CN116579363A - Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence - Google Patents
Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence Download PDFInfo
- Publication number
- CN116579363A CN116579363A CN202310480575.7A CN202310480575A CN116579363A CN 116579363 A CN116579363 A CN 116579363A CN 202310480575 A CN202310480575 A CN 202310480575A CN 116579363 A CN116579363 A CN 116579363A
- Authority
- CN
- China
- Prior art keywords
- module
- cigarette
- code
- artificial intelligence
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 67
- 238000012937 correction Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000005520 cutting process Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 210000004556 brain Anatomy 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 2
- 238000003032 molecular docking Methods 0.000 claims description 2
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 239000000047 product Substances 0.000 description 7
- 238000003860 storage Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 241000208125 Nicotiana Species 0.000 description 3
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 3
- 238000005282 brightening Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 101100384355 Mus musculus Ctnnbip1 gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
- G06K7/1473—Methods for optical code recognition the method including quality enhancement steps error correction
Abstract
The invention relates to the technical field of artificial intelligence, and particularly discloses an intelligent recognition and correction system and method for a cigarette carton code based on artificial intelligence, wherein the system comprises a pre-trigger sensor, and the trigger sensor is used for sensing whether the cigarette carton reaches a specified position or not and triggering a recognition program; the image acquisition module is used for acquiring image information of the cigarettes at multiple angles; the AI identification cutting module is used for processing the image to identify the position and the size information of the two-dimensional code image and cutting the two-dimensional code image; a decoder module, etc.; the invention relates to an auxiliary system added to a cigarette bar code recognition system, which is a two-dimensional code decoding system based on machine vision, wherein a high-speed industrial camera is adopted to collect images of cigarette bar codes; positioning a plurality of two-dimensional codes by using an AI algorithm; decoding the two-dimensional code by utilizing a stable, reliable and high-speed decoding algorithm; and correcting the error of the system by using an interface provided by the cigarette decoding system.
Description
Technical Field
The invention relates to the technical field of intelligent recognition, in particular to an intelligent recognition and error correction system and method for a cigarette bar code based on artificial intelligence.
Background
The cigarette two-dimensional code project is a basic, systematic and strategic project in the tobacco industry, is the first step for realizing the digitization of cigarette products, and is an important measure for further standardizing the production and operation of the industry. The construction content of the cigarette two-dimension code project comprises a two-dimension code management and control platform in the construction industry of a main company, a box condition association management system and a strip zero association management system are deployed and implemented in the industry and commerce enterprises, the data of all links of cigarette production and circulation are penetrated, a cigarette two-dimension code management system is formed, the innovative application of all units in the support industry based on the cigarette two-dimension code is carried out, and the efficiency and the level of production, operation and management in the industry are improved.
After the business enterprise finishes coding to strip on the sorting line through the industry production and operation decision-making system, the strip zero association management system establishes association relation (namely strip zero association) between the cigarette strip two-dimension code and the retail customer order by scanning the strip box two-dimension code and collecting retail customer order data, and forms the two-dimension code state of 'quotient zero distribution'.
In the existing 'strip zero' association management system, due to the problem of the posture of the cigarette strip, the condition of missing detection on the identification of the two-dimension code of the cigarette strip under a certain condition is caused. In order to improve the recognition rate and the decoding rate of the two-dimension code of the cigarette and avoid missing detection, an intelligent recognition and error correction system and method for the cigarette code based on artificial intelligence are provided.
Disclosure of Invention
The invention aims to provide an intelligent recognition and correction system and an intelligent recognition and correction method for a cigarette bar code based on artificial intelligence, wherein the intelligent recognition and correction system for the cigarette bar code based on AI adopts 4 industrial cameras (MV-CH 089-10 GM) for each special-shaped line to acquire images in the visual field where the bar code and the two-dimensional code possibly exist. The acquired image locates the bar code existing in the image through an AI algorithm; then decoding each bar code image to obtain bar code data; after operations such as collection and duplicate removal of bar code data, the summarized data are submitted to the bar zero-association field management subsystem through a communication interface provided by the bar zero-association field management subsystem, so that the bar zero-association field management subsystem performs error correction and supplements two-dimension codes according to the result, and therefore line stop is avoided, and the sorting efficiency of a sorting line is guaranteed.
In order to achieve the above purpose, the present invention provides the following technical solutions: an artificial intelligence based intelligent smoke code recognition and correction system, the system comprising:
the triggering sensor is used for sensing whether the cigarette reaches a specified position or not and triggering an identification program;
the image acquisition module is used for acquiring image information of the cigarettes at multiple angles;
the AI identification cutting module is used for processing the image to identify the position and the size information of the two-dimensional code image and cutting the two-dimensional code image;
a decoder module for decoding the final two-bit code image information;
the de-duplication module is used for removing repeated decoded information;
the lighting module is used for controlling the light supplementing illumination;
the data interface module is used for interfacing the system, and the decoded data packets after the duplication removal are shared as an error correction basis;
and the comparison module is used for receiving and comparing the decoded data packet and the code reader result and judging whether the code reading error exists or not.
As a preferred embodiment of the invention, the triggering sensor is a photoelectric sensor which continuously emits a triggering signal to the image acquisition module when the cigarette rod passes through the recognition area.
As a preferred embodiment of the present invention, the image acquisition module comprises four industrial cameras, and the industrial cameras respectively irradiate four angles of the cigarette.
As a preferred embodiment of the present invention, the AI-recognition clipping module includes:
the identification module is used for identifying the bar code as the position and the size;
and the cutting module is used for cutting the area with the bar code identified to generate two-dimensional code image data.
As a preferred embodiment of the present invention, the identification module includes:
the algorithm model module is used for storing a training algorithm model, and the concurrence model adopts a YOLOV5s deep learning model;
the picture cutting module is used for cutting the picture of the cigarette code into a plurality of specific areas with unique properties;
the similarity calculation module is used for calculating the region information and the data set in the AI model, then providing an interested target and giving the given target similarity;
and the output module is used for outputting files with up-to-standard similarity.
As a preferred embodiment of the present invention, wherein the decoder module is based on an open source decoding algorithm of zxing.
As a preferred embodiment of the present invention, wherein the lighting module comprises:
the LED light source is used as a basic light source;
a controller module for controlling a light source, comprising:
a flash mode module for adjusting to a flash mode,
a strobe mode module for adjusting to a strobe mode,
a brightness enhancement mode module for adjusting to a brightness enhancement mode,
a light source brightness module for adjusting the brightness of the light source,
and the strobe pulse width module is used for adjusting the strobe pulse width.
As a preferred implementation scheme of the invention, the system also provides a TCP/IP standard communication protocol for facilitating the docking of an external system.
An intelligent recognition and error correction method for a cigarette bar code based on artificial intelligence comprises the following steps:
step S1: detecting whether the cigarette reaches a detection position or not through a sensor, and continuously sending acquisition information to an image acquisition module when the sensor reaches the detection position;
step S2: the image acquisition module triggers the stroboscopic light source and continuously acquires image information after receiving the acquisition information;
step S3: identifying the position and the size information of the two-dimensional code through an AI identification cutting module, and cutting off the area information of the two-dimensional code;
step S4: decoding the cut two-dimensional code, performing de-duplication operation on the decoded information, and outputting an error correction information packet;
step S5: and importing the error correction information packet into a next hierarchical system as a comparison basis to carry out comparison and determine whether to identify errors.
As a preferred embodiment of the invention, the AI identification is based on a large amount of data marked by a cigarette code picture, after the large amount of data is fed into the convolutional neural network of the AI, the neurons similar to the human brain can perform calculation and data fitting, and the multi-layer artificial neural network trains the data to generate a data set as an AI model.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to an auxiliary system added to a cigarette bar code recognition system, which is a two-dimensional code decoding system based on machine vision, wherein a high-speed industrial camera is adopted to collect images of cigarette bar codes; positioning a plurality of two-dimensional codes by using an AI algorithm; decoding the two-dimensional code by utilizing a stable, reliable and high-speed decoding algorithm; and correcting the error of the system by using an interface provided by the cigarette decoding system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a block diagram of a system according to the present invention;
FIG. 2 is a diagram of an AI identification clipping module of the system of the invention;
FIG. 3 is a block diagram of an identification module of the system of the present invention;
FIG. 4 is a block diagram of a lighting module of the system of the present invention;
FIG. 5 is a block diagram of a controller module of the system of the present invention;
fig. 6 is a flow chart of the method of the present invention.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1 to 6, the technical scheme of the present invention is described in detail for achieving the above purpose.
The invention provides an artificial intelligence-based intelligent recognition and correction system for cigarette codes, which comprises the following components:
the triggering sensor is used for sensing whether the cigarette reaches a specified position or not and triggering an identification program;
the image acquisition module is used for acquiring image information of the cigarettes at multiple angles, and the image acquisition module adopts a black-and-white area array camera, such as: MV-CH089-10GM high-end area array camera adopts an IMX267 CMOS chip of Sony, has low noise point and high resolution and excellent image. Through the gigabit Ethernet interface, the uncompressed image is transmitted in real time, the highest frame rate under the full resolution can reach 13fps, the highest frame rate can reach 40fps through setting camera parameters, and automatic or manual adjustment of gain, exposure time, white balance, LUT, gamma correction and the like are supported; by adopting a gigabit Ethernet interface, the maximum transmission distance can reach 100m under the condition of no relay; the 128MB on-board cache can cache a plurality of pictures and is used for data transmission or image retransmission in a Burst mode; the method is compatible with the GigEVis ionV2.0 protocol and the GenlCap standard, and is seamlessly accessed into a third party software platform; the service life of the camera is more than or equal to 10 ten thousand hours, wherein the lens can be optimally designed aiming at the machine vision light source and the chip by adopting a KF series FA lens, the resolution is high, the imaging quality is excellent, the transmittance is high, and the stability is good. The manual aperture is compact in appearance due to fixed focal length. Can meet the application of the machine vision industry and is an ideal choice of industrial cameras. High resolution, high uniformity of picture definition; ultra-low distortion, high peripheral light ratio; maximum target surface 1.1"; the ultra-short working distance is supported, and excellent optical characteristics are kept at different object distances;
the AI identification cutting module is used for processing the image to identify the position and the size information of the two-dimensional code image and cutting the two-dimensional code image;
a decoder module for decoding the final two-bit code image information;
the de-duplication module is used for removing repeated decoded information;
a lighting module for controlling light replenishment, as shown in fig. 4-5, the lighting module comprising: the LED light source is used as a basic light source; a controller module for controlling a light source, comprising: the device comprises a normally-flashing mode module, a stroboscopic mode module, a brightening mode module, a light source brightness module, a stroboscopic pulse width module and a stroboscopic pulse width module, wherein the normally-flashing mode module is used for adjusting to a normally-flashing mode, the stroboscopic mode module is used for adjusting to a stroboscopic mode, the brightening mode module is used for adjusting to a brightening mode, the light source brightness module is used for adjusting the light source brightness, and the stroboscopic pulse width module is used for adjusting the stroboscopic pulse width; the specific lighting module adopts a high-brightness LED light source produced by OPT (ompter), and the continuous normal operation time of the light source reaches 50,000 hours; in the visual inspection system, it is important to obtain a contrast-sharp image, especially in the case of relatively special external conditions in the tobacco industry, the OSe light source can obtain a high brightness, uniform and stable effect. The OSe vision detection special light source is composed of LEDs with high performance chips, the LEDs are screened according to working voltage, brightness and wavelength (namely color) of the LEDs, the LEDs are divided into 32 grades, and according to shooting requirements and detection positions of a vision sensor of a vision detection device and the characteristics of colors of tobacco bales, the LED light source with relatively high grade is selected and is installed in a special light source processing device, so that consistency of brightness and color is ensured; to ensure that the vision system obtains stable image input, a special light source consisting of a group of independent LEDs for the vision detection system needs to be selected, so that the image processing part can maintain consistent accuracy, and the image system can obtain stable image input for a long time; the LED light source selected by the user enters a semi-debilitation period after 50,000 ten thousand hours under the condition of continuous use; in order to prolong the service life of the LED light source, the LED light source adopts a stroboscopic working mode, the service life of the light source can be prolonged to 100,000 ten thousand hours at maximum, and the light source parameters can set the exposure time and the brightness through software; the OPT DPA current type digital controller is adopted for the light source driver: 256-level brightness adjustment function (each brightness is individually controllable); a highlight triggering function; triggering a pulse width function; automatically detecting the maximum current of the light source; manually setting an output maximum current function; 100M ethernet communication; RS232 communication function; protection: with short-circuit protection and overload protection; the brightness of the light source, the exposure time and the like can be adjusted on line through software, and the light source and the man-machine interface are integrated into a whole, so that quick replacement of the license plate is facilitated.
The data interface module is used for interfacing the system, and the decoded data packets after the duplication removal are shared as an error correction basis;
and the comparison module is used for receiving and comparing the decoded data packet and the code reader result and judging whether the code reading error exists or not.
Further, the triggering sensor adopts a photoelectric sensor, and the photoelectric sensor continuously transmits a triggering signal to the image acquisition module when the cigarette rod passes through the identification area.
Further, the image acquisition module comprises four industrial cameras, and the industrial cameras respectively irradiate four angles of the cigarette carton.
Further, as shown in fig. 2, the AI-recognition clipping module includes:
the identification module is used for identifying the bar code as the position and the size;
and the cutting module is used for cutting the area with the bar code identified to generate two-dimensional code image data.
Further, as shown in fig. 3, the identification module includes:
the algorithm model module is used for storing a training algorithm model, and the concurrence model adopts a YOLOV5s deep learning model;
the picture cutting module is used for cutting the picture of the cigarette code into a plurality of specific areas with unique properties;
the similarity calculation module is used for calculating the region information and the data set in the AI model, then providing an interested target and giving the given target similarity;
and the output module is used for outputting files with up-to-standard similarity.
Further, a decoding algorithm based on open source decoding zxing is provided in the decoder module.
Furthermore, the system also provides a TCP/IP standard communication protocol which is used for facilitating the butt joint of an external system.
As shown in fig. 6, the invention further provides an artificial intelligence based intelligent recognition and correction method for the cigarette codes, which comprises the following steps:
step S1: detecting whether the cigarette reaches a detection position or not through a sensor, and continuously sending acquisition information to an image acquisition module when the sensor reaches the detection position;
step S2: the image acquisition module triggers the stroboscopic light source and continuously acquires image information after receiving the acquisition information;
step S3: identifying the position and the size information of the two-dimensional code through an AI identification cutting module, and cutting off the area information of the two-dimensional code;
step S4: decoding the cut two-dimensional code, performing de-duplication operation on the decoded information, and outputting an error correction information packet;
step S5: and importing the error correction information packet into a next hierarchical system as a comparison basis to carry out comparison and determine whether to identify errors.
Furthermore, the AI identification is based on a large amount of data calibrated by the cigarette code picture, after the large amount of data is fed to the convolutional neural network of the AI, the neurons similar to the human brain can perform calculation and data fitting, and the multi-layer artificial neural network trains the data to generate a data set as an AI model.
The present invention will be described in detail with reference to the following practical examples:
four high-speed high-resolution industrial cameras are installed on each special-shaped line in an actual use mode of the intelligent identification and error correction system of the cigarette bar codes based on the AI, shooting of different angles of the cigarette bar boxes on the assembly line is achieved, the obtained pictures are subjected to bar code positioning and decoding by the system, and decoding results are sent to the bar zero-association field management subsystem.
After the logistics system generates orders, the on-site sorting assembly line can form order assembly line, and one order assembly line comprises a plurality of cigarettes of different brands. When order flowing water flows to the installation position of the system, the photoelectric sensor is triggered; the sensor transmits a signal of flowing water arrival to the PLC, the PLC sends continuous pulse signals to the four cameras after receiving the signal, the cameras are triggered to continuously shoot, and the PLC stops pulse signal output until flowing water completely flows through the system. All pictures shot by a camera are subjected to two-dimension code positioning and decoding by a real-time decoding system running in an industrial personal computer, an obtained two-dimension code information set and an order serial number acquired from a streaming system are bound to form a data packet, the data packet is sent to an on-site subsystem through a TCP when one streaming process is finished, and the subsystem judges whether error correction is performed according to actual conditions after the two-dimension code is taken.
The principle for AI identification is as follows:
the AI identification is based on a large amount of data calibrated by the cigarette code picture, after the large amount of data is fed to the convolutional neural network of the AI, the neuron similar to the human brain can perform calculation and data fitting, the multi-layer artificial neural network trains the data, and a data set is generated as an AI model, so that intelligent identification can be realized.
When the AI performs intelligent recognition, the picture of the cigarette code is cut into a plurality of specific areas with unique properties, after calculation is performed with a data set in the AI model, an interesting target is put forward, the given target is endowed with similarity, and when the similarity reaches a certain upper limit, the successfully recognized cigarette code is obtained.
And opening a cigarette code picture group required to be trained by Adopting Intelligent (AI) image service platform software, calibrating cigarette codes in the pictures, and storing to generate json files, wherein the json files and the cigarette code pictures are data sets required to be fed to a nerve convolution network.
After a large number of data sets are obtained, the neural convolution network divides the picture into grids, predicts class probability and boundary boxes of each grid, and accordingly performs fitting calculation with real data calibrated in json files, the data sets can be obtained through fitting calculation once, meanwhile, the difference between the predicted value and the real value of the model is smaller and smaller, and when the difference value is infinitely close to 0, an AI model capable of being intelligently identified can be obtained.
In the selection of the AI algorithm, we selected the YoLOV5s deep learning model. The model ensures the detection precision and the detection speed.
Target detection is classified into Two stage and One stage. An algorithm for simultaneously generating candidate regions and predicting the class and position of an object using only One network is generally called a single-stage detection algorithm (One stage). Common One stage models are YOLO, SSD, etc. One stage is an important reason for implementing the YOLO algorithm to detect rapidly.
After the trained AI model is adopted for detection, the position and the size of the two-dimensional code in the shot photo can be preliminarily determined.
After the shape and position size ROI of the two-dimensional code on the graph is determined, the image wrapped by the two-dimensional code ROI can be cut out and sent to a two-dimensional code decoding program for decoding.
Two-dimensional code decoding algorithm we use a self-developed improved decoding algorithm based on open source decoding zxing. The zxing item is an open source item which is pushed out by google and used for identifying bar codes in various formats, the item address is https:// github.
And for error correction, finally comparing the output data packet with the read data of the code reader through a comparison module, judging whether the difference exists, and reporting errors if the condition of missing detection exists.
The processor takes out instructions from the memory one by one, analyzes the instructions, then completes corresponding operation according to the instruction requirement, generates a series of control commands, enables all parts of the computer to automatically, continuously and cooperatively act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
For example, a computer program may be split into one or more modules, one or more modules stored in memory and executed by a processor to perform the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the terminal device.
It will be appreciated by those skilled in the art that the foregoing description of the service device is merely an example and is not meant to be limiting, and may include more or fewer components than the foregoing description, or may combine certain components, or different components, such as may include input-output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Process ing Unit, CPU), other general purpose processors, digital signal processors (Digi tal Signal Processor, DSP), application specific integrated circuits (Appl icat ion Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal device described above, and which connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used for storing computer programs and/or modules, and the processor may implement various functions of the terminal device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as an information acquisition template display function, a product information release function, etc.), and the like; the storage data area may store data created according to the use of the berth status display system (e.g., product information acquisition templates corresponding to different product types, product information required to be released by different product providers, etc.), and so on. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid state storage device.
The modules/units integrated in the terminal device may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on this understanding, the present invention may implement all or part of the modules/units in the system of the above-described embodiments, or may be implemented by instructing the relevant hardware by a computer program, which may be stored in a computer-readable storage medium, and which, when executed by a processor, may implement the functions of the respective system embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention thereto. Any modifications, equivalent substitutions, improvements, etc. within the principles and practice of the present invention are intended to be included within the scope of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. An artificial intelligence based intelligent recognition and error correction system for cigarette codes, which is characterized by comprising:
the triggering sensor is used for sensing whether the cigarette reaches a specified position or not and triggering an identification program;
the image acquisition module is used for acquiring image information of the cigarettes at multiple angles;
the AI identification cutting module is used for processing the image to identify the position and the size information of the two-dimensional code image and cutting the two-dimensional code image;
a decoder module for decoding the final two-bit code image information;
the de-duplication module is used for removing repeated decoded information;
the lighting module is used for controlling the light supplementing illumination;
the data interface module is used for interfacing the system, and the decoded data packets after the duplication removal are shared as an error correction basis;
and the comparison module is used for receiving and comparing the decoded data packet and the code reader result and judging whether the code reading error exists or not.
2. The intelligent recognition and correction system for cigarette codes based on artificial intelligence of claim 1, wherein the triggering sensor employs a photoelectric sensor which continuously transmits a triggering signal to the image acquisition module when the cigarette passes through the recognition area.
3. The intelligent recognition and correction system for cigarette codes based on artificial intelligence of claim 2, wherein the image acquisition module comprises four industrial cameras, and the industrial cameras respectively irradiate four angles of the cigarette.
4. The intelligent artificial intelligence based cigarette rod recognition and correction system of claim 3, wherein the AI recognition clipping module comprises:
the identification module is used for identifying the bar code as the position and the size;
and the cutting module is used for cutting the area with the bar code identified to generate two-dimensional code image data.
5. The intelligent artificial intelligence based cigarette rod code identification and correction system of claim 4, wherein the identification module comprises:
the algorithm model module is used for storing a training algorithm model, and the concurrence model adopts a YOLOV5s deep learning model;
the picture cutting module is used for cutting the picture of the cigarette code into a plurality of specific areas with unique properties;
the similarity calculation module is used for calculating the region information and the data set in the AI model, then providing an interested target and giving the given target similarity;
and the output module is used for outputting files with up-to-standard similarity.
6. The intelligent artificial intelligence based bar code recognition and correction system of claim 5, wherein the decoder module is based on an open source decoding algorithm of zxing.
7. The intelligent artificial intelligence based cigarette rod code identification and correction system of claim 6, wherein the lighting module comprises:
the LED light source is used as a basic light source;
a controller module for controlling a light source, comprising:
the normal flash mode module is used for adjusting to a normal flash mode;
a strobe mode module for adjusting to a strobe mode;
the brightness enhancement mode module is used for adjusting to a brightness enhancement mode;
the light source brightness module is used for adjusting the brightness of the light source;
and the strobe pulse width module is used for adjusting the strobe pulse width.
8. The intelligent recognition and correction system for cigarette codes based on artificial intelligence according to claim 7, wherein the system further provides a TCP/IP standard communication protocol for facilitating the docking of an external system.
9. An artificial intelligence based intelligent recognition and correction method for cigarette codes, which is characterized in that the method is based on the system of any one of claims 1-8, and comprises the following steps:
step S1: detecting whether the cigarette reaches a detection position or not through a sensor, and continuously sending acquisition information to an image acquisition module when the sensor reaches the detection position;
step S2: the image acquisition module triggers the stroboscopic light source and continuously acquires image information after receiving the acquisition information;
step S3: identifying the position and the size information of the two-dimensional code through an AI identification cutting module, and cutting off the area information of the two-dimensional code;
step S4: decoding the cut two-dimensional code, performing de-duplication operation on the decoded information, and outputting an error correction information packet;
step S5: and importing the error correction information packet into a next hierarchical system as a comparison basis to carry out comparison and determine whether to identify errors.
10. The intelligent recognition and error correction method for the cigarette bar codes based on the artificial intelligence according to claim 9, wherein the AI recognition is based on a large amount of data calibrated by a cigarette bar code picture, after the large amount of data is fed into an AI convolutional neural network, the neurons similar to human brain can perform calculation and data fitting, and the multi-layer artificial neural network trains the data to generate a data set as an AI model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310480575.7A CN116579363A (en) | 2023-04-28 | 2023-04-28 | Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310480575.7A CN116579363A (en) | 2023-04-28 | 2023-04-28 | Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116579363A true CN116579363A (en) | 2023-08-11 |
Family
ID=87538886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310480575.7A Pending CN116579363A (en) | 2023-04-28 | 2023-04-28 | Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116579363A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117556847A (en) * | 2024-01-05 | 2024-02-13 | 深圳爱莫科技有限公司 | Identification method of two-dimension code of cigarette end |
-
2023
- 2023-04-28 CN CN202310480575.7A patent/CN116579363A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117556847A (en) * | 2024-01-05 | 2024-02-13 | 深圳爱莫科技有限公司 | Identification method of two-dimension code of cigarette end |
| CN117556847B (en) * | 2024-01-05 | 2024-04-26 | 深圳爱莫科技有限公司 | Identification method of two-dimension code of cigarette end |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10373024B2 (en) | Image processing device, object detection device, image processing method | |
| US11087447B2 (en) | Systems and methods for quality assurance of image recognition model | |
| KR102097905B1 (en) | Apparatus and method for recognizing one or more objects in images | |
| CN108717530B (en) | Image processing method, image processing device, computer-readable storage medium and electronic equipment | |
| CN116579363A (en) | Intelligent recognition and error correction system and method for cigarette bar codes based on artificial intelligence | |
| US20230394818A1 (en) | Systems and methods for enhancing real-time image recognition | |
| CN112699697B (en) | Code reader and method for reading optical code | |
| US20210024297A1 (en) | System and method for sorting moving objects | |
| US20210337073A1 (en) | Print quality assessments via patch classification | |
| CN114511820A (en) | Goods shelf commodity detection method and device, computer equipment and storage medium | |
| CN113361657A (en) | Device and method for identifying box number of cigarette box, tobacco shred boxing equipment and industrial personal computer | |
| CN110580185B (en) | Data preprocessing method, device and storage medium | |
| US11562561B2 (en) | Object verification/recognition with limited input | |
| CN115479891A (en) | Automatic detection system and method for circuit board mounted components based on image recognition | |
| CN114022367A (en) | Image quality adjusting method, device, electronic equipment and medium | |
| Kuo et al. | Design and Implementation of AI aided Fruit Grading Using Image Recognition | |
| CN111351754A (en) | Bottle bottom defect detection system and method | |
| CN113837173A (en) | Target object detection method and device, computer equipment and storage medium | |
| WO2020079391A1 (en) | Method and apparatus for tracking nematode worms | |
| JP2021050945A (en) | Object recognition device and object recognition program | |
| JP5853345B2 (en) | Focus index calculation apparatus, image processing apparatus, computer program, and focus index calculation method | |
| CN116050447B (en) | Scanning method and related equipment | |
| CN113556536B (en) | Camera synchronization detection method and device, electronic equipment and storage medium | |
| CN116753496A (en) | Stage lamp maintenance method and system | |
| US20210327047A1 (en) | Local defect determinations |
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 |