CN117766061A - Artificial intelligence-based tomato extract purity detection method and system - Google Patents
Artificial intelligence-based tomato extract purity detection method and system Download PDFInfo
- Publication number
- CN117766061A CN117766061A CN202410044620.9A CN202410044620A CN117766061A CN 117766061 A CN117766061 A CN 117766061A CN 202410044620 A CN202410044620 A CN 202410044620A CN 117766061 A CN117766061 A CN 117766061A
- Authority
- CN
- China
- Prior art keywords
- tomato
- tomato extract
- artificial intelligence
- representing
- feature map
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 235000007688 Lycopersicon esculentum Nutrition 0.000 title claims abstract description 211
- 240000003768 Solanum lycopersicum Species 0.000 title claims abstract description 211
- 239000000284 extract Substances 0.000 title claims abstract description 139
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 31
- 239000012528 membrane Substances 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 15
- 239000000126 substance Substances 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims abstract description 6
- 230000003595 spectral effect Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000005855 radiation Effects 0.000 claims description 12
- 239000006228 supernatant Substances 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000011010 flushing procedure Methods 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 28
- 230000008569 process Effects 0.000 description 8
- 239000012535 impurity Substances 0.000 description 7
- 239000007788 liquid Substances 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000000701 chemical imaging Methods 0.000 description 5
- 238000004128 high performance liquid chromatography Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 235000013305 food Nutrition 0.000 description 2
- 239000010985 leather Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005119 centrifugation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000010298 pulverizing process Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a tomato extract purity detection method and system based on artificial intelligence, comprising the following steps: obtaining a tomato image to be crushed after cleaning, and converting the tomato image into a gray image; extracting a tomato region in the gray level image, and obtaining the maturity of tomatoes according to the color characteristics of the tomato region; a tomato extract is obtained, wherein the tomato extract is a substance extracted from tomatoes after processing. According to the invention, the concentration of the tomato extract can be accurately detected and evaluated by adopting an artificial intelligence method, and whether the filtering operation of the filtering membrane is stopped can be determined according to the concentration grade detected by the tomato extract until the tomato extract meeting the concentration requirement is obtained, and then the filtering operation of the filtering membrane is stopped, so that the accuracy of the concentration detection result of the tomato extract is improved.
Description
Technical Field
The invention relates to the technical field of image processing. More particularly, the invention relates to an artificial intelligence-based tomato extract purity detection method and system.
Background
Image processing, a technique of analyzing an image with a computer to achieve a desired result. Also known as image processing. Image processing generally refers to digital image processing. The digital image is a large two-dimensional array obtained by photographing with equipment such as an industrial camera, a video camera, a scanner and the like, wherein the elements of the array are called pixels, and the values of the pixels are called gray values. Image processing techniques generally include image compression, enhancement and restoration, matching, description and recognition of 3 parts. Currently, the image processing can be applied to the fields of crops, leather, food or metal processing and the like, and can be used for detecting the growth condition of crops or detecting the quality of leather, for example, the concentration of tomato extract is detected through the image processing.
The detection of the concentration of the tomato extract refers to the process of quantitatively measuring the content of related components in the tomato extract. Such detection can be used to evaluate the quality of tomato extracts, control the production process, ensure consistency of the product and assist in related studies. The tomato extract is widely applied to the fields of foods, health-care products, medicines and the like, the concentration detection can help manufacturers to control and authenticate the quality of the products, and the concentration of various related components in the tomato extract can help to optimize the production process so as to obtain higher yield and better product quality.
The existing method for detecting the concentration of the tomato extract is High Performance Liquid Chromatography (HPLC), but a large amount of mobile phase is needed in the detection process of the HPLC method, and the chromatographic column is easy to block leakage and the detection process generally needs 30 minutes, so that the time is long, the efficiency is low and the detection result is inaccurate.
Therefore, the use of artificial intelligence and image processing methods to improve the accuracy of tomato extract detection results is a problem addressed by this patent.
Disclosure of Invention
To solve one or more of the above technical problems, the present invention proposes to detect the concentration of tomato extract by an artificial intelligence method. To this end, the present invention provides solutions in various aspects as follows.
In a first aspect, the invention provides an artificial intelligence-based tomato extract purity detection method, comprising the steps of obtaining a tomato image to be crushed after cleaning, and converting the tomato image into a gray level image; extracting a tomato region in the gray level image, and obtaining the maturity of tomatoes according to the color characteristics of the tomato region; obtaining a tomato extract, wherein the tomato extract is a substance extracted from tomatoes after processing; collecting pressure values of the tomato extract at different positions in a container, and calculating the stability of the tomato extract according to the pressure values; obtaining spectral radiation information of the tomato extract under different wavelengths, and calculating spectral information amounts of different wavelengths according to the spectral radiation information; inputting the characteristics of the maturity of the tomatoes, the stability of the tomato extracts and the spectral information into a detection model to detect the tomato extracts in real time and obtain the current concentration level; judging whether the current concentration level meets the target level requirement or not; and in response to the current concentration level not meeting the target level requirement, continuing to perform filtering operation of the filtering membrane on the tomato extract.
In one embodiment, the maturity of the tomato is calculated as follows:
wherein,mean value of R channel color values in RGB image representing tomato area,/->Element values representing the j-th column of the i-th row in matrix a,/->Showing the degree of confusion of the color characteristics of the tomato area, < >>Indicating tomato maturity.
In one embodiment, the stability of the tomato extract is calculated as follows:
wherein,mean value representing the pressure at different locations, +.>Pressure value representing the i-th position, +.>Indicating the total number of sensors in the container.
In one embodiment, calculating different amounts of wavelength spectral information from the spectral radiation information includes: and (3) a characteristic diagram of the tomato extract corresponding to each wavelength, wherein each characteristic diagram comprises three characteristics of rank, condition number and energy value, the quantity of information contained in each characteristic diagram is calculated, and a calculation formula is as follows:
wherein,information quantity representing normalized ith feature map,/->Representing the rank of the normalized ith feature map, ++>Energy value representing normalized ith feature map,/->The condition number of the normalized i-th feature map is represented.
In one embodiment, the method comprises the steps of:
wherein,rank, ->Energy representing characteristic map, ++>Condition number representing the feature map.
In one embodiment, the energy value of the ith signature is the thThe calculation method of (1) is as follows:
wherein,energy value representing the ith signature, < +.>Representing the number of clusters obtained by clustering after dividing the ith feature map into pixel levels, and +.>Pixel value representing the jth cluster on the ith feature map, +.>Representing the number of pixels in a j-th cluster in the feature map;
the pixel level of each feature map is divided into 8 levels, and the level division formula is as follows:
wherein,is the gray value of the ith row and jth column position on the gray map, symbol' []The' representation is rounded down.
In one embodiment, obtaining a tomato extract comprises: crushing tomatoes, putting the crushed tomatoes into a centrifuge, performing filtering operation of a filtering membrane to obtain supernatant, and then putting the supernatant into a filtering membrane machine; and detecting by a flushing control concentration detection device, and when the concentration of the supernatant reaches a preset threshold value, obtaining a tomato extract, and then placing the tomato extract into a refrigerator for preservation.
In one embodiment, obtaining a tomato extract further comprises: crushing tomatoes, putting the crushed tomatoes into a filter membrane sleeve, and extruding the filter membrane sleeve to obtain the tomato extract.
In one embodiment, the filter membrane sleeve has a filtration diameter of 100-8000 mesh.
In a second aspect, the present invention provides an artificial intelligence based tomato extract purity detection system comprising a processor and a memory, having stored thereon a computer program which when executed implements an artificial intelligence based tomato extract purity detection method as defined in any one of the above methods.
The invention has the beneficial effects that:
firstly, the concentration of the tomato extract can be accurately detected and evaluated by adopting an artificial intelligence method, and whether the filtering operation of the filtering membrane is stopped or not can be determined according to the concentration grade detected by the tomato extract until the tomato extract meeting the concentration requirement is obtained, and then the filtering operation of the filtering membrane is stopped.
(II) and by three features of tomato extract: the maturity of the tomatoes, the stability of the tomato extracts and the spectral information quantity are used for detecting the concentration of the tomato extracts, so that the accuracy of the detection result of the concentration of the tomato extracts is improved.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart schematically illustrating training a detection model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram schematically illustrating pressure values versus distance according to an embodiment of the present invention;
fig. 3 is a flowchart schematically showing calculation of information amount according to an embodiment of the present invention;
FIG. 4 is a flow chart schematically showing a determination of whether to stop a filtering operation of a filtering membrane according to an embodiment of the invention;
fig. 5 is a system structural diagram schematically illustrating an embodiment according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
The existing method for detecting the concentration of the tomato extract is High Performance Liquid Chromatography (HPLC), but the HPLC method requires a large amount of mobile phase in the detection process, is complex to operate, is easy to block and leak by a chromatographic column, and generally requires 30 minutes in the detection process, so that the detection time is long, the efficiency is low and the detection result is inaccurate. Therefore, the use of artificial intelligence and image processing methods to improve the accuracy of tomato extract detection results is a problem addressed by this patent. The final objective is to control whether the filtration operation of the filtration membrane is performed or not according to the concentration level of the tomato extract.
Fig. 1 and 2 schematically illustrate a method for detecting purity of tomato extract based on artificial intelligence, comprising:
and grading the known concentration of the tomato extract according to experimental results, historical experience and expert experience, and completing the construction of a tomato extract concentration grade data set. Specifically, the concentration of the tomato extract is obtained through experiments by physical and chemical methods, or the concentration of the tomato extract is classified through historical data, expert experience, and the like, in this embodiment, the concentration is classified into three levels of high, medium, and low, in other embodiments, the concentration is classified into two, four, and more, and in this embodiment, the classification of the concentration is not limited.
And S1, acquiring a tomato image to be crushed after cleaning, and converting the tomato image into a gray image.
Specifically, some photographing devices may be used to obtain images of tomatoes to be crushed after cleaning is completed.
In one embodiment, a CCD/CMOS camera is used to capture a clear finished tomato image to be crushed, and the tomato image is converted into a gray scale image.
And S2, extracting a tomato region in the gray level image, and obtaining the maturity of the tomatoes according to the color characteristics of the tomato region.
Where tomato region refers to a region containing tomatoes and may be by thresholding or edge detection. In addition, the tomato region may be characterized by texture features or brightness variations, etc., e.g., higher brightness indicates higher maturity of the tomato.
Step S3: a tomato extract is obtained, wherein the tomato extract is a substance extracted from tomatoes after processing.
In one embodiment, the method of obtaining a tomato extract is: firstly cleaning, crushing and filtering tomatoes, putting the liquid obtained by filtering into a centrifuge, starting the centrifuge, centrifuging to obtain supernatant, putting the supernatant into a filter membrane machine (the filter membrane filtering amount is 500D-1000D, D represents the molecular weight), automatically detecting by a flushing control concentration detection device, namely, primary concentration and secondary concentration (substances smaller than 1000D are washed out and remain more than 1000), and when the concentration of the supernatant reaches a preset threshold, wherein the preset threshold is set manually, extracting the supernatant, putting the supernatant into a refrigerator for refrigeration, and finally preparing the solid tomato extract.
A filter membrane machine is a device for solid-liquid separation and separation of solute molecules, and separates solid particles or solute substances from a liquid by using a filter membrane having a specific pore size. Whereas primary and secondary concentration refer to two stages of operation during concentration. Primary concentration generally refers to an initial concentration step in which the liquid is separated by a filter into a more concentrated liquid and a more diluted liquid. And the secondary concentration is to concentrate the diluted liquid again after the primary concentration so as to further increase the concentration of the effective components of the solution.
In another embodiment, the method of obtaining a tomato extract is: pulverizing fructus Lycopersici Esculenti, placing into a filter membrane sleeve (filter diameter of the filter membrane sleeve is 100-8000 mesh), and squeezing the filter membrane sleeve to obtain fructus Lycopersici Esculenti extract.
Step S4: collecting pressure values of the tomato extract at different positions in the container, and calculating the stability of the tomato extract according to the pressure values.
The pressure value is obtained by detecting the compression condition of the tomato extract by using components, wherein the components can be a pressure sensor, a strain gauge or a force sensor, and the compression condition of the tomato extract can be obtained by using the three components.
Step S5: spectral radiation information of the tomato extract under different wavelengths is obtained, and the spectral information quantity of the different wavelengths is calculated according to the spectral radiation information.
The amount of spectral information refers to a measure of useful information contained in the spectral data. Obtaining a tomato extract through centrifugal equipment, obtaining spectral radiation information of the tomato extract under different wavelengths by using a multispectral imaging technology on the tomato extract, obtaining the information quantity of different wavelengths through the spectral radiation information, and judging that the spectral radiation information is from the tomato extract or impurities according to the information quantity.
Multispectral imaging technology is an image processing technology that utilizes spectral information in multiple bands to obtain features of an object. While conventional color cameras typically record color information in three bands, red, green, and blue, multispectral imaging techniques can use more bands to record spectral information reflected or emitted by an object in order to distinguish and identify different object features.
Step S6: the characteristics of the maturity of the tomatoes, the stability of the tomato extract and the spectral information are input into a detection model to detect the tomato extract in real time and obtain the current concentration level.
Regarding the detection model, the detection model needs to be trained through the maturity of tomatoes, the stability of tomato extracts, the information content of spectral images of the tomato extracts and a tomato concentration data set, and the concentration of the tomato extracts can be detected in real time after training is completed.
According to the steps, the concentration of the tomato extract can be accurately detected and evaluated by adopting an artificial intelligence method, so that the accuracy of the detection result of the concentration of the tomato extract is improved.
The above description describes a method for detecting purity of tomato extract based on artificial intelligence, and regarding step S2, the manner of obtaining the maturity of tomato may be as follows:
in one embodiment, the maturity of the tomato can be obtained according to the stability of the color characteristics of the tomato region, specifically, the connected domain extraction is used for extracting the tomato region in the image from the gray level map, the corrosive and expansive morphological operation is used for removing the noise region in the image from the connected domain image, the pixel value of the connected domain position in the image is set to be 1 after the removal is finished, the pixel value of the other region is set to be 0 to obtain the tomato 0/1 map, the RGB image of the tomato region is obtained by multiplying the 0/1 map with the original tomato image, the gray level map of the tomato region is obtained by multiplying the 0/1 map with the gray level map of the tomato, the gray level symbiotic matrix of the gray level map of the tomato region is calculated to obtain the matrix A, and the tomato maturity is calculated by the matrix A and the RGB image of the tomato region, and the calculation formula is as follows:
wherein,mean value of R channel color values in RGB image representing tomato area,/->Element values representing the j-th column of the i-th row in matrix a,/->Showing the degree of confusion of the color characteristics of the tomato area, < >>Indicating tomato maturity, ->The greater and lesser degree of confusion means that the higher the maturity of the tomato, which is one of the characteristics affecting the concentration of tomato extract, and thus the maturity of the tomato.
With respect to step S4, in one embodiment, a pressure sensor may be employed to obtain the stress profile of the tomato extract. Specifically, after crushing tomatoes, obtaining tomato extracts through centrifugal equipment, and after centrifugation for a set time, placing the tomato extracts into a container, wherein a plurality of pressure sensors are arranged in the container. In this embodiment, a plurality of pressure sensors may be disposed on the side wall of the container, and in other embodiments, a plurality of pressure sensors may be disposed on the inner side wall and the inner bottom wall of the container, respectively.
If the concentration of the tomato extract is different, the pressure at different positions in the container is different, and the concentration determines the pressure difference at different positions; thus, the stability of the tomato extract reflects how much of the combined concentration of tomato extract contains both tomato extract molecules and impurity molecules (impurities: molecules that are not tomato extract that are soluble in water). The purpose is that: the tomato extract molecules can reach the set concentration as the impurity molecules can be removed in the filter membrane machine.
Specifically, the calculation formula of the stability of the tomato extract is as follows:
wherein,mean value representing the pressure at different locations, +.>Pressure value representing the i-th position, +.>Indicating the total number of sensors in the container, the greater the stability, the higher the mixing concentration, the higher the impurity concentration in the tomato extract, the smaller the variation of the pressure values at different positions indicates the higher the tomato extract concentration, i.e./the higher the concentration of tomato extract>The smaller the value of (2) the higher the tomato extract concentration. Thus, the stability of tomato extract is obtained. In addition, the pressure values of tomato extract at different concentrations monitored by the pressure sensor are shown in fig. 2.
With respect to step S5, in one embodiment, as shown in fig. 3, the magnitude calculation process for the different wavelength spectrum information amounts is as follows:
the method comprises the steps of obtaining a tomato extract through a centrifugal device, obtaining the characteristics of the tomato extract and the characteristics of impurities in the tomato extract through a multispectral imaging technology, obtaining spectral radiation information of the tomato extract at different wavelengths by using the multispectral imaging technology on the tomato extract, and then calculating the amount of information contained in each characteristic map, wherein the characteristic map with small information content is generated by an impurity reflection spectrum in all the color characteristic maps, and the characteristic map with large information content is generated by a tomato extract reflection spectrum. The calculation process of the spectrum information quantity of different wavelengths is as follows:
step S501: the rank of each eigen graph and the condition number of the eigen matrix are calculated.
Specifically, the rank of each feature map is calculated first, the larger the rank is, the more information the feature map contains, and then the condition number of the feature matrix is calculated, wherein the condition number of the matrix is the ratio of the maximum value to the minimum value of the singular values of the matrix. The larger the condition number, the smaller the amount of information contained in the representation matrix; the smaller the condition number, the more information is contained in the representation matrix.
Step S502: the pixel level of each feature map is divided into 8 levels, and the level division formula is as follows:
wherein,is the gray value of the ith row and jth column position on the gray map, symbol' []' means rounding down.
Step S503: and calculating the energy value of the characteristic diagram.
Specifically, after classification, the pixel values on the feature map are clustered, the pixel points with equal pixel values and adjacent pixel points are clustered into one type, a plurality of clustering clusters are obtained after the clustering is completed, and then the energy value of the feature map is calculated according to the clustering result, wherein the calculation formula is as follows:
wherein,energy value representing the ith signature, < +.>Representing the number of clusters obtained by clustering after dividing the ith feature map into pixel levels, and +.>Pixel value representing the jth cluster on the ith feature map, +.>Representing the number of pixels in the jth cluster in the feature map,/for each cluster>The larger the energy of the profile, the larger the amount of information contained, which is more likely to be a profile of tomato extract.
Step S504: when the information quantity contained in the feature map is calculated through the features such as the rank, the condition number and the energy value of the feature map, the features are normalized, and the normalization formula is as follows:
wherein,rank, ->Energy representing characteristic map, ++>The condition number of the feature map is represented, and the relation between the rank and energy of the feature map and the information quantity of the feature map is a proportional relation, so that a normalization formula adopts a formula of the proportional relation, and the relation between the condition number and the information quantity of the feature map is an inverse relation, so that the normalization formula adopts a formula of the inverse relation.
Step S505: the calculated feature map contains information quantity, and the calculation formula is as follows:
wherein,information quantity representing normalized ith feature map, namely spectral information quantity, ++>Representing the rank of the normalized ith feature map, ++>Energy value representing normalized ith feature map,/->The condition number of the normalized i-th feature map is represented.
The larger the rank of the feature map, the larger the amount of information contained therein, the larger the energy value of the feature map, and the larger the amount of information contained therein, the smaller the condition number of the feature map. Thus, the information content of the spectral image of the tomato extract is obtained.
As shown in fig. 4, the current concentration level of the tomato extract is compared with the target level, and the operation process is determined according to the comparison result, wherein the specific steps are as follows:
step S601: and judging whether the current concentration level meets the target level requirement.
Step S602: and if the current concentration level does not reach the target level requirement, continuing to carry out the filtering operation of the filtering membrane on the tomato extract.
Step S603: and if the current concentration level meets the target level requirement, stopping the filtering operation of the filtering membrane.
For example: the concentration level of the tomato extract is low, medium and high, and the target level is assumed to be the tomato extract at the high concentration level, and then the characteristics of the maturity of the tomato, the stability of the tomato extract and the spectral information are input into a detection model to obtain a detection result; assuming that the detection result is a low-grade concentration tomato extract, the filtering operation of the filtering membrane on the tomato extract is continued. After a period of time, inputting the features into a detection model again, outputting a detection result by the detection model, and stopping the filtering operation of the filtering membrane to obtain the tomato extract meeting the concentration requirement if the current detection result is the tomato extract with high-grade concentration, that is, the concentration grade of the tomato extract reaches the high-grade concentration at the moment.
In one embodiment, the present invention also provides an artificial intelligence based tomato extract purity detection system, the system comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement an artificial intelligence based tomato extract purity detection method according to the first aspect of the present invention.
In one embodiment, the present invention provides a computer device whose internal structure may be as shown in FIG. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. The processor of the computer equipment is used for providing calculation and control capability, and various varieties such as CPU, singlechip, DSP or FPGA can be selected. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The steps described in the above method embodiments, e.g. S1-S6, may be completed when the computer program is executed. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program when executed by the processor is used for realizing a tomato extract purity detection method based on artificial intelligence. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of a portion of the structure associated with aspects of the present invention and is not intended to limit the computer device of the present invention, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The system further comprises other components known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and are therefore not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. An artificial intelligence-based tomato extract purity detection method is characterized by comprising the following steps:
obtaining a tomato image to be crushed after cleaning, and converting the tomato image into a gray image;
extracting a tomato region in the gray level image, and obtaining the maturity of tomatoes according to the color characteristics of the tomato region;
obtaining a tomato extract, wherein the tomato extract is a substance extracted from tomatoes after processing;
collecting pressure values of the tomato extract at different positions in a container, and calculating the stability of the tomato extract according to the pressure values;
obtaining spectral radiation information of the tomato extract under different wavelengths, and calculating spectral information amounts of different wavelengths according to the spectral radiation information;
inputting the characteristics of the maturity of the tomatoes, the stability of the tomato extracts and the spectral information into a detection model to detect the tomato extracts in real time and obtain the current concentration level;
judging whether the current concentration level meets the target level requirement or not;
and in response to the current concentration level not meeting the target level requirement, continuing to perform filtering operation of the filtering membrane on the tomato extract.
2. The artificial intelligence based tomato extract purity detection method of claim 1, wherein: the maturity of the tomatoes is calculated as follows:
wherein,mean value of R channel color values in RGB image representing tomato area,/->Element values representing the j-th column of the i-th row in matrix a,/->Showing the degree of confusion of the color characteristics of the tomato area, < >>Indicating tomato maturity.
3. The artificial intelligence based tomato extract purity detection method of claim 1, wherein: the stability of the tomato extract is calculated as follows:
wherein,mean value representing the pressure at different locations, +.>Pressure value representing the i-th position, +.>Indicating the total number of sensors in the container.
4. The artificial intelligence based tomato extract purity detection method of claim 1, wherein: calculating different wavelength spectral information amounts according to the spectral radiation information, including:
and (3) a characteristic diagram of the tomato extract corresponding to each wavelength, wherein each characteristic diagram comprises three characteristics of rank, condition number and energy value, the quantity of information contained in each characteristic diagram is calculated, and a calculation formula is as follows:
wherein,information quantity representing normalized ith feature map,/->Representing the rank of the normalized ith feature map, ++>Energy value representing normalized ith feature map,/->The condition number of the normalized i-th feature map is represented.
5. The artificial intelligence based tomato extract purity detection method according to claim 4, characterized in that: comprising the following steps:
wherein,rank, ->Energy representing characteristic map, ++>Condition number representing the feature map.
6. The artificial intelligence based tomato extract purity detection method of claim 5, wherein: energy value of ith feature mapThe calculation method of (1) is as follows:
wherein,energy value representing the ith signature, < +.>Representing the number of clusters obtained by clustering after dividing the ith feature map into pixel levels, and +.>Pixel value representing the jth cluster on the ith feature map, +.>Representing the number of pixels in a j-th cluster in the feature map;
the pixel level of each feature map is divided into 8 levels, and the level division formula is as follows:
wherein,is the gray value of the ith row and jth column position on the gray map, symbol' []The' representation is rounded down.
7. The artificial intelligence based tomato extract purity detection method of claim 1, wherein: obtaining a tomato extract comprising:
crushing tomatoes, putting the crushed tomatoes into a centrifuge to obtain supernatant, and then putting the supernatant into a filter membrane machine;
and detecting by a flushing control concentration detection device, and when the concentration of the supernatant reaches a preset threshold value, obtaining a tomato extract, and then placing the tomato extract into a refrigerator for preservation.
8. The artificial intelligence based tomato extract purity detection method of claim 1, wherein: obtaining a tomato extract, further comprising:
crushing tomatoes, putting the crushed tomatoes into a filter membrane sleeve, and extruding the filter membrane sleeve to obtain the tomato extract.
9. The artificial intelligence based tomato extract purity detection method of claim 8, wherein: the filter diameter of the filter membrane sleeve is 100-8000 meshes.
10. An artificial intelligence based tomato extract purity detection system comprising a processor and a memory, having stored thereon a computer program, characterized in that: the computer program when executed implements the artificial intelligence based tomato extract purity detection method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044620.9A CN117766061B (en) | 2024-01-12 | 2024-01-12 | Artificial intelligence-based tomato extract purity detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044620.9A CN117766061B (en) | 2024-01-12 | 2024-01-12 | Artificial intelligence-based tomato extract purity detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117766061A true CN117766061A (en) | 2024-03-26 |
| CN117766061B CN117766061B (en) | 2024-05-14 |
Family
ID=90312666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410044620.9A Active CN117766061B (en) | 2024-01-12 | 2024-01-12 | Artificial intelligence-based tomato extract purity detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117766061B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113808153A (en) * | 2021-09-22 | 2021-12-17 | 航天新气象科技有限公司 | Tomato maturity detection method and device, computer equipment and storage medium |
| CN116342505A (en) * | 2023-03-08 | 2023-06-27 | 北京金控数据技术股份有限公司 | Detection method and detection system for granulating degree of aerobic granular sludge |
| WO2023231902A1 (en) * | 2022-06-15 | 2023-12-07 | 浙江大学 | Spectrum detection method for detecting lycopene content in agricultural product |
-
2024
- 2024-01-12 CN CN202410044620.9A patent/CN117766061B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113808153A (en) * | 2021-09-22 | 2021-12-17 | 航天新气象科技有限公司 | Tomato maturity detection method and device, computer equipment and storage medium |
| WO2023231902A1 (en) * | 2022-06-15 | 2023-12-07 | 浙江大学 | Spectrum detection method for detecting lycopene content in agricultural product |
| CN116342505A (en) * | 2023-03-08 | 2023-06-27 | 北京金控数据技术股份有限公司 | Detection method and detection system for granulating degree of aerobic granular sludge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117766061B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Adrian et al. | Sentinel SAR-optical fusion for crop type mapping using deep learning and Google Earth Engine | |
| Li et al. | Robust saliency detection via regularized random walks ranking | |
| CN111524137B (en) | Cell identification counting method and device based on image identification and computer equipment | |
| CN105021529B (en) | Fusion spectrum and the crop disease and insect of image information identify and distinguish between method | |
| CN102779338B (en) | Image processing method and image processing device | |
| CN111738344B (en) | Rapid target detection method based on multi-scale fusion | |
| US9715729B2 (en) | Method and apparatus for processing block to be processed of urine sediment image | |
| Gui et al. | A new method for soybean leaf disease detection based on modified salient regions | |
| CN112200787B (en) | Cloud detection method, storage medium and system for optical remote sensing image | |
| CN111007013B (en) | Crop rotation fallow remote sensing monitoring method and device for northeast cold region | |
| Wang et al. | Unsupervised discrimination between lodged and non-lodged winter wheat: A case study using a low-cost unmanned aerial vehicle | |
| CN112991238B (en) | Food image segmentation method, system and medium based on texture and color mixing | |
| Tech et al. | Methods of image acquisition and software development for leaf area measurements in pastures | |
| CN107423715B (en) | Automatic footprint identification method based on multi-feature joint decision | |
| Yorulmaz et al. | Detection of fungal damaged popcorn using image property covariance features | |
| CN115861210B (en) | Transformer substation equipment abnormality detection method and system based on twin network | |
| Petrellis | Plant Disease Diagnosis Based on Image Processing, Appropriate for Mobile Phone Implementation. | |
| Hasanlou et al. | A sub-pixel multiple change detection approach for hyperspectral imagery | |
| Zhang et al. | Salient target detection based on the combination of super-pixel and statistical saliency feature analysis for remote sensing images | |
| Sannakki et al. | SVM-DSD: SVM based diagnostic system for the detection of pomegranate leaf diseases | |
| CN117766061B (en) | Artificial intelligence-based tomato extract purity detection method and system | |
| Yang et al. | Detection method of rice blast based on 4D light field refocusing depth information fusion | |
| CN116883893A (en) | Tunnel face underground water intelligent identification method and system based on infrared thermal imaging | |
| CN110766655A (en) | Hyperspectral image significance analysis method based on abundance | |
| Beirami et al. | SVM classification of hyperspectral images using the combination of spectral bands and Moran's I features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |