Movatterモバイル変換


[0]ホーム

URL:


CN104269003A - Food recognition method, device and system - Google Patents

Food recognition method, device and system
Download PDF

Info

Publication number
CN104269003A
CN104269003ACN201410464419.2ACN201410464419ACN104269003ACN 104269003 ACN104269003 ACN 104269003ACN 201410464419 ACN201410464419 ACN 201410464419ACN 104269003 ACN104269003 ACN 104269003A
Authority
CN
China
Prior art keywords
food
image
default
source images
target image
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
Application number
CN201410464419.2A
Other languages
Chinese (zh)
Inventor
李龙龙
庞达
王新欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by IndividualfiledCriticalIndividual
Priority to CN201410464419.2ApriorityCriticalpatent/CN104269003A/en
Publication of CN104269003ApublicationCriticalpatent/CN104269003A/en
Pendinglegal-statusCriticalCurrent

Links

Landscapes

Abstract

The embodiment of the invention discloses a food recognition method, device and system. The method can comprise the steps that a target image collected by a camera is acquired; the target image is analyzed to obtain target features of the target image, wherein the target features comprise the food image feature and the food container image feature; preset image features matched with the target features are searched for in a preset feature library, and the food identification of the target image is determined through the preset image features matched with the target features; preset result information corresponding to the food identification is generated; the preset result information is transmitted to a result processing terminal so that the result processing terminal can inform a user of the preset result information. By the adoption of the food recognition method, the food identification can be obtained through the food image feature and the food container feature of the target image, and then the preset result information corresponding to the food identification is generated; in this way, the cost of food recognition can be lowered, and the accuracy and the efficiency of food recognition can be improved.

Description

A kind of food recognition methods, Apparatus and system
Technical field
The present invention relates to field of computer technology, particularly relate to a kind of food recognition methods, Apparatus and system.
Background technology
When settling accounts food, by cashier's manually valuation or scanning barcode tag computation price one by one, in the free dish dining room of unified cash register, cashier is adopted manually to valuate one by one checkout, during mealtime rush, cashier's efficiency of manually valuating is low and easily make mistakes.Existingly bottom service plate, add RFID (Radio Frequency Identification, radio-frequency (RF) identification) chip, at RFID chip write pricing information, RFID chip on cashier's card reader induction dinner plate is with valuation, but be required to be each service plate and load RFID chip, complex steps, and the service plate requiring dining room configure band RFID chip, cost is high.
Summary of the invention
The embodiment of the present invention provides a kind of food recognition methods, Apparatus and system, can reduce the cost of food identification, can improve the precision of food identification and improve the efficiency of food identification.
Embodiment of the present invention first aspect, provides a kind of food recognition methods, comprising:
Obtain the target image of camera collection;
Resolve described target image, obtain the target signature of described target image, described target signature comprises: food image characteristic sum food container characteristics of image;
From default feature database, search the pre-set image feature of mating with described target signature, the pre-set image feature of being mated by described and described target signature determines that the food of described target image identifies;
Generate the default object information that described food mark is corresponding, described default object information comprises default settlement information and/or default recommendation information;
Described default object information is transferred to result treatment terminal, to make described result treatment terminal, described default object information is notified user.
Embodiment of the present invention second aspect, provides a kind of food recognition device, comprising:
Acquisition module, for obtaining the target image of camera collection;
Parsing module, for resolving described target image, obtain the target signature of described target image, described target signature comprises: food image characteristic sum food container characteristics of image;
Matching module, for searching the pre-set image feature of mating with described target signature from default feature database, the pre-set image feature of being mated by described and described target signature determines that the food of described target image identifies;
Generation module, for generating default object information corresponding to described food mark, described default object information comprises default settlement information and/or default recommendation information;
Transport module, for described default object information is transferred to result treatment terminal, notifies user to make described result treatment terminal by described default object information.
The embodiment of the present invention third aspect, provides a kind of food recognition system, comprising: camera, result treatment terminal and server; Described camera is connected with described server; Described server is connected with described result treatment terminal;
Described server, the device as described in second aspect;
Described result treatment terminal, for when receiving the default object information of described server transmission, notifies user by described default object information.
Implement the embodiment of the present invention, the target image of camera collection can be obtained, and then parsing target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, also can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, the default object information that further generation food mark is corresponding, wherein, default object information comprises default settlement information and/or default recommendation information, and then default object information is transferred to result treatment terminal, to make result treatment terminal, default object information is notified user.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default object information corresponding to food mark, the cost of food identification can be reduced, the precision of food identification can be improved and improve the efficiency of food identification.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of a kind of food recognition methods that first embodiment of the invention provides;
Fig. 2 A is the schematic flow sheet of a kind of food recognition methods provided in second embodiment of the invention;
Fig. 2 B is a kind of food recognition methods schematic diagram provided in the embodiment of the present invention;
Fig. 3 A is the schematic flow sheet of a kind of food recognition methods provided in third embodiment of the invention;
Fig. 3 B is the another kind of food recognition methods schematic diagram that the embodiment of the present invention provides;
Fig. 4 is that the target image that the embodiment of the present invention provides gathers schematic diagram;
Fig. 5 is the Image Feature Matching schematic diagram that the embodiment of the present invention provides;
Fig. 6 is the structural representation of a kind of food recognition device that the embodiment of the present invention provides;
Fig. 7 is the structural representation of a kind of server that the embodiment of the present invention provides;
Fig. 8 A is the structural representation of a kind of food recognition system provided in the embodiment of the present invention;
Fig. 8 B is a kind of food recognition system schematic diagram provided in the embodiment of the present invention;
Fig. 8 C is the another kind of food recognition system schematic diagram provided in the embodiment of the present invention;
Fig. 8 D is another the food recognition system schematic diagram provided in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The embodiment of the present invention provides a kind of food recognition methods, device and terminal.Concrete, the target image gathered in the embodiment of the present invention is including, but not limited to food and food container, wherein, the food materials that food can comprise source food materials and cook, concrete example as: the thing that grain, vegetables, meat, beverage, fruit, cake etc. can be edible, food container such as bowl, dish, basin, cup, lunch box etc. are for the thing of accommodating food.
Further, the food identifying schemes that the embodiment of the present invention provides can be applied to: the clearing scene in free dish dining room or dining room, clearing scene in free supermarket etc., concrete example as, user 1 is at free dining room breakfast, have selected one glass of hot soya-bean milk, two steamed buns and one bowl of milled congee are also placed in pallet, then can gather the image of food in pallet and food container, carry out food identification, recognize the mark of soya-bean milk, the mark of steamed bun and the mark of milled congee, generate corresponding pricing information, card swiping terminal shows the pricing information of generation, user 1 can carry out clearing of swiping the card, user 2 is at free dish dining room lunch, have selected meal, Scrambled Egg with Tomato, chicken leg be placed in service plate, then can collect the food image in service plate image and service plate thereof, carry out food identification, recognize the mark of the mark of meal, the mark of Scrambled Egg with Tomato and chicken leg, generate corresponding pricing information, card swiping terminal shows the pricing information bar code of generation, and user 2 pays by mobile telephone scanning pricing information bar code, user 3 in free supermarket, have selected a dish fresh fruit platter and one bowl cold and dressed with sauce, user 3 cold and dressed with saucely to take pictures to this dish fresh fruit platter and this bowl by mobile phone, the image obtained taking pictures is uploaded, then the food recognition device of this programme can identify image, recognize fruit variety and the cold and dressed with sauce food qualification category comprised that concrete fresh fruit platter comprises, default object information can be generated and occur to the mobile phone of user 3, wherein, default object information can comprise: the fruit variety recognized and the cold and dressed with sauce food qualification category that comprises and each fruit, the nutritional information of cold and dressed with sauce correspondence, edible points for attention etc., thus user 3 finds default object information etc. by mobile phone.
The embodiment of the present invention provides food recognition system to comprise: camera, result treatment terminal and server, wherein, result treatment terminal can comprise: settlement terminal and/or mobile terminal, concrete, the smart mobile phone etc. of settlement terminal such as machine for punching the card, checkout machine, support payment function, the mobile terminal devices such as mobile terminal such as smart mobile phone, panel computer or Worn type smart machine.
Refer to Fig. 1, Fig. 1 is the schematic flow sheet of a kind of food recognition methods provided in first embodiment of the invention, and the food recognition methods as shown in the figure in the embodiment of the present invention can comprise: S101 ~ S105.
S101, obtains the target image of camera collection.
As the optional embodiment of one, by camera collection target image in the embodiment of the present invention, and then can get target image, wherein, target image can comprise: food image and food container image.
In specific implementation, as shown in Figure 4, be that the target image that the embodiment of the present invention provides gathers schematic diagram, as shown in the figure, step S401 ~ S412 can be comprised.
S401, detects timer and whether arrives the predetermined period time.
S402, if detect timer to arrive first predetermined period time, obtains the image of camera shooting, obtains period 1 source images.
S403, if detect timer to arrive second predetermined period time, obtains the image of camera shooting, obtains source images second round.
S404, if detect timer to arrive the 3rd predetermined period time, obtains the image of camera shooting, obtains period 3 source images.
S405, calculate period 1 source images and second round source images difference.
S406, judge period 1 source images and second round source images difference whether be zero.If judged result is no, perform step S407, if the determination result is YES, perform step S412.
S407, preserves source images second round.
S408, the difference of calculating source images second round and period 3 source images.
S409, judge second round source images and the difference of period 3 source images whether be zero.If the determination result is YES, perform step S410, if judged result is no, perform step S411.
S410, is defined as target image by source images second round.
S411, preserves period 3 source images.
S412, is defined as target image by period 1 source images.
In specific implementation, the predetermined period time can for the cycle length of camera collection image pre-set, such as 0.3 second etc.During every predetermined period time, camera takes an image, then when first the predetermined period time of arrival, period 1 source images can be collected, when second the predetermined period time of arrival, source images second round can be collected, when the 3rd the predetermined period time of arrival, period 3 source images can be collected ... in the embodiment of the present invention, be described for the image that three predetermined period times collect, Fig. 4 that the image that other predetermined period times collect can provide see the embodiment of the present invention, be not repeated.
By detecting the data that camera collection arrives, and calculate image that previous predetermined period time and a rear predetermined period time collects carry out poor, if difference is zero, the image document then collected, can be defined as target image by the present image collected, thus identify image, if difference is non-vanishing, the image then collected has renewal, judder, continues the image gathering the next predetermined period time.Thus accurately can obtain target image.Further alternative, can also using without image when any food and food container as basic image, when the difference of the image collected and basic image is zero, returning the next predetermined period time continues to gather next image.
S102, resolve target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image.
As the optional embodiment of one, can resolve, obtain the target signature of target image to the target image got, wherein, target signature can comprise: food image characteristic sum food container characteristics of image.
Further, S102 resolves target image, and the target signature obtaining target image can comprise:
Resolve target image, extract multiple proper vectors of target image, multiple proper vector comprises: image color proper vector, image texture characteristic vector sum image detail proper vector;
Multiple proper vector is weighted, obtains the target signature of target image.
In specific implementation, can extract multiple proper vectors of target image, wherein, multiple proper vector is including, but not limited to image color proper vector, image texture characteristic vector sum image detail proper vector, and then multiple proper vector is weighted, obtain the target signature of target image.
S103, searches the pre-set image feature of mating with target signature from default feature database, is identified by the food of the pre-set image feature determination target image mated with target signature.
As the optional embodiment of one, the pre-set image feature of mating with target signature is searched from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, in specific implementation, default feature database can be set up in advance, see Fig. 5, it is the Image Feature Matching schematic diagram that the embodiment of the present invention provides.
S501, the food container image that the food image that the food obtaining user's input identifies, food mark is corresponding, food mark are corresponding and food identify corresponding food price.
Further alternative, also can obtain the default recommendation information that the food mark of user's input is corresponding, the nutritional information, eating attention information etc. of the default recommendation information such as food that food mark is corresponding, specifically not by the restriction of the embodiment of the present invention.
S502, extracts the feature of the characteristic sum food container image of food image.
S503, carries out classification based training by the feature of the characteristic sum food container image of the food image extracted, obtains default sorter model.
S504, classification based training obtains pre-set image feature corresponding to food mark.
S505, by pre-set image characteristic storage corresponding for food mark in default feature database.
S506, obtains target image.
S507, extracts the target signature of target image.
S508, imports the default sorter model obtained in S503 by the target signature of the target image extracted.
S509, sorter is classified to target signature, searches the pre-set image feature of mating with target signature, exports the food mark that target signature is corresponding.
S510, if when sorter is classified to target signature, when matching rate when classifying to target signature is lower than predetermined threshold value, then send warning message to default result terminal, thus the object information carrying out reaffirming target image can be pointed out to export, and obtain the object information of user feedback, be updated in default sorter.
Further alternative, default sorter model can be stored in default feature database, thus the pre-set image feature of searching and mating with target signature can be preset in sorter model again, identified by the food of the pre-set image feature determination target image mated with target signature.
S104, generate the default object information that food mark is corresponding, default object information comprises default settlement information and/or default recommendation information.
As the optional embodiment of one, the default object information that food mark is corresponding can be generated, wherein, default object information comprises default settlement information and/or default recommendation information, concrete, the pricing information of default settlement information such as food, default recommendation information can comprise the nutritional information of food, the evaluation information, the eating attention information of food, each dining room comparative information of food etc. of food.
Further, the default object information generating food mark corresponding specifically can comprise: the default object information obtained can be converted to the information that result treatment terminal can directly show or play, such as binary message, voice messaging, bar code information etc., specifically not by the restriction of the embodiment of the present invention.
Concrete, can obtain and identify corresponding food price with the food of target image, generate food by the food price got and identify corresponding default settlement information.
S105, is transferred to result treatment terminal by default object information, to make result treatment terminal, default object information is notified user.
As the optional embodiment of one, default object information can be transferred to result treatment terminal, to make result treatment terminal, default object information be notified user.Wherein, result treatment terminal comprises: settlement terminal and/or mobile terminal.Further, default settlement information can be transferred to settlement terminal or mobile terminal, thus user pays by settlement terminal or mobile terminal, and then user can consult or hear default object information, pays, pays in cash by card, Third-party payment etc.Further alternative, result treatment terminal, when user pays failed, can also be reported to the police.
Further, also default recommendation information can be transferred to mobile terminal, thus mobile terminal can run this default recommendation information, further, preset recommendation information including, but not limited to text message, can also voice messaging, pictorial information etc. be comprised, specifically not by the restriction of the embodiment of the present invention.
The embodiment of the present invention provides a kind of food recognition methods, the target image of camera collection can be obtained, and then parsing target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, also can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, the default object information that further generation food mark is corresponding, wherein, default object information comprises default settlement information and/or default recommendation information, and then default object information is transferred to result treatment terminal, to make result treatment terminal, default object information is notified user.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default object information corresponding to food mark, the cost of food identification can be reduced, the precision of food identification can be improved and improve the efficiency of food identification.
Refer to Fig. 2 A, Fig. 2 A is the schematic flow sheet of a kind of food recognition methods provided in second embodiment of the invention, and the food recognition methods as shown in the figure in the embodiment of the present invention can comprise: S201 ~ S208.
S201, server obtains the target image of camera collection.
S202, server parses target image, obtains the target signature of target image.
In specific implementation, the target signature of target image can comprise: food image characteristic sum food container characteristics of image.
S203, server searches the pre-set image feature of mating with target signature from default feature database, is identified by the food of the pre-set image feature determination target image mated with target signature.
S204, server obtains and identifies corresponding food price with the food of target image, generates food identify corresponding default settlement information by the food price got.
S205, default settlement information is transferred to settlement terminal by server.
In specific implementation, the default settlement information generated can be sent to settlement terminal by server, wherein, settlement terminal can comprise existing machine for punching the card, in the embodiment of the present invention, without the need to changing existing machine for punching the card, default settlement information server process in the embodiment of the present invention obtained by preset interface is transferred in machine for punching the card, and carries out showing or playing in machine for punching the card.Thus compatibility can be carried out with existing machine for punching the card, plug and play, eliminate the inconvenience needing to change existing machine for punching the card.
S206, default settlement information is notified user by settlement terminal.
S207, whether settlement terminal detects and pays successfully.
S208, pays unsuccessfully if settlement terminal detects, output alarm information.
In specific implementation, settlement terminal pays unsuccessfully detecting, exportable warning message, wherein, warning message is buzzer warning, audio alert etc. such as.
As shown in Figure 2 B, it is a kind of food recognition methods schematic diagram provided in the embodiment of the present invention, camera collection is to target data, be transferred in server, server can be resolved target data, obtain target signature, food mark is matched from the default sorter model default feature database, and then find from default feature database and identify corresponding food price with food, generate thus and preset settlement information, default settlement information is transferred to settlement terminal by server, user pays by card or other payment terminals, if pay unsuccessfully, settlement terminal output alarm information.
The embodiment of the present invention provides a kind of food recognition methods, the target image of camera collection can be obtained, and then parsing target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, also can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, the default settlement information that further generation food mark is corresponding, and then default settlement information is transferred to settlement terminal, default object information can be notified user by settlement terminal, settlement terminal also can be reported to the police when user pays failure detecting.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default settlement information corresponding to food mark, can be compatible with existing settlement terminal, the cost of food identification can be reduced, the precision of food identification can be improved and improve the efficiency of food identification.
Refer to Fig. 3 A, Fig. 3 A is the schematic flow sheet of a kind of food recognition methods provided in third embodiment of the invention, and the food recognition methods as shown in the figure in the embodiment of the present invention can comprise:
S301, mobile terminal is by camera collection target image.
In specific implementation, user before having a meal, can take pictures to food and food container information, such as, photographs food and food container image by the camera in mobile phone; Also target image, such as video camera etc. can be gathered by capture apparatus by other.
S302, target image is transferred to server by mobile terminal.
In specific implementation, mobile terminal can by target image by wireless network transmissions in server, or also by wireless network transmissions to the addressable shared section key of server, thus server may have access to shared section key reads this target image.
S303, server parses target image, obtains the target signature of target image.
In specific implementation, the target signature of target image can comprise: food image characteristic sum food container characteristics of image.
S304, searches the pre-set image feature of mating with target signature from default feature database, is identified by the food of the pre-set image feature determination target image mated with target signature.
S305, generates the default recommendation information that food mark is corresponding.
In specific implementation, the nutritional information of default recommendation information such as food, the evaluation information of food, the eating attention information of food, each dining room comparative information of food etc.
Further alternative, default recommendation information can also for repeatedly getting target image and after analyzing target image, to the better feed diet information that user recommends, such as, according to the target image collected during user's diet of a week, analyze user's nutrition intake of a week, thus recommend the nutrition arrangement information needing absorption.
S306, is transferred to mobile terminal by default recommendation information.
S307, default recommendation information is notified user by mobile terminal.
Concrete, preset recommendation information including, but not limited to text message, can also voice messaging, pictorial information etc. be comprised, specifically not by the restriction of the embodiment of the present invention.
As shown in Figure 3 B, it is the another kind of food recognition methods schematic diagram provided in the embodiment of the present invention, user by the camera collection in mobile terminal to target data, mobile terminal uploads target image to server, server can be resolved target data, obtain target signature, food mark is matched from the default sorter model default feature database, and then find from default feature database and identify corresponding recommendation information with food, generate thus and preset recommendation information, default recommendation information is transferred to mobile terminal by server, presetting health check-up information can be Word message or video information, thus the display screen of user's movable termination consults default recommendation information, further, default recommendation information also can be voice messaging.
The embodiment of the present invention provides a kind of food recognition methods, mobile terminal can obtain the target image of camera collection, and send to server, thus server can resolve target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, also can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, the default recommendation information that further generation food mark is corresponding, and then default recommendation information is transferred to mobile terminal, default recommendation information can be notified user by mobile terminal.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default recommendation information corresponding to food mark, the target image that identifiable design user is collected by mobile terminal, and then return default recommendation information, enhance Consumer's Experience, improve the intelligent of food identification.
Refer to Fig. 6, Fig. 6 is the structural representation of a kind of food recognition device that the embodiment of the present invention provides.It should be noted that, the food recognition device shown in accompanying drawing 6, shows the method for embodiment for performing Fig. 1 of the present invention, for convenience of explanation, illustrate only the part relevant to the embodiment of the present invention, concrete ins and outs do not disclose, and please refer to the embodiment shown in Fig. 1 of the present invention.Food recognition device as shown in the figure in the embodiment of the present invention at least can comprise: acquisition module 61, parsing module 62, matching module 63, generation module 64 and transport module 65.
Acquisition module 61, for obtaining the target image of camera collection.
As the optional embodiment of one, by camera collection target image in the embodiment of the present invention, and then acquisition module 61 can get target image, and wherein, target image can comprise: food image and food container image.
Further alternative, acquisition module 61 can comprise: acquiring unit, computing unit, storage unit and determining unit.
Acquiring unit, when detecting that timer arrives the predetermined period time, obtains the image of camera shooting, obtain period 1 source images, second round source images and period 3 source images;
Computing unit, for calculate period 1 source images and second round source images difference;
Storage unit, for calculate at computing unit period 1 source images and second round source images difference non-vanishing time, preserve second round source images;
Computing unit, also for calculating source images and the difference of period 3 source images second round;
Determining unit, for calculate at computing unit second round source images and the difference of period 3 source images be zero time, source images second round is defined as target image.
In specific implementation, the predetermined period time can for the cycle length of camera collection image pre-set, such as 0.3 second etc.During every predetermined period time, camera takes an image, then when first the predetermined period time of arrival, period 1 source images can be collected, when second the predetermined period time of arrival, source images second round can be collected, when the 3rd the predetermined period time of arrival, period 3 source images can be collected ... in the embodiment of the present invention, be described for the image that three predetermined period times collect, Fig. 4 that the image that other predetermined period times collect can provide see the embodiment of the present invention, be not repeated.
By detecting the data that camera collection arrives, and calculate image that previous predetermined period time and a rear predetermined period time collects carry out poor, if difference is zero, the image document then collected, can be defined as target image by the present image collected, thus identify image, if difference is non-vanishing, the image then collected has renewal, judder, continues the image gathering the next predetermined period time.Thus accurately can obtain target image.Further alternative, can also using without image when any food and food container as basic image, when the difference of the image collected and basic image is zero, returning the next predetermined period time continues to gather next image.
Parsing module 62, for resolving target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image.
As the optional embodiment of one, parsing module 62 can be resolved the target image that acquisition module 61 gets, and obtains the target signature of target image, and wherein, target signature can comprise: food image characteristic sum food container characteristics of image.
Further alternative, parsing module 62 can comprise: feature extraction unit and feature extraction unit.
Feature extraction unit, for resolving target image, extract multiple proper vectors of target image, multiple proper vector comprises: image color proper vector, image texture characteristic vector sum image detail proper vector;
Weight calculation unit, for being weighted multiple proper vector, obtains the target signature of target image.
Matching module 63, for searching the pre-set image feature of mating with target signature from default feature database, is identified by the food of the pre-set image feature determination target image mated with target signature.
As the optional embodiment of one, default feature database can be set up in advance, thus the pre-set image feature of mating with target signature can be searched from default feature database, be identified by the food of the pre-set image feature determination target image mated with target signature.
Generation module 64, for generating default object information corresponding to food mark, default object information comprises default settlement information and/or default recommendation information.
As the optional embodiment of one, generation module 64 can generate default object information corresponding to food mark, wherein, default object information comprises default settlement information and/or default recommendation information, concrete, the pricing information of default settlement information such as food, default recommendation information can comprise the nutritional information of food, the evaluation information, the eating attention information of food, each dining room comparative information of food etc. of food.
Further, the default object information that generation module 64 generates food mark corresponding specifically can comprise: the default object information obtained can be converted to the information that result treatment terminal can directly show or play, such as binary message, voice messaging, bar code information etc., specifically not by the restriction of the embodiment of the present invention.
Transport module 65, for default object information is transferred to result treatment terminal, notifies user to make result treatment terminal by default object information.
As the optional embodiment of one, default object information can be transferred to result treatment terminal by transport module 65, to make result treatment terminal, default object information is notified user.Wherein, result treatment terminal comprises: settlement terminal and/or mobile terminal.Further, default settlement information can be transferred to settlement terminal or mobile terminal by transport module 65, thus user pays by settlement terminal or mobile terminal, and then user can consult or hear default object information, pays, pays in cash by card, Third-party payment etc.Further alternative, result treatment terminal, when user pays failed, can also be reported to the police.
Further, default recommendation information also can be transferred to mobile terminal by transport module 65, thus mobile terminal can run this default recommendation information, further, preset recommendation information including, but not limited to text message, voice messaging, pictorial information etc. can also be comprised, specifically not by the restriction of the embodiment of the present invention.
Further alternative, the device that the embodiment of the present invention provides can also comprise: characteristic extracting module 66 and memory module 67.
Acquisition module 61, the food container image that the food image that the food also for obtaining user's input identifies, food mark is corresponding, food mark are corresponding and food identify corresponding food price;
Characteristic extracting module 66, for extracting the feature of the characteristic sum food container image of food image, carries out classification based training, obtains the pre-set image feature that food mark is corresponding.
Memory module 67, for identifying corresponding pre-set image characteristic storage in default feature database by food.
Generation module 64 is passable, comprising: acquiring unit and generation unit, wherein:
Price acquiring unit, identifies corresponding food price for obtaining with the food of target image;
Generation unit, identifies corresponding default settlement information for generating food by the food price got.
The embodiment of the present invention provides a kind of food recognition device, acquisition module can obtain the target image of camera collection, and then parsing module can resolve target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, matching module can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, generation module can generate default object information corresponding to food mark, wherein, default object information comprises default settlement information and/or default recommendation information, default object information can be transferred to result treatment terminal by output module, to make result treatment terminal, default object information is notified user.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default object information corresponding to food mark, the cost of food identification can be reduced, the precision of food identification can be improved and improve the efficiency of food identification.
Refer to Fig. 7, Fig. 7 is the structural representation of a kind of server provided in the embodiment of the present invention, and wherein, the server that the present embodiment provides is corresponding with the method shown in Fig. 1, is the executive agent based on the food recognition methods shown in Fig. 1.As shown in Figure 7, this terminal 700 comprises: at least one processor 710, such as CPU, at least one input media 730, at least one output unit 740, storer 750, at least one bus 720.Wherein, communication bus 720 is for realizing the connection communication between these assemblies.Such as, input media 730 can comprise Trackpad, keyboard etc., and output unit 740 can comprise display screen.Storer 750 can be high-speed RAM storer, also can be non-labile storer (non-volatile memory), such as at least one magnetic disk memory.Storer 750 can also be optionally that at least one is positioned at the storage terminal away from aforementioned processor 710.Wherein processor 710 can the device shown in composition graphs 6, wherein stores batch processing code in storer 750, and processor 710 calls the program code stored in storer 750, for performing following operation:
Obtain the target image of camera collection;
Resolve target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image;
From default feature database, search the pre-set image feature of mating with target signature, identified by the food of the pre-set image feature determination target image mated with target signature;
Generate the default object information that food mark is corresponding, default object information comprises default settlement information and/or default recommendation information;
Default object information is transferred to result treatment terminal, to make result treatment terminal, default object information is notified user.
The embodiment of the present invention provides a kind of server, processor can obtain the target image of camera collection, and then parsing target image, obtain the target signature of target image, target signature comprises: food image characteristic sum food container characteristics of image, also can search the pre-set image feature of mating with target signature from default feature database, identified by the food of the pre-set image feature determination target image mated with target signature, the default object information that further generation food mark is corresponding, wherein, default object information comprises default settlement information and/or default recommendation information, and then default object information is transferred to result treatment terminal, to make result treatment terminal, default object information is notified user.Adopt the embodiment of the present invention, can identify the food image characteristic sum food container feature of target image, thus the food mark of target image can be determined, and then generate default object information corresponding to food mark, the cost of food identification can be reduced, the precision of food identification can be improved and improve the efficiency of food identification.
The embodiment of the invention also discloses a kind of food recognition system, as shown in Figure 8 A, is the structural representation of a kind of food recognition system provided in the embodiment of the present invention.As shown in Figure 8 A, the food recognition system that the embodiment of the present invention provides can comprise camera 10, result treatment terminal 20 and server 30, and wherein, camera 10 is connected with server 30, and result treatment terminal 20 and server 30 communicate to connect.Wherein, result treatment terminal 20, for when receiving the default object information that server 30 transmits, notifies user by default object information, the device of server 30 as shown in Figure 6 in embodiment.Result treatment terminal 20 in the embodiment of the present invention can comprise: settlement terminal and/or mobile terminal, the mobile terminal devices such as mobile terminal such as smart mobile phone, panel computer or Worn type smart machine, settlement terminal is machine for punching the card, checkout machine, the smart mobile phone supporting payment function etc. such as.It should be noted that, the system of the present embodiment can be applicable in said method.
As shown in Figure 8 B, be a kind of food recognition system schematic diagram provided in the embodiment of the present invention, server, settlement terminal, card and camera can be comprised.Camera can collect target data, be transferred to server, server processes rear output to target data and presets object information, default object information is transferred to settlement terminal by server, default object information can be notified user by settlement terminal, and user pays by being stuck on settlement terminal.It should be noted that, the system of the present embodiment can be applicable in said method.
Wherein, settlement terminal can be existing machine for punching the card, in the embodiment of the present invention, without the need to changing existing machine for punching the card, default object information server process in the embodiment of the present invention obtained by preset interface is transferred in machine for punching the card, and carries out showing or playing in machine for punching the card.Thus compatibility can be carried out with existing machine for punching the card, plug and play, eliminate the inconvenience needing to change existing machine for punching the card.
As shown in Figure 8 C, be the another kind of food recognition system schematic diagram provided in the embodiment of the present invention, server, settlement terminal, mobile terminal and camera can be comprised.Camera can collect target data, be transferred to server, server processes rear output to target data and presets object information, and default object information is transferred to settlement terminal by server, default object information can be notified user by settlement terminal, and user pays by mobile terminal.Wherein, default object information can comprise default settlement information, the pricing information of default settlement information such as food, and can be bar code etc., then user be undertaken paying etc. by mobile scanning terminal bar code.It should be noted that, the system of the present embodiment can be applicable in said method.
As in fig. 8d, be another the food recognition system schematic diagram provided in the embodiment of the present invention, server and mobile terminal can be comprised.Wherein, mobile terminal comprises camera, by the camera collection in mobile terminal to target data, be transferred to server, server processes rear output to target data and presets object information, default object information is transferred to mobile terminal by server, and default object information can be notified user by settlement terminal.Wherein, default object information comprises: preset recommendation information, the nutritional information of default recommendation information such as food, the evaluation information of food, the eating attention information of food, each dining room comparative information of food etc.It should be noted that, the system of the present embodiment can be applicable in said method.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
It should be noted that, in the above-described embodiments, the description of each embodiment is all emphasized particularly on different fields in certain embodiment, there is no the part described in detail, can see the associated description of other embodiments.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and involved action and module might not be that the embodiment of the present invention is necessary.
Step in embodiment of the present invention method can be carried out order according to actual needs and be adjusted, merges and delete.
Unit in embodiment of the present invention terminal can carry out merging, divide and deleting according to actual needs.
Unit described in the embodiment of the present invention, universal integrated circuit can be passed through, such as CPU (Central Processing Unit, central processing unit), or realized by ASIC (Application Specific Integrated Circuit, special IC).
The information prompting method provided the embodiment of the present invention above and terminal are described in detail, apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.

Claims (10)

CN201410464419.2A2014-09-122014-09-12Food recognition method, device and systemPendingCN104269003A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201410464419.2ACN104269003A (en)2014-09-122014-09-12Food recognition method, device and system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201410464419.2ACN104269003A (en)2014-09-122014-09-12Food recognition method, device and system

Publications (1)

Publication NumberPublication Date
CN104269003Atrue CN104269003A (en)2015-01-07

Family

ID=52160521

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201410464419.2APendingCN104269003A (en)2014-09-122014-09-12Food recognition method, device and system

Country Status (1)

CountryLink
CN (1)CN104269003A (en)

Cited By (33)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN104983292A (en)*2015-06-102015-10-21小米科技有限责任公司Food making method and device
CN105184697A (en)*2015-10-292015-12-23上海久点触控计算机系统股份有限公司Queuing machine of restaurant
CN105653636A (en)*2015-12-252016-06-08北京搜狗科技发展有限公司Information processing method and apparatus as well as information processing apparatus
CN107220650A (en)*2017-05-312017-09-29广州炒米信息科技有限公司Food image detection method and device
CN108205664A (en)*2018-01-092018-06-26美的集团股份有限公司A kind of food recognition methods and device, storage medium, computer equipment
CN108319641A (en)*2017-12-212018-07-24无锡雅座在线科技股份有限公司Dish information input method and device
CN108364420A (en)*2018-01-082018-08-03阿里巴巴集团控股有限公司Image-recognizing method and device and electronic equipment
CN108389316A (en)*2018-03-022018-08-10北京京东尚科信息技术有限公司Automatic vending method, device and computer readable storage medium
CN109035558A (en)*2018-06-122018-12-18武汉市哈哈便利科技有限公司A kind of commodity recognizer on-line study system for self-service cabinet
CN109118681A (en)*2018-08-222019-01-01明超Dining room service plate vegetable is had a prescription priced mechanism
CN109116434A (en)*2018-09-062019-01-01广东万濠精密仪器股份有限公司Instant detection method
CN109145839A (en)*2018-08-292019-01-04福建超汇信息技术有限公司Pricing method and computer readable storage medium based on Machine Vision Recognition
CN109241815A (en)*2018-06-292019-01-18北京百度网讯科技有限公司Detection method, device and the robot of user behavior
CN109389753A (en)*2017-08-082019-02-26刘凑华Bulk commodity self-help selling system
CN109659007A (en)*2018-11-132019-04-19平安科技(深圳)有限公司Dining room dining method of servicing, device, computer equipment and storage medium
CN109697481A (en)*2017-10-232019-04-30北京京东尚科信息技术有限公司Method and apparatus for determining article tag
WO2019083813A1 (en)*2017-10-242019-05-02Uber Technologies, Inc.On-demand coordinated comestible item delivery system
CN109830072A (en)*2019-02-262019-05-31魔珐(上海)信息科技有限公司The valuation of view-based access control model identification and cash device, control system and method
CN109887574A (en)*2019-01-312019-06-14广州市格利网络技术有限公司Health preserving with food and dietetic therapy guidance method and device based on food materials identification
CN109993623A (en)*2018-11-302019-07-09广州富港万嘉智能科技有限公司Item Information methods of exhibiting, system and electronic equipment based on image recognition
CN110246004A (en)*2019-05-212019-09-17深圳市梵高控股有限公司Method for pushing, device and the computer readable storage medium of food bill
CN110349358A (en)*2019-06-132019-10-18深圳市科拜斯物联网科技有限公司Food and drink settlement method, device, terminal and readable medium based on health control
CN110415463A (en)*2019-07-252019-11-05腾讯科技(深圳)有限公司A kind of method of payment and terminal
CN110598119A (en)*2019-09-232019-12-20广东小乘科技有限公司Method and system for providing fruit health package customized service
CN110763675A (en)*2018-07-252020-02-07淮阴师范学院 A food detection and reminder system for refrigerators
CN110880223A (en)*2018-09-062020-03-13阿里巴巴集团控股有限公司Commodity settlement method, server, electronic device, medium, and terminal
CN112115901A (en)*2020-09-252020-12-22广州市派客朴食信息科技有限责任公司High-accuracy food identification method
CN112115903A (en)*2020-09-252020-12-22广州市派客朴食信息科技有限责任公司Method for improving dish identification system identification precision based on deep learning
CN112132063A (en)*2020-09-252020-12-25广州市派客朴食信息科技有限责任公司Food identification method based on clustering quantification real-time matching
CN112132060A (en)*2020-09-252020-12-25广州市派客朴食信息科技有限责任公司Method for intelligently identifying and settling food
CN112508659A (en)*2021-02-052021-03-16浙江口碑网络技术有限公司Commodity settlement processing method and device, computing equipment and computer storage medium
CN112861886A (en)*2021-04-262021-05-28浙江口碑网络技术有限公司Information processing and model training method, device, electronic equipment and storage medium
CN114202683A (en)*2020-10-302022-03-18杭州食方科技有限公司Food information identification method and device, electronic equipment and computer readable medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
JP2000107006A (en)*1998-10-022000-04-18Toray Ind IncFoodstuff control device, foodstuff control method, foodstuff serving method and foodstuff
JP2001216571A (en)*2000-02-032001-08-10Glory LtdMethod and device for adjusting charge
CN102760335A (en)*2012-07-182012-10-31朱磊Intelligent wireless mobile cash register system and implementation method thereof
CN103034839A (en)*2012-12-042013-04-10南京航空航天大学Canteen payment system and method based on image recognition technology
CN103208156A (en)*2013-02-062013-07-17浙江科技学院Automatic catering settlement system and automatic catering settlement method
CN103646477A (en)*2013-11-142014-03-19成都博约创信科技有限责任公司Micro settlement system and method based on cloud platform
CN103824048A (en)*2012-11-152014-05-28东芝泰格有限公司Commodity recognition apparatus and commodity recognition method
CN103942569A (en)*2014-04-162014-07-23中国计量学院Chinese style dish recognition device based on computer vision

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
JP2000107006A (en)*1998-10-022000-04-18Toray Ind IncFoodstuff control device, foodstuff control method, foodstuff serving method and foodstuff
JP2001216571A (en)*2000-02-032001-08-10Glory LtdMethod and device for adjusting charge
CN102760335A (en)*2012-07-182012-10-31朱磊Intelligent wireless mobile cash register system and implementation method thereof
CN103824048A (en)*2012-11-152014-05-28东芝泰格有限公司Commodity recognition apparatus and commodity recognition method
CN103034839A (en)*2012-12-042013-04-10南京航空航天大学Canteen payment system and method based on image recognition technology
CN103208156A (en)*2013-02-062013-07-17浙江科技学院Automatic catering settlement system and automatic catering settlement method
CN103646477A (en)*2013-11-142014-03-19成都博约创信科技有限责任公司Micro settlement system and method based on cloud platform
CN103942569A (en)*2014-04-162014-07-23中国计量学院Chinese style dish recognition device based on computer vision

Cited By (42)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN104983292B (en)*2015-06-102019-02-19小米科技有限责任公司Method for making food and device
CN104983292A (en)*2015-06-102015-10-21小米科技有限责任公司Food making method and device
CN105184697A (en)*2015-10-292015-12-23上海久点触控计算机系统股份有限公司Queuing machine of restaurant
CN105653636B (en)*2015-12-252020-07-28北京搜狗科技发展有限公司Information processing method and device for information processing
CN105653636A (en)*2015-12-252016-06-08北京搜狗科技发展有限公司Information processing method and apparatus as well as information processing apparatus
CN107220650A (en)*2017-05-312017-09-29广州炒米信息科技有限公司Food image detection method and device
CN107220650B (en)*2017-05-312020-07-17广州炒米信息科技有限公司Food image detection method and device
CN109389753A (en)*2017-08-082019-02-26刘凑华Bulk commodity self-help selling system
CN109697481A (en)*2017-10-232019-04-30北京京东尚科信息技术有限公司Method and apparatus for determining article tag
WO2019083813A1 (en)*2017-10-242019-05-02Uber Technologies, Inc.On-demand coordinated comestible item delivery system
CN108319641A (en)*2017-12-212018-07-24无锡雅座在线科技股份有限公司Dish information input method and device
CN108364420A (en)*2018-01-082018-08-03阿里巴巴集团控股有限公司Image-recognizing method and device and electronic equipment
CN108205664A (en)*2018-01-092018-06-26美的集团股份有限公司A kind of food recognition methods and device, storage medium, computer equipment
US11461753B2 (en)2018-03-022022-10-04Beijing Jingdong Shangke Information Technology Co., Ltd.Automatic vending method and apparatus, and computer-readable storage medium
CN108389316A (en)*2018-03-022018-08-10北京京东尚科信息技术有限公司Automatic vending method, device and computer readable storage medium
CN109035558A (en)*2018-06-122018-12-18武汉市哈哈便利科技有限公司A kind of commodity recognizer on-line study system for self-service cabinet
CN109241815A (en)*2018-06-292019-01-18北京百度网讯科技有限公司Detection method, device and the robot of user behavior
CN109241815B (en)*2018-06-292019-10-01北京百度网讯科技有限公司Detection method, device and the robot of user behavior
CN110763675A (en)*2018-07-252020-02-07淮阴师范学院 A food detection and reminder system for refrigerators
CN109118681A (en)*2018-08-222019-01-01明超Dining room service plate vegetable is had a prescription priced mechanism
CN109145839A (en)*2018-08-292019-01-04福建超汇信息技术有限公司Pricing method and computer readable storage medium based on Machine Vision Recognition
CN109116434A (en)*2018-09-062019-01-01广东万濠精密仪器股份有限公司Instant detection method
CN110880223B (en)*2018-09-062022-03-04阿里巴巴集团控股有限公司Commodity settlement method, server, electronic device, medium, and terminal
CN110880223A (en)*2018-09-062020-03-13阿里巴巴集团控股有限公司Commodity settlement method, server, electronic device, medium, and terminal
CN109659007A (en)*2018-11-132019-04-19平安科技(深圳)有限公司Dining room dining method of servicing, device, computer equipment and storage medium
CN109993623A (en)*2018-11-302019-07-09广州富港万嘉智能科技有限公司Item Information methods of exhibiting, system and electronic equipment based on image recognition
CN109887574A (en)*2019-01-312019-06-14广州市格利网络技术有限公司Health preserving with food and dietetic therapy guidance method and device based on food materials identification
CN109830072A (en)*2019-02-262019-05-31魔珐(上海)信息科技有限公司The valuation of view-based access control model identification and cash device, control system and method
CN110246004A (en)*2019-05-212019-09-17深圳市梵高控股有限公司Method for pushing, device and the computer readable storage medium of food bill
CN110349358A (en)*2019-06-132019-10-18深圳市科拜斯物联网科技有限公司Food and drink settlement method, device, terminal and readable medium based on health control
CN110415463A (en)*2019-07-252019-11-05腾讯科技(深圳)有限公司A kind of method of payment and terminal
CN110598119A (en)*2019-09-232019-12-20广东小乘科技有限公司Method and system for providing fruit health package customized service
CN112115901A (en)*2020-09-252020-12-22广州市派客朴食信息科技有限责任公司High-accuracy food identification method
CN112115903A (en)*2020-09-252020-12-22广州市派客朴食信息科技有限责任公司Method for improving dish identification system identification precision based on deep learning
CN112132063A (en)*2020-09-252020-12-25广州市派客朴食信息科技有限责任公司Food identification method based on clustering quantification real-time matching
CN112132060A (en)*2020-09-252020-12-25广州市派客朴食信息科技有限责任公司Method for intelligently identifying and settling food
CN112132063B (en)*2020-09-252023-06-20广州市派客朴食信息科技有限责任公司Clustering quantification real-time matching-based food identification method
CN114202683A (en)*2020-10-302022-03-18杭州食方科技有限公司Food information identification method and device, electronic equipment and computer readable medium
CN114202683B (en)*2020-10-302025-03-14杭州食方科技有限公司 Food information identification method, device, electronic device and computer readable medium
CN112508659B (en)*2021-02-052021-09-07浙江口碑网络技术有限公司 Commodity settlement processing method, device, computing device, and computer storage medium
CN112508659A (en)*2021-02-052021-03-16浙江口碑网络技术有限公司Commodity settlement processing method and device, computing equipment and computer storage medium
CN112861886A (en)*2021-04-262021-05-28浙江口碑网络技术有限公司Information processing and model training method, device, electronic equipment and storage medium

Similar Documents

PublicationPublication DateTitle
CN104269003A (en)Food recognition method, device and system
CN110458649B (en) Information recommendation method, device, electronic device and readable storage medium
Aslan et al.Benchmarking algorithms for food localization and semantic segmentation
CN111984837B (en)Commodity data processing method, device and equipment
US11216862B2 (en)Smart shopping cart, server, smart shopping system and method
CN102538379B (en)Refrigerator food information management device and method
CN105574089B (en)Knowledge graph generation method and device, and object comparison method and device
US11562338B2 (en)Automated point of sale systems and methods
CN111882524A (en)Food weight calculation method and device and storage medium
CN111832590A (en)Article identification method and system
CN110033027A (en)A kind of item identification method, device, terminal and readable storage medium storing program for executing
KR20170015988A (en)Method, device and apparatus for processing menu data, and non-volatile computer storage medium
CN110931109A (en)Diet condition analysis method and system
Rahmana et al.A new texture feature for improved food recognition accuracy in a mobile phone based dietary assessment system
US11478096B2 (en)Food monitoring system
CN111460888A (en)Article identification method and device based on machine learning
CN111612026A (en)Method, device and system for obtaining evaluation result of product or class
CN111860211B (en)Tableware and reference object identification method, device and storage medium
CN111415328B (en)Method and device for determining article analysis data and electronic equipment
JP6345656B2 (en) Information processing system and crime prevention system for identifying articles used in home appliances
CN109949124A (en)The processing method of information, apparatus and system are searched in shop
RU2724797C1 (en)Cash register system and method for identification of courses on tray
CN112016582B (en)Dish recommending method and device
CN112966617B (en)Method for generating balance image, method and device for training image generation model
CN110163704A (en)The method and system of recommendation information

Legal Events

DateCodeTitleDescription
C06Publication
PB01Publication
C10Entry into substantive examination
SE01Entry into force of request for substantive examination
RJ01Rejection of invention patent application after publication
RJ01Rejection of invention patent application after publication

Application publication date:20150107


[8]ページ先頭

©2009-2025 Movatter.jp