行预处理。
在本申请的一种可选实施例中，所述对所述第一图像数据进行预处理，包括：将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
步骤203、运用深度学习图像分类器识别谷物类别。
在本申请的一种可选实施例中，所述运用深度学习图像分类器识别谷物类别，包括：基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别。
步骤204、根据谷物类别和预处理后的图像进行谷物评估。
在本申请的一种可选实施例中，所述根据谷物类别和预处理后的图像进行谷物评估，包括：根据所述待评估谷物的类别获取对应的评估策略； 根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物的离散性、颗粒间的致密性、光泽度等，从而获得针对所述待评估谷物的质量、口感和评分等的评估结果。
步骤205、获得谷物的评估结果。
本申请实施例的方案中，采集谷物的图像并进行特征增强处理，根据特征增强处理后的图像准确识别谷物，根据谷物识别结果和增强处理后的图像进行评估，获得所述谷物的评估结果，所述评估结果反映出谷物的质量和口感，从而根据评估结果可修正烹饪设备的烹饪曲线，为用户烹饪出口感更好的谷物。
图3为本申请实施例提供的一种谷物评估装置的结构示意图；如图3所示，所述装置包括：获取模块301和处理模块302；其中，
所述获取模块301，配置为获取包括待评估谷物的第一图像数据；
所述处理模块302，配置为基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
在本申请的一种可选实施例中，所述处理模块302，还配置为对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
在本申请的一种可选实施例中，所述处理模块302，配置为将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数 据。
在本申请的一种可选实施例中，所述处理模块302，还配置为获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据；基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得第一识别模型。
在本申请的一种可选实施例中，所述处理模块302，配置为对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
这里，对特征增强图像数据进行旋转，旋转的角度可为第一预设角度，所述第一预设角度为以下角度的其中之一：90度、180度、270度；对特征增强图像数据进行翻转，翻转后的特征增强图像数据进一步进行旋转，旋转的角度可为第二预设角度，所述第二预设角度为以下角度的其中之一：90度、180度、270度。
在本申请的一种可选实施例中，所述处理模块302，配置为根据所述待评估谷物的类别获取对应的评估策略；根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物，确定所述待评估谷物的评估结果。
本发明实施例中，所述装置中的获取模块301和处理模块302，在实际应用中均可由所述终端中的中央处理器(CPU，Central Processing Unit)、数字信号处理器(DSP，Digital Signal Processor)、微控制单元(MCU，Microcontroller Unit)或可编程门阵列(FPGA，Field－Programmable Gate  Array)实现。
需要说明的是：上述实施例提供的谷物评估装置在进行谷物评估时，仅以上述各程序模块的划分进行举例说明，实际应用中，可以根据需要而将上述处理分配由不同的程序模块完成，即将装置的内部结构划分成不同的程序模块，以完成以上描述的全部或者部分处理。另外，上述实施例提供的谷物评估装置与谷物评估方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
为实现本申请实施例的方法，本申请实施例提供另一种谷物评估装置，设置在烹饪设备或移动终端上，如图4所示，该装置40包括：
处理器401和用于存储能够在所述处理器上运行的计算机程序的存储器402；其中，
所述处理器401用于运行所述计算机程序时，执行：获取包括待评估谷物的第一图像数据；基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
在一实施例中，所述处理器401用于运行所述计算机程序时，执行：对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
在一实施例中，所述处理器401用于运行所述计算机程序时，执行：将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征 增强图像数据。
在一实施例中，所述处理器401用于运行所述计算机程序时，执行：获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据；基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得第一识别模型。
在一实施例中，所述处理器401用于运行所述计算机程序时，执行：对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
在一实施例中，所述处理器401用于运行所述计算机程序时，执行：根据所述待评估谷物的类别获取对应的评估策略；根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物，确定所述待评估谷物的评估结果。
需要说明的是：上述实施例提供的谷物评估装置与谷物评估方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
当然，实际应用时，如图4所示，该装置40还可以包括：至少一个网络接口403。谷物评估装置40中的各个组件通过总线系统404耦合在一起。可理解，总线系统404用于实现这些组件之间的连接通信。总线系统404除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图4中将各种总线都标为总线系统404。其中，所述处理器401的个数可以为至少一个。网络接口403用于谷物评估装置40与其他设备之间有线或无线方式的通信。本申请实施例中的存储器402用于 存储各种类型的数据以支持装置40的操作。
上述本申请实施例揭示的方法可以应用于处理器401中，或者由处理器401实现。处理器401可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器401中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器401可以是通用处理器、数字信号处理器(DSP，Digital Signal Processor)，或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。处理器401可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本申请实施例所公开的方法的步骤，可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于存储介质中，该存储介质位于存储器402，处理器401读取存储器402中的信息，结合其硬件完成前述方法的步骤。
存储器402可以由任何类型的易失性或非易失性存储设备、或者它们的组合来实现。其中，非易失性存储器可以是只读存储器(ROM，Read Only Memory)、可编程只读存储器(PROM，Programmable Read-Only Memory)、可擦除可编程只读存储器(EPROM，Erasable Programmable Read-Only Memory)、电可擦除可编程只读存储器(EEPROM，Electrically Erasable Programmable Read-Only Memory)、磁性随机存取存储器(FRAM，Ferromagnetic Random Access Memory)、快闪存储器(Flash Memory)、磁表面存储器、光盘、或只读光盘(CD-ROM，Compact Disc Read-Only Memory)；磁表面存储器可以是磁盘存储器或磁带存储器。易失性存储器可以是随机存取存储器(RAM，Random Access Memory)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(SRAM，Static Random Access Memory)、同步静态随机存 取存储器(SSRAM，Synchronous Static Random Access Memory)、动态随机存取存储器(DRAM，Dynamic Random Access Memory)、同步动态随机存取存储器(SDRAM，Synchronous Dynamic Random Access Memory)、双倍数据速率同步动态随机存取存储器(DDRSDRAM，Double Data Rate Synchronous Dynamic Random Access Memory)、增强型同步动态随机存取存储器(ESDRAM，Enhanced Synchronous Dynamic Random Access Memory)、同步连接动态随机存取存储器(SLDRAM，SyncLink Dynamic Random Access Memory)、直接内存总线随机存取存储器(DRRAM，Direct Rambus Random Access Memory)。本发明实施例描述的存储器402旨在包括但不限于这些和任意其它适合类型的存储器。
在示例性实施例中，所述谷物评估装置40可以被一个或多个应用专用集成电路(ASIC，Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD，Programmable Logic Device)、复杂可编程逻辑器件(CPLD，Complex Programmable Logic Device)、现场可编程门阵列(FPGA，Field-Programmable Gate Array)、通用处理器、控制器、微控制器(MCU，Micro Controller Unit)、微处理器(Microprocessor)、或其他电子元件实现，用于执行前述方法。
具体地，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器运行时，执行本申请实施例所述方法的步骤。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互 之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本申请各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本申请上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
本申请所提供的几个方法实施例中所揭露的方法，在不冲突的情况下 可以任意组合，得到新的方法实施例。
本申请所提供的几个产品实施例中所揭露的特征，在不冲突的情况下可以任意组合，得到新的产品实施例。
本申请所提供的几个方法或设备实施例中所揭露的特征，在不冲突的情况下可以任意组合，得到新的方法实施例或设备实施例。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (14)

  1. 一种谷物评估方法，所述方法包括：
    获取包括待评估谷物的第一图像数据；
    基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；
    根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；
    相应的，所述基于所述第一图像数据和第一识别模型获得第一识别结果，包括：基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
  3. 根据权利要求2所述的方法，其中，所述对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据，包括：
    将所述第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；
    基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
  4. 根据权利要求1所述的方法，其中，所述方法还包括：
    获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；
    对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；
    对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据；
    基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得所述第一识别模型。
  5. 根据权利要求4所述的方法，其中，所述对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据，包括：
    对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
  6. 根据权利要求2所述的方法，其中，所述根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，包括：
    根据所述待评估谷物的类别获取对应的评估策略；
    根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物。
  7. 一种谷物评估装置，所述装置包括：获取模块和处理模块；其中，
    所述获取模块，配置为获取包括待评估谷物的第一图像数据；
    所述处理模块，配置为基于所述第一图像数据和第一识别模型获得第一识别结果，所述第一识别结果表征所述待评估谷物的类别；根据所述第一图像数据和所述待评估谷物的类别对应的评估策略评估所述待评估谷物，获得评估结果。
  8. 根据权利要求7所述的装置，其中，所述处理模块，还配置为对所述第一图像数据进行特征增强处理，获得所述第一图像数据对应的特征增强图像数据；基于所述第一图像数据对应的特征增强图像数据和第一识别模型获得第一识别结果。
  9. 根据权利要求8所述的装置，其中，所述处理模块，配置为将所述 第一图像数据转换为灰度图像，对所述灰度图像进行对比度增强处理，获得所述第一图像数据的对比度增强图像数据；对所述第一图像数据进行边缘检测，获得边缘检测图像数据；基于所述第一图像数据的对比度增强图像数据和所述边缘检测图像数据获得所述第一图像数据对应的特征增强图像数据。
  10. 根据权利要求7所述的装置，其中，所述处理模块，还配置为获得多个第二图像信息；所述第二图像信息包括第二图像数据和对应的标签数据；所述标签数据表征谷物所属类别；对所述第二图像数据进行特征增强处理，获得所述第二图像数据对应的特征增强图像数据；对所述第二图像数据对应的特征增强图像数据进行数据增强处理，获得数据增强图像数据；基于所述特征增强图像数据和/或所述数据增强图像数据和对应的标签数据进行学习训练，获得所述第一识别模型。
  11. 根据权利要求10所述的装置，其中，所述处理模块，配置为对所述第二图像数据对应的特征增强图像数据进行旋转和/或翻转，获得与所述特征增强图像数据对应的翻转图像数据和/或旋转图像数据，基于所述翻转图像数据和/或旋转图像数据生成数据增强图像数据。
  12. 根据权利要求8所述的装置，其中，所述处理模块，配置为根据所述待评估谷物的类别获取对应的评估策略；根据所述评估策略和所述第一图像数据对应的特征增强图像数据评估所述待评估谷物。
  13. 一种谷物评估装置，所述装置包括：处理器和用于存储能够在处理器上运行的计算机程序的存储器；
    其中，所述处理器用于运行所述计算机程序时，执行权利要求1至6任一所述方法的步骤。
  14. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1至6任一所述方法的步骤。
PCT/CN2019/091399 2018-06-15 2019-06-14 谷物评估方法、装置和存储介质 WO2019238130A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2020569744A JP2021526646A (ja) 2018-06-15 2019-06-14 穀物の評価方法、装置及び記憶媒体
KR1020217000926A KR102453207B1 (ko) 2018-06-15 2019-06-14 곡물 평가 방법, 장치 및 저장 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810621682.6A CN110610183A (zh) 2018-06-15 2018-06-15 谷物评估方法、装置和存储介质
CN201810621682.6 2018-06-15

Publications (1)

Publication Number Publication Date
WO2019238130A1 true WO2019238130A1 (zh) 2019-12-19

Family

ID=68841744

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/091399 WO2019238130A1 (zh) 2018-06-15 2019-06-14 谷物评估方法、装置和存储介质

Country Status (4)

Country Link
JP (1) JP2021526646A (zh)
KR (1) KR102453207B1 (zh)
CN (1) CN110610183A (zh)
WO (1) WO2019238130A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111879735A (zh) * 2020-07-22 2020-11-03 武汉大学 一种基于图像的大米外观品质检测方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111579724B (zh) * 2020-06-01 2022-07-12 中国标准化研究院 一种麻和辣阈上感觉敏感度快速分类方法、装置及应用
CN114486877B (zh) * 2020-10-23 2024-01-19 合肥美亚光电技术股份有限公司 大米品质检测方法、设备以及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398886A (zh) * 2008-03-17 2009-04-01 杭州大清智能技术开发有限公司 一种基于双目被动立体视觉的快速三维人脸识别方法
CN102436589A (zh) * 2010-09-29 2012-05-02 中国科学院电子学研究所 一种基于多类基元自主学习的复杂目标自动识别方法
CN107951485A (zh) * 2017-11-27 2018-04-24 乐普（北京）医疗器械股份有限公司 基于人工智能自学习的动态心电图分析方法和装置

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4402915B2 (ja) * 2003-08-01 2010-01-20 セイレイ工業株式会社 穀粒選別装置
CN101234381B (zh) * 2008-03-07 2011-09-07 天津市华核科技有限公司 基于视觉识别的颗粒物料分选分级方法
CN101271522A (zh) * 2008-05-21 2008-09-24 中国农业大学 一种大米中黄粒米的自动识别方法
CN101701916B (zh) * 2009-12-01 2011-05-18 中国农业大学 一种玉米品种快速鉴定、鉴别方法
JP5716234B2 (ja) * 2010-12-28 2015-05-13 独立行政法人農業・食品産業技術総合研究機構 収穫予定米の断面撮像画像を用いた収穫時品質予測システム及び収穫時品質予測方法
JP6435740B2 (ja) * 2014-09-22 2018-12-12 日本電気株式会社 データ処理システム、データ処理方法およびデータ処理プログラム
CN106198442A (zh) * 2016-09-14 2016-12-07 南京财经大学 一种鉴别盘锦大米的光谱分析方法
WO2018084612A1 (ko) * 2016-11-02 2018-05-11 한국식품연구원 쌀의 품질측정 시스템, 쌀의 식미평가방법, 곡물의 발아율 예측 시스템 및 발아율 예측 방법
CN108108767B (zh) * 2017-12-29 2021-03-23 美的集团股份有限公司 一种谷物识别方法、装置和计算机存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398886A (zh) * 2008-03-17 2009-04-01 杭州大清智能技术开发有限公司 一种基于双目被动立体视觉的快速三维人脸识别方法
CN102436589A (zh) * 2010-09-29 2012-05-02 中国科学院电子学研究所 一种基于多类基元自主学习的复杂目标自动识别方法
CN107951485A (zh) * 2017-11-27 2018-04-24 乐普（北京）医疗器械股份有限公司 基于人工智能自学习的动态心电图分析方法和装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111879735A (zh) * 2020-07-22 2020-11-03 武汉大学 一种基于图像的大米外观品质检测方法

Also Published As

Publication number Publication date
JP2021526646A (ja) 2021-10-07
KR20210019089A (ko) 2021-02-19
KR102453207B1 (ko) 2022-10-07
CN110610183A (zh) 2019-12-24

Similar Documents

Publication Publication Date Title
CN108108767B (zh) 一种谷物识别方法、装置和计算机存储介质
JP6849824B2 (ja) セルフィーを撮影するためにユーザをガイドするためのシステム及び方法
Radman et al. Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut
WO2019238130A1 (zh) 谷物评估方法、装置和存储介质
US10032287B2 (en) System and method for assessing wound
US20180357763A1 (en) System and method for assessing wound
Pouladzadeh et al. Using graph cut segmentation for food calorie measurement
US10121273B2 (en) Real-time reconstruction of the human body and automated avatar synthesis
Hsu et al. Chronic wound assessment and infection detection method
Chen et al. Examining palpebral conjunctiva for anemia assessment with image processing methods
Pouladzadeh et al. You are what you eat: So measure what you eat!
CN108090518A (zh) 一种谷物识别方法、装置和计算机存储介质
CN108090517A (zh) 一种谷物识别方法、装置和计算机存储介质
Kumar et al. Age and gender classification using Seg-Net based architecture and machine learning
Nanni et al. A standardized approach for skin detection: Analysis of the literature and case studies
KR102333500B1 (ko) 곡물 인식 방법, 장치 및 컴퓨터 판독 가능 저장 매체
Mastelini et al. Computer vision system for characterization of pasta (noodle) composition
Raikwar et al. Calorie estimation from fast food images using support vector machine
JP7337124B2 (ja) 眼底検査画像用の画像前処理方法及び画像処理装置
CN108416788A (zh) 一种基于感受野及其明暗适应性的边缘检测方法
JP2017158921A (ja) 肌状態評価方法
Singh et al. Machine Learning Methods in Non-Invasive Detection of Iron Deficiency
Wang et al. OBJECT RECOGNITION FOR WASTED FOOD A BRIEF REVIEW
Ahuja et al. Dietary Assessment of Nutrition Status of an Individual on the basis of Weekly Intake
Pouladzadeh An Image Processing and Pattern Analysis Approach for Food Recognition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19820063

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020569744

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20217000926

Country of ref document: KR

Kind code of ref document: A

122 Ep: pct application non-entry in european phase

Ref document number: 19820063

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 16.06.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19820063

Country of ref document: EP

Kind code of ref document: A1