CN112307944A - Dish inventory information processing method, dish delivery method and related device - Google Patents
Dish inventory information processing method, dish delivery method and related device Download PDFInfo
- Publication number
- CN112307944A CN112307944A CN202011179226.4A CN202011179226A CN112307944A CN 112307944 A CN112307944 A CN 112307944A CN 202011179226 A CN202011179226 A CN 202011179226A CN 112307944 A CN112307944 A CN 112307944A
- Authority
- CN
- China
- Prior art keywords
- picture
- target
- target container
- processed
- dish
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
A method and a device for processing dish inventory information are provided, the method comprises the following steps: acquiring a picture to be processed; if the picture to be processed contains dishes held by a target container, determining the position information of the target container in the picture to be processed according to a target container picture template; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target pictures to obtain dish classification results; and writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer. The application also relates to a dish ex-warehouse method and device. When the method is used for carrying out inventory management on the dishes which are cut, matched and stored, because the dishes are identified and classified and stored by the computer in the whole process and the dish classification result is recorded, the classification and placement errors caused by manual classification and storage can be avoided, and the accuracy of inventory management of the dishes is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for processing information on inventory of dishes, a computer device, and a storage medium, and a method and an apparatus for exporting dishes, a computer device, and a storage medium.
Background
In the kitchen of a conventional restaurant, after the cutting and matching are completed, dishes to be stored in a sealed manner are generally classified by workers in a sealed manner and stored in a refrigeration house according to different dish categories.
However, the following problems exist when the dishes are manually classified and placed when being put in storage: the manual dish classification errors and the placing errors of dishes with similar appearances and shapes are avoided.
Disclosure of Invention
In view of the above, there is a need to provide a method for processing dish inventory information, a method for delivering dishes from a warehouse, and a related device, which can reduce the number of mistakes made.
A method of processing inventory information for a dish, the method comprising:
acquiring a picture to be processed;
if the picture to be processed contains dishes held by a target container, determining the position information of the target container in the picture to be processed according to a target container picture template;
dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container;
classifying the dishes based on the target pictures to obtain dish classification results;
and writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
A method of ex-warehouse dishes, the method comprising:
detecting a readable and writable chip embedded in a target container in a target area through a reader-writer;
if a readable and writable chip embedded in a target container is detected in a target area, communicating with the readable and writable chip through the reader-writer, and reading a dish classification result in the readable and writable chip; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by a target container, determining the position information of the target container in the picture to be processed according to a target container picture template; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target pictures to obtain dish classification results; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer;
and displaying the dish classification result.
A vegetable inventory manager device, the device comprising:
the image acquisition module is used for acquiring an image to be processed;
the detection module is used for determining the position information of a target container in the picture to be processed according to a target container picture template if the picture to be processed contains dishes held by the target container;
the segmentation module is used for segmenting the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container;
the classification module is used for classifying the dishes based on the target pictures to obtain dish classification results;
and the writing module is used for writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
A dish retrieval apparatus, the apparatus comprising:
the detection module is used for detecting the readable and writable chip embedded in the target container in the target area through the reader-writer;
the communication module is used for communicating with the readable and writable chip through the reader-writer and reading a dish classification result in the readable and writable chip if the readable and writable chip embedded in the target container is detected in the target area; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by a target container, determining the position information of the target container in the picture to be processed according to a target container picture template; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target pictures to obtain dish classification results; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer;
and the result display module is used for displaying the dish classification result.
A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the dish inventory information processing method and the dish ex-warehouse method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the above-mentioned dish inventory information processing method, dish stocking method.
According to the dish inventory information processing method, the dish delivery method and the related device, when the obtained graph to be processed contains dishes contained in the target container, the position information of the target container is determined according to the target container picture template, the target picture corresponding to the target container is obtained through segmentation based on the position information, then the dishes in the graph are classified according to the target picture to determine a dish classification result, and the dish classification result is written into the readable and writable chip in the target container through the reader-writer; therefore, when the dishes are taken and used, the dishes can be placed at the appointed position, the dish classification result in the readable and writable chip arranged on the containing container used by the dishes is read through the reader-writer, and the dish delivery is completed. When the method is used for carrying out inventory management on the dishes which are cut, matched and stored, because the dishes are identified and classified and stored by the computer in the whole process and the dish classification result is recorded, the classification and placement errors caused by manual classification and storage can be avoided, and the accuracy of inventory management of the dishes is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a method for processing inventory information of dishes;
FIG. 2 is a flowchart illustrating a method for processing inventory information of dishes according to an embodiment;
FIG. 3 is a flowchart illustrating a method for processing inventory information of dishes according to another embodiment;
FIG. 4 is a flowchart illustrating the process of determining location information of a target container in a to-be-processed picture according to a target container picture template in one embodiment;
FIG. 5 is a diagram of a target container picture template in one embodiment;
fig. 6 is a schematic flow chart illustrating a process of screening location information corresponding to a target container from a target matching result by using a non-maximum suppression method in an embodiment;
FIG. 7 is a flowchart illustrating a method for processing inventory information of dishes according to an exemplary embodiment;
FIG. 8 is a block diagram showing a configuration of a dish inventory information processing apparatus according to an embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The dish inventory information processing method provided by the application can be applied to the application environment shown in fig. 1. The terminal 101 communicates with the picture collecting device 102, and communicates with the reader/writer 103 through a network, and the reader/writer communicates with the readable/writable chip 104 embedded in the container for holding dishes. The method comprises the steps that a terminal 101 obtains a picture to be processed from a picture acquisition device 102, when the picture to be processed contains dishes contained in a target container, position information of the target container is determined according to a picture template of the target container, the target picture corresponding to the target container is obtained through segmentation based on the position information, then the dishes in the picture are classified according to the target picture to determine a dish classification result, and the dish classification result is written into a readable and writable chip 104 in the target container through a reader-writer 103; therefore, when the dishes are taken, the dishes can be placed at the designated positions, the dish classification results in the readable and writable chip 104 arranged on the containing container used by the dishes are read through the reader-writer 103, and the dish delivery is completed. The terminal 101 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the image capturing device 102 may be any device capable of capturing images, and may be connected to the terminal 101 for data transmission, including, but not limited to, a camera, a mobile phone with a photographing function, and the like; the reader/writer 103 may be any device having a reading/writing function, and the readable/writable chip 104 may be any chip capable of reading and writing data.
In one embodiment, as shown in fig. 2, a method for processing menu inventory information is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes steps S210 to S250.
Step S210, acquiring a to-be-processed picture.
In one embodiment, the terminal acquires a picture to be processed from the picture acquisition device; in another embodiment, the terminal acquires an original picture from the picture acquisition device, and pre-processes the original picture to obtain a picture to be processed.
In one embodiment, acquiring a to-be-processed picture includes: acquiring an acquired original picture; carrying out mean value filtering processing on the original picture to obtain a picture after mean value filtering; in this embodiment, the to-be-processed picture includes a picture after mean filtering.
The original picture is a picture acquired by the picture acquisition device for a container containing dishes, and the picture to be processed is acquired after mean filtering is performed on the original picture.
Mean filtering is typically a linear filtering algorithm, which means that a template is given to a target pixel on an image, the template includes its surrounding neighboring pixels (8 surrounding pixels centered on the target pixel, which form a filtering template, i.e., includes the target pixel itself), and the average value of all pixels in the template is used to replace the original pixel value. Further, in an embodiment, performing mean filtering processing on the original picture to obtain a mean filtered picture, includes: and performing convolution processing on the original picture based on a preset operator to obtain the picture after mean filtering.
Wherein, the preset operator (Kernel) is a matrix with a predefined preset size; in one embodiment, a preset operator with a size of 3 × 3 is used to perform convolution processing on the original picture, so as to obtain a filtered picture.
In one embodiment, the picture acquisition device comprises a camera, the camera is arranged above the dish operation table and faces to a designated area, and in the process of warehousing and ex-warehouse of the dishes, a worker can place a container which is embedded with a readable and writable chip and contains the dishes in the area so that the camera can acquire the container and the dishes to obtain an original picture; further, in one embodiment, the camera captures raw pictures at a preset frequency.
In this embodiment, the noise in the original picture can be eliminated by filtering the original picture to obtain the picture to be processed.
Step S220, if the picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container.
The target container is a container fixedly used for containing dishes in the embodiment, and in one embodiment, only one type of target container is contained, and correspondingly, the picture template of the target container is also only one type; in other embodiments, a plurality of different types of target containers can be adopted, and correspondingly, each type of target container corresponds to one target container picture template, and whether a corresponding target container (for containing dishes) appears in the picture to be processed is sequentially identified according to each type of target container picture template during identification, so that the position information of the target container is determined in the picture to be processed; further, in this embodiment, the method may further include determining a category of a target container appearing in the picture to be processed; for example, different types of target containers are used for different types of dishes (meat/vegetables/meatballs, etc.).
In the embodiment, the objects in the picture to be processed are identified to determine whether the picture contains dishes held by the target container; in one embodiment, identifying whether the dishes contained in the target container are contained in the picture to be processed can be realized by means of target identification, for example, identifying the picture to be processed based on a target identification neural network determined by training; in another embodiment, identifying whether the picture to be processed contains dishes held by the target container can be performed by subtracting the grayscale pictures corresponding to the target container picture templates after performing grayscale processing on the picture to be processed, and determining whether the target container and the dishes held by the target container appear in the picture to be processed by judging pixels in the pictures obtained by subtracting. In other embodiments, whether the dishes contained in the target container are contained in the to-be-processed picture may be determined in other ways.
In one embodiment, the position information of the target container is determined in the picture to be processed according to the picture template of the target container, the possible position information of the target container can be obtained by comparing the picture template of the target container with pictures with preset sizes in the picture to be processed after certain transformation is carried out on the picture template of the target container, and an optimal position information is determined from the possible position information through a certain algorithm and is output as the position information of the target container; and the step of transforming the target container picture template comprises angle transformation and scaling transformation.
And step S230, segmenting the target picture corresponding to the target container from the picture to be processed based on the position information of the target container.
After the position information of the target container is obtained, a picture corresponding to the target container can be divided from the picture to be processed to obtain a picture with the contour of the target container as a frame, which is marked as a target picture in this embodiment; it is understood that the target picture correspondingly includes the target container and the dishes stored in the target container.
And S240, classifying the dishes based on the target picture to obtain a dish classification result.
In one embodiment, the process of classifying dishes in the target picture can be realized through a trained neural network. The dish classification result represents the category of dishes, such as beef, mutton, chicken or baby dish, contained in the target container in the target picture.
And step S250, writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
The reader-writer is a device with a reading-writing function, and can write and read data in the readable and writable chip. In one embodiment, the reader comprises an RFID (Radio Frequency Identification) reader, and the readable and writable chip comprises an RFID chip; the target object is automatically identified and related data are obtained through the radio frequency identification signal, manual intervention is not needed, high-speed moving objects can be identified, a plurality of RFID labels can be identified at the same time, and the operation is rapid and convenient.
In one embodiment, the reader-writer is arranged below the operating platform, the target container containing dishes is placed on the operating platform surface, the picture acquisition device is arranged above the operating platform, and the lens is opposite to the operating platform, so that pictures containing the target container containing the dishes can be acquired.
Further, in one embodiment, after the dish classification result is written into the readable and writable chip arranged on the target container through the reader-writer, the dishes contained in the target container can be sealed and stored in a warehouse.
According to the dish inventory information processing method, when the obtained graph to be processed contains dishes contained in the target container, the position information of the target container is determined according to the picture template of the target container, the target picture corresponding to the target container is obtained through segmentation based on the position information, then the dishes in the graph are classified according to the target picture to determine a dish classification result, and the dish classification result is written into a readable and writable chip in the target container through a reader-writer; therefore, when the dishes are taken and used, the dishes can be placed at the appointed position, the dish classification result in the readable and writable chip arranged on the containing container used by the dishes is read through the reader-writer, and the dish delivery is completed. When the method is used for carrying out inventory management on the dishes which are cut, matched and stored, because the dishes are identified and classified and stored by the computer in the whole process and the dish classification result is recorded, the classification and placement errors caused by manual classification and storage can be avoided, and the accuracy of inventory management of the dishes is improved.
In one embodiment, as shown in fig. 3, after the to-be-processed picture is acquired, steps S310 to S350 are further included.
And step S310, carrying out gray level processing on the picture to be processed to obtain a gray level picture.
Wherein, each pixel of the gray image only needs one byte to store the gray value (also called as intensity value and brightness value), and the gray range is 0-255.
Step S320, subtracting the preset grayscale background picture from the grayscale picture to obtain an intermediate picture.
The background picture refers to a picture collected when no object is placed in the operation table, and the preset gray background picture is a picture obtained by performing gray processing on the collected background picture; in one embodiment, subtracting the grayscale picture from the preset grayscale background picture comprises: the pixels in the grayscale image and the preset grayscale background image are subtracted to obtain a pixel matrix, which is recorded as an intermediate image in this embodiment.
And step S330, carrying out binary processing on the intermediate picture to obtain a binary intermediate picture.
Image Binarization (Image Binarization) is a process of setting the gray value of a pixel point on an Image to be 0 or 255, namely, the whole Image presents an obvious black-white effect. In one embodiment, setting a threshold between 0 and 255, and performing binary processing on the intermediate picture includes: and setting the pixel gray value of the point with the pixel value larger than or equal to the threshold value in the intermediate picture as 255, and setting the pixel gray value of the point with the pixel value smaller than the threshold value in the intermediate picture as 0 to obtain the binary intermediate picture. In other embodiments, the binarized intermediate picture may also be obtained by performing binarization processing on the intermediate picture in other manners.
In step S340, the ratio of the number of white pixels in the binarized intermediate picture is calculated.
The binarization intermediate picture only comprises black pixels and white pixels, and the number proportion of the white pixels can be calculated by counting the number of the white pixels and the number of all the pixels in the binarization intermediate picture.
In step S350, if the ratio of the number of white pixels is greater than the preset ratio threshold, it is determined that the to-be-processed picture contains dishes held by the target container.
The preset ratio threshold value can be set according to actual conditions.
In the embodiment, the picture to be processed is subjected to gray level processing, and whether dishes contained in the target container are contained in the picture to be processed is determined according to the difference value between the picture to be processed and the background picture template, so that the method is convenient and quick.
In one embodiment, as shown in fig. 4, determining the position information of the target container in the to-be-processed picture according to the target container picture template includes steps S410 to S430.
And step S410, carrying out gray level processing on the picture to be processed to obtain a gray level picture.
And step S420, after the target container picture template is transformed based on generalized Hough transform, traversing the gray-scale picture by using the transformed target container picture template to obtain a target matching result of which the matching degree with the target container picture template in the gray-scale picture exceeds a matching degree threshold value.
Among them, hough transform is a kind of feature detection, and it is originally designed to detect shapes (e.g., straight lines, circles, ellipses, etc.) that can be accurately resolved as defined; the generalized Hough transform is adjusted on the basis of the Hough transform according to the principle of template matching; the generalized hough transform does not require an analytical expression that gives the shape to be detected, and it can detect any given shape. In one embodiment, transforming the grayscale picture using a generalized hough transform comprises: carrying out angle and scaling transformation on the gray level picture; in one specific embodiment, the angle transformation for the grayscale picture includes an angle range of 0-360 degrees, and the scaling transformation for the grayscale picture includes a scaling range of 0.8-1.2 times, and it is understood that in other embodiments, the angle range and the scaling range that can be transformed can be set to other ranges.
Fig. 5 is a diagram illustrating a target container picture template in one embodiment. In one embodiment, traversing the grayscale picture using the transformed target container picture template comprises: and respectively taking each point in the gray level picture as a candidate point, taking the candidate point as a vertex, taking each preset size as a length and a width to obtain a candidate rectangle, and matching the candidate rectangle with the transformed target container picture template to obtain matching results, wherein each matching result corresponds to a matching degree, and the matching results with the matching degrees larger than a threshold value of the matching degree are considered to be more likely to be the real positions of the target container.
In one embodiment, each candidate rectangle is matched with the transformed target container picture template, and the similarity may be used as the matching degree between the candidate rectangle and the transformed target container picture template in a manner of calculating the similarity between the candidate rectangle and the transformed target container picture template. In one embodiment, the matching result includes the coordinates of the candidate point, the size (length and width) of the rectangle positioned by the bounding rectangle of the candidate point, and the matching degree of the candidate rectangle with the transformed target container picture template. In one embodiment, the matching degree of the candidate rectangle and the transformed target container picture template is represented by a score, and the score is between 0 and 1.
Step S430, selecting the matching result with the maximum score in the target matching results, and determining the position information of the target container based on the matching result.
In one embodiment, if there is only one target (dishes held in the target container) in the to-be-processed picture, a matching result with the largest score in the target matching results is selected, and the candidate point and the size corresponding to the matching result are determined as the position information of the target container.
In another embodiment, for each matching result obtained by traversal, a non-maximum suppression method can be adopted to screen and obtain position information corresponding to the target container from each matching result; the method in the embodiment is also applicable to the embodiment that the picture to be processed contains a plurality of targets (dishes contained in the target container).
The non-maximum suppression is to suppress an element which is not a maximum and search for a local maximum as the name implies. Further, in a specific embodiment, the step of screening the position information corresponding to the target container from the target matching result by using the non-maximum suppression method includes the steps shown in fig. 6:
sorting according to the matching scores in the target matching result, selecting a coordinate point in the matching result with the highest score as A, judging whether the coordinate point A is restrained or not, if not, selecting a coordinate point with the second matching score in the sorting result as a coordinate B, judging whether the coordinate point A is restrained or not, if not, calculating the overlapping area of a rectangle in the matching result corresponding to the coordinate point A and a rectangle in the matching result corresponding to the coordinate point B, and if the overlapping area is larger than an overlapping area threshold value, marking the matching result corresponding to the coordinate point B as restrained; and selecting the next coordinate point in the sequencing result, similarly calculating the overlapping area of the rectangle corresponding to the coordinate point and the rectangle corresponding to the coordinate point A until all matching results are traversed, respectively calculating the overlapping area between every two coordinate points to obtain the uninhibited matching result, and determining the uninhibited matching result as the position information corresponding to the target container.
In the embodiment, the picture to be processed is processed to a certain extent, and the position information corresponding to the target container is determined from the picture to be processed according to the target container picture template, so that the target picture corresponding to the target container can be segmented from the picture to be processed for subsequent dish identification.
In one embodiment, classifying the dishes based on the target picture to obtain a dish classification result, including: inputting the target picture into a neural network determined by training to obtain an output result of the neural network; and selecting a target output result with the maximum confidence score in the output results, and determining the output result as a dish classification result if the confidence score corresponding to the target output result is greater than or equal to a preset score threshold value.
In one embodiment, before inputting a target picture into a trained neural network, performing gray processing on the target picture, calculating an average gray value of the gray picture corresponding to the target picture, judging whether the average gray value is greater than a preset average gray value range, if so, determining that the target may have an overexposure condition or an underexposure condition, and generating and sending prompt information to prompt a worker to adjust the exposure level of a picture acquisition device to acquire the picture again; and if the average gray value is within the range of the preset average gray value, the gray value of the target picture is considered to be qualified, and at the moment, the step of inputting the target picture into the neural network determined by training is carried out. The preset average gray value range can be set according to actual conditions; in one embodiment, the preset average gray value range includes: greater than or equal to the second grayscale threshold and less than or equal to the first grayscale threshold. In one specific embodiment, the first gray scale value is set to 230 and the second gray scale value is set to 25.
In an embodiment, the format of the target picture is a jpg format, and in this embodiment, before the target picture is input into the neural network, the target picture in the jpg format is converted into a one-dimensional tensor, and the one-dimensional tensor is input into the neural network determined by training. In one embodiment, the neural network employs the Google initiation V3 network architecture. Further, the neural network outputs a matrix of 1 × N; wherein N represents the total classified number of dishes, namely the possible kinds of dishes; the output result of the neural network includes confidence levels of the target picture corresponding to the dish classifications, the dish classification with the highest confidence level (in this embodiment, the dish classification is recorded as the target output result) is selected for confidence level judgment, if the confidence level is greater than or equal to a preset score threshold, the classification is considered to be accurate, and the dish classification corresponding to the confidence level is determined as the dish classification result corresponding to the target picture.
In another embodiment, the method further comprises: and if the confidence score corresponding to the target output result is smaller than the preset score threshold, or the confidence score difference value between the target output result and the output result with the second confidence score in the output result is smaller than the preset score threshold, generating and sending a prompt signal.
And if the dish classification with the highest confidence degree in the output result of the neural network is smaller than a preset score threshold value, or the confidence degree score difference value corresponding to the dish classification with the highest confidence degree and the dish classification with the second confidence degree in the output result of the neural network is smaller than a difference threshold value, the classification result is considered to be uncertain, and at the moment, a prompt signal is generated and sent to trigger an alarm mechanism, and the result is delivered to a worker for judgment. In one embodiment, after the prompt signal is generated and sent, the results output by the neural network are sorted and displayed according to the confidence level; and receiving a final classification result selected by the staff, and determining the final classification result as a dish classification result corresponding to the target picture.
In the embodiment, the determined neural network is trained to input the target picture for dish identification, so that dish type identification accuracy can be improved, dish type identification efficiency of the neural network is high, and dish warehousing efficiency can be improved. Meanwhile, prompting is triggered for uncertain classification results, and accuracy of dish inventory management can be improved through manual processing.
In another embodiment, the present application further provides a dish warehousing method, which is also described by taking the application of the method to the terminal in fig. 1 as an example, and the method includes the steps of: detecting a readable and writable chip embedded in a target container in a target area through a reader-writer; if the readable and writable chip embedded in the target container is detected in the target area, communicating with the readable and writable chip through a reader-writer, and reading a dish classification result in the readable and writable chip; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer; and displaying the dish classification result.
The dish delivery method provided in the embodiment can be applied to an application scenario of delivering dishes stored in a warehouse, when the dishes are delivered from the warehouse, the target container is placed on the operation table, the reader-writer below the operation table reads information of the readable and writable chip embedded in the target container, dish classification results in the readable and writable chip are obtained, the reader-writer sends the classification results to the terminal to be displayed, a worker can know the category of the dishes without secondary confirmation, secondary pollution is reduced, and the possibility of manual judgment errors is reduced.
For the specific limitation of the dish inventory information processing method, the above limitation on the dish inventory information processing method can be referred to, and details are not repeated here.
Fig. 7 is a schematic flow chart of a method for processing dish inventory information in an embodiment, which may be summarized as the following steps: (1) the method comprises the steps of (1) image acquisition, (2) image noise reduction processing, (3) target positioning, (4) image segmentation, (5) gray detection, (6) data format conversion, (7) neural network calculation, and (8) result storage and recording.
The following is a detailed description of the above steps:
in the operation process, the camera is always kept in an open state, image acquisition is carried out according to preset FPS (frame transmission per second) parameters, and data are transmitted to the computer through the DVP interface. If the camera is not able to return data effectively, the system will alert and request human intervention.
In the data acquisition process, the system acquires a current frame as an original picture, and performs arithmetic mean filtering by using the original picture as an input parameter, thereby achieving the effect of reducing noise. The specific flow of the mean filtering is as follows:
defining a preset operator Kernel:
as described in equation (1), the operator is a mean filtering operator of 3 × 3 size, but while eliminating noise, the operator causes blurring so that certain features are missing. In one embodiment, if the blur level needs to be reduced, the operator described in (2) can be used.
And secondly, selecting one Kernel in the first step as a convolution Kernel, and performing convolution calculation on the image.
Where f (x, y) represents the result obtained after convolution (the above-mentioned picture to be processed), and is denoted as I1. M and N represent the length and width of the operator, respectively (both 3 in this embodiment). SxyRepresenting a sample area of size M × N in the original picture centered on point (x, y); g (s, t) represents the original picture.
And then judging whether dishes exist or not: (1) the obtained picture I1 (the picture to be processed) and a preset background picture I2 are subjected to gray scale processing and subtracted, and the absolute value of the difference of the gray scale images of the two pictures is output to form a new image which is taken as an intermediate picture Iout. (2) To IoutCarrying out binary processing to obtain a binary intermediate picture; setting threshold value T (between 0 and 255), changing the gray value of the pixel with the gray value larger than or equal to the value to 255 and the pixel value smaller than or equal to the value to 0 to obtain new image Ithresh. (3) Calculation of IthreshIf the number of the medium white pixels is greater than a preset ratio threshold T1 (for example, 20%), it can be determined that the target container is in the camera view.
After determining the image, the system determines the exact location of the target container by: (1) and carrying out gray level processing on the picture I1 to be processed to obtain Ib. (2) For Ib, performing generalized Hough transform according to a target container picture template ItemplateTraversing I1 with a certain angle range (e.g., 0-360 degrees) and a certain scaling (0.8-1.2 times) to obtain a result set U1; u1 contains N matching results with degree of matching with I1 greater than threshold, each matching result includes: coordinate point (x, y), size (length, width) of rectangle circumscribing the coordinate point as vertex of rectangle frame, and the rectangle and targetContainer picture template ItemplateIs given as the score S (0)<S<1) A larger value indicates a higher degree of matching. (3) The set U1 is processed by an NSM (non-maximum suppression) algorithm to obtain an optimal result, which includes the position coordinates and size (pixels) of the object, as the position information corresponding to the object container.
And performing image segmentation on the picture I1 to be processed according to the position information corresponding to the target container to obtain a picture It only containing the target container and dishes contained in the target container. After the gradation processing is performed, the average gradation of the picture It is calculated to obtain a gradation value B1. If B1 is greater than the preset threshold Th (usually 230) or less than the preset threshold Tl (usually 25), it is determined that there is a possibility of overexposure or underexposure of the target, and the exposure of the camera needs to be modified for image acquisition again.
After confirming that the gray scale is qualified, It is converted into a one-dimensional tensor from the jpg format, and is transmitted into a trained neural network (using a Google initiation V3 network architecture) as an input quantity to be calculated. A matrix with a result of 1xN (N is the total number of classes) is obtained, the content of which includes the confidence of each sample.
Usually, the output result with the highest confidence of the neural network is taken as a classification result, and if the output result is lower than a preset score threshold T1 (usually set to 40%), or the confidence score difference value between the result with the highest confidence and the second result is smaller than a preset difference threshold (30%), an alarm mechanism is triggered and manual judgment is needed.
Finally, writing the obtained dish classification result into an RFID chip arranged in the dish container through an RFID reader-writer; and meanwhile, sending the result to a background inventory management system to finish the warehousing process.
The dish inventory information processing method in the above embodiment may analyze the texture, color, and shape of the object to be recognized to obtain a correct conclusion, and complete some food materials that are difficult to distinguish manually, such as: beef and mutton, various balls (fish balls, beef balls, pork balls and the like) and various bean curds. Moreover, the calculation speed of computer vision on a single target is far higher than that of manual input (the whole process is usually within 0.5 second), and the stock preparation efficiency of a kitchen chef is greatly improved. Meanwhile, for the target with uncertain classification results, prompt information is generated and generated to trigger an alarm mechanism so as to remind an operator to determine the dish classification results manually (by selecting or manually inputting in options). Finally, after the dish classification result is successfully written into the built-in chip of the container, an operator can store the dish in a sealed mode, when the dish is delivered, the dish can be placed on the RFID reader-writer to obtain the content of the dish, the package does not need to be opened, and the risk of secondary pollution is reduced.
It should be understood that although the various steps in the flow charts of fig. 2-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 8, there is provided a dish inventory information processing apparatus including: picture acquisition module 810, detection module 820, segmentation module 830, classification module 840, and write-in module 850, wherein:
the picture obtaining module 810 is configured to obtain a picture to be processed;
the detection module 820 is used for determining the position information of the target container in the picture to be processed according to the picture template of the target container if the picture to be processed contains dishes held by the target container;
the segmentation module 830 is configured to segment the target picture corresponding to the target container from the to-be-processed picture based on the position information of the target container;
the classification module 840 is used for classifying the dishes based on the target pictures to obtain dish classification results;
and a writing module 850, configured to write the dish classification result into a readable and writable chip arranged on the target container through a reader/writer.
According to the dish inventory information processing device, when the obtained graph to be processed contains dishes contained in the target container, the position information of the target container is determined according to the picture template of the target container, the target picture corresponding to the target container is obtained through segmentation based on the position information, then the dishes in the graph are classified according to the target picture to determine a dish classification result, and the dish classification result is written into a readable and writable chip in the target container through a reader-writer; therefore, when the dishes are taken and used, the dishes can be placed at the appointed position, the dish classification result in the readable and writable chip arranged on the containing container used by the dishes is read through the reader-writer, and the dish delivery is completed. When inventory management is carried out on the dishes which are cut, matched and stored through the device, due to the fact that the dishes are identified and stored in a classified mode through the computer in the whole process, and dish classification results are recorded, classification and placing errors caused by manual classified storage can be avoided, and accuracy of inventory management of the dishes is improved.
In one embodiment, the image capturing module 810 of the above apparatus includes: the original picture acquisition unit is used for acquiring the acquired original picture; the filtering processing unit is used for carrying out mean value filtering processing on the original picture to obtain a picture after mean value filtering; and the picture to be processed comprises the picture after mean filtering.
In an embodiment, the filtering processing unit is specifically configured to perform convolution processing on an original picture based on a preset operator to obtain a picture after mean filtering.
In one embodiment, the above apparatus further comprises: the gray processing module is used for carrying out gray processing on the picture to be processed to obtain a gray picture; the operation module is used for subtracting the gray level picture from a preset gray level background picture to obtain an intermediate picture; the binarization processing module is used for carrying out binarization processing on the intermediate picture to obtain a binarization intermediate picture; the proportion calculation module is used for calculating the proportion of the number of white pixels in the binaryzation intermediate picture; in this embodiment, the detecting module 820 determines that the to-be-processed picture includes dishes held in the target container when the number ratio of the white pixels is greater than the preset ratio threshold.
In one embodiment, the above apparatus further comprises: the gray processing module is used for carrying out gray processing on the picture to be processed to obtain a gray picture; the matching module is used for traversing the gray-scale picture by using the transformed target container picture template after the target container picture template is transformed based on the generalized Hough transform, and obtaining a target matching result of which the matching degree with the target container picture template in the gray-scale picture exceeds a matching degree threshold value; the detection module 820 is specifically configured to select a matching result with the largest score in the target matching results, and determine the position information of the target container based on the matching result.
In one embodiment, the classification module 840 of the apparatus comprises: the input unit is used for inputting the target picture into the neural network determined by training to obtain an output result of the neural network; the classification module is specifically configured to: and selecting a target output result with the maximum confidence score in the output results, and determining the output result as a dish classification result if the confidence score corresponding to the target output result is greater than or equal to a preset score threshold value.
In an embodiment, the prompt module is configured to generate and send a prompt signal if the confidence score corresponding to the target output result is smaller than a preset score threshold, or a confidence score difference between the target output result and an output result with a second confidence score in the output results is smaller than a preset difference threshold.
In another embodiment, the present application further provides a dish delivery device, including: the detection module is used for detecting the readable and writable chip embedded in the target container in the target area through the reader-writer; the information reading module is used for communicating with the readable and writable chip through the reader-writer and reading the dish classification result in the readable and writable chip if the readable and writable chip embedded in the target container is detected in the target area; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer; and the display module is used for displaying the dish classification result.
For the specific limitations of the dish inventory information processing device and the dish delivery device, reference may be made to the above limitations of the dish inventory information processing method and the dish delivery method, which are not described herein again. The modules in the dish inventory information processing device and the dish delivery device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to realize a dish inventory information processing method and a dish delivery method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a picture to be processed; if the picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; and writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring an acquired original picture; carrying out mean value filtering processing on the original picture to obtain a picture after mean value filtering; the picture to be processed comprises the picture after mean filtering.
In one embodiment, the processor, when executing the computer program, further performs the steps of: carrying out gray level processing on the picture to be processed to obtain a gray level picture; subtracting the gray level picture from a preset gray level background picture to obtain an intermediate picture; carrying out binary processing on the intermediate picture to obtain a binary intermediate picture; calculating the number ratio of white pixels in the binaryzation intermediate picture; and if the number ratio of the white pixels is larger than a preset ratio threshold, determining that the dishes contained in the target container are contained in the picture to be processed.
In one embodiment, the processor, when executing the computer program, further performs the steps of: carrying out gray level processing on the picture to be processed to obtain a gray level picture; after the target container picture template is transformed based on the generalized Hough transform, traversing the gray-scale picture by using the transformed target container picture template to obtain a target matching result of which the matching degree with the target container picture template in the gray-scale picture exceeds a matching degree threshold; and selecting the matching result with the maximum score in the target matching results, and determining the position information of the target container based on the matching result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: inputting the target picture into a neural network determined by training to obtain an output result of the neural network; and selecting a target output result with the maximum confidence score in the output results, and determining the output result as a dish classification result if the confidence score corresponding to the target output result is greater than or equal to a preset score threshold value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and if the confidence score corresponding to the target output result is smaller than the preset score threshold, or the confidence score difference value between the target output result and the output result with the second confidence score in the output result is smaller than the preset score threshold, generating and sending a prompt signal.
In one embodiment, the processor, when executing the computer program, further performs the steps of: detecting a readable and writable chip embedded in a target container in a target area through a reader-writer; if the readable and writable chip embedded in the target container is detected in the target area, communicating with the readable and writable chip through a reader-writer, and reading a dish classification result in the readable and writable chip; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer; and displaying the dish classification result.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a picture to be processed; if the picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; and writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring an acquired original picture; carrying out mean value filtering processing on the original picture to obtain a picture after mean value filtering; the picture to be processed comprises the picture after mean filtering.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out gray level processing on the picture to be processed to obtain a gray level picture; subtracting the gray level picture from a preset gray level background picture to obtain an intermediate picture; carrying out binary processing on the intermediate picture to obtain a binary intermediate picture; calculating the number ratio of white pixels in the binaryzation intermediate picture; and if the number ratio of the white pixels is larger than a preset ratio threshold, determining that the dishes contained in the target container are contained in the picture to be processed.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out gray level processing on the picture to be processed to obtain a gray level picture; after the target container picture template is transformed based on the generalized Hough transform, traversing the gray-scale picture by using the transformed target container picture template to obtain a target matching result of which the matching degree with the target container picture template in the gray-scale picture exceeds a matching degree threshold; and selecting the matching result with the maximum score in the target matching results, and determining the position information of the target container based on the matching result.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the target picture into a neural network determined by training to obtain an output result of the neural network; and selecting a target output result with the maximum confidence score in the output results, and determining the output result as a dish classification result if the confidence score corresponding to the target output result is greater than or equal to a preset score threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of: and if the confidence score corresponding to the target output result is smaller than the preset score threshold, or the confidence score difference value between the target output result and the output result with the second confidence score in the output result is smaller than the preset score threshold, generating and sending a prompt signal.
In one embodiment, the computer program when executed by the processor further performs the steps of: detecting a readable and writable chip embedded in a target container in a target area through a reader-writer; if the readable and writable chip embedded in the target container is detected in the target area, communicating with the readable and writable chip through a reader-writer, and reading a dish classification result in the readable and writable chip; wherein, the writing of the dish classification result comprises the following steps: when the obtained picture to be processed contains dishes held by the target container, determining the position information of the target container in the picture to be processed according to the picture template of the target container; dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container; classifying the dishes based on the target picture to obtain a dish classification result; writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer; and displaying the dish classification result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A method for processing inventory information of dishes, the method comprising:
acquiring a picture to be processed;
if the picture to be processed contains dishes held by a target container, determining the position information of the target container in the picture to be processed according to a target container picture template;
dividing the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container;
classifying the dishes based on the target pictures to obtain dish classification results;
and writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
2. The method according to claim 1, wherein the obtaining the picture to be processed comprises:
acquiring an acquired original picture;
carrying out mean value filtering processing on the original picture to obtain a picture after mean value filtering; the picture to be processed comprises the picture after mean filtering.
3. The method according to claim 1, further comprising, after said obtaining the picture to be processed:
carrying out gray level processing on the picture to be processed to obtain a gray level picture;
subtracting the gray level picture from a preset gray level background picture to obtain an intermediate picture;
carrying out binary processing on the intermediate picture to obtain a binary intermediate picture;
calculating the number ratio of white pixels in the binaryzation intermediate picture;
and if the number ratio of the white pixels is larger than a preset ratio threshold, determining that the to-be-processed picture contains dishes held by a target container.
4. The method according to any one of claims 1 to 3, wherein the determining the position information of the target container in the picture to be processed according to the target container picture template comprises:
carrying out gray level processing on the picture to be processed to obtain a gray level picture;
transforming the target container picture template based on generalized Hough transform, traversing the gray-scale picture by using the transformed target container picture template, and obtaining a target matching result of which the matching degree with the target container picture template in the gray-scale picture exceeds a matching degree threshold;
and selecting the matching result with the maximum score in the target matching results, and determining the position information of the target container based on the matching result.
5. The method of any one of claims 1 to 3, wherein the classifying the dish based on the target picture to obtain a dish classification result comprises:
inputting the target picture into a neural network determined by training to obtain an output result of the neural network;
and selecting a target output result with the maximum confidence score in the output results, and determining the output result as the classification result of the dishes if the confidence score corresponding to the target output result is greater than or equal to a preset score threshold value.
6. The method of claim 5, further comprising:
and if the confidence score corresponding to the target output result is smaller than the preset score threshold, or the confidence score difference value between the target output result and the output result with the second confidence score is smaller than the preset score threshold, generating and sending a prompt signal.
7. The method of claim 5, further comprising, prior to inputting the target picture into the neural network determined by training:
carrying out gray level processing on the target picture to obtain a gray level picture corresponding to the target picture;
calculating the average gray value of the gray picture corresponding to the target picture;
and if the average gray value is within a preset average gray value range, entering the step of inputting the target picture into a neural network determined through training.
8. A method for ex-warehouse dishes, comprising:
detecting a readable and writable chip embedded in a target container in a target area through a reader-writer;
if a readable and writable chip embedded in a target container is detected in a target area, communicating with the readable and writable chip through the reader-writer, and reading a dish classification result in the readable and writable chip; wherein the step of writing the dish classification result into the readable and writable chip comprises the method steps of any one of claims 1-7;
and displaying the dish classification result.
9. A dish inventory information processing apparatus characterized by comprising:
the image acquisition module is used for acquiring an image to be processed;
the detection module is used for determining the position information of a target container in the picture to be processed according to a target container picture template if the picture to be processed contains dishes held by the target container;
the segmentation module is used for segmenting the picture to be processed based on the position information of the target container to obtain a target picture corresponding to the target container;
the classification module is used for classifying the dishes based on the target pictures to obtain dish classification results;
and the writing module is used for writing the dish classification result into a readable and writable chip arranged on the target container through a reader-writer.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179226.4A CN112307944A (en) | 2020-10-29 | 2020-10-29 | Dish inventory information processing method, dish delivery method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179226.4A CN112307944A (en) | 2020-10-29 | 2020-10-29 | Dish inventory information processing method, dish delivery method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112307944A true CN112307944A (en) | 2021-02-02 |
Family
ID=74330749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011179226.4A Withdrawn CN112307944A (en) | 2020-10-29 | 2020-10-29 | Dish inventory information processing method, dish delivery method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112307944A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112880295A (en) * | 2021-02-05 | 2021-06-01 | 河南华天机电工程有限公司 | NFC-based automatic control system and method for refrigeration house and storage medium |
| CN116310619A (en) * | 2022-09-08 | 2023-06-23 | 广州里工实业有限公司 | Image data set generation method, system, electronic equipment and storage medium |
| CN117522281A (en) * | 2024-01-05 | 2024-02-06 | 山东通广电子股份有限公司 | Tool and instrument warehouse-in and warehouse-out management method and system based on visual identification |
| CN117522281B (en) * | 2024-01-05 | 2024-04-16 | 山东通广电子股份有限公司 | Tool and instrument warehouse-in and warehouse-out management method and system based on visual identification |
-
2020
- 2020-10-29 CN CN202011179226.4A patent/CN112307944A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112880295A (en) * | 2021-02-05 | 2021-06-01 | 河南华天机电工程有限公司 | NFC-based automatic control system and method for refrigeration house and storage medium |
| CN116310619A (en) * | 2022-09-08 | 2023-06-23 | 广州里工实业有限公司 | Image data set generation method, system, electronic equipment and storage medium |
| CN116310619B (en) * | 2022-09-08 | 2023-09-12 | 广州里工实业有限公司 | Image data set generation method, system, electronic equipment and storage medium |
| CN117522281A (en) * | 2024-01-05 | 2024-02-06 | 山东通广电子股份有限公司 | Tool and instrument warehouse-in and warehouse-out management method and system based on visual identification |
| CN117522281B (en) * | 2024-01-05 | 2024-04-16 | 山东通广电子股份有限公司 | Tool and instrument warehouse-in and warehouse-out management method and system based on visual identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN111259889A (en) | Image text recognition method and device, computer equipment and computer storage medium | |
| CN109886928B (en) | Target cell marking method, device, storage medium and terminal equipment | |
| US20030152272A1 (en) | Detecting overlapping images in an automatic image segmentation device with the presence of severe bleeding | |
| CA3115811C (en) | Methods and systems for processing an image in which a machine-readable code is at least partially obscured | |
| US10713530B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN108121982B (en) | Method and device for acquiring facial single image | |
| CN111325717B (en) | Mobile phone defect position identification method and equipment | |
| CN113469921B (en) | Image defect repairing method, system, computer device and storage medium | |
| CN114758249B (en) | Target object monitoring method, device, equipment and medium based on field night environment | |
| CN107862235B (en) | Two-dimensional code position positioning method and device and terminal equipment | |
| CN112307944A (en) | Dish inventory information processing method, dish delivery method and related device | |
| CN110781890A (en) | Identification card identification method and device, electronic equipment and readable storage medium | |
| CN111144372A (en) | Vehicle detection method, device, computer equipment and storage medium | |
| CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
| CN111241966A (en) | Invoice target area positioning method, device, equipment and medium | |
| CN110751004A (en) | Two-dimensional code detection method, device, equipment and storage medium | |
| KR101842535B1 (en) | Method for the optical detection of symbols | |
| WO2023160061A1 (en) | Method and apparatus for determining moving object in image, electronic device, and storage medium | |
| CN112307945A (en) | Dish inventory information processing method, dish delivery method and related device | |
| CN115909151A (en) | Method for identifying serial number of motion container under complex working condition | |
| CN112348112B (en) | Training method and training device for image recognition model and terminal equipment | |
| CN113780116A (en) | Invoice classification method and device, computer equipment and storage medium | |
| KR20220083347A (en) | Method, apparatus, and computer program for measuring volume of objects by using image | |
| CN111626074A (en) | Face classification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210202 |