CN108662842A - The detecting system and refrigerator of food in refrigerator - Google Patents
The detecting system and refrigerator of food in refrigerator Download PDFInfo
- Publication number
- CN108662842A CN108662842A CN201710188926.1A CN201710188926A CN108662842A CN 108662842 A CN108662842 A CN 108662842A CN 201710188926 A CN201710188926 A CN 201710188926A CN 108662842 A CN108662842 A CN 108662842A
- Authority
- CN
- China
- Prior art keywords
- food
- refrigerator
- imaging devices
- hyperspectral imaging
- detection
- 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.)
- Pending
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D11/00—Self-contained movable devices, e.g. domestic refrigerators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D27/00—Lighting arrangements
- F25D27/005—Lighting arrangements combined with control means
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2700/00—Means for sensing or measuring; Sensors therefor
- F25D2700/06—Sensors detecting the presence of a product
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
Abstract
The present invention provides the detecting systems and refrigerator of food in a kind of refrigerator, and wherein the detecting system of food includes in refrigerator：Hyperspectral imaging devices, are set to the box house of refrigerator and shooting angle is towards detection zone, and detection zone is formed in box house, and food is detected for placing；Light supply apparatus is also disposed on the box house of refrigerator comprising tungsten halogen lamp, and using tungsten halogen lamp shooting light is provided for Hyperspectral imaging devices；Controller is detected, is configured to obtain species detection trigger signal, and start Hyperspectral imaging devices and tungsten halogen lamp according to trigger signal；Type detection device, the high-spectral data for being configured with Hyperspectral imaging devices shooting identify the type of tested food.This programme comprehensively utilizes image information and spectral information carries out the category identification of food, and recognition accuracy is high.The wide tungsten halogen lamp of spectral region is used simultaneously, shooting light is provided, meet imaging requirements.
Description
Technical field
The present invention relates to storing technical fields, more particularly to the detecting system and refrigerator of food in a kind of refrigerator.
Background technology
With the progress of society and the improvement of people's living standards, consumer is not concerned only with the battalion of food when buying food
Value and safety are supported, the factors such as price, mouthfeel, appearance and freshness are further accounted for, and the role of refrigerator also deposits from simple
Store up it is fresh-keeping be gradually converted into food materials administrative center and family's nutrition center, this also proposes refrigerator new challenge, meanwhile, this
It is applied for various intelligent identification technologies and provides opportunity on refrigerator.The mode that food materials type is stored in refrigerator is understood, also from beating
It opens refrigerator doors and actually looks at change for Weigh sensor.Using automatic identification technology, the type of food is realized on domestic refrigerator
Identification function has become the development trend of intelligent refrigerator.
Automatic identification technology is exactly to obtain quilt automatically by identified article close to identification device using specific identification device
It identifies the relevant information of article, and is supplied to computer processing system to complete a kind of technology of relevant subsequent processing.It answers at present
Automatic identification technology for refrigerator includes radio frequency identification and image recognition etc., and radio frequency identification is opened on the food materials for put into refrigerator
Radio-frequency identification code is pasted, is identified using the rfid device on refrigerator, which needs purchased food materials sheet
Body contains radio-frequency identification code, and most of food currently on the market does not all contain radio-frequency identification code, especially veterinary antibiotics,
Identification code is not contained even more, therefore the technology receives prodigious application limitation.
Image recognition technology has also been applied on refrigerator, but correct recognition rata is relatively low, since the technology relies primarily on
It is identified in food materials color of image or food materials shape, the difference of texture, therefore very for food materials similar in color, shape
Difficult correctly identification, such as orange and orange are difficult difference, and recognition result is mandarin orange class, therefore the accuracy of the technology needs further
It improves.
Invention content
It is an object of the present invention to provide the detecting system and refrigerator of food in a kind of refrigerator that accuracy rate is high.
Present invention firstly provides a kind of detecting system of food in refrigerator, which includes：Hyperspectral imaging devices, if
It is placed in the box house of refrigerator and shooting angle is towards detection zone, detection zone is formed in box house, tested for placing
Food；Light supply apparatus is also disposed on the box house of refrigerator comprising tungsten halogen lamp, and using tungsten halogen lamp be EO-1 hyperion at
As device provides shooting light；Controller is detected, is configured to obtain species detection trigger signal, and start height according to trigger signal
Optical spectrum imaging device and tungsten halogen lamp, so that Hyperspectral imaging devices shoot to obtain the high-spectral data of tested food；Type
Detection device, the high-spectral data for being configured with Hyperspectral imaging devices shooting identify the type of tested food.
Optionally, detection controller is configured to：After Hyperspectral imaging devices complete shooting, control tungsten halogen lamp closes
It closes, to prevent the luminous heat diffusion of tungsten halogen lamp.
Optionally, light supply apparatus is set to the roof rear portion of detection zone, oliquely downward provides shooting light.
Optionally, Hyperspectral imaging devices use wide-angle lens or fish eye lens, and be set to detection zone just on
Side.
Optionally, the detecting system of food further includes in above-mentioned refrigerator：Speculum is also disposed on box house, with bloom
It is opposite to compose imaging device interval；And the detection for placing food to be identified is formed between Hyperspectral imaging devices and speculum
Area, wherein Hyperspectral imaging devices are configured to shoot speculum, to obtain speculum to the reflected image of detection zone
High-spectral data.
Optionally, type detection device is configured to：Food type identification model is obtained, food type identification model is advance
It trains to obtain according to the high-spectral data of different types of food；It is extracted from the high-spectral data that Hyperspectral imaging devices are shot
Go out the image feature information and characteristic spectrum information needed for food type identification model；By the figure needed for food type identification model
As characteristic information and characteristic spectrum information input food type identification model；Pattern-recognition is carried out by food type identification model,
Determine the type of tested food.
Optionally, the high-spectral data of Hyperspectral imaging devices shooting includes the trinary data group for setting quantity, Mei Gesan
Metadata group includes the two image pixel elements and a spectral wavelength element of a pixel, and each pixel has more
Group trinary data group；And the image feature information needed for food type identification model passes through to number in described image pixel element
According to analysis extraction obtain and the food type identification model needed for characteristic spectrum information pass through to the spectral wavelength member
Data analysis extraction in element obtains.
Optionally, the resolution ratio of the spectral wavelength of each pixel is less than or equal to 2nm in high-spectral data.
Optionally, the detecting system of food further includes in above-mentioned refrigerator：Freshness detection device is configured to obtain tested food
High-spectral data, obtain the freshness detection model for being suitable for tested food, using freshness detection model to EO-1 hyperion at
As the high-spectral data that device is shot is classified, so that it is determined that go out the freshness of tested food, wherein freshness detection model
It trains to obtain according to the high-spectral data of the food of different qualities in advance.
According to another aspect of the present invention, a kind of refrigerator is additionally provided.The refrigerator includes：Babinet inside defines storage
Object compartment, the indoor detection zone being formed with for placing tested food of storing；Food in any refrigerator of above-mentioned introduction
Detecting system, for being detected to tested food.
Hyperspectral imaging devices, shooting is arranged in refrigerator inside in the detecting system and refrigerator of food in the refrigerator of the present invention
The high-spectral data of food is obtained, image information is comprehensively utilized and spectral information carries out the category identification of food, recognition accuracy
It is high.Spectral region requirement for category identification to high-spectral data simultaneously, uses the light supply apparatus including tungsten halogen lamp and carries
For shooting light, the wide feature of tungsten halogen lamp spectral region is taken full advantage of.
Further, in refrigerator of the invention food detecting system and refrigerator, to Hyperspectral imaging devices and light source
The position of device is optimized, and can meet to detection zone entirety photographing request.
According to the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will be brighter
The above and other objects, advantages and features of the present invention.
Description of the drawings
Some specific embodiments that the invention will be described in detail by way of example and not limitation with reference to the accompanying drawings hereinafter.
Identical reference numeral denotes same or similar component or part in attached drawing.It should be appreciated by those skilled in the art that these
What attached drawing was not necessarily drawn to scale.In attached drawing：
Fig. 1 is the schematic functional block diagram of the detecting system of food in refrigerator according to an embodiment of the invention；
Fig. 2 is the structural schematic diagram of the detecting system of food in refrigerator according to an embodiment of the invention；
Fig. 3 is the structural schematic diagram of refrigerator according to an embodiment of the invention；
Fig. 4 is the schematic diagram of refrigerator according to another embodiment of the present invention；
Fig. 5 is the structural schematic diagram of the detecting system of food in refrigerator according to another embodiment of the present invention；And
Fig. 6 is the schematic functional block diagram of the detecting system of food in refrigerator according to another embodiment of the present invention.
Specific implementation mode
Present embodiments provide the detecting system of food and the detecting system with food in the refrigerator in a kind of refrigerator
Refrigerator, wherein in refrigerator the detecting system of food can utilize high light spectrum image-forming technology realize food type identification.Fig. 1 is
The schematic functional block diagram of the detecting system 200 of food in refrigerator according to an embodiment of the invention, Fig. 2 are according to the present invention one
The structural schematic diagram and Fig. 3 of the detecting system 200 of food are according to an embodiment of the invention in the refrigerator of a embodiment
The structural schematic diagram of refrigerator 10.
The detecting system 200 of food may include in general manner in the refrigerator：Hyperspectral imaging devices 210, light supply apparatus
220, controller 230, type detection device 240 are detected.Hyperspectral imaging devices 210 are set to inside the babinet 110 of refrigerator 10
And shooting angle is formed in towards detection zone 130, detection zone 130 inside babinet 110, and food 300 is detected for placing.
Light supply apparatus 220 is also disposed on inside the babinet 110 of refrigerator 10 comprising tungsten halogen lamp 221, and utilize halogen tungsten
Lamp 221 is that Hyperspectral imaging devices 210 provide shooting light.
Detection controller 230 is configured to obtain species detection trigger signal, and starts high light spectrum image-forming according to trigger signal
Device 210 and tungsten halogen lamp 221, so that Hyperspectral imaging devices 210, which are shot, obtains the high-spectral data of tested food 300；
Mentioned kind detection trigger signal can be user by the pressing operation of the specific keys of refrigerator 10, by being bound with refrigerator 10
The instruction that issues of mobile terminal, refrigerator 10 signal, timing pip etc. that door body 120 is turned off or on.
Type detection device 240 be configured with Hyperspectral imaging devices 210 shooting high-spectral data identify it is tested
The type of food 300.
The type for the tested food 300 that type detection device 240 identifies can by the display screen display of refrigerator 10,
The message for the type for including above-mentioned tested food 300 can also be sent to the mobile terminal bound with refrigerator 10.According to determining
Food type, the storage archives of the food 300 can be established, the storage information for recording food 300 (such as the shelf-life, preserves
Environment), provide data basis for the intelligent food materials management of refrigerator.Since synthesis has used two features of image and spectrum, significantly
Improve recognition correct rate.
The refrigerator 10 of the present embodiment may include in general manner：Babinet 110, door body 120, the present embodiment refrigerator in food
Detecting system 200.The open storing compartment at least one front side is defined in babinet 110, it is usually multiple, as refrigerating chamber,
Freezing chamber, temperature-changing chamber etc..The quantity and function of specific storing compartment can be configured according to advance demand, at some
In embodiment, the preservation temperature of refrigerating chamber can be 2~9 DEG C, or can be 4~7 DEG C；The preservation temperature of freezing chamber can be -22~-
14 DEG C, or can be -20~16 DEG C.Freezing chamber is set to the lower section of refrigerating chamber, temperature-changing chamber be set to freezing chamber and refrigerating chamber it
Between.Indoor temperature range is freezed generally at -14 DEG C to -22 DEG C.Temperature-changing chamber can be adjusted according to demand, suitable to store
Food, or as antistaling storing room.
Door body 120 is set to 110 front side of babinet, for being opened and closed storing compartment.Such as door body 120 can be by hinged
The side of 110 front of babinet is arranged in mode, and by being pivotably opened and closed storing compartment, the quantity of door body 120 can be with storing
The quantity Matching of compartment, so as to individually open storing compartment one by one.Such as can be refrigerating chamber, freezing chamber, temperature-changing chamber
Refrigerating chamber door body, freezing chamber door body, temperature-changing chamber door body is respectively set.In some optional embodiments, door body 120 can also use
The forms such as vertical hinged door, clamshell doors, side sliding door, sliding door.
Storing compartment provides cold by refrigeration system, to realize refrigeration, freeze, the storage environment of alternating temperature.Refrigeration system can
For the cooling cycle system being made of compressor, condenser, throttling set and evaporator etc..Evaporator is configured to directly or indirectly
Ground is to the indoor offer cold of storing.Such as in compression direct cooling refrigerator, evaporator may be disposed at outside the rear surface of inner container of icebox
Side or inside.In compression wind cooling refrigerator, also there is evaporator room, evaporator room to pass through air path system and storing in babinet 110
Compartment is connected to, and evaporator is arranged in evaporator room, and exit is provided with wind turbine, to carry out circularly cooling to storing compartment.By
It is that those skilled in the art are known and be easily achieved in above-mentioned babinet 110, door body 120, refrigeration system itself, in order not to cover
With fuzzy present invention point, babinet 110, door body 120, refrigeration system itself are not repeated hereinafter.
Storing is indoor to be formed with detection zone 130, which can be used as an individual storing compartment, another
In some alternative embodiments, detection zone 130 can be a certain layer of a certain storing compartment, such as can be a certain of refrigerator room
Layer.Detection zone 130 can also be directly as the Storage of food 300.
Hyperspectral imaging devices 210, are set to 110 inside of babinet and shooting angle is towards detection zone 130, obtain bloom
Modal data.High-spectral data can be a series of trinary data groups, and each trinary data group includes two of a pixel
Image pixel element and a spectral wavelength element, each pixel have multigroup trinary data group.Therefore high-spectral data is same
When obtain the continuous spectrum data of each pixel and the consecutive image data of each spectral band.High-spectrum seems continuous wave
Long optical imagery, spectral region could be provided as 200nm to 2500nm, have higher spectral resolution, resolution ratio reachable
To 2~3nm.High-spectral data can indicate that wherein two dimension is image pixel information (x, y), the third dimension with three-dimensional data block
It is wavelength information (λ).Resolution ratio is that the data cube that the arrays of x × y pixels obtain at n wavelength is x × y
The cubical array of × λ.
In the present embodiment, type detection device 240 is preferably by the spectrum number that spectral region is 400nm to 1100nm
According to this is because being conducive to the identification to food 300 and detection by largely studying the spectroscopic data in above-mentioned spectral region.
The resolution requirement of the spectral wavelength of each pixel is less than or equal in the high-spectral data that Hyperspectral imaging devices 210 are shot
2nm, to meet the requirement of category identification.
Since detection zone 130 is generally closed, it is therefore desirable to which it is 220 Hyperspectral imaging devices 210 that light supply apparatus, which is arranged,
Shooting light is provided.Since required spectral region is wider, current general light source cannot be satisfied this requirement.By a large amount of
Test finds that tungsten halogen lamp 221 can meet the wide requirement of spectral region.In conventional refrigerator field, it is considered that hot light
Source will produce influence to refrigerating environment, therefore thermal light source (tungsten halogen lamp 221 belongs to thermal light source) will not be used in refrigerator, and at this
In embodiment, existing technology prejudice is breached, tungsten halogen lamp 221 has been used, due to only being clapped in Hyperspectral imaging devices
It is used when taking the photograph, therefore, in order to meet the requirement of spectral region 400-1100nm, the present embodiment selection is made using tungsten halogen lamp 221
For light source so that the 200 food materials type that can be detected of detecting system of food is more in the refrigerator of the present embodiment.
Since the space of detection zone 130 is limited, in order to ensure that Hyperspectral imaging devices 210 can take detection zone 130
The overall picture of the food 300 of interior placement.It is preferable to use wide-angle lens or fish eye lenses for Hyperspectral imaging devices 210, and are arranged
In the surface of detection zone 130.Light supply apparatus 220 is set to the roof rear portion of detection zone 130, oliquely downward provides pickup light
Line.Tungsten halogen lamp 221 can follow Hyperspectral imaging devices 210 while start, to the middle offer in closed detection zone 130
Light.
Fig. 4 is the schematic diagram of refrigerator 10 according to another embodiment of the present invention, and Fig. 5 is according to another embodiment of the present invention
The structural schematic diagram of the detecting system 200 of food in refrigerator.It is narrow for interior refrigerator space in the refrigerator 10 of this example, bloom
The problem of spectrum imaging device 210 is difficult to 130 overall picture of shot detection area utilizes shooting reflected image by the way that reflective mirror 260 is arranged
Mode obtains the high-spectral data of reflection 130 overall picture of detection zone.
Speculum 260 and Hyperspectral imaging devices 210 are relatively arranged on inside storing compartment, speculum 260 and EO-1 hyperion
Region between imaging device 210 can be used as detection zone 130.Hyperspectral imaging devices 210 can be configured to speculum 260
It is shot, to obtain high-spectral data of the speculum 260 to the reflected image of detection zone 130.Due to the space of refrigerator inside
Than narrow, and storing compartment is generally flat layered structure for the ease of storing, in the flat area of this narrow space
Interior, existing Hyperspectral imaging devices 210 are difficult the overall picture in shot detection area, therefore in the present embodiment, are reflected by shooting
The reflected image of mirror 260 can efficiently solve this problem.In some optional embodiments, speculum 260 can select to make
With convex lens, to reflect entire detection zone 130.Light supply apparatus 220 is also disposed on the roof rear portion of detection zone 130, oliquely downward carries
For shooting light.
Speculum 260 is set to the top (such as on roof of storage compartment) of detection zone 130, and high light spectrum image-forming fills
Set 210 bottoms (such as in bottom wall of storage compartment) for being set to detection zone 130.Region where Hyperspectral imaging devices 210
Clear area is could be provided as, prevents user that food 300 to be identified is placed on to the top of Hyperspectral imaging devices 210, blocks mirror
Head.
Either Hyperspectral imaging devices 210 use angle mirror head or fish eye lens, or the reflection using speculum 260
Mode, Hyperspectral imaging devices can obtain the high-spectral data of reflection 130 overall picture of detection zone, to meet to tested food
The photographing request of object 300.
Detection controller 230 starts Hyperspectral imaging devices 210 and halogen when Hyperspectral imaging devices 210 are shot
Plain tungsten lamp 221, so that Hyperspectral imaging devices 210, which are shot, obtains the high-spectral data of tested food 300.For tungsten halogen lamp
221 heats generated influence the refrigeration of refrigerator 10, and detection controller 230 is configured to：It completes to clap in Hyperspectral imaging devices 210
After taking the photograph, control tungsten halogen lamp 221 is closed, to prevent the luminous heat diffusion of tungsten halogen lamp 221.
The process of the carry out type identification of type detection device 240 can be to obtain food type identification model, from bloom
The image feature information and characteristic light needed for food type identification model are extracted in the high-spectral data of spectrum imaging device shooting
Spectrum information；By the image feature information and characteristic spectrum information input food type identification mould needed for food type identification model
Type；Pattern-recognition is carried out by food type identification model, determines the type of tested food.
The food type identification model that type detection device 240 uses is in advance according to the EO-1 hyperion number of different types of food
It is obtained according to training.Food type identification model can be trained and be obtained in the following manner：Be pre-selected a certain number of foods and
Its high-spectral data is trained to obtain using these training samples as training sample to decision function.In identification process,
Type detection device 240 is by image feature information and characteristic spectrum information input identification model, according to different rules by its stroke
It assigns to its immediate classification, completes the determination of type.It can include using matching algorithm：Minimum distance method, it is maximum
Likelihood method, mahalanobis distance method, neural network (BP), support vector machines (SVM), Adaboost etc..
Type detection device 240 equally can carry out type identification by means of cloud using high in the clouds.Such as it is getting
It, will after the progress preliminary treatment of type detection device 240 of refrigerator 10 after the high-spectral data that Hyperspectral imaging devices 210 are shot
High-spectral data after preliminary treatment is uploaded to high in the clouds, and the pattern-recognition that food type identification model is completed by high in the clouds walks
Suddenly, the mobile terminal for then type of tested food 300 being supplied to refrigerator 10 or being bound with refrigerator 10 is carried with feeding to user
For.Food type identification model preserves beyond the clouds, reduces the data processing pressure of refrigerator 10.
Type detection device 240 is split high-spectral data, classifies, to automatically determine the type of article.Make
When with cloud identification technology, type detection device 240 can utilize the data-transformation facility of refrigerator 10 to know to food type is disposed with
The cloud device of other model sends image feature information and characteristic spectrum information, to identify mould using food type by cloud device
Type matches image feature information and characteristic spectrum information.
Fig. 6 is the schematic functional block diagram of the detecting system 200 of food in refrigerator according to another embodiment of the present invention, the ice
The detecting system 200 of food is also provided with freshness detection device 250 in case.Freshness detection device 250.Freshness is examined
It surveys device 250 to be configured to obtain the high-spectral data of tested food 300, obtains the freshness detection for being suitable for tested food 300
Model, the high-spectral data shot to Hyperspectral imaging devices 210 using freshness detection model is classified, so that it is determined that going out
The freshness of tested food 300, wherein freshness detection model are trained according to the high-spectral data of the food of different qualities in advance
It obtains.
Since the otherness of the high-spectral data of different foods is also larger, type detection device 240 can be sharp in advance
The high-spectral data shot with Hyperspectral imaging devices identifies the type of tested food, for determining the type with tested food
Corresponding freshness detection model.
In detection zone 130 there are in the case of a variety of foods, type detection device 240 may also detect that a variety of foods,
To carry out freshness detection respectively to various foods, such as distinguished respectively using the corresponding freshness detection model of various foods
Freshness measurement is carried out, to obtain the respective freshness of a variety of foods.
The freshness detection model that freshness detection device 250 uses can pass through the food to a large amount of different freshness
High-spectral data, which is trained, to be obtained, the training algorithm that may be used may include neural network (BP), support vector machines
(SVM)、Adaboost.Can in advance according to a variety of different freshness detection models at the type training of food, such as
Corresponding freshness detection model is respectively trained out in various meats, various fruit, various vegetables.
When carrying out freshness detection, freshness detection device 250 can execute following steps：From Hyperspectral imaging devices
The image feature information and characteristic spectrum information needed for freshness detection model are extracted in the high-spectral data of 210 shootings, it will
Image feature information needed for freshness detection model and characteristic spectrum information input freshness detection model, are detected by freshness
Model carries out pattern-recognition, obtains the freshness of tested food.
Freshness detection device 250 can also be realized by means of cloud and be detected, such as get high light spectrum image-forming dress
After the high-spectral data for setting 210 shootings, the data processing equipment of refrigerator 10, will be after preliminary treatment after preliminary treatment
High-spectral data is uploaded to high in the clouds, the pattern recognition step of freshness detection model is completed by high in the clouds, then by tested food 300
The freshness mobile terminal that is supplied to refrigerator 10 or is bound with refrigerator 10, for providing a user.
Above-mentioned freshness can reflect the rancid degree of food, moulding ability, degree of dehydration etc..It is more than setting in freshness
Degree after, user can be reminded in time.
When using the freshness detection function of refrigerator 10, a specific example is：User places in detection zone 130
After one apple, identification instruction is issued by button on refrigerator 10 or mobile terminal, to which detection trigger controller 230 opens
Dynamic Hyperspectral imaging devices 210 and tungsten halogen lamp 221.Hyperspectral imaging devices 210 shoot detection zone 130, obtain
High-spectral data including apple.By preliminary treatment, the food type that can extract tested food 300 (apple) is known
Image feature information needed for other model and characteristic spectrum information, type detection device 240 obtain food type identification model, and
By the image feature information and characteristic spectrum information input food type identification model needed for food type identification model；By food
Type identification model carries out pattern-recognition, obtains the type of tested food 300, namely determines that tested food is apple.Freshness
Detection device 250 determines the freshness detection model of apple, is carried from the high-spectral data that Hyperspectral imaging devices 210 are shot
The image feature information and characteristic spectrum information needed for freshness detection model are taken out, by the image needed for freshness detection model
Characteristic information and characteristic spectrum information input apple freshness detection model carry out pattern knowledge by apple freshness detection model
Not, the freshness of apple is obtained.Freshness is by the display screen of refrigerator 10 or the mobile terminal bound with refrigerator 10 to user
Report can alarm when the freshness of apple declines to a certain extent to user.
It is introduced take apple as an example in examples detailed above, when the present embodiment is embodied, the detection system of food in refrigerator
System 200 can carry out type detection to the various foods that detection zone 130 is placed, and further detect freshness, tungsten halogen lamp 221
Fully ensure that Hyperspectral imaging devices 210 shoot the high spectrum image that spectral region is met the requirements.And due to comprehensive profit
The category identification of food is carried out with image information and spectral information, recognition accuracy is high, and food materials management is provided for refrigerator 10
Data basis.
So far, although those skilled in the art will appreciate that present invention has been shown and described in detail herein multiple shows
Example property embodiment still without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (10)
1. the detecting system of food in a kind of refrigerator, including：
Hyperspectral imaging devices, are set to the box house of the refrigerator and shooting angle is towards detection zone, the detection zone
It is formed in the box house, food is detected for placing；
Light supply apparatus is also disposed on the box house of the refrigerator comprising tungsten halogen lamp, and be institute using the tungsten halogen lamp
It states Hyperspectral imaging devices and shooting light is provided；
Detect controller, be configured to obtain species detection trigger signal, and according to the trigger signal start the EO-1 hyperion at
As device and the tungsten halogen lamp, so that the Hyperspectral imaging devices shoot to obtain the EO-1 hyperion number of the tested food
According to；
Type detection device, the high-spectral data for being configured with the Hyperspectral imaging devices shooting identify the tested food
The type of object.
2. detecting system according to claim 1, wherein
The detection controller is configured to：After the Hyperspectral imaging devices complete shooting, controls the tungsten halogen lamp and close
It closes, to prevent the luminous heat diffusion of the tungsten halogen lamp.
3. detecting system according to claim 1, wherein
The light supply apparatus is set to the roof rear portion of the detection zone, oliquely downward provides the shooting light.
4. detecting system according to claim 3, wherein
The Hyperspectral imaging devices use wide-angle lens or fish eye lens, and are set to the surface of the detection zone.
5. detecting system according to claim 3, further includes：
Speculum is also disposed on the box house, opposite with the Hyperspectral imaging devices interval；And
The detection zone for placing food to be identified is formed between the Hyperspectral imaging devices and the speculum, wherein described
Hyperspectral imaging devices are configured to shoot the speculum, to obtain the speculum to the reflected image of detection zone
High-spectral data.
6. detecting system according to claim 1, wherein the type detection device is configured to：
Food type identification model is obtained, the food type identification model is in advance according to the EO-1 hyperion number of different types of food
It is obtained according to training；
The figure needed for the food type identification model is extracted from the high-spectral data that the Hyperspectral imaging devices are shot
As characteristic information and characteristic spectrum information；
By needed for the food type identification model image feature information and characteristic spectrum information input described in food type know
Other model；
Pattern-recognition is carried out by the food type identification model, determines the type of the tested food.
7. detecting system according to claim 6, wherein
The high-spectral data of the Hyperspectral imaging devices shooting includes the trinary data group for setting quantity, each Three-ary Number
Include the two image pixel elements and a spectral wavelength element of a pixel according to group, each pixel has multigroup institute
State trinary data group；And the image feature information needed for food type identification model passes through to data in image pixel element point
Analysis extraction obtain and food type identification model needed for characteristic spectrum information pass through to data in spectral wavelength element point
Analysis extraction obtains.
8. detecting system according to claim 7, wherein
The resolution ratio of the spectral wavelength of each pixel is less than or equal to 2nm in the high-spectral data.
9. detecting system according to claim 1, further includes：
Freshness detection device is configured to obtain the high-spectral data of the tested food, obtains and be suitable for the tested food
Freshness detection model, the high-spectral data that the Hyperspectral imaging devices are shot using the freshness detection model into
Row classification, so that it is determined that going out the freshness of the tested food, wherein the freshness detection model is in advance according to different qualities
The high-spectral data of food train to obtain.
10. a kind of refrigerator, including：
Babinet inside defines storing compartment, the indoor detection zone being formed with for placing tested food of the storing；
The detecting system of food in refrigerator according to any one of claim 1 to 9, for being carried out to the tested food
Detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188926.1A CN108662842A (en) | 2017-03-27 | 2017-03-27 | The detecting system and refrigerator of food in refrigerator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710188926.1A CN108662842A (en) | 2017-03-27 | 2017-03-27 | The detecting system and refrigerator of food in refrigerator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108662842A true CN108662842A (en) | 2018-10-16 |
Family
ID=63786171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710188926.1A Pending CN108662842A (en) | 2017-03-27 | 2017-03-27 | The detecting system and refrigerator of food in refrigerator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108662842A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020125456A1 (en) * | 2018-12-18 | 2020-06-25 | 广东美的白色家电技术创新中心有限公司 | Food monitoring method, refrigerator, and apparatus having storage function |
| CN113218141A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113218878A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Method for judging freshness of food materials of refrigerator, refrigerator and storage medium |
| CN113220658A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113218880A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113494833A (en) * | 2020-04-02 | 2021-10-12 | 青岛海尔电冰箱有限公司 | Article temperature detection method, refrigerator and storage medium |
| CN113794010A (en) * | 2021-09-09 | 2021-12-14 | 嘉兴极展科技有限公司 | Flexible battery pack of stretching |
| CN113811880A (en) * | 2019-06-07 | 2021-12-17 | 巴斯夫涂料有限公司 | Device and method for forming at least one ground truth database for an object recognition system |
| CN115335835A (en) * | 2020-03-31 | 2022-11-11 | 大金工业株式会社 | Learning device, fresh product storage device, and program |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650317A (en) * | 2009-09-15 | 2010-02-17 | 南京农业大学 | Detection method of pollutants on surface of whole chicken rinses |
| CN101696935A (en) * | 2009-10-27 | 2010-04-21 | 中国农业大学 | Apple rigidity nondestructive testing method based on hyperspectral space scattering curve |
| CN101718682A (en) * | 2009-12-14 | 2010-06-02 | 浙江大学 | Egg freshness on-line detection method and device based on multivariate information fusion |
| CN102323267A (en) * | 2011-08-10 | 2012-01-18 | 中国农业大学 | System and method used for rapidly evaluating freshness of raw meat products |
| CN103618878A (en) * | 2013-12-04 | 2014-03-05 | 洛阳愿景科技有限公司 | Camera shooting direct reading remote water meter device |
| CN105928889A (en) * | 2016-04-29 | 2016-09-07 | 合肥华凌股份有限公司 | Refrigerator and food nutrient real-time detection method for refrigerator |
| CN106203522A (en) * | 2016-07-15 | 2016-12-07 | 西安电子科技大学 | Hyperspectral image classification method based on three-dimensional non-local mean filtering |
-
2017
- 2017-03-27 CN CN201710188926.1A patent/CN108662842A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650317A (en) * | 2009-09-15 | 2010-02-17 | 南京农业大学 | Detection method of pollutants on surface of whole chicken rinses |
| CN101696935A (en) * | 2009-10-27 | 2010-04-21 | 中国农业大学 | Apple rigidity nondestructive testing method based on hyperspectral space scattering curve |
| CN101718682A (en) * | 2009-12-14 | 2010-06-02 | 浙江大学 | Egg freshness on-line detection method and device based on multivariate information fusion |
| CN102323267A (en) * | 2011-08-10 | 2012-01-18 | 中国农业大学 | System and method used for rapidly evaluating freshness of raw meat products |
| CN103618878A (en) * | 2013-12-04 | 2014-03-05 | 洛阳愿景科技有限公司 | Camera shooting direct reading remote water meter device |
| CN105928889A (en) * | 2016-04-29 | 2016-09-07 | 合肥华凌股份有限公司 | Refrigerator and food nutrient real-time detection method for refrigerator |
| CN106203522A (en) * | 2016-07-15 | 2016-12-07 | 西安电子科技大学 | Hyperspectral image classification method based on three-dimensional non-local mean filtering |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020125456A1 (en) * | 2018-12-18 | 2020-06-25 | 广东美的白色家电技术创新中心有限公司 | Food monitoring method, refrigerator, and apparatus having storage function |
| CN113811880A (en) * | 2019-06-07 | 2021-12-17 | 巴斯夫涂料有限公司 | Device and method for forming at least one ground truth database for an object recognition system |
| CN113218141A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113218878A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Method for judging freshness of food materials of refrigerator, refrigerator and storage medium |
| CN113220658A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113218880A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN113220658B (en) * | 2020-01-21 | 2023-06-20 | 青岛海尔电冰箱有限公司 | Food material detection method of refrigerator, refrigerator and storage medium |
| CN113218880B (en) * | 2020-01-21 | 2023-05-16 | 青岛海尔电冰箱有限公司 | Food material detection method of refrigerator, refrigerator and storage medium |
| CN113218141B (en) * | 2020-01-21 | 2022-10-28 | 青岛海尔电冰箱有限公司 | Food material detection method for refrigerator, refrigerator and storage medium |
| CN115335835A (en) * | 2020-03-31 | 2022-11-11 | 大金工业株式会社 | Learning device, fresh product storage device, and program |
| CN113494833A (en) * | 2020-04-02 | 2021-10-12 | 青岛海尔电冰箱有限公司 | Article temperature detection method, refrigerator and storage medium |
| CN113794010A (en) * | 2021-09-09 | 2021-12-14 | 嘉兴极展科技有限公司 | Flexible battery pack of stretching |
| CN113794010B (en) * | 2021-09-09 | 2023-09-19 | 嘉兴极展科技有限公司 | Flexible stretchable battery pack |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108662842A (en) | The detecting system and refrigerator of food in refrigerator | |
| CN108663331A (en) | Detect the method and refrigerator of food freshness in refrigerator | |
| CN108662843A (en) | The detecting system and refrigerator of food in refrigerator | |
| CN106871568A (en) | The category identification method and refrigerator of refrigerator inside food | |
| CN110966833B (en) | Method for detecting food material information in refrigerator and refrigerator | |
| US11060735B2 (en) | Connected food preparation system and method of use | |
| CN106871569A (en) | The category identification method and refrigerator of refrigerator inside food | |
| CN106705564B (en) | The control method and refrigerator of refrigerator | |
| US20220381439A1 (en) | Connected food preparation system and method of use | |
| CN110966834A (en) | Method for identifying food material types in refrigerator and refrigerator | |
| CN104197632A (en) | Intelligent temperature regulating refrigerator | |
| CN110017659A (en) | Domestic refrigerator equipment | |
| CN109869966A (en) | Refrigerator | |
| CN110966835B (en) | Method for detecting nutrient components of food materials in refrigerator and refrigerator | |
| CN108663332A (en) | High light spectrum image-forming component and refrigerator for detecting food in refrigerator | |
| CN108663333A (en) | High light spectrum image-forming component and refrigerator for detecting food in refrigerator | |
| KR102017979B1 (en) | Refrigerator with controlling operation based on thermal capacity of goods using artificial intelligence and method of controlling thereof | |
| US11928769B2 (en) | Employing controlled illumination for hyperspectral or multispectral imaging of food in an appliance |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181016 |
|
| RJ01 | Rejection of invention patent application after publication |