49 results about "Food recognition" patented technology

A method and system for analyzing at least one food item on a food plate is disclosed. A plurality of images of the food plate is received by an image capturing device. A description of the at least one food item on the food plate is received by a recognition device. The description is at least one of a voice description and a text description. At least one processor extracts a list of food items from the description; classifies and segments the at least one food item from the list using color and texture features derived from the plurality of images; and estimates the volume of the classified and segmented at least one food item. The processor is also configured to estimate the caloric content of the at least one food item.

The present invention relates to a method for automatic food recognition by means of portable devices equipped with digital cameras.With this system, it is possible to identify a previously established food menu. To this purpose, a semi-automated method of segmentation is applied to delineate the regions in which each type of food in an image of a plate of food, captured by a user.Pattern recognition techniques are used in images, integrated into a system whose goal is to label each type of food contained in the photo of a plate of food. No type of preprocessing is performed to correct deficiencies in capturing the image, just using the auto-focus component present in the portable device to capture a clear image.

The invention relates to the fields of intelligent refrigerators, food management, image recognition and the like, in particular to an intelligent-refrigerator based food recognition method. The intelligent-refrigerator based food recognition method is provided to solve the technical problems in the prior art, so that when people use the intelligent refrigerators, repeated manual input operations for newly-added food are reduced or omitted, time is saved, and use efficiency is improved. The method includes collecting food information by the intelligent refrigerators and matching food image information by cloud servers.

The invention discloses a food recognition method at an intelligent terminal, and the method is based on a convolution neural network method, and comprises a training process and an automatic classification process. The training process comprises the following steps: firstly building a training sample set; secondly constructing a network structure model according to a classic AlexNet network; thirdly carrying out network training through an open-source Caffe network framework, and continuously adjusting initial conditions so as to obtain an optimal network structure model and parameter configuration. The automatic classification process comprises the steps: enabling a to-be-recognized image photographed by a user to serve as an input image of the network; configuring the network according to parameters of a trained network structure in a computer, and classifying input images; and finally displaying the former 10 optimal classification results to the user. The method can achieve the automatic recognition of the type of food at the intelligent terminal, is high in speed, is small in storage capacity, is high in accuracy, and is good in user experience.

The invention relates to the field of refrigerators, and provides an intelligent food recommending refrigerator and a method. A menu is recommended to a user; and meanwhile, food which is suitable for the user and the food which is unsuitable for the user in the refrigerator are marked. The refrigerator comprises a health data collection system, a data storage system, a data analysis system, a face recognition system, a food recognition system, a weather information collection system, a display label and a display system. In summary, the method comprises the following steps: firstly collecting face data; collecting health data, weather data and food data; analyzing the health data, the weather data and the food data to obtain the menus which are suitable for various users in a family and appropriate food; and finally recognizing the identity of the user close to the refrigerator, displaying the menus on the refrigerator, and displaying the display labels of the food in the refrigerator with different color books according to whether the food is suitable for the user or not. The intelligent food recommending refrigerator is suitable for families with high-quality life demands.

The present disclosure provides a system and method for determining a nutritional value of a food item. The system and method utilizes a food container as a model to adjust various types of distortions that exists in an instant image of the food container that retains the food item. The instant image may be compared to the model image of the food container to correct any distortions. The food container includes a boundary which has a predetermined color. The predetermined color of the boundary can be used to adjust the color configuration of the instant image, thereby increasing the accuracy of the food identification.

The invention discloses a food fresh-keeping storehouse with a full-automatic vending function. The food fresh-keeping storehouse comprises a storehouse body, a computer network platform, a food storage bin, an environment adjusting system, a food identification code recognition system, an automatic-warehouse-in-out system and a computer centralized control system. The food fresh-keeping storehouse is capable of storing and keeping fresh of a plurality of varieties of food and is provided with the full-automatic vending function and an internet communication function. The invention further discloses a vending method of the food fresh-keeping storehouse with the full-automatic vending function. The method includes that the food fresh-keeping storehouse for storing the varieties of the food is set close to users and connected into the internet, a commercial tenant uploads related data to a commercial tenant website and the computer network platform of the food fresh-keeping storehouse with the full-automatic vending function; a user logs in the network platform of the food fresh-keeping storehouse with the full-automatic vending function to selectively purchase the food, pays via a third party payment platform to complete a transaction to obtain a pickup identification code for the purchased food, and goes to the food fresh-keeping storehouse with the full-automatic vending function to pick up the purchased food on the basis of the food identification code. The food fresh-keeping storehouse with the full-automatic vending function is convenient, quick, safe and reliable and is provided with an extremely high commercial value.

The invention discloses an intelligent refrigerator system, which is characterized by comprising a refrigerator control module, a data processing module, a memory module, a system broadcasting module, a food recognition module, and a wireless communication module, wherein the refrigerator control module comprises a refrigerator control panel and a refrigerator display panel; the food recognition module comprises a radio frequency tag, an antenna and a radio card reader; the wireless communication module comprises a wifi unit, a home router, a remote cloud server and a remote control terminal. The intelligent refrigerator system disclosed by the invention adopts an RFID (Radio Frequency Identification) mode, the recognition rate of input of food information is high, the food information can be viewed by a mobile terminal anytime and anywhere, and the intelligent refrigerator system can facilitate the viewing and information management of a user.

The invention relates to a method and system of identifying a target object in an image, and a method and system of identifying food in a refrigerator. The method of identifying a target object in an image includes the steps: acquiring a training image, utilizing the training image to establish an image identification model; and acquiring a test image, matching the test image with the image identification model, and realizing identification of a target object in the test image, wherein performing normalization processing on the acquired training image and the acquired test image, and mapping the training image and the test image to a unified space; and / or performing regularization processing during the process of establishing the image identification model to enable the image identification model to express full sample distribution. The method of identifying a target object in an image enables expression on the test data of the image identification model to approach to the expression on the training data as possible, thus realizing consistency of image identification and improving image identification accuracy.

A method for automatic food recognition by using portable devices equipped with digital cameras. With this system, it is possible to identify a previously established food menu. To this purpose, a semi-automated method of segmentation is applied to delineate the regions in which each type of food in an image of a plate of food, captured by a user. Pattern recognition techniques are used in images, integrated into a system whose goal is to label each type of food contained in the photo of a plate of food. No type of preprocessing is performed to correct deficiencies in capturing the image, just using the auto-focus component present in the portable device to capture a clear image.

The invention provides a food image big data collecting method and system, and a food recognition method. The collecting method comprises the steps of constructing a collecting device for collecting the real scene of food, wherein the collecting device is provided with an accommodation cavity, and a video collecting device for collecting the video of the food is installed in the accommodation cavity of the collecting device; constructing a rotary tray for rotating the food and mounting the rotary tray in the accommodation cavity of the collecting device; after the food is placed on the rotating tray in different shapes, controlling the rotating tray to rotate, and controlling the video collecting device to collect the video of the rotating food; and converting food video collected in a preset period of time into corresponding food images to obtain food images at multiple angles. Therefore, through the collecting method provided by the invention, a large number of rich food images can be obtained, and furthermore, a recognition model trained by the food images obtained by the method has high recognition accuracy, so that the recognition model can accurately identify the food type.

The invention provides a packaged food recognition method and device, and the method comprises the steps: obtaining a packaging image of to-be-recognized food, and recognizing an ingredient information region and / or a nutritional ingredient information region from the packaging image through a pre-trained and built region recognition model; recognizing each row of character regions in the ingredient information region and / or the nutritional ingredient information region through a pre-trained and established character region recognition model; identifying characters in each row of character regions through the character recognition model to obtain ingredient information and / or nutritional ingredient information of the food; and acquiring health information of a target user, and judging whether the food has a risk of influencing the health state of the target user or not according to the ingredient information and / or the nutritional ingredient information and the health information. By applying the scheme provided by the invention, the problem that a user cannot accurately judge whether food is suitable for eating or not in the prior art can be solved.

The invention discloses a rapid food recognition method based on a Markov random field, and mainly solves the problem that food is difficult to recognize due to the conditions that the food lacks of feature points and the shapes of the food are not fixed in food image recognition. The realization process of the rapid food recognition method comprises the following steps: (1) establishing a retrieval database, extracting feature descriptors in retrieval images, and constructing index files; (2) extracting feature descriptors of queried images; (3) calculating out the likelihood score of the queried images in food label types of the retrieval base according to the feature descriptors; (4) according to the likelihood score of the queried images in the label type food in the retrieval database and according to the condition probability between labels in menus of queried people, constructing a Markov energy formula and a smallest energy formula so as to obtain the food label type of the queried images. According to the rapid food recognition method disclosed by the invention, rapid and accurate recognition and classification can be performed on the food images, the food images can be easily expanded to a larger retrieval database and a queried image set, and the rapid food recognition method can be used for cultivating a healthy diet manner.

The invention discloses an intelligent management method of a refrigerator. The intelligent management method comprises the steps of providing an intelligent manager host and a camera, wherein the intelligent manager host comprises a mainboard module, a radiator, an onboard chip, a memory card, an onboard wireless network module, a solid state disk, a battery and a touch screen system; an operation system and a refrigerator intelligent management program are mounted on the intelligent manager host; food recognition, suggest for placing positions, recording of shelf life and shelf life comingreminding are achieved through the intelligent manager host; the intelligent manager host is in communication connection with a mobile phone through household broadband and telecommunication network;refrigeration management software is installed in the mobile phone; and information like placing time, placing positions and shelf life of food can be inquired in real time through the mobile phone. According to the intelligent management method, food and beverages in the refrigerator can be conveniently recorded, managed and utilized through details, placing time, placing positions and shelf lifeof good and beverages.

The invention provides a food identification method combining label semantic embedding and attention fusion, which comprises the following steps: a window attention fusion module adaptively selects a discrimination area by using a self-attention mechanism of transformer, and does not need extra frame labeling training; the module fuses window attention of the Swin Transform, cuts an attention area from an original image and amplifies the attention area to serve as input of a next network so as to learn more discriminant features, names of food categories contain important text information such as main components, producing areas and cooking methods, and the module is easy to obtain and helpful for food recognition. Therefore, context-sensitive semantic center loss is proposed, and semantic embedding of the food label is used as the center of the feature space, so that the image expression is guided to learn fine-grained semantic information. The combination of the two improves the food recognition precision.

The invention discloses a food recognition heating method, a microwave oven, a control terminal and a computer storage medium. The food recognition heating method comprises the steps that the mass offoods to be heated is obtained, the foods to be heated are heated, and real-time temperature of the foods to be heated is detected; the numerical range of the product A of the rate of temperature rising and the mass of the foods to be heated is determined, and the type of the foods to be heated is determined according to the numerical range of the product A; and the heating target temperature corresponding to the type of the foods to be heated is determined, and the foods to be heated are heated to the target temperature. The type of the foods to be heated is judged according to the product Aof the rate of temperature rising and the mass of the foods to be heated, the heating target temperature is determined according to the determined type of the foods, the foods to be heated are heateduntil the target temperature is obtained, the type of the foods to be heated is automatically recognized, intelligent heating control over the foods to be heated is achieved, and the problem that a user needs to set different heating temperatures and heating times in the process of heating the different foods is solved.

Embodiments of the present invention provide a model generation method and device, and a food identification method and device. The method for generating the model comprises the following steps: acquiring a plurality of corresponding food pictures for each food in a plurality of food categories; preprocessing the food images separately; obtaining at least one corresponding picture to be trained according to each food picture obtained after the pretreatment; using the convolutional neural network model to train the images to be trained, and obtaining the food recognition model. The technical proposal provided by the embodiment of the invention is used for solving the problem that there is no corresponding identification scheme for Chinese food at present to a certain extent.

The invention discloses a diet health management system. The system comprises a spoon with a specified volume and a mobile phone APP client. The mobile phone APP client is internally provided with a personalized customization module, a food source acquisition module, a food identification module, a food nutrition and calorie calculation module, a food recommended consumption calculation module anda recipe recommendation module. The personalized customization module is used for outputting a highest intake threshold value, a lowest nutrition intake threshold value and / or a highest intake threshold value of food calories of each day and each meal according to the basic information of the user and the selected diet mode; and the food recommended consumption calculation module is used for outputting the recommended consumption of the current food according to the data output by the personalized customization module and the nutrition and heat corresponding to each kind of food based on thespecified volume of the spoon. According to the invention, the calculation, recording and personalized effective control of nutrition and calorie data of edible food can be realized; and meanwhile, the food usage amount or recipe recommendation can be realized according to the current situation.

The invention discloses a control method for a photographing device of a refrigerator. The control method comprises the steps that after a door opening signal of the refrigerator is detected, the photographing device is controlled to be powered on; after a door closing signal of the refrigerator is detected, the photographing device is controlled to conduct photographing and collect food information of a monitored area in the refrigerator multiple times; after information collecting is finished, the photographing device is controlled to be powered off. According to the control method for the photographing device of the refrigerator, the service life of the photographing device can be prolonged, and energy consumption can be reduced. The invention further discloses a food recognition method, the refrigerator and a food recognition system.

The invention relates to a cook machine and a food recognition method thereof. The cook machine comprises a temperature detection device, a heating device and a control device. The food recognition method of the cook machine comprises the steps that S1, the control device receives temperature information sent by the temperature detection device after preheating is completed; S2, the control deviceprocesses the temperature information and determines a food state in a pot body of the cook machine according to a processing result; S3, the control device controls the heating device to perform heating according to a heating mode corresponding to the food state and recognizing the food categories and food amount in the pot body. The cook machine and the food recognition method thereof have theadvantages that the food state of the pot body of the cook machine can be recognized intelligently, the pot body is heated by adopting the corresponding heating mode according to the food state in thepot body of the cook machine, thereby avoiding wrong judging results caused by the deviation of temperature detection results, and ensuring the normal operation of a cooking function.

The invention relates to the technical field of artificial intelligence, provides a physiological health characteristic data monitoring method, a device and equipment and a storage medium, and is usedfor solving the problem of relatively low health analysis accuracy in the prior art. The physiological health characteristic data monitoring method comprises the following steps: calling corresponding initial physiological health characteristic data according to user authorization information and user mode information; calling a preset food recognition model, and recognizing the diet image through the food recognition model to obtain target food information; according to auxiliary information called from the health monitoring system and a food health analysis rule corresponding to the auxiliary information, carrying out food health analysis on the target food information to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various environmental information of a region where the user is located; determining a target health influence value corresponding to the target food information according to an analysis result; and updating the initial physiological health feature data according to the target health influence value to obtain target physiological health feature data.

The invention discloses a cabinet food identification system and identification method, the cabinet food identification system comprises an identification mechanism, a video streaming server, an identification server and a storage server, the identification mechanism is used for collecting image information of food entering and exiting a cabinet and transmitting the image information to the videostreaming server; the video streaming server is used for receiving the image information acquired by the identification mechanism and distributing the image information to the identification server; the identification server receives the image information, recognizes a picture according to the image information, performs tracking judgment and identification judgment through the picture, and finally sends a judgment result to the storage server; the storage server is used for receiving the judgment result and updating the food data information in the cabinet; the cabinet food recognition systemand recognition method are high in intelligent degree and good in recognition effect.

The invention discloses a food recognition system based on an intelligent refrigerator, and relates to the field of intelligent refrigerators. The system comprises a controller, a gesture recognitionunit, an image recognition unit, an acquisition unit and a storage unit, wherein the gesture recognition unit, the image recognition unit, the acquisition unit and the storage unit are connected withthe controller; the posture recognition unit is used for judging the posture of a user for accessing food; the image recognition unit is used for recognizing the type and the number of foods accessedby the user; the acquisition unit comprises an infrared sensor 1, an infrared sensor 2, a liquid crystal touch screen and a CDD camera, wherein the infrared sensor 1 and the infrared sensor 2 are arranged on the front frame and the rear frame of the inner wall of a refrigerator door body correspondingly, the liquid crystal touch screen is embedded on the outer wall of the refrigerator door body, and the CDD camera is arranged on the top of a refrigerator body; and the controller is used for acquiring the real-time posture of the current user from the posture recognition unit, acquiring the type and the number of foods accessed by the user from the image recognition unit, performing processing to obtain the information of the refrigerator foods and displaying the information on the liquid crystal touch screen. The system reduces the production cost of the intelligent refrigerator and improves the accuracy rate of food recognition.

The invention discloses a standard food identification-based daily nutrition intake analysis method, which comprises the following steps of: firstly, acquiring personal information of a user, and constructing an artificial intelligent user nutritional ingredient intake model according to the personal information; obtaining a food information database and constructing a standard food identification model; a user uses electronic equipment to shoot food to obtain a shot image, the shot image is input into the standard food recognition model to be recognized, and a food category name is obtained; providing eating suggestions for the user through an artificial intelligence user nutritional ingredient intake model; updating and optimizing according to whether the user confirms to eat the food or not; according to the invention, the food shot by the user can be accurately positioned, the food image in the positioning area is classified and identified, the identification effect is good, the method can be suitable for daily life, meanwhile, different eating suggestions can be provided according to different requirements of the user, the method is suitable for monitoring and managing daily nutrition intake of the user, and the automation degree is high.

The invention relates to a food recognition method and device based on deep learning, and the method comprises the steps: obtaining a to-be-recognized image, carrying out the food recognition of the to-be-recognized image, and determining the to-be-recognized image containing food as a first recognition image; then, conducting food target detection on the first recognition image, determining position parameters of food in the first recognition image, wherein the position parameters comprise coordinates of the food and the length and width of the area where the food is located in the first recognition image; determining a second recognition image according to the first recognition image and the position parameter; and finally, carrying out food recognition on the second recognition image todetermine the name of the food. According to the scheme provided by the invention, the problem that a food recognition mode is relatively tedious can be solved.

The invention provides a method and device for identifying food. The method comprises the following steps of obtaining a picture of the food to be detected, taking the picture as the input of a preset model; obtaining an output corresponding to the picture, wherein the output is a label for setting the food in the picture, for example, the production place of the food, the taste of the food, the freshness of the food and the like; displaying the label on a display, and receiving the purchase information indicating that a target object purchases the food, for example, receiving three of the left side of the food to be purchased by the target object; sending out the alarm information on the condition that the labels of part of food indicated by the purchase information do not accord with the labels in the historical purchase record of the target object. According to the scheme, the food recognition is completed through the trained preset model, the wrong recognition caused by human eye recognition is avoided, meanwhile, the current purchase behavior of the target object is prompted according to the historical purchase record, and the food waste caused by impulse consumption is avoided.

The invention relates to an intelligent food container identification method, device, system and storage medium. The method includes: acquiring an image of a food container to be identified; dividing the image into a plurality of sub-image blocks; inputting each sub-image block into the first neural network model, and outputting a judgment result of whether each sub-image block belongs to an intelligent food container; The inner wall of the smart food container has a first identification pattern and a second identification pattern, and the first neural network model is a neural network model obtained by training sub-image blocks containing the first identification pattern and / or the second identification pattern as positive samples; In the image block, if the proportion of the sub-image blocks that are determined to belong to the smart food container to all the sub-image blocks is greater than the set value, then it is determined to be a smart food container. The above-mentioned method can accurately identify smart food containers, avoid misjudgment caused by indistinguishable patterns in ordinary containers from smart food containers, and improve the accuracy of food recognition in smart food containers.