CN113220658B - Food material detection method of refrigerator, refrigerator and storage medium - Google Patents
Food material detection method of refrigerator, refrigerator and storage medium Download PDFInfo
- Publication number
- CN113220658B CN113220658B CN202010069845.1A CN202010069845A CN113220658B CN 113220658 B CN113220658 B CN 113220658B CN 202010069845 A CN202010069845 A CN 202010069845A CN 113220658 B CN113220658 B CN 113220658B
- Authority
- CN
- China
- Prior art keywords
- food material
- spectrum
- information
- mathematical model
- food
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a food material detection method of a refrigerator, the refrigerator and a storage medium, wherein the food material detection method utilizes spectral analysis to model information of food materials to obtain a relation between the food material information and a spectral mathematical model, enhances the precision degree of the spectral mathematical model through a plurality of iterative and learning modes, perfects the spectral mathematical model which can embody the food material information, and can judge the information of the food materials more accurately through the spectral analysis in the later use process, so that the intelligent degree of the refrigerator is higher, and the requirements of intelligent families are met.
Description
Technical Field
The present invention relates to the field of refrigeration apparatuses, and in particular, to a method for detecting food materials in a refrigerator, and a storage medium.
Background
With the development of intelligent home, people put forward higher and higher requirements on the intelligence of home equipment, for example, hope that the home equipment can understand own preference, provide more intelligent service, and the refrigerator is used as equipment for high-frequency use in life, and the premise of intelligence comprises the identification and detection of stored articles, so that more expansion service can be provided on the basis.
In order to conveniently identify food materials, the method is provided with a patent of identifying through photographing at present, but the method is limited by a placement mode and light rays, such as food stacking, dark corners and the like, the image identification is limited, the identification result is inaccurate, a plurality of varieties exist for the same type of food, the composition of the different varieties is different, the difference of the components of the different varieties is large, the food materials cannot be accurately identified at different time, the deeper analysis cannot be performed only by image identification, the refrigerator is not intelligent enough, intelligent preservation cannot be realized, and the requirements of intelligent families cannot be met.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide a food material detection method of a refrigerator, the refrigerator and a storage medium.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for detecting food materials in a refrigerator, including the steps of:
putting a first food material into the refrigerator, and inputting food material information of the first food material;
detecting spectrum information of the first food material, and establishing a first spectrum mathematical model of the first food material according to the food material information of the first food material and the spectrum information;
placing a second food material which is the same as the first food material in the refrigerator, and detecting spectrum information of the second food material;
judging whether the spectrum information of the second food material is matched with the first spectrum mathematical model;
if the spectrum information of the second food material is not matched with the first spectrum mathematical model, a second spectrum mathematical model is built according to the food material information and the spectrum information of the second food material;
if the spectrum information of the second food material is matched with the first spectrum mathematical model, increasing the weight of the first spectrum mathematical model;
repeatedly putting new food materials which are the same as the food material information of the first food materials into the refrigerator, and detecting the spectrum information of the new food materials;
judging whether the spectrum information of the new food material is matched with a plurality of spectrum mathematical models of the same food material information, and if so, increasing the weight of the spectrum mathematical model;
if the spectrum information of the new food material is not matched with all the spectrum mathematical models, a new spectrum mathematical model is built according to the food material information and the spectrum information of the new food material;
and determining the spectrum mathematical model with the highest weight as the spectrum mathematical model corresponding to the food material information.
As a further improvement of an embodiment of the present invention, the food material information includes kind information, a place of production, and freshness of the food material.
As a further improvement of an embodiment of the present invention, the step of "establishing a spectral mathematical model of the first food material based on the food material information of the first food material and the spectral information" includes:
collecting spectrum information of a first food material;
removing abnormal values in the spectrum data;
selecting an appropriate spectral region;
and selecting an algorithm for establishing a spectrum mathematical model according to the food material information, and establishing the spectrum mathematical model of the first food material according to the data in the spectrum region.
As a further improvement of an embodiment of the present invention, the method further comprises the steps of:
spectral information of the environmental background when no food material is placed is scanned.
As a further improvement of an embodiment of the present invention, the step of "collecting spectral information of the first food material" includes:
and comparing the spectrum information of the first food material with the spectrum information of the environment background, and removing noise information in the spectrum information of the first food material.
As a further improvement of an embodiment of the present invention, the step of "eliminating outliers in the spectral data" includes:
and removing abnormal values in the spectrum data, wherein the removing algorithm comprises a smoothing algorithm, a derivative algorithm, multi-element scattering correction and a data enhancement algorithm.
As a further improvement of an embodiment of the present invention, the step of "selecting an algorithm for establishing a spectral mathematical model according to the food material information" includes:
and selecting an algorithm for establishing a spectrum mathematical model according to the food material information, wherein the algorithm comprises a partial least square method, stepwise regression analysis and principal component regression analysis.
As a further improvement of an embodiment of the present invention, the method comprises the steps of:
placing food materials in the refrigerator, and detecting spectrum information of the food materials;
matching the spectrum information of the food material with a plurality of spectrum mathematical models;
if the food material information corresponding to the matched spectrum mathematical model is consistent with the actual information of the food material, increasing the weight of the matched spectrum mathematical model;
if the food material information corresponding to the matched spectrum mathematical model is inconsistent with the actual information of the food material, setting that the spectrum mathematical model is no longer matched with the food material information of the food material, and establishing the spectrum mathematical model according to the spectrum information of the food material and the food material information.
To achieve one of the above objects, an embodiment of the present invention provides a refrigerator including a memory and a processor, the memory storing a computer program executable on the processor, further comprising:
the food material is placed in the spectrum scanning area;
the spectrometer scans the food material to obtain spectrum information;
the analysis module is used for analyzing the spectrum information, reducing noise of the spectrum information and selecting a spectrum region at a proper position;
the steps in the food material detection method of the refrigerator can be realized when the processor executes the computer program.
As a further improvement of an embodiment of the present invention, the spectrum scanning area is a storage space in a drawer of the refrigerator.
To achieve one of the above objects, an embodiment of the present invention provides a storage medium storing a computer program which, when executed by a processor, performs the steps in the above-described food material detection method of a refrigerator.
Compared with the prior art, the invention has the following beneficial effects: modeling is carried out on the information of the food materials by utilizing a spectrum analysis method to obtain the relation between the information of the food materials and a spectrum mathematical model, the accuracy of the spectrum mathematical model is enhanced by a plurality of iteration and learning modes, and the spectrum mathematical model which can embody the information of the food materials is perfected, so that the information of the food materials can be judged more accurately by spectrum analysis in the later use process, the intelligent degree of the refrigerator is higher, and the requirements of intelligent families are met.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for detecting and identifying food materials in a refrigerator according to the present invention;
fig. 2 is a schematic view of a refrigerator according to an embodiment of the present invention;
1, a spectrum scanning area; 2. a spectrometer; 3. an analysis module; 4. a processor; 5. a memory.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the invention and structural, methodological, or functional modifications of these embodiments that may be made by one of ordinary skill in the art are included within the scope of the invention.
According to the food material detection method of the refrigerator, the refrigerator and the storage medium, the food material is subjected to spectral analysis, the matched spectral mathematical model is built, and the model is continuously verified and perfected, so that the built spectral mathematical model can accurately correspond to food material information, the food is identified and detected by the spectral analysis method, the refrigerator is more intelligent, and the requirements of intelligent families are met.
The method comprises the following specific steps:
1) Putting a first food material into the refrigerator, and inputting food material information of the first food material;
detecting spectrum information of the first food material, and establishing a spectrum mathematical model of the first food material according to the food material information of the first food material and the spectrum information;
2) Placing a second food material which is the same as the first food material in the refrigerator, and detecting spectrum information of the second food material;
judging whether the spectrum information of the second food material is matched with the first spectrum mathematical model;
if the spectrum information of the second food material is not matched with the first spectrum mathematical model, a second spectrum mathematical model is built according to the food material information and the spectrum information of the second food material;
if the spectrum information of the second food material is matched with the first spectrum mathematical model, increasing the weight of the first spectrum mathematical model;
3) Repeating the step 2), putting a new food material which is the same as the food material information of the first food material into the refrigerator, and detecting the spectrum information of the new food material;
judging whether the spectrum information of the new food material is matched with a plurality of spectrum mathematical models of the same food material information, and if so, increasing the weight of the spectrum mathematical model;
if the spectrum information of the new food material is not matched with all the spectrum mathematical models, a new spectrum mathematical model is built according to the food material information and the spectrum information of the new food material;
4) And determining the spectrum mathematical model with the highest weight as the spectrum mathematical model corresponding to the food material information.
The first food material, the second food material and the new food material can be fruits, vegetables or other foods in the same batch, the spectrum information of the food materials is approximately equal, but because of the difference of the individual information,
the food material information comprises the kind information, the production place and the freshness of the food materials, and a user can repeat the steps to perform multiple operations on the food materials of different production places, different freshness and different kinds, so that different spectrum mathematical models of different food materials are built.
When a user puts in food to be refrigerated or frozen, information related to the food is input to the refrigerator according to the label of the food, and the information content comprises the type of the food, the place where the food is produced and approximate judgment of freshness as a preset value of the food information. The spectrometer scans the placed food to obtain the corresponding spectrum of the food, and marks and processes the spectrum information and the food information correspondingly.
In the early stage, the entry of the spectral mathematical model can be performed by two ways, as explained below.
Pathway 1
The system mainly establishes a spectrum mathematical model through user operation. For example, a user puts a plurality of oranges into a local place, the freshness is mature, the spectrometer scans out the spectrum information of the food, the analysis processor matches the spectrum information with the information input by the user, and then the analysis software processes the data to obtain the spectrum mathematical model of the orange of the type.
The data of the spectrum mathematical model of the main food is preset in the refrigerator, the data can be stored in advance when leaving the factory, an interface for connecting a server can be arranged on the refrigerator, the spectrum mathematical model of the main food is stored in the server, and then the data of the spectrum mathematical model can be updated.
The mathematical model of the spectrum in the server can be pre-established by the method described above. The model in the refrigerator of the user can be customized to build some models based on the existing spectrum mathematical model, for example, some unusual food materials in the local places of the user can be perfected by the user. For users in the same area, the same food materials purchased daily are generally produced in the same place, the spectrum data are generally close, the consistency of the spectrum mathematical model is good, and the server can transmit the data of the spectrum mathematical model in the corresponding area to the users according to the information of the places of the users so as to help the refrigerator to quickly establish the spectrum mathematical model.
The server locates the refrigerator according to the locating device or the network IP of the refrigerator, or the user inputs the address of the refrigerator by himself or the built-in locating module locates, the server determines the position of the refrigerator according to the locating information, the area can be a city or a region, a range which is defined manually, if the spectrum mathematical models of a plurality of food materials in a region are relatively close, the position is judged to be close, and the average value of the spectrum mathematical models of the region is fed back to a new user in the region.
After the system builds a preliminary mathematical model, the mathematical model is stored corresponding to the food, and for foods in which food materials are put in later stages and the food material information detected by the spectral mathematical model is inconsistent with the food material information actually, a user is prompted to input new food information, and the spectral mathematical model is not corresponding to the food materials. If the spectrum information of the food put in later is approximate, the method is carried out according to the following steps:
after being scanned by a spectrometer and processed and analyzed by software, the food is compared with the existing spectrum mathematical model, if the detected spectrum mathematical model of the new food is the same as or similar to the spectrum mathematical model of the existing food, the information of the placed food, such as oranges, is preliminarily pre-judged, and the weight of the spectrum mathematical model judged to be the oranges is increased.
Inquiring whether the client is an orange or not and whether the freshness is the current orange state or not, if the user selects to identify inaccurately, prompting to input information of the new food, for example, the user inputs the new food as an orange, the system establishes a spectrum mathematical model of the orange, marks the preliminarily pre-judged food information and the new food information at the same time, for example, marks as an orange-orange copy, and reduces the weight of the spectrum mathematical model identified as the orange; if the user chooses to identify correctly, the spectral mathematical model continues to be marked as corresponding food information, such as orange-copy, increasing the weight of the spectral mathematical model identified as orange.
After the next time the customer puts in the food with the approximate spectral information, for example, spectral analysis still identifies the spectral model corresponding to the orange detected for the first time, consults whether the user is the food information of the spectral mathematical model for the first time or the newly input food information, for example, consults whether the user is an orange or an orange, if the user confirms that the food is the orange, judges that the weight of the orange is increased and judges that the weight of the orange is reduced; if the user judges that the orange is detected, the spectrum mathematical model judges that the weight of the orange is increased, the weight of the orange is judged to be reduced, and the spectrum model corresponding to the orange detected for the second time is identified by spectrum analysis. If the judgment of the user is not the same, repeating the step of prompting the user to input the information of the new food, establishing a new spectrum mathematical model, prompting the user to judge the new food in the next detection, and adding corresponding weight.
After repeating the above steps for a plurality of times, if the weight of a certain type of food is highest, judging that the spectrum mathematical model of the information of the food corresponding to the model is closest to the real situation, and establishing and confirming the spectrum mathematical model of the refrigerator at the user side is basically completed.
Further, an embodiment of the present invention provides a refrigerator including a memory 5 and a processor 4, the memory 5 storing a computer program executable on the processor 4, further including:
a spectrum scanning area 1, wherein food materials are placed in the spectrum scanning area 1;
the spectrometer 2 scans the food material to obtain spectral information;
the analysis module 3 analyzes the spectrum information, reduces the noise of the spectrum information and selects a spectrum region at a proper position;
the processor 4 may implement any one of the steps of the above-mentioned method for detecting food materials of a refrigerator, that is, implement any one of the steps of the above-mentioned method for detecting food materials of a refrigerator when executing the computer program.
Further, the spectrum scanning area is a storage space in a drawer of the refrigerator.
Further, an embodiment of the present invention provides a storage medium storing a computer program, where the computer program when executed by a processor can implement any one of the steps in the method for detecting food materials in a refrigerator, that is, implement any one of the steps in the method for detecting food materials in a refrigerator.
The spectrum recognition analysis may be performed in a plurality of stages, and in the initial use, after a customer puts in food and inputs food information, the spectrum analysis is performed for the type of the current food, and specific components or properties of the type are analyzed, and parameters of content analysis required to be detected for different types of food may be stored in advance or obtained from a server, for example, for bakery foods of bread, main detection indexes include fat, protein, moisture, starch, gluten, etc., for example, for foods of fruit, main detection indexes include sugar, acidity, vitamins, moisture, cellulose, quality classification, maturity, hardness, etc., for example, tea leaves are placed, and main detection indexes include tenderness, tea polyphenols, amino acids, caffeine, quality classification, total nitrogen, moisture, variety identification, true and false identification, etc.
In the later use process, food is put into for many times, after the placed food information is identified through spectrum analysis, specific analysis of specific components or properties of the food is carried out according to the analyzed information such as the type of the food, the production place and the like, and the analysis of specific components of the specific food is carried out, so that the identified result is more specialized and specific, and the requirements of users on the intelligent refrigerator are met.
The spectrum analysis can adopt near infrared spectrum analysis or hyperspectral analysis, the analysis technology is mature, the information of hydrogen-containing groups such as C-O, O-H, N-H, S-H, P-H and the like is recorded, the detection of different groups is very accurate, the method is very suitable for being applied to the detection of organic matters, and the qualitative and quantitative identification of foods can be carried out.
In the spectrum mathematical modeling process, the method comprises a plurality of stages of scanning, identifying and collecting data, identifying background information of food, measuring chemical values of various substances and components in the food, removing abnormal values, selecting proper spectrum regions, selecting proper algorithms and parameters for modeling, checking a calibration model and the like, and is developed as follows in detail:
in order to reduce random errors occurring in different times of identification, a certain area in the refrigerator is set to be a special area for spectrum analysis, for example, a range of a fresh keeping drawer is selected to be specially used for spectrum analysis, so that the whole spectrum detection space cannot be made to be too large, the distances from the spectrum of food to the food detected each time are similar, the temperature and the humidity in the area are generally stable, excessive fluctuation is not easy to occur due to uneven cold and hot of the direct-cooling refrigerator and uneven humidity caused by air circulation of the air-cooling refrigerator, and a spectrum analyzer is arranged in the area to perform spectrum scanning analysis on the food.
For a specific space in the fresh-keeping drawer, the background of food is mostly consistent, spectral analysis scans the background to obtain spectral information of the background, and in the later scanning process of the food, the same background information is included each time, so that the background information can be identified through an algorithm and the background information can be removed in a targeted manner to analyze the food, and the difference of detection results caused by different backgrounds at different positions is prevented.
Through the detected food spectrum, analysis of the food type is carried out, or after specific food information is informed, corresponding analysis is carried out on the type of food, and data of chemical values of various substances and components of the food to be measured are obtained.
Outliers are rejected when the information entered by a certain food item differs significantly from the information detected by the spectrum, for example, due to serious distortion caused by random reasons, the detected value is called outlier. For the abnormal value generated by the detection itself, the part which can be called noise can be removed by a mathematical method, a common method comprises a smoothing algorithm, a derivative algorithm, a multi-element scattering correction, a data enhancement algorithm and the like, the smoothing algorithm can be used for correcting by a convolution smoothing algorithm, a moving smoothing algorithm and the like, the derivative algorithm uses first-order and second-order derivatives to carry out correction processing, the multi-element scattering correction eliminates the influence caused by uneven distribution, the data enhancement algorithm comprises mean value centering, normalization and the like, and the noise is removed to obtain spectral data which is more in line with the real characteristics of the food.
If the spectrum data are more, the authenticity is better, but the errors are more, so that the proper spectrum region which can represent the characteristic part of food is selected for reservation, the analysis of other data with large errors or distortion can be reduced, the workload is reduced, and the detection precision is improved.
According to the obtained parameters, proper algorithms are selected, common algorithms comprise partial least square method, stepwise regression analysis, principal component regression analysis and the like, the data of the spectrum are utilized to eliminate background noise, filtering, derivative, fourier transformation and other modes can be utilized to reduce the background noise of the spectrum, and a more accurate spectrum mathematical model is established. And establishing respective proper spectrum mathematical models for different food types, and establishing multiple sets of models for some foods simultaneously.
After the spectrum mathematical model is established, foods put in later stage can be analyzed, if the information obtained by analyzing the spectrum mathematical model is inconsistent, the user can adjust, and for a plurality of models, the results obtained by different models are evaluated, and the model with the best fit is obtained after iteration for a plurality of times.
Compared with the prior art, the embodiment has the following beneficial effects: modeling is carried out on the information of the food materials by utilizing a spectrum analysis method to obtain the relation between the information of the food materials and a spectrum mathematical model, the accuracy of the spectrum mathematical model is enhanced by a plurality of iteration and learning modes, and the spectrum mathematical model which can embody the information of the food materials is perfected, so that the information of the food materials can be judged more accurately by spectrum analysis in the later use process, the intelligent degree of the refrigerator is higher, and the requirements of intelligent families are met.
The above detailed description is merely illustrative of possible embodiments of the present invention, which should not be construed as limiting the scope of the invention, and all equivalent embodiments or modifications that do not depart from the spirit of the invention are intended to be included in the scope of the invention.
Claims (10)
1. The food material detection method for the refrigerator is characterized by comprising the following steps of:
putting a first food material into the refrigerator, and inputting food material information of the first food material;
detecting spectrum information of the first food material, and establishing a first spectrum mathematical model of the first food material according to the food material information of the first food material and the spectrum information;
placing a second food material similar to the first food material information in the refrigerator, and detecting spectrum information of the second food material;
judging whether the spectrum information of the second food material is matched with the first spectrum mathematical model;
if the spectrum information of the second food material is not matched with the first spectrum mathematical model, a second spectrum mathematical model is built according to the food material information and the spectrum information of the second food material;
if the spectrum information of the second food material is identical to the first spectrum mathematical model, judging whether the second food material is the food material information of the first food material, if the first spectrum mathematical model is confirmed to be the first food material by a user, increasing the weight of the food material information of the first food material, if the first spectrum mathematical model is confirmed to be the new food material by the user, establishing a new spectrum mathematical model according to the new food material information input by the user, simultaneously marking the food material information of the first food material and the food material information of the second food material by the first spectrum mathematical model, reducing the weight of the food material information of the first food material judged by the first spectrum mathematical model, and increasing the weight of the food material information of the second food material judged by the first spectrum mathematical model;
repeatedly putting a new food material similar to the food material information of the first food material into the refrigerator, and detecting the spectrum information of the new food material;
judging whether the spectrum information of the new food material is matched with a plurality of spectrum mathematical models, if so, confirming whether the food material information judged by one spectrum mathematical model is correct by a user, and if so, increasing the weight of the one spectrum mathematical model for identifying the food material information and reducing the weight of the one spectrum mathematical model for identifying other food material information; if not, repeating the step of prompting the user to input the information of the new food, and establishing a new spectrum mathematical model;
if the spectrum information of the new food material is not matched with all the spectrum mathematical models, a new spectrum mathematical model is built according to the food material information and the spectrum information of the new food material;
and determining a spectrum mathematical model corresponding to the food material information with the highest weight as the spectrum mathematical model corresponding to the food material information.
2. The method of claim 1, wherein the food material information includes kind information, a place of production, and freshness of the food material.
3. The method of claim 1, wherein the step of establishing a mathematical spectrum model of the first food material based on the food material information of the first food material and the spectral information comprises:
collecting spectrum information of a first food material;
removing abnormal values in the spectrum data;
selecting a spectral region;
and selecting an algorithm for establishing a spectrum mathematical model according to the food material information, and establishing the spectrum mathematical model of the first food material according to the data in the spectrum region.
4. The food material detecting method of a refrigerator as claimed in claim 3, further comprising the steps of:
spectral information of the environmental background when no food material is placed is scanned.
5. The method of claim 4, wherein the step of collecting spectral information of the first food material comprises:
and comparing the spectrum information of the first food material with the spectrum information of the environment background, and removing noise information in the spectrum information of the first food material.
6. The method of detecting food materials in a refrigerator according to claim 3, wherein the step of "eliminating abnormal values in the spectrum data" includes:
and removing abnormal values in the spectrum data, wherein the removing algorithm comprises a smoothing algorithm, a derivative algorithm, multi-element scattering correction and a data enhancement algorithm.
7. The method of claim 3, wherein the step of selecting an algorithm for establishing a mathematical model of a spectrum according to the food material information comprises:
and selecting an algorithm for establishing a spectrum mathematical model according to the food material information, wherein the algorithm comprises a partial least square method, stepwise regression analysis and principal component regression analysis.
8. A refrigerator comprising a memory and a processor, the memory storing a computer program executable on the processor, further comprising:
the food material is placed in the spectrum scanning area;
the spectrometer scans the food material to obtain spectrum information;
the analysis module is used for analyzing the spectrum information, reducing noise of the spectrum information and selecting a spectrum region;
the processor, when executing the computer program, may implement the steps in the food material detection method of the refrigerator according to any one of claims 1 to 7.
9. The refrigerator of claim 8, wherein the spectral scanning area is a storage space within a drawer of the refrigerator.
10. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps in the food material detection method of the refrigerator according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010069845.1A CN113220658B (en) | 2020-01-21 | 2020-01-21 | Food material detection method of refrigerator, refrigerator and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010069845.1A CN113220658B (en) | 2020-01-21 | 2020-01-21 | Food material detection method of refrigerator, refrigerator and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113220658A CN113220658A (en) | 2021-08-06 |
| CN113220658B true CN113220658B (en) | 2023-06-20 |
Family
ID=77085088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010069845.1A Active CN113220658B (en) | 2020-01-21 | 2020-01-21 | Food material detection method of refrigerator, refrigerator and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113220658B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106871569A (en) * | 2016-12-30 | 2017-06-20 | 青岛海尔智能技术研发有限公司 | The category identification method and refrigerator of refrigerator inside food |
| CN106871568A (en) * | 2016-12-30 | 2017-06-20 | 青岛海尔智能技术研发有限公司 | The category identification method and refrigerator of refrigerator inside food |
| CN108663331A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | Detect the method and refrigerator of food freshness in refrigerator |
| CN108662842A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | The detecting system and refrigerator of food in refrigerator |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203493B (en) * | 2016-07-04 | 2019-07-12 | 何广森 | A kind of food identification device and recognition methods |
| CN107886028A (en) * | 2016-09-29 | 2018-04-06 | 九阳股份有限公司 | The food materials input method and food materials input device of a kind of refrigerator |
| CN108319968A (en) * | 2017-12-27 | 2018-07-24 | 中国农业大学 | A kind of recognition methods of fruits and vegetables image classification and system based on Model Fusion |
-
2020
- 2020-01-21 CN CN202010069845.1A patent/CN113220658B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106871569A (en) * | 2016-12-30 | 2017-06-20 | 青岛海尔智能技术研发有限公司 | The category identification method and refrigerator of refrigerator inside food |
| CN106871568A (en) * | 2016-12-30 | 2017-06-20 | 青岛海尔智能技术研发有限公司 | The category identification method and refrigerator of refrigerator inside food |
| CN108663331A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | Detect the method and refrigerator of food freshness in refrigerator |
| CN108662842A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | The detecting system and refrigerator of food in refrigerator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113220658A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110411957B (en) | Nondestructive rapid prediction method and device for shelf life and freshness of fruits | |
| Srivastava et al. | Data processing approaches and strategies for non-destructive fruits quality inspection and authentication: a review | |
| Kim et al. | Authentication of rice using near‐infrared reflectance spectroscopy | |
| CN110196265B (en) | Method for evaluating distribution stability of cut tobacco in cigarette branches in batch based on distribution probability | |
| Pallottino et al. | Image analysis techniques for automated hazelnut peeling determination | |
| CN116485418B (en) | Tracing method and system for tea refining production | |
| CN110987865A (en) | Method for detecting fig quality based on near infrared spectrum | |
| CN107219184A (en) | A kind of meat discrimination method and device traced to the source applied to the place of production | |
| Jiang et al. | Identification of tomato maturity based on multinomial logistic regression with kernel clustering by integrating color moments and physicochemical indices | |
| CN114778484B (en) | Tea quality grade classification method and device, equipment and storage medium | |
| Chen et al. | Prediction of milled rice grades using Fourier transform near-infrared spectroscopy and artificial neural networks | |
| Ehounou et al. | Predicting quality, texture and chemical content of yam (Dioscorea alata L.) tubers using near infrared spectroscopy | |
| CN113220658B (en) | Food material detection method of refrigerator, refrigerator and storage medium | |
| Liu et al. | Identification of heat damage in imported soybeans based on hyperspectral imaging technology | |
| CN110308111B (en) | Method for rapidly predicting time for smoldering yellow tea by using near infrared spectrum technology | |
| CN109187385B (en) | Method for identifying microorganisms through hyperspectral imaging | |
| CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
| CN113218880B (en) | Food material detection method of refrigerator, refrigerator and storage medium | |
| CN113218141B (en) | Food material detection method for refrigerator, refrigerator and storage medium | |
| CN102519903B (en) | Method for measuring whiteness value of Agaricus bisporus by using near infrared spectrum | |
| Hu et al. | An efficient model transfer approach to suppress biological variation in elastic modulus and firmness regression models using hyperspectral data | |
| Akter et al. | Development of a computer vision based eggplant grading system | |
| CN113218878A (en) | Method for judging freshness of food materials of refrigerator, refrigerator and storage medium | |
| CN110320174B (en) | Method for rapidly predicting time for smoldering yellow tea by applying polynomial net structure artificial neural network | |
| CN113310933A (en) | Spectrum identification method for number of days for storing raw buffalo milk |
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 |