Intelligent cooking processing ingredient monitoring method and system based on machine vision recognition

Through machine vision recognition technology, the identification and comparison of raw materials in food production is solved, and the problem of difficult to ensure the confidentiality of formulas and the accuracy of raw materials is achieved, efficient and accurate ingredients identification and intelligent monitoring are achieved, and product quality and production stability are ensured.

CN118942027APending Publication Date: 2024-11-12QINGDAO RICHEN FOODS

Patent Information

Application Number
CN202410935970.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the food production process, traditional methods are difficult to ensure the confidentiality of the formula and the accuracy of raw materials, especially when thousands of raw materials are involved, confusion and misinvestment are prone to occur, affecting production efficiency and product quality.

Method used

Using intelligent cooking processing ingredients monitoring methods and systems based on machine vision recognition, raw materials are pre-processed and featured extracted through image acquisition module and visual recognition module, and compared with preset recipe standard images to ensure the accuracy of the recipe. The correct delivery is achieved through the control module to control the feeding device.

Benefits of technology

It realizes rapid and accurate identification of raw materials, improves the accuracy and efficiency of ingredients, ensures product quality and consistency, protects the confidentiality of the formula, reduces the work burden of operators, and improves the synchronization of real-time alarms and data Continuity and stability of production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942027A_ABST
    Figure CN118942027A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent stir-frying processing ingredient monitoring method and system based on machine vision recognition, and relates to the technical field of intelligent stir-frying, and the method comprises the steps: a control module determines the coding information of N ingredients through searching a database, and transmits the coding information to an equipment side of an operator; an operator takes out N ingredients from a goods allocation and scans code information through a code scanning device, in the dish processing process, an image collection module is used for collecting images of a main material and the N ingredients, a visual recognition module is used for conducting preprocessing and feature extraction on the images, the extracted features are compared with a preset formula standard image, and a food processing result is obtained. If the comparison succeeds, the formula requirement is met, otherwise, an output result of the visual identification module is generated; and the control module controls the feeding device to feed the main materials and the auxiliary materials meeting the formula requirements to the dish processing device. The method is used for quickly and accurately identifying the raw materials in the production process, so that the confidentiality of a formula and the correctness of the raw materials are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cooking, and in particular to an intelligent cooking processing ingredient monitoring method and system based on machine vision recognition. Background Art

[0002] In the food production process, it is crucial to ensure the confidentiality of the formula and the accuracy of the raw materials. Traditional methods usually rely on labels (such as codes, batch numbers, quantities, etc.) to identify materials. However, when there are thousands of raw materials involved in the batching and feeding, operators are prone to confusion and mis-feeding, which not only affects production efficiency, but is also likely to threaten product quality. Therefore, while ensuring the confidentiality of the formula, developing a technical means to quickly select ingredients that match the formula and effectively prevent mis-feeding is an urgent problem that food processing companies need to solve. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent cooking ingredient monitoring method and system based on machine vision recognition, so as to realize the rapid and accurate identification of raw materials in the production process, thereby ensuring the confidentiality of the recipe and the correctness of the raw materials.

[0004] In a first aspect, an embodiment of the present invention provides an intelligent cooking ingredient monitoring method based on machine vision recognition, comprising:

[0005] The control module searches the database according to the preset recipe formula, determines the coding information of the required N kinds of ingredients, and transmits the coding information of the N kinds of ingredients to the device side of the operator;

[0006] The operator takes out N kinds of ingredients matching the coding information of the N kinds of ingredients from the cargo position, and scans the coding information of the cargo position through a code scanning device, wherein each cargo position stores one kind of ingredient correspondingly, and each cargo position is provided with a unique coding picture;

[0007] During the dish processing, the image acquisition module is used to collect images of the main ingredients and N kinds of ingredients. The visual recognition module preprocesses and extracts features from the images, and compares the extracted features with the preset recipe standard images. If the comparison is successful, it meets the recipe requirements. Otherwise, it does not meet the recipe requirements, and the output result of the visual recognition module is generated;

[0008] According to the output result of the visual recognition module, the control module controls the feeding device to feed the main ingredients and side ingredients that meet the recipe requirements into the dish processing device according to the processing sequence of the recipe.

[0009] In a possible implementation, the above method embodiment further includes: preprocessing and extracting features from the image, and comparing the extracted features with a preset standard image of a recipe, including:

[0010] The image is preprocessed to obtain a region of interest of the image; each feature point in the region of interest is extracted, and the extracted feature points are classified and quantified to obtain feature parameters of the feature points; the feature parameters of the feature points are compared with feature parameters of a preset standard image of a recipe formula.

[0011] In another possible implementation, it also includes: the control module transmits the composition ratio information of the N ingredients to the equipment side of the batching personnel; the batching personnel weighs and proportions the N ingredients into composite auxiliary materials according to the composition ratio of the N ingredients.

[0012] In a possible implementation, each cargo location is provided with a sensing element, and the sensing element is connected to an alarm device. The sensing element is used to control the alarm device to sound an alarm when the weight of the cargo location is lower than a set requirement, so as to remind the operator to replenish the goods in time.

[0013] In a possible implementation, after the operator scans the coding information of each cargo location on the shelf through a barcode scanning device, the following steps are also included:

[0014] The code scanning device is connected to the server for communication, and the code scanning device synchronizes the scanning results of the coding information of each cargo location to the server;

[0015] The server updates the scanning result to the database, and the database stores the coding information, quantity information, location information of the cargo location and the corresponding relationship between the shelves.

[0016] In a possible implementation, the database stores recipes in encrypted form and configures different access rights for users of different levels.

[0017] In a possible implementation, after the control module transmits the coding information of the N kinds of ingredients to the equipment side of the operator, it also includes:

[0018] The control module controls the indicator lights of the shelves corresponding to N kinds of ingredients on the shelf to light up, wherein the control module is in communication with the control unit of the shelf; the operator scans the coding information of each shelf on the shelf through a code scanning device, including: the operator scans the coding information of each shelf on which the indicator lights are lit up through a code scanning device.

[0019] In a possible implementation, the coded image is a QR code or a barcode.

[0020] In a possible implementation, the barcode scanning device is an industrial barcode scanning gun that supports barcode scanning software installation and secondary customized development.

[0021] In a second aspect, the present invention provides an intelligent cooking ingredient monitoring system based on machine vision recognition, comprising:

[0022] Control module, code scanning device, image acquisition module and visual recognition module;

[0023] The control module is used to determine the coding information of the required N kinds of ingredients according to the preset recipe formula, and transmit the coding information of the N kinds of ingredients to the equipment side of the operator;

[0024] The code scanning device is used to accept the operation of the operator, scan the coding information of each shelf on the shelf, and find out the N ingredients that match the coding information of the N ingredients, wherein each shelf stores one ingredient and each shelf is provided with a unique coding picture;

[0025] An image acquisition module is used to collect images of main ingredients and side ingredients during the dish processing;

[0026] A visual recognition module is used to preprocess and extract features from the image, compare the extracted features with a preset standard image of a recipe, and if the comparison is successful, the recipe requirement is met; otherwise, the recipe requirement is not met, and an output result of the visual recognition module is generated;

[0027] The control module is also used to control the feeding device to feed the main ingredients and ingredients that meet the recipe requirements into the dish processing device according to the processing order of the recipe recipe based on the output results of the visual recognition module.

[0028] The intelligent cooking ingredient monitoring method and system based on machine vision recognition provided by the present invention has significant beneficial effects, which are mainly reflected in the following aspects:

[0029] 1. Efficient and accurate ingredient identification: Through machine vision recognition technology, the system can quickly and accurately identify the raw materials required in the production process, greatly improving the correctness and efficiency of ingredients, effectively avoiding human errors, and ensuring product quality and consistency.

[0030] 2. Recipe confidentiality and raw material correctness: The system stores recipes in encrypted form in the database and configures different access rights for users at different levels, effectively protecting the confidentiality of the recipes. At the same time, the system uses code scanning equipment and machine vision recognition technology to ensure the correctness of the raw materials and avoid confusion or incorrect use of raw materials.

[0031] 3. Intelligent monitoring and operation: The system realizes intelligent monitoring and operation of the cooking ingredients process through the coordinated work of the control module, code scanning equipment, image acquisition module and visual recognition module. The operator only needs to perform simple operations according to the system prompts to complete the selection and placement of ingredients, which greatly reduces the workload and improves work efficiency.

[0032] 4. Real-time alarm and replenishment reminder: The system realizes real-time monitoring of the weight of the cargo space by setting up sensing elements and alarm devices at the cargo space. When the cargo space weight is lower than the set requirement, the alarm device will automatically alarm to remind the operator to replenish the cargo in time, thus ensuring the continuity and stability of production.

[0033] 5. Data synchronization and update: The system realizes real-time synchronization and update of the scanning results of the cargo location coding information through the communication connection between the scanning device and the server. This not only ensures the accuracy and consistency of the data, but also provides strong support for subsequent data analysis and decision-making.

[0034] In summary, the intelligent cooking ingredient monitoring method and system based on machine vision recognition provided by the present invention has the advantages of high efficiency and accuracy, recipe confidentiality, intelligent monitoring, real-time alarm, data synchronization and flexibility, which brings significant benefits and value to the cooking processing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A schematic diagram of a smart shelf system provided by an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of a scanning device provided by an embodiment of the present invention;

[0038] Figure 3 A flow chart of a method for monitoring ingredients for intelligent cooking based on machine vision recognition provided by an embodiment of the present invention;

[0039] Figure 4 A schematic diagram of an intelligent cooking ingredient monitoring architecture based on machine vision recognition provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0041] The present invention provides an intelligent cooking ingredient monitoring method based on machine vision recognition. The method realizes rapid and accurate recognition of raw materials in the production process by applying an intelligent shelf management system and advanced vision recognition technology, thereby ensuring the confidentiality of the recipe and the correctness of the raw materials.

[0042] First, the smart shelf management system provided by the present invention comprises: a smart shelf and a code scanning device. The smart shelf comprises a shelf body with at least one shelf layer and a plurality of cargo spaces on each shelf layer, each cargo space being used to store a kind of ingredient. Figure 1 The schematic diagram of a smart shelf is shown as an example, and each shelf body and cargo position is provided with a unique coded image. The coded image can be a specific visual identifier to mark the raw materials, for example, these identifiers can be colors, shapes, patterns or specific QR codes or bar codes. Currently, the more commonly used coded images are generally QR codes and bar codes.

[0043] like Figure 1 As shown, each cargo position is provided with a sensing element, and the sensing element is connected to an alarm device. The sensing element is used to detect the weight of each cargo position. When the control unit of the smart shelf determines that the weight is lower than the set requirement, the alarm device is controlled to alarm to remind the operator to replenish the goods in time. For example, the sensing element is a weight sensor. In addition, each cargo position can also be provided with an indicator light. When the control unit of the smart shelf receives a lighting instruction, the indicator light of the corresponding cargo position can be lit.

[0044] Figure 2 An exemplary code scanning device is shown, which can be a personal digital assistant (PDA) device. The PDA device supports the installation of code scanning software and secondary custom-developed industrial code scanning guns, such as supporting Windows or Android software installation. The code scanning software used in the PDA supports two upload methods: one is offline code scanning and then local storage, and wired upload after connecting to the network cable, and the other is wireless real-time upload.

[0045] In addition, the shelf body of the smart shelf in the embodiment of the present invention is also provided with a control unit. The control unit can establish wireless communication with other devices, for example, the control unit can communicate with the control module of the smart cooking system, so that the code scanning device can synchronize the scanning results of each shelf body and cargo position to the manufacturing execution system (MES) of the server.

[0046] Exemplarily, the correspondence between the shelf body and the cargo position is shown in Table 1. The identifications (SLF_ID) of the 7 layers of shelves corresponding to a shelf body are SLF-01, SLF-02, SLF-03, SLF-04, SLF-05, SLF-06 and SLF-07 respectively. Each layer of the shelf is provided with 6 rows of cargo positions, and the coding images corresponding to the first row of cargo positions to the sixth row of cargo positions are CARRIER_1, CARRIER_2, CARRIER_3, CARRIER_4, CARRIER_5 and CARRIER_6. The coding information of the first row of cargo positions on the first layer of the shelf is PL000001, the coding information of the first row of cargo positions on the second layer of the shelf is PL001001, and so on.

[0047] Table 1

[0048] SLF_ID CARRIER_1 CARRIER_2 CARRIER_3 CARRIER_4 CARRIER_5 CARRIER_6 SLF-01 PL000001 PL000002 PL000003 PL000004 PL000005 PL000006 SLF-02 PL001001 PL001002 PL001003 PL001004 PL001005 PL001006 SLF-03 PL002001 PL002002 PL002003 PL002004 PL002005 PL002006 SLF-04 PL003001 PL003002 PL003003 PL003004 PL003005 PL003006 SLF-05 PL004001 PL004002 PL004003 PL004004 PL004005 PL004006 SLF-06 PL005001 PL005002 PL005003 PL005004 PL005005 PL005006 SLF-07 PL006001 PL006002 PL006003 PL006004 PL006005 PL006006

[0049] The operator can enter the ingredient code in the system on the equipment side to query the current corresponding cargo position of the ingredient, that is, the cargo position. For example, the system is preset with a database shown in Table 2, which includes the ingredient code, the cargo position and the latest scanning time.

[0050] Table 2

[0051] Ingredients Code Cargo location Scan time PL000001 (SLF-01, CARRIER_1) 2024 / 07 / 058:00 PL001001 (SLF-02, CARRIER_1) 2024 / 07 / 058:03 PL002001 (SLF-03, CARRIER_1) 2024 / 07 / 059:03 ...... ...... ......

[0052] In Table 2, the cargo location corresponding to the ingredient code PL000001 is located in the first row of the first shelf SLF-01, and the latest scan time is 2024 / 7 / 058:00. When the operator enters the ingredient code PL000001, the corresponding cargo location can be determined, so that the required ingredients can be accurately taken out from the corresponding cargo location. Moreover, because all ingredients are only displayed with numbers and the original names are not shown, the operator does not know the specific names of the raw materials, so the formula can be kept confidential for the operator.

[0053] Based on the above-mentioned intelligent shelf management system, an embodiment of the present invention provides an intelligent cooking ingredient monitoring method based on machine vision recognition, which can be executed by a control module of a manufacturing execution system (MES), such as Figure 3 As shown, the method comprises the following steps:

[0054] S301, the control module searches the database according to the preset recipe formula, determines the coding information of the required N kinds of ingredients, and transmits the coding information of the N kinds of ingredients to the device side of the operator;

[0055] S302, the operator takes out N kinds of ingredients matching the coding information of the N kinds of ingredients from the cargo location, and scans the coding information of the cargo location through a code scanning device, wherein each cargo location stores one kind of ingredient and each cargo location is provided with a unique coding picture;

[0056] S303, during the dish processing, the image acquisition module is used to collect images of the main ingredient and N kinds of ingredients, the visual recognition module preprocesses and extracts features from the images, and compares the extracted features with the preset recipe standard images. If the comparison is successful, it meets the recipe requirements, otherwise it does not meet the recipe requirements, and an output result of the visual recognition module is generated;

[0057] S304, according to the output result of the visual recognition module, the control module controls the feeding device to feed the main ingredients and the side ingredients that meet the recipe requirements into the dish processing device according to the processing sequence of the recipe.

[0058] In the above S303, the visual recognition module first preprocesses the image to obtain the region of interest of the image; extracts each feature point in the region of interest, and classifies and quantifies the extracted feature points to obtain the feature parameters of the feature points; and compares the feature parameters of the feature points with the feature parameters of the standard image of the preset recipe formula. Specifically, the visual recognition module classifies and quantifies the extracted feature points to form a series of comparable numerical parameters. These parameters may include the position, color, shape, texture, etc. of the feature points, which together constitute the unique "fingerprint" of the image. Next, the visual recognition module compares these numerical parameters with the feature parameters in the preset standard image library of the recipe formula. This process may involve complex algorithms and a large amount of calculations to ensure the accuracy and efficiency of the match. During the comparison process, the visual recognition module considers multiple dimensions and factors, including the similarity, distribution pattern, weight distribution, etc. of the feature points. These factors jointly determine the degree of match between the image and the standard image. If the degree of match between the image and a standard image exceeds a preset threshold, the visual recognition module will consider that the image matches the standard image and output the corresponding result. The result may be a recipe name, a list of ingredients, cooking steps, etc., depending on the information contained in the preset standard image library. For example, the image acquisition module may be a camera or other device, and the visual recognition module may be a processing device integrated with an AI function processor.

[0059] However, if the image does not match all standard images to a certain degree, the visual recognition module will consider the image unrecognizable and output a corresponding error message. In this case, it may be necessary to retake the image or provide more information to assist in recognition. In short, through the preprocessing, feature extraction and comparison process of the visual recognition module, the system can automatically recognize the ingredients in the image and provide users with convenient recipe recommendations and cooking guidance services.

[0060] In the above S302, in one possible embodiment, after receiving N kinds of ingredient information, the operator can input the ingredient code PL000001 on the device side, find and determine the corresponding cargo position, so as to accurately take out the required ingredients from the corresponding cargo position. In another possible embodiment, after determining the N kinds of ingredients, the control module can control the indicator lights of the cargo positions corresponding to the N kinds of ingredients on the shelf to light up, so that the operator does not need to find the cargo position of the ingredients, and can directly take out the ingredients from the cargo position with the indicator lights on. In the process of taking out the ingredients, the corresponding cargo position is scanned by a scanning device, and the scanning device connected to the server communicates with the server to synchronize the scanning results of the coding information of each cargo position to the server, and the server updates the scanning results to the database, which stores the coding information, quantity information, location information of the cargo position and the corresponding relationship of the shelf. This process realizes data management by collecting each action of the operator, sorting and analyzing the in-and-out information of various ingredients, which is helpful for subsequent product traceability. It should be understood that the preset recipes are stored in an encrypted form in the database, and the database is configured with different access rights for users at different levels, and different confidentiality levels are adopted according to the importance of the recipes. In this way, the operation rights of different users to the recipe information can be limited, thereby ensuring the confidentiality of the recipes.

[0061] In a possible embodiment, the control module can also transmit the composition ratio information of N kinds of ingredients to the equipment side of the batching personnel; the batching personnel weigh and proportion the N kinds of ingredients into composite auxiliary ingredients according to the composition ratio of the N kinds of ingredients, and can also affix a unique coded picture to the composite auxiliary ingredients. In this way, on the one hand, the configuration of the ingredients can be completed in advance, which is convenient for direct use in subsequent cooking. On the other hand, some small ingredients that can be compounded separately are compounded together, and the composite ingredients are numbered and then enter the production workshop. The production workshop is then weighed by the batching room according to the number of numbers, so that the confidentiality effect can be achieved well. Generally, the process is carried out by at least two batchers, each of whom prepares a part, and the entire process is reviewed and approved by the R&D personnel.

[0062] Based on the above-described intelligent cooking ingredient monitoring method, its beneficial effects are mainly reflected in the following aspects:

[0063] 1. Enhanced formula confidentiality: By only displaying the ingredient number instead of its original name, operators do not need to know the specific raw material name during the execution process, thus achieving a high degree of formula confidentiality. This has important commercial value for companies that need to protect unique formulas or intellectual property rights.

[0064] 2. Improve processing efficiency: The visual recognition module automatically compares the images of the main ingredients and side ingredients with the preset recipe standard images, greatly reducing the time and error rate of manual comparison, making the cooking process faster and more accurate.

[0065] 3. Realize digital management: Scan the code to record the code information, quantity information, location information, etc. of each cargo location, and update it to the database in real time, so as to realize the accurate tracking and digital management of the in and out information of ingredients. This not only helps product traceability, but also provides strong support for subsequent inventory management, order tracking, etc.

[0066] 4. Improve formula flexibility: Since formula information is stored in the database in encrypted form and different access rights can be configured for users at different levels, this allows companies to flexibly adjust formulas according to different needs without worrying about the leakage of formula information.

[0067] 5. Optimize the ingredient configuration process: By affixing a unique coding picture to the composite auxiliary materials, the pre-configuration of the ingredients and the rapid connection with the subsequent cooking processing are achieved, which not only improves work efficiency, but also further enhances the confidentiality of the recipe.

[0068] In summary, the intelligent cooking ingredient monitoring method based on machine vision recognition not only improves processing efficiency and product quality, but also realizes high confidentiality and data management of the formula through a series of technical means, providing a strong guarantee for the sustainable development of the enterprise.

[0069] Figure 4 It is a structural diagram of an intelligent cooking ingredient monitoring system based on machine vision recognition provided by the present invention, which specifically includes: a control module 401, a code scanning device 402, an image acquisition module 403 and a visual recognition module 404;

[0070] The control module 401 is used to determine the coding information of the required N kinds of ingredients according to the preset recipe formula, and transmit the coding information of the N kinds of ingredients to the device side of the operator;

[0071] The code scanning device 402 is used to accept the operation of the operator, scan the coding information of each shelf on the shelf, and find out N ingredients that match the coding information of N ingredients, wherein each shelf stores one ingredient and each shelf is provided with a unique coding picture;

[0072] The image acquisition module 403 is used to acquire images of the main ingredients and the side ingredients during the dish processing;

[0073] The visual recognition module 404 is used to pre-process and extract features from the image, and compare the extracted features with a preset standard image of a recipe. If the comparison is successful, the recipe requirement is met; otherwise, the recipe requirement is not met, and an output result of the visual recognition module is generated;

[0074] The control module 401 is also used to control the feeding device to feed the main ingredients and side ingredients that meet the recipe requirements into the dish processing device according to the processing sequence of the recipe recipe based on the output results of the visual recognition module.

[0075] The specific implementation scheme of the control device provided in the embodiment of the present invention can refer to the implementation scheme of any of the above monitoring methods, which will not be described in detail here.

[0076] The present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, each step of the monitoring method of a heating constant-humidity heat pump direct expansion unit provided in the first embodiment is implemented.

[0077] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0078] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0079] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0080] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0081] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0083] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0084] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0085] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent cooking ingredient monitoring method based on machine vision recognition, characterized in that: include: The control module searches the database according to the preset recipe formula, determines the coding information of the required N kinds of ingredients, and transmits the coding information of the N kinds of ingredients to the device side of the operator; The operator takes out N kinds of ingredients matching the coding information of the N kinds of ingredients from the cargo position, and scans the coding information of the cargo position through a code scanning device, wherein each cargo position stores one kind of ingredient correspondingly, and each cargo position is provided with a unique coding picture; During the dish processing, the image acquisition module is used to collect images of the main ingredients and N kinds of ingredients. The visual recognition module preprocesses and extracts features from the images, and compares the extracted features with the preset recipe standard images. If the comparison is successful, it meets the recipe requirements. Otherwise, it does not meet the recipe requirements, and the output result of the visual recognition module is generated; According to the output result of the visual recognition module, the control module controls the feeding device to feed the main ingredients and side ingredients that meet the recipe requirements into the dish processing device according to the processing sequence of the recipe.

2. The monitoring method according to claim 1, characterized in that: Preprocessing and feature extraction are performed on the image, and the extracted features are compared with a preset standard image of a recipe, including: Preprocessing the image to obtain a region of interest of the image; Extracting each feature point in the region of interest, and classifying and quantifying the extracted feature points to obtain feature parameters of the feature points; The characteristic parameters of the characteristic points are compared with the characteristic parameters of a preset standard image of a recipe.

3. The monitoring method according to claim 1, characterized in that: Also includes: The control module transmits the composition ratio information of N kinds of ingredients to the equipment side of the batching personnel; The batching personnel weigh and mix the N kinds of ingredients into composite auxiliary materials according to the composition ratio of the N kinds of ingredients.

4. The monitoring method according to any one of claims 1 to 3, characterized in that: Each cargo position is provided with a sensing element, and the sensing element is connected to an alarm device. The sensing element is used to control the alarm device to sound an alarm when the weight of the cargo position is lower than the set requirement, so as to remind the operator to replenish the goods in time.

5. The monitoring method according to any one of claims 1 to 3, characterized in that: After the operator scans the code information of each shelf position through the barcode scanning device, it also includes: The code scanning device is connected to the server for communication, and the code scanning device synchronizes the scanning results of the coding information of each cargo location to the server; The server updates the scanning result to the database, and the database stores the coding information, quantity information, location information of the cargo location and the corresponding relationship between the shelves.

6. The monitoring method according to claim 5, characterized in that: The database stores recipes in encrypted form and configures different access rights for users of different levels.

7. The monitoring method according to claim 1, characterized in that: After the control module transmits the coding information of the N kinds of ingredients to the equipment side of the operator, it also includes: The control module controls the indicator lights of the shelves corresponding to the N kinds of ingredients on the shelf to light up, wherein the control module is in communication connection with the control unit of the shelf; The operator uses the barcode scanning device to scan the coding information of each shelf location, including: The operator scans the coding information of each cargo position with the indicator lights on on the shelf through a code scanning device.

8. The monitoring method according to any one of claims 1 to 3, characterized in that: The coded image is a QR code or a barcode.

9. The monitoring method according to any one of claims 1 to 3, characterized in that: The barcode scanning device is an industrial barcode scanning gun that supports barcode scanning software installation and secondary customized development.

10. An intelligent cooking ingredient monitoring system based on machine vision recognition, characterized in that: include: Control module, code scanning device, image acquisition module and visual recognition module; The control module is used to determine the coding information of the required N kinds of ingredients according to the preset recipe formula, and transmit the coding information of the N kinds of ingredients to the equipment side of the operator; The code scanning device is used to accept the operation of the operator, scan the coding information of each shelf on the shelf, and find out the N ingredients that match the coding information of the N ingredients, wherein each shelf stores one ingredient and each shelf is provided with a unique coding picture; An image acquisition module is used to collect images of main ingredients and side ingredients during the dish processing; A visual recognition module is used to preprocess and extract features from the image, compare the extracted features with a preset standard image of a recipe, and if the comparison is successful, the recipe requirement is met; otherwise, the recipe requirement is not met, and an output result of the visual recognition module is generated; The control module is also used to control the feeding device to feed the main ingredients and ingredients that meet the recipe requirements into the dish processing device according to the processing order of the recipe recipe based on the output results of the visual recognition module.

Citation Information

Patent Citations

  • Multi-material weighing method

    CN104316154A

  • Batching, feeding and weighing system

    CN110467009A

  • Food making safety monitoring method, device and system

    CN113077135A

  • Full-automatic intelligent cooking system

    CN113208406A

  • Intelligent cooking system and method

    CN115381298A

Cited By

  • Special meal beverage blending system based on laser calibration and intelligent batching

    CN120299627A