CN110263596A - A kind of two dimensional code detection system and method - Google Patents
A kind of two dimensional code detection system and method Download PDFInfo
- Publication number
- CN110263596A CN110263596A CN201910554030.XA CN201910554030A CN110263596A CN 110263596 A CN110263596 A CN 110263596A CN 201910554030 A CN201910554030 A CN 201910554030A CN 110263596 A CN110263596 A CN 110263596A
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- code
- dimensional
- good fortune
- described 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
Classifications
-
- 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
- G06K17/0025—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 consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
-
- 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
- G06K7/1417—2D bar codes
-
- 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
Abstract
The present invention provides a kind of two dimensional code detection system and method, is detected from described image in the present invention using fpga chip and obtain two dimensional code, and two dimensional code identification is carried out to the two dimensional code, obtain the particular content of two dimensional code.Since fpga chip belongs to hardware, in the task that operation is simple and repeatability is high, FPGA computing capability is very strong.Also, the programming and optimization of FPGA is all directly to carry out in hardware view, and energy consumption can be much lower.Two dimensional code positioning and identification are carried out by using fpga chip, can reduce energy consumption and improve computational efficiency.
Description
Technical field
The present invention relates to two dimensional code detection fields, more specifically, being related to a kind of two dimensional code detection system and method.
Background technique
Full-automatic press quality amount detection systems are a kind of detection systems that view-based access control model is online, most of to pass through video camera
Both online scanning printing image, is then sent to memory and is handled by image processing software, as a result compared with normal data, find out
Between difference and analyze generation source of error, and then redesign parameter, preferably improve printing quality.
The support of printed matter is two dimensional code, fast and accurately positions and identify that two dimensional code becomes the head of print quality inspection
Want task.The current positioning and identification that GPU and CPU can be used and carry out two dimensional code, but processing of the CPU as general purpose computer
Core, it is necessary to have the ability that all kinds of very strange instructions of processing require, and because to handle from multiple equipment
Request, it, which must possess, stops current operation at any time and transfers to carry out other operations, and therefrom breakpoint succession is current again after the completion
The ability of operation.So CPU general-purpose capability enhancing and computational efficiency will weaken.And although GPU is versed in largely repeating
Operation, but power consumption is very big.
Summary of the invention
In view of this, the present invention provides a kind of two dimensional code detection system and method, to solve in the positioning for carrying out two dimensional code
And when identification, the computational efficiency of CPU is lower and the power consumption of GPU is larger problem.
In order to solve the above technical problems, present invention employs following technical solutions:
A kind of two dimensional code detection system, comprising:
Two dimensional code locating module, for the movement velocity of the equipment according to transmission two dimensional code, to determine the two dimensional code
Move distance orient the position where the two dimensional code according to the move distance;
Two dimensional code acquisition module, for acquiring the image of the position according to the position where the two dimensional code;
Field programmable gate array fpga chip obtains two dimensional code for detecting from described image, and to described
Two dimensional code carries out two dimensional code identification, obtains the particular content of two dimensional code.
Preferably, the fpga chip is for being specifically used for when detection obtains two dimensional code from described image:
Extract the two dimensional code location information in described image;
Described image is split as multiple suggestion windows;
Convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to last convolution
Layer;
Data after convolution operation are subjected to pondization operation, to navigate to two-dimentional code position and position from described image
The position of good fortune code in the two dimensional code.
Preferably, the fpga chip is used to carry out two dimensional code identification to the two dimensional code, obtains the specific interior of two dimensional code
Rong Shi is specifically used for:
According to the two-dimentional code position navigated to, the two dimensional code is identified, two-dimensional barcode information is obtained;
According to the position of the good fortune code navigated to, the good fortune code is identified, good fortune code information is obtained;
Summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
Preferably, the fpga chip is used to identify the good fortune code according to the position of the good fortune code navigated to, obtain
When good fortune code information, it is specifically used for:
According to the position of the good fortune code navigated to, the good fortune code is extracted from described image;
The good fortune code extracted is identified, the good fortune code information is obtained.
It preferably, further include that two dimensional code rejects module;
The fpga chip is also used to make comparisons the particular content of the two dimensional code with default QR code content, if not
Unanimously, it issues two dimensional code and rejects instruction to two dimensional code rejecting module;
The two dimensional code rejects module, for executing goods rejection operation to the two dimensional code.
Preferably, the two dimensional code acquisition module includes multiple camera units;
Each camera unit, for either synchronously or asynchronously according to the position where the different two dimensional codes, acquisition to be every
The image of one position.
Preferably, the fpga chip is used for before detection obtains two dimensional code in described image, is also used to:
Image pretreatment operation is carried out to described image;Described image pretreatment operation includes image format conversion and image
At least one of compression.
A kind of two dimension code detection method, applied to above-mentioned fpga chip, the two dimension code detection method includes:
Detection obtains two dimensional code from the image that two dimensional code acquisition module acquires, and carries out two dimensional code knowledge to the two dimensional code
Not, the particular content of two dimensional code is obtained.
Preferably, the detection from the image that two dimensional code acquisition module acquires obtains two dimensional code, comprising:
Extract the two dimensional code location information in described image;
Described image is split as multiple suggestion windows;
Convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to last convolution
Layer;
Data after convolution operation are subjected to pondization operation, to navigate to two-dimentional code position and position from described image
The position of good fortune code in the two dimensional code.
Preferably, described that two dimensional code identification is carried out to the two dimensional code, obtain the particular content of two dimensional code, comprising:
According to the two-dimentional code position navigated to, the two dimensional code is identified, two-dimensional barcode information is obtained;
According to the position of the good fortune code navigated to, the good fortune code is identified, good fortune code information is obtained;
Summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
Compared to the prior art, the invention has the following advantages:
The present invention provides a kind of two dimensional code detection system and method, use fpga chip from described image in the present invention
Detection obtains two dimensional code, and carries out two dimensional code identification to the two dimensional code, obtains the particular content of two dimensional code.Due to fpga chip
Belong to hardware, in the task that operation is simple and repeatability is high, FPGA computing capability is very strong.Also, the programming and optimization of FPGA
It is all directly to be carried out in hardware view, energy consumption can be much lower.Two dimensional code positioning and identification, energy are carried out by using fpga chip
It enough reduces energy consumption and improves computational efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of structural schematic diagram of two dimensional code detection system provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of another two dimensional code detection system provided in an embodiment of the present invention;
Fig. 3 is a kind of method of the two dimensional code localization method applied to two dimensional code detection system provided in an embodiment of the present invention
Flow chart;
Fig. 4 be it is provided in an embodiment of the present invention another be applied to two dimensional code detection system two dimensional code localization method side
Method flow chart;
Fig. 5 be it is provided in an embodiment of the present invention another be applied to two dimensional code detection system two dimensional code localization method side
Method flow chart.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The current positioning and identification that GPU and CPU can be used and carry out two dimensional code, but place of the CPU as general purpose computer
Manage core, it is necessary to have the ability that all kinds of very strange instructions of processing require, and set because to handle from multiple
Standby request, it, which must possess, stops current operation at any time and transfers to carry out other operations, and therefrom breakpoint succession is worked as again after the completion
The ability of preceding operation.So CPU general-purpose capability enhancing and computational efficiency will weaken.And although GPU is versed in largely weight
Multiple operation, but power consumption is very big.Based on this, the embodiment of the present invention is proposed.
Specifically, the two dimensional code detection system is used for two the embodiment of the invention provides a kind of two dimensional code detection system
Tie up code positioning and identification.Referring to Fig.1, two dimensional code detection system may include:
Two dimensional code locating module 101, for the movement velocity of the equipment according to transmission two dimensional code, to determine the two dimension
The move distance of code orients the position where the two dimensional code according to the move distance;
Two dimensional code acquisition module 103, for acquiring the image of the position according to the position where the two dimensional code;
Field programmable gate array fpga chip 102 obtains two dimensional code for detecting from described image, and to institute
It states two dimensional code and carries out two dimensional code identification, obtain the particular content of two dimensional code.
Wherein, two dimensional code locating module 101 includes incremental encoder and sensor, incremental encoder rotating wheel perimeter
204mm, pulse are 2500, and each pulse is 0.082mm, and pulse represents platform movement velocity.Transmit the platform of two dimensional code
Pulse number is calculated by sensor after operation, to judge range ability, and then two dimensional code region is judged, figure can be locked
As acquisition position.
Two dimensional code acquisition module 103 may include multiple camera units;
Each camera unit, for either synchronously or asynchronously according to the position where the different two dimensional codes, acquisition to be every
The image of one position.The image of camera unit acquisition includes complete two dimensional code.
Specifically, camera unit can be more mesh cameras, 1-8 complementary metal oxide semiconductor CMOS camera shooting is supported
Head, it is synchronous or asynchronous that image capture module 1021 in fpga chip 102 according to image capture position triggers CMOS camera
Image is acquired, and is connected respectively by gigabit network interface with the image capture module 1022 in fpga chip 102, image capture module
1021 send great amount of images the image processing module 1022 into fpga chip 102.
It should be noted that being programmed by FPGA, can change between the arithmetic logic and unit of each unit of FPGA
Connection type, this framework makes FPGA computing capability very strong, especially in the task that operation is simple and repeatability is high.Simultaneously
The programming and optimization of FPGA is all directly to carry out in hardware view, and energy consumption can be much lower, so this hardware makes depth neural
The training time of network is very suitable.
After image processing module 1022 gets a large amount of image, image pretreatment operation is carried out to described image;Institute
Stating image pretreatment operation includes at least one of image format conversion and compression of images.
After image processing module 1022 carries out image pretreatment operation to image, image is exported to two dimensional code and detects mould
Then block 1023, two dimensional code detection module 1023 export to two dimensional code for positioning to the two dimensional code in image and identify mould
Block 1024 obtains two dimensional code recognition result, is exported by result output module 1025.
It optionally, further include that two dimensional code rejects module 104 referring to Fig. 2 on the basis of the present embodiment;
The fpga chip 102 is also used to make comparisons the particular content of the two dimensional code with default QR code content, if
It is inconsistent, it issues two dimensional code and rejects instruction to two dimensional code rejecting module 104;
The two dimensional code rejects module 104, for executing goods rejection operation to the two dimensional code.
Specifically, setting two dimensional code in the present embodiment rejects module 104, for executing rejecting to underproof two dimensional code
Operation, fpga chip 102, if inconsistent, lead in the particular content of the two dimensional code is made comparisons with default QR code content
Know that two dimensional code rejects module 104 and executes goods rejection operation.Wherein, default QR code content is that the two dimensional code is corresponding correctly
QR code content.Goods rejection operation can be using rejection device waste product removing, go up wrong two words as scanning machine scans, or
Hair dryer blows underproof two dimensional code to waste product area, and at the same time alarm lamp is alarmed.
Two dimensional code detection system uses power supply module 105 fixed for two dimensional code acquisition module 103, fpga chip 102, two dimensional code
Position module 101 and two dimensional code reject module 104 and power.
Detected from described image in the present embodiment using fpga chip 102 and obtain two dimensional code, and to the two dimensional code into
The identification of row two dimensional code, obtains the particular content of two dimensional code.Since fpga chip 102 belongs to hardware, and repeatability simple in operation
When high task, FPGA computing capability is very strong.Also, the programming and optimization of FPGA is all directly to carry out in hardware view, energy consumption
It can be much lower.Two dimensional code positioning and identification are carried out by using fpga chip 102, energy consumption is can reduce and improves to calculate and imitate
Rate.Also, in printing machine high-speed cruising, more mesh camera collection images are triggered using FPGA, can guarantee that no leakage is adopted and nothing
Leakage is picked.
Optionally, based on any of the above embodiments, referring to Fig. 3, the fpga chip 102 is used for from described image
When middle detection obtains two dimensional code, it is specifically used for:
Two dimensional code location information in S11, extraction described image.
Specifically, being provided with location information in four corners of two dimensional code there are three angle, the spy being extracted from image
Sign, and as deep learning model, such as the input of convolutional neural networks.
Wherein, the building process of convolutional neural networks includes:
1, the index of framing is understood first;
Index respectively include:
1) inference time of free hand drawing operation;
2) single image operation EMS memory occupation amount;
3) time loss of free hand drawing image;
4) time loss of more figure parallel processings;
5) there are linear approximate relationships between operand and inference time.
2, deep learning frame is built, is specifically included:
One, installation foundation library
Two, installation unified calculation equipment framework Cuda;
Three, certain dependence library such as opencv boost Cudnn are installed
Four, convolutional neural networks frame Caffe is installed.
3, sample production, label, pretreatment, Configuration network parameter and training.
Specifically, forward direction input image data is closely related by calculating intersection using ZFnet as network structure structural classification device
Softmax function calculates all kinds of probability, and according to calibration class, the likelihood probability that forward direction maximizes the class where a certain picture may
Derivation is crossed, gradient derivation is carried out to preceding layer by retrospectively calculate later layer and thus obtains the optimal weight of each layer of model.
Deep learning model is being obtained, after convolutional neural networks, the two dimensional code in the described image of extraction is being positioned
Information exports convolutional neural networks.
S12, described image is split as multiple suggestion windows.
S13, convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to last
Convolutional layer.
It is generated with RPN (RegionProposal Network) and suggests window (proposals), every image generates N number of
It is recommended that window.
Specifically, one picture breakdown is suggested that window, each suggestion window stretch the figure to be formed at a large amount of with RPN
As that all can extract feature separately through convolutional neural networks CNN, actually suggestion window can be largely overlapped, so only last
On convolutional layer feature map, it is added and suggests that window makes suggestion number of windows so that CNN operation before this is shared
Greatly reduce, quality also has the raising of essence.
S14, the data after convolution operation are carried out to pondization operation, to navigate to two-dimentional code position from described image
With the position for the good fortune code being located in the two dimensional code.
Wherein, include good fortune code in image in 2 D code, the position of two dimensional code and good fortune code can be recognized simultaneously through this embodiment
It sets.Good fortune code is a kind of two dimensional code of improvement, the characteristic with anti-copying and non-boundary.
Specifically, making each RoI generate fixed-size Feature Mapping feature by pooling layers of pond layer RoI
map.Using Softmax Loss (detection class probability) and Smooth L1 Loss (detection frame returns) to class probability with
Frame returns (Bounding box regression) associated prediction, and then can navigate to two-dimentional code position and be located at described
The position of good fortune code in two dimensional code, and the successful probability of positioning.
Optionally, on the basis of the present embodiment, referring to Fig. 4, the fpga chip 102 is used to carry out the two dimensional code
Two dimensional code identification, when obtaining the particular content of two dimensional code, is specifically used for:
The two-dimentional code position that S21, foundation navigate to, identifies the two dimensional code, obtains two-dimensional barcode information;
The position for the good fortune code that S22, foundation navigate to, identifies the good fortune code, obtains good fortune code information;
S23, summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
Optionally, on the basis of the present embodiment, the fpga chip 102 is used for the position according to the good fortune code navigated to,
The good fortune code is identified, when obtaining good fortune code information, is specifically used for:
The position for the good fortune code that S31, foundation navigate to, extracts the good fortune code from described image;
S32, the good fortune code extracted is identified, obtains the good fortune code information.
Two dimensional code identification module 1024 can be according to the code position of the acquisition of two dimensional code detection module 1023 and according to code classification tune
It is decoded with the recognition algorithm of corresponding code, obtains code value and be transmitted to next result output module 1025.
Specifically, corresponding image data is extracted, to picture number according to the code position that two dimensional code detection module 1023 obtains
According to the necessary image procossings such as gray processing, image enhancement, binaryzation are carried out, then corresponding recognition is called to calculate according to code classification
Method is decoded, i.e. two dimensional code identification uses two dimensional code recognizer, and the identification of good fortune code uses good fortune code recognizer, and identification obtains
As a result after, result is transferred to result output module 1025.
The present embodiment, using the positioning of two dimensional code in deep learning model realization image and the positioning of good fortune code, it is fixed to improve
Position efficiency.In addition, identifying to two dimensional code and good fortune code using different recognizers, a plurality of types of code systems can be quickly positioned.
And improve recognition accuracy and efficiency.
Optionally, on the basis of the embodiment of above-mentioned two dimensional code detection system, another embodiment of the present invention is provided
A kind of two dimension code detection method, applied to above-mentioned fpga chip, the two dimension code detection method includes:
Detection obtains two dimensional code from the image that two dimensional code acquisition module acquires, and carries out two dimensional code knowledge to the two dimensional code
Not, the particular content of two dimensional code is obtained.
Further, the detection from the image that two dimensional code acquisition module acquires obtains two dimensional code, comprising:
Extract the two dimensional code location information in described image;
Described image is split as multiple suggestion windows;
Convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to last convolution
Layer;
Data after convolution operation are subjected to pondization operation, to navigate to two-dimentional code position and position from described image
The position of good fortune code in the two dimensional code.
Further, described that two dimensional code identification is carried out to the two dimensional code, obtain the particular content of two dimensional code, comprising:
According to the two-dimentional code position navigated to, the two dimensional code is identified, two-dimensional barcode information is obtained;
According to the position of the good fortune code navigated to, the good fortune code is identified, good fortune code information is obtained;
Summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
Further, the position according to the good fortune code navigated to, identifies the good fortune code, obtains good fortune code information, comprising:
According to the position of the good fortune code navigated to, the good fortune code is extracted from described image;
The good fortune code extracted is identified, the good fortune code information is obtained.
Detected from described image in the present embodiment using fpga chip 102 and obtain two dimensional code, and to the two dimensional code into
The identification of row two dimensional code, obtains the particular content of two dimensional code.Since fpga chip 102 belongs to hardware, and repeatability simple in operation
When high task, FPGA computing capability is very strong.Also, the programming and optimization of FPGA is all directly to carry out in hardware view, energy consumption
It can be much lower.Two dimensional code positioning and identification are carried out by using fpga chip 102, energy consumption is can reduce and improves to calculate and imitate
Rate.Also, in printing machine high-speed cruising, more mesh camera collection images are triggered using FPGA, can guarantee that no leakage is adopted and nothing
Leakage is picked.
It should be noted that in the present embodiment FPGA the course of work, please refer to the respective description in above-described embodiment,
This is repeated no more.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of two dimensional code detection system characterized by comprising
Two dimensional code locating module, for the movement velocity of the equipment according to transmission two dimensional code, to determine the fortune of the two dimensional code
Dynamic distance orients the position where the two dimensional code according to the move distance;
Two dimensional code acquisition module, for acquiring the image of the position according to the position where the two dimensional code;
Field programmable gate array fpga chip obtains two dimensional code for detecting from described image, and to the two dimension
Code carries out two dimensional code identification, obtains the particular content of two dimensional code.
2. two dimensional code detection system according to claim 1, which is characterized in that the fpga chip is used for from described image
When middle detection obtains two dimensional code, it is specifically used for:
Extract the two dimensional code location information in described image;
Described image is split as multiple suggestion windows;
Convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to concluding volume lamination;
Data after convolution operation are subjected to pondization operation, to navigate to two-dimentional code position from described image and be located at institute
State the position of the good fortune code in two dimensional code.
3. two dimensional code detection system according to claim 2, which is characterized in that the fpga chip is used for the two dimension
Code carries out two dimensional code identification and is specifically used for when obtaining the particular content of two dimensional code:
According to the two-dimentional code position navigated to, the two dimensional code is identified, two-dimensional barcode information is obtained;
According to the position of the good fortune code navigated to, the good fortune code is identified, good fortune code information is obtained;
Summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
4. two dimensional code detection system according to claim 3, which is characterized in that the fpga chip is used for foundation and navigates to
Good fortune code position, the good fortune code is identified, when obtaining good fortune code information, is specifically used for:
According to the position of the good fortune code navigated to, the good fortune code is extracted from described image;
The good fortune code extracted is identified, the good fortune code information is obtained.
5. two dimensional code detection system according to claim 1, which is characterized in that further include that two dimensional code rejects module;
The fpga chip is also used to make comparisons the particular content of the two dimensional code with default QR code content, if inconsistent,
It issues two dimensional code and rejects instruction to two dimensional code rejecting module;
The two dimensional code rejects module, for executing goods rejection operation to the two dimensional code.
6. two dimensional code detection system according to claim 1, which is characterized in that the two dimensional code acquisition module includes multiple
Camera unit;
Each camera unit, for either synchronously or asynchronously according to the position where the different two dimensional codes, acquiring each institute
The image that rheme is set.
7. two dimensional code detection system according to claim 1, which is characterized in that the fpga chip is used for from described image
Before middle detection obtains two dimensional code, it is also used to:
Image pretreatment operation is carried out to described image;Described image pretreatment operation includes image format conversion and compression of images
At least one of.
8. a kind of two dimension code detection method, which is characterized in that be applied to fpga chip as described in claim 1, the two dimension
Code detection method includes:
Detection obtains two dimensional code from the image that two dimensional code acquisition module acquires, and carries out two dimensional code identification to the two dimensional code,
Obtain the particular content of two dimensional code.
9. it is according to claim 8 two dimension code detection method, which is characterized in that it is described from two dimensional code acquisition module acquire
Detection obtains two dimensional code in image, comprising:
Extract the two dimensional code location information in described image;
Described image is split as multiple suggestion windows;
Convolution operation is carried out to the two dimensional code location information;Wherein, the suggestion window is mapped to concluding volume lamination;
Data after convolution operation are subjected to pondization operation, to navigate to two-dimentional code position from described image and be located at institute
State the position of the good fortune code in two dimensional code.
10. two dimension code detection method according to claim 9, which is characterized in that described to carry out two dimension to the two dimensional code
Code identification, obtains the particular content of two dimensional code, comprising:
According to the two-dimentional code position navigated to, the two dimensional code is identified, two-dimensional barcode information is obtained;
According to the position of the good fortune code navigated to, the good fortune code is identified, good fortune code information is obtained;
Summarize the two-dimensional barcode information and the good fortune code information to obtain the particular content of the two dimensional code.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910554030.XA CN110263596A (en) | 2019-06-25 | 2019-06-25 | A kind of two dimensional code detection system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910554030.XA CN110263596A (en) | 2019-06-25 | 2019-06-25 | A kind of two dimensional code detection system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110263596A true CN110263596A (en) | 2019-09-20 |
Family
ID=67921261
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910554030.XA Pending CN110263596A (en) | 2019-06-25 | 2019-06-25 | A kind of two dimensional code detection system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110263596A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017157034A1 (en) * | 2016-03-15 | 2017-09-21 | 中兴通讯股份有限公司 | Method, device, and storage medium for identifying two-dimensional code |
CN109815770A (en) * | 2019-01-31 | 2019-05-28 | 北京旷视科技有限公司 | Two-dimentional code detection method, apparatus and system |
-
2019
- 2019-06-25 CN CN201910554030.XA patent/CN110263596A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017157034A1 (en) * | 2016-03-15 | 2017-09-21 | 中兴通讯股份有限公司 | Method, device, and storage medium for identifying two-dimensional code |
CN109815770A (en) * | 2019-01-31 | 2019-05-28 | 北京旷视科技有限公司 | Two-dimentional code detection method, apparatus and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113673425B (en) | Multi-view target detection method and system based on Transformer | |
CN110781838A (en) | Multi-modal trajectory prediction method for pedestrian in complex scene | |
Zheng et al. | HLU 2-Net: a residual U-structure embedded U-Net with hybrid loss for tire defect inspection | |
CN110610210B (en) | Multi-target detection method | |
CN115861619A (en) | Airborne LiDAR (light detection and ranging) urban point cloud semantic segmentation method and system of recursive residual double-attention kernel point convolution network | |
CN114529821A (en) | Offshore wind power safety monitoring and early warning method based on machine vision | |
Yin | Object Detection Based on Deep Learning: A Brief Review | |
Wang et al. | Based on the improved YOLOV3 small target detection algorithm | |
CN114782827B (en) | Object capture point acquisition method and device based on image | |
CN110263596A (en) | A kind of two dimensional code detection system and method | |
Tian et al. | BAN, a barcode accurate detection network | |
CN115410160A (en) | Pedestrian detection method and system based on MPDNet model | |
CN115063831A (en) | High-performance pedestrian retrieval and re-identification method and device | |
CN111143544B (en) | Method and device for extracting bar graph information based on neural network | |
CN114937153A (en) | Neural network-based visual feature processing system and method under weak texture environment | |
Yu et al. | Surface Defect inspection under a small training set condition | |
CN113496210A (en) | Attention mechanism-based photovoltaic string tracking and fault tracking method | |
Yang | FMP-Net: Fractal Multi-Gate Mixture-of-Experts Panoramic Segmentation for Point Cloud | |
Wu et al. | Express parcel detection based on improved faster regions with CNN features | |
Zhang et al. | RUI LI | |
Vaidya et al. | Detecting Buildings from Remote Sensing Imagery: Unleashing the Power of YOLOv5 and YOLOv8 | |
Baczmanski et al. | Detection-segmentation convolutional neural network for autonomous vehicle perception | |
Wang et al. | Self-Attentive Local Aggregation Learning With Prototype Guided Regularization for Point Cloud Semantic Segmentation of High-Speed Railways | |
Patel et al. | Object Detection using Machine Learning: A Survey | |
Kumar et al. | GPU Acceleration of Multi-Vehicle Detection and Classification For Unmanned Aerial Vehicle Surveillance Application using YOLOv3 |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |