CN110222629A - Bale No. recognition methods and Bale No. identifying system under a kind of steel scene - Google Patents
Bale No. recognition methods and Bale No. identifying system under a kind of steel scene Download PDFInfo
- Publication number
- CN110222629A CN110222629A CN201910476054.8A CN201910476054A CN110222629A CN 110222629 A CN110222629 A CN 110222629A CN 201910476054 A CN201910476054 A CN 201910476054A CN 110222629 A CN110222629 A CN 110222629A
- Authority
- CN
- China
- Prior art keywords
- image
- bale
- pixel
- detected
- target area
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
Bale No. recognition methods and Bale No. identifying system under a kind of steel scene of the invention, pass through the real-time original image of automatic collection, to whether have in original image Bale No. indicate region i.e. target area, the target image for marking off target area and background area handle the location information mark of target area by using Bale No. position mark network, obtain images to be recognized, it is subsequent when being identified to images to be recognized, target area is identified according to the location information of mark, reads Bale No. information;The present invention can be during the movements such as ladle, iron packet and material packet, realize the Bale No. information automatic identification wrapped to ladle, iron packet and material, it may be implemented severe in working environment, automatic identification is carried out under conditions of extreme temperatures, the generation for reducing safety accident reduces the identification difficulty of Bale No..
Description
Technical field
The present invention relates to a kind of steel making equipment monitoring technical fields, more particularly to the Bale No. under a kind of steel scene
Recognition methods and Bale No. identifying system.
Background technique
Complex process, the link of steelmaking process are various, for the ability for improving production link, and intelligent vehicle
Between construction need, it should implement steel-making logistics intelligent recognition tracking.It is most crucial, most important in steel-making logistics system
Production equipment is then various backpack bodies under steel scene, Ru Tiebao, ladle and material packet.
The management and scheduling to iron packet, ladle and material packet such as steel mill, electric furnace factory, Foundry Works, especially Bale No. at present
Identification, or by the way of artificial.However, the working environment under steel scene is severe, extreme temperatures, using artificial side
Formula is easy to happen safety accident, and the difficulty of Bale No. identification is larger.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide the Bale No. knowledges under a kind of steel scene
Other method and Bale No. identifying system are easy to happen safety accident, Bale No. for solving by the way of artificial in the prior art
The larger problem of the difficulty of identification.
In order to achieve the above objects and other related objects, the present invention provides Bale No. recognition methods under a kind of steel scene, packet
It includes: acquisition standard picture and original image;The original image is pre-processed, image to be detected is obtained;To it is described to
Detection image carries out multidomain treat-ment, obtains target image;Sample image is obtained, sample data set is constructed;To the sample data
Collection is trained, and building Bale No. position marks network;Using the Bale No. position mark network to the target image at
Reason obtains images to be recognized;The images to be recognized is identified, Bale No. information is read.
Optionally, described to pre-process to the original image, obtaining image to be detected includes: to obtain the standard drawing
The pixel coordinate and standard gray angle value of each pixel of picture;Obtain the pixel of each pixel of the original image
Coordinate and actual grey value;Obtain the actual grey value of the pixel of the corresponding original image of the pixel coordinate with
The difference of the standard gray angle value of the pixel of the standard picture;Judge whether the difference is greater than threshold value;If the difference is big
In the threshold value, then the original image is image to be detected, obtains described image to be detected.
Optionally, the Bale No. recognition methods under steel scene of the invention further includes;According to the picture of described image to be detected
The difference of the standard gray angle value of the actual grey value and pixel of the standard picture of vegetarian refreshments is greater than the described to be detected of threshold value
The set of the pixel of image divides described image to be detected into target area and background area;According to described image to be detected
The target area and the background area obtain the target image, the target image include the target area with
And the background area.
Optionally, described that the target image is handled using Bale No. position mark network, it obtains to be identified
Image includes: to be labeled to the location information of the target area of the target image, acquisition have the target area with
And the images to be recognized of the location information of the target area.
Optionally, described to identify to the images to be recognized, reading Bale No. information includes: according to the positional information
The target area of the images to be recognized is split, multiple monocase images are obtained;To the monocase image into
The processing of row gray processing, obtains grayscale image;The grayscale image is filtered, filtered grayscale image is obtained;To the filter
Grayscale image after wave carries out binary conversion treatment, obtains binary map;Size normalization processing is carried out to the binary map, obtains normalizing
Change monocase binary map;Point feature pixel-by-pixel is carried out to the normalization monocase binary map to extract, and obtains feature vector square
Battle array;The eigenvectors matrix is matched with multiple Character mother plates, multiple similarity parameters are obtained, according to described similar
Degree parameter completion identifies the images to be recognized, reads Bale No. information.
The present invention also provides the Bale No. identifying systems under a kind of steel scene, comprising:
Image collection module, acquisition standard picture, original image and sample image, and sample is constructed according to the sample set
Notebook data collection;
Processing module obtains image to be detected for pre-processing to the original image;And to the mapping to be checked
As carrying out multidomain treat-ment, target image is obtained;
Training module for being trained to the sample data set, and constructs Bale No. position mark network;
Bale No. position labeling module, for being handled using Bale No. position mark network the target image,
Obtain images to be recognized;
Picture recognition module for identifying to the images to be recognized, and reads Bale No. information.
Optionally, the processing module is also used to: obtain the pixel coordinate of each pixel of the standard picture with
And standard gray angle value;Obtain the pixel coordinate and actual grey value of each pixel of the original image;Described in acquisition
The standard of the pixel of the actual grey value and standard picture of the pixel of the corresponding original image of pixel coordinate
The difference of gray value;And judge whether the difference is greater than threshold value;If the difference is greater than the threshold value, the original graph
As being image to be detected, described image to be detected is obtained.
Optionally, the processing module be also used to according to the actual grey value of the pixel of described image to be detected with it is described
The difference of the standard gray angle value of the pixel of standard picture is greater than the set of the pixel of described image to be detected of threshold value for institute
It states image to be detected and divides target area and background area into;According to the target area of described image to be detected and described
Background area obtains the target image, and the target image includes the target area and the background area.
Optionally, Bale No. position labeling module is used for the location information to the target area of the target image
It is labeled, obtains the images to be recognized for having the location information of the target area and the target area.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, and the program is processed
The Bale No. recognition methods under the steel scene is realized when device executes.
The present invention also provides a kind of electric terminals, comprising: processor and memory;
The memory is used to execute the computer of the memory storage for storing computer program, the processor
Program, so that the terminal executes the Bale No. recognition methods under the steel scene.
Bale No. recognition methods and Bale No. identifying system under a kind of steel scene of the invention, it is real-time by automatic collection
Original image, to whether have in original image Bale No. indicate region i.e. target area, by using the Bale No. position mark
Network carries out at the location information mark to target area the target image for marking off target area and background area
Reason, obtains images to be recognized, subsequent when identifying to images to be recognized, is carried out according to the location information of mark to target area
Bale No. information is read in identification.Bale No. recognition methods and Bale No. identifying system under a kind of steel scene of the invention, Ke Yi
During the movements such as ladle, iron packet and material packet, the Bale No. information automatic identification wrapped to ladle, iron packet and material is realized,
It may be implemented severe in working environment, automatic identification carried out under conditions of extreme temperatures, reduces the generation of safety accident, reduce
The identification difficulty of Bale No..
Detailed description of the invention
Fig. 1 is shown as the flow diagram of the Bale No. recognition methods under a kind of steel scene of one embodiment of the invention.
Fig. 2 is shown as the flow diagram of the Bale No. recognition methods under a kind of steel scene of further embodiment of this invention.
Fig. 3 is shown as the structural block diagram of the Bale No. identifying system under a kind of steel scene of one embodiment of the invention.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Please refer to Fig. 1 and Fig. 2, the present invention provides the Bale No. recognition methods under a kind of steel scene, comprising:
S10: acquisition standard picture and original image;
S20: pre-processing the original image, obtains image to be detected;
S30: multidomain treat-ment is carried out to described image to be detected, obtains target image;
S40: obtaining sample image, constructs sample data set;
S50: being trained the sample data set, and building Bale No. position marks network;
S60: the target image is handled using Bale No. position mark network, obtains images to be recognized;
S70: identifying the images to be recognized, reads Bale No. information.
It should be understood that obtaining the sample image for having Bale No. information, sample data set is constructed, using convolutional neural networks pair
The sample data set is trained.Network is marked by the Bale No. position based on deep learning, will be had in the target image
The location information in the region of Bale No. information, which marks out, to be come, i.e. acquisition images to be recognized, subsequent that optical character knowledge can be directly used
Other technology completes the identification to images to be recognized, that is, directlys adopt optical character recognition technology and identify and read Bale No. information, such as
This, may be implemented under the steel scene based on intelligent vision technology Bale No. identification, without artificial mode to Bale No. into
Row identification, can apply under the severe scene of Various Complex, save manpower, reduce the generation of safety accident, while base
In the combination of deep learning and optical character recognition technology, the accuracy rate to Bale No. identification can be improved.
In some embodiments, about building Bale No. position mark network the step of, i.e., step S40's and S50 is suitable
Sequence does not do specific limitation, and step S40 and S50 can be can be arranged side by side with S10, S20 and S30, is also possible to before having
Sequence afterwards.
In some embodiments, standard picture, original image and sample image all can be by the same image capturings
Device such as CCD camera obtains, and is not particularly limited herein.
In some embodiments, described to pre-process to the original image, obtaining image to be detected includes: to obtain
The pixel coordinate and standard gray angle value of each pixel of the standard picture;Obtain each pixel of the original image
The pixel coordinate and actual grey value of point;Obtain the reality of the pixel of the corresponding original image of the pixel coordinate
The difference of the standard gray angle value of the pixel of border gray value and the standard picture;Judge whether the difference is greater than threshold value;If
The difference is greater than the threshold value, then the original image is image to be detected, obtains described image to be detected.
It should be understood that standard picture is the image under no raw material traffic condition, or perhaps static steel scene
Under image, no ladle, iron packet or material packet movement;And original image is then the movement in ladle, iron packet or material packet
The image obtained under scene.The pixel coordinate and standard grayscale of each pixel of the standard picture are obtained by calculating
Actual grey value and mark are compared in the pixel coordinate and actual grey value of each pixel of value and original image, judgement
The difference of quasi- gray value, when the difference be greater than the threshold value, then the original image is classified as image to be detected, so as to it is subsequent into
Row training and identification.I.e. by comparing the gray value of standard picture and each pixel of the original image obtained in real time
Variation, the original image changed is the image to be detected that possible have Bale No. information to occur, if difference is less than or equal to threshold value,
Then judge that there is no the Bale No. information original image is unavailable in the original image.
In some embodiments, by the pixel coordinate and standard gray angle value of each pixel of standard picture with
The pixel coordinate of each pixel of original image and actual grey value realize the selection of testing image;Pixel coordinate
The difference of the standard gray angle value of the pixel of the actual grey value and standard picture of the pixel of the corresponding original image
Value is greater than threshold value, and the actual grey value of the pixel of the corresponding original image of pixel coordinate and the standard picture
The difference of the standard gray angle value of pixel be greater than threshold value original image pixel be more than it is a certain number of, it is to be measured to realize
The selection of image;The actual grey value of the pixel for the original image that such as pixel coordinate pair is answered and the standard picture
Pixel standard gray angle value difference be greater than threshold value original image pixel quantity be greater than original image pixel
The 10% of point sum, that is, complete the selection of image to be detected, judge the original image for testing image.
It is appreciated that the image acquiring device for obtaining standard picture and original image be same image acquiring device and
It is obtained under same device parameter, pixel coordinate point is established to the standard picture of acquisition and each pixel of original image,
Pixel coordinate point is established to the original image and standard picture that directly obtain, is sat in the pixel of original image and standard picture
The standard gray angle value and actual grey value of pixel coordinate point, the image to be detected selected accordingly are calculated under the premise of punctuate is corresponding
It can be more accurate.
In some embodiments, for example, threshold value can be 8, the i.e. difference of standard gray angle value and actual grey value
It is decision condition more than 8;It can be combined with the actual grey value of pixel in threshold value and original image and the mark of standard picture
The difference of quasi- gray value be greater than threshold value quantity as decision condition, i.e., under corresponding pixel coordinate, standard gray angle value and reality
The difference of border gray value is greater than 8, and the pixel quantity of original image of the difference of standard gray angle value and actual grey value greater than 8
Greater than the 10% of total pixel quantity, the original image is judged for image to be detected and obtains the image to be detected.Such as, phase
With pixel coordinate, the actual grey value of the pixel of the corresponding original image is 15, the pixel of the standard picture
Standard gray angle value is 0, the actual grey value of the pixel of the corresponding original image of pixel coordinate and the standard picture
The difference of standard gray angle value of pixel be greater than 8, the value of the gray value of pixel is 0-255, if pixel coordinate pair is answered
The original image pixel actual grey value and the difference of the standard gray angle value of the pixel of the standard picture it is big
It is greater than the 10% of the pixel sum of original image in the quantity of the pixel of 8 original image, then the original image is to be checked
Altimetric image.
In some embodiments, the Bale No. recognition methods under steel scene of the invention further includes;According to described to be checked
The difference of the standard gray angle value of the pixel of the actual grey value and standard picture of the pixel of altimetric image is greater than threshold value
The set of the pixel of described image to be detected divides described image to be detected into target area and background area;According to described
The target area of image to be detected and the background area obtain the target image, and the target image includes described
Target area and the background area.
It should be understood that the image acquiring device for obtaining standard picture and original image is same image acquiring device,
Pixel coordinate point is established to the standard picture of acquisition and each pixel of original image, i.e., to the original graph directly obtained
Picture and standard picture establish pixel coordinate point, count under the premise of original image is corresponding with the pixel coordinate of standard picture point
The standard gray angle value and actual grey value of pixel coordinate point are calculated, then image is divided, the target image selected accordingly can be more
It is accurate to add;Such as, under corresponding pixel coordinate, pixel standard gray angle value and the difference of actual grey value are original greater than 8
Image is classified as image to be detected and is stored, and pixel standard gray angle value and the difference of actual grey value is to be checked greater than 8
The set of the pixel of altimetric image divides target area into, remaining region is background area, to have obtained target area and background
The target image in region.
It is in some embodiments, described that the target image is handled using Bale No. position mark network,
Obtaining images to be recognized includes: to be labeled to the location information of the target area of the target image, and acquisition has described
The images to be recognized of the location information of target area and the target area.
In some embodiments, described to identify to the images to be recognized, reading Bale No. information includes: according to institute
It states location information to be split the target area of the images to be recognized, obtains multiple monocase images;To the list
Character picture carries out gray processing processing, obtains grayscale image;The grayscale image is filtered, filtered gray scale is obtained
Figure;Binary conversion treatment is carried out to the filtered grayscale image, obtains binary map;The binary map is carried out at size normalization
Reason obtains normalization monocase binary map;Point feature pixel-by-pixel is carried out to the normalization monocase binary map to extract, and is obtained
Eigenvectors matrix;The eigenvectors matrix is matched with multiple Character mother plates, obtains multiple similarity parameters, root
The images to be recognized is identified according to similarity parameter completion, reads Bale No. information.
In some embodiments, the Bale No. under steel scene includes the Bale No. mark in ladle, iron packet and material packet, there is packet
Number Sign Board use high temperature resistant, the metal material with distinct contrast with container so improves the resolution to Bale No., Sign Board
Shape is round or rectangle, and Bale No. is using Arabic numerals and letter engraving or hollow out on Sign Board.
It should be understood that being labeled by the location information to target area, when being identified, directly with target area
Domain reduces the workload of identification step as identification object;Multiple Character mother plates can store in memory, it is possible to understand that
Memory in be stored with the eigenvectors matrix of each Character mother plate simultaneously, it is described by the eigenvectors matrix with it is multiple
Character mother plate is matched, and specifically can be, which will carry out point feature extraction pixel-by-pixel to the normalization monocase binary map, obtains
The eigenvectors matrix for obtaining eigenvectors matrix and Character mother plate carries out similarity calculation, obtains similarity parameter, similarity ginseng
Several values can be 95%, identify according to similarity parameter completion to the images to be recognized.Such as normalizing
The similarity parameter for changing the eigenvectors matrix of monocase binary map and the eigenvectors matrix of Character mother plate " A " is 95%, then
The monocase image " A " so completes each monocase image of the images to be recognized, with this, completes to described wait know
Other image is identified.
The present invention also provides the Bale No. identifying systems under a kind of steel scene, comprising:
Image collection module 10, for acquiring standard picture, original image and sample image, and according to the sample set
Construct sample data set;
Processing module 20 obtains image to be detected for pre-processing to the original image;And to described to be detected
Image carries out multidomain treat-ment, obtains target image;
Training module 30 for being trained to the sample data set, and constructs Bale No. position mark network;
Bale No. position labeling module 40, for using the Bale No. position mark network to the target image at
Reason obtains images to be recognized;
Picture recognition module 50 for identifying to the images to be recognized, and reads Bale No. information.
In some embodiments, image collection module 10 can include at least CCD camera, can be to image collection module
10 dust-proof grade and waterproofing grade is set, and such as degree of protection IP65 can be.IP65 is exactly completely dust-proof and can
To prevent the water of injection from immersing.The grade that first reference numerals " 6 " indicates that electric appliance is dust-proof, prevents foreign object from invading;Second mark
The tightness that word " 5 " expression electric appliance blocks moisture, the waterproof of counting invade, number is bigger, and its degree of protection of expression is higher, here institute
The foreign object of finger is containing tool, finger of people etc..
In some embodiments, the processing module 20 is also used to: obtaining each pixel of the standard picture
Pixel coordinate and standard gray angle value;Obtain the pixel coordinate and actual grey of each pixel of the original image
Value;Obtain the actual grey value of the pixel of the corresponding original image of the pixel coordinate and the picture of the standard picture
The difference of the standard gray angle value of vegetarian refreshments;And judge whether the difference is greater than threshold value;If the difference is greater than the threshold value,
The original image is image to be detected, obtains described image to be detected.
In some embodiments, the processing module 20 is also used to judge the corresponding original image of pixel coordinate
Pixel actual grey value and the standard picture pixel standard gray angle value difference be greater than threshold value original graph
Whether the quantity of the pixel of picture is greater than the 10% of the pixel sum of original image, if pixel coordinate is corresponding described original
The difference of the standard gray angle value of the pixel of the actual grey value and standard picture of the pixel of image is greater than the original of threshold value
The quantity of the pixel of beginning image is greater than the 10% of the pixel sum of original image, then the original image is image to be detected,
Obtain described image to be detected.
In some embodiments, the processing module 20 is also used to the reality of the pixel according to described image to be detected
The difference of the standard gray angle value of the pixel of gray value and the standard picture is greater than the pixel of described image to be detected of threshold value
The set of point divides described image to be detected into target area and background area;According to the target of described image to be detected
Region and the background area obtain the target image, and the target image includes the target area and the background
Region.
In some embodiments, Bale No. position labeling module 40 is used for the target area to the target image
The location information in domain is labeled, and obtains the to be identified of the location information for having the target area and the target area
Image.
In some embodiments, the Bale No. identifying system under the steel scene further includes memory module.
It should be understood that steel field provided by the invention may be implemented in the Bale No. identifying system under steel scene of the invention
Bale No. recognition methods under scape, therefore the related embodiment of the Bale No. identifying system under steel scene of the invention and beneficial effect
Fruit is identical as the content of Bale No. recognition methods, and details are not described herein.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, and the program is processed
The Bale No. recognition methods under the steel scene is realized when device executes.
The present invention also provides a kind of electric terminals, comprising: processor and memory;The memory is for storing computer
Program, the processor is used to execute the computer program of the memory storage, so that the terminal executes the steel
Bale No. recognition methods under scene.
Bale No. recognition methods and Bale No. identifying system under a kind of steel scene of the invention, it is real-time by automatic collection
Original image, to whether have in original image Bale No. indicate region i.e. target area, by using the Bale No. position mark
Network carries out at the location information mark to target area the target image for marking off target area and background area
Reason, obtains images to be recognized, subsequent when identifying to images to be recognized, is carried out according to the location information of mark to target area
Bale No. information is read in identification.Bale No. recognition methods and Bale No. identifying system under a kind of steel scene of the invention, Ke Yi
During the movements such as ladle, iron packet and material packet, the Bale No. information automatic identification wrapped to ladle, iron packet and material is realized,
It may be implemented severe in working environment, automatic identification carried out under conditions of extreme temperatures, reduces the generation of safety accident, reduce
The identification difficulty of Bale No..
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, red
The system of outside line or semiconductor, device or device, or any above combination.The more specific example of readable storage medium storing program for executing
(non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
(RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The program product of embodiments of the present invention can use portable compact disc read only memory (CD-ROM) and wrap
Program code is included, and can be run on the computing device.However, program product of the invention is without being limited thereto, it in this document, can
Read storage medium can be it is any include or storage program tangible medium, the program can be commanded execution system, device or
The use or in connection of person's device.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including --- but being not limited to --- electromagnetism letter
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be other than readable storage medium storing program for executing it is any can
Read medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Program in connection.
The program code for including on readable medium can transmit with any suitable medium, including --- but being not limited to ---
Wirelessly, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind --- including local area network (LAN) or extensively
Domain net (WAN)-be connected to user calculating equipment, or, it may be connected to external computing device (such as utilize Internet service
Provider is connected by internet).
It should be noted that although being referred to several unit or sub-units of device in the above detailed description, this stroke
It point is only exemplary not enforceable.In fact, embodiment according to the present invention, it is above-described two or more
The feature and function of unit can embody in a unit.Conversely, the feature and function of an above-described unit can
It is to be embodied by multiple units with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
It should be understood by those skilled in the art that, the embodiment of the present invention 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 present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, 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 present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
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.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (11)
1. Bale No. recognition methods under a kind of steel scene characterized by comprising
Acquire standard picture and original image;
The original image is pre-processed, image to be detected is obtained;
Multidomain treat-ment is carried out to described image to be detected, obtains target image;
Sample image is obtained, sample data set is constructed;
The sample data set is trained, building Bale No. position marks network;
The target image is handled using Bale No. position mark network, obtains images to be recognized;
The images to be recognized is identified, Bale No. information is read.
2. the Bale No. recognition methods under steel scene according to claim 1, which is characterized in that described to the original graph
As being pre-processed, obtaining image to be detected includes:
Obtain the pixel coordinate and standard gray angle value of each pixel of the standard picture;
Obtain the pixel coordinate and actual grey value of each pixel of the original image;
Obtain the pixel of the corresponding original image of the pixel coordinate actual grey value and the standard picture
The difference of the standard gray angle value of pixel;
Judge whether the difference is greater than threshold value;
If the difference is greater than the threshold value, the original image is image to be detected, obtains described image to be detected.
3. the Bale No. recognition methods under steel scene according to claim 2, which is characterized in that further include;
According to the standard gray angle value of the actual grey value of the pixel of described image to be detected and the pixel of the standard picture
Difference be greater than threshold value described image to be detected pixel set by described image to be detected divide into target area and
Background area;
The target image, the target are obtained according to the target area of described image to be detected and the background area
Image includes the target area and the background area.
4. the Bale No. recognition methods under steel scene according to claim 3, which is characterized in that described to use the Bale No.
Position mark network handles the target image, obtains images to be recognized and includes:
The location information of the target area of the target image is labeled, acquisition has the target area and described
The images to be recognized of the location information of target area.
5. the Bale No. recognition methods under steel scene according to claim 4, which is characterized in that described to described to be identified
Image is identified that reading Bale No. information includes:
The target area of the images to be recognized is split according to the positional information, obtains multiple monocase figures
Picture;
Gray processing processing is carried out to the monocase image, obtains grayscale image;
The grayscale image is filtered, filtered grayscale image is obtained;
Binary conversion treatment is carried out to the filtered grayscale image, obtains binary map;
Size normalization processing is carried out to the binary map, obtains normalization monocase binary map;
Point feature pixel-by-pixel is carried out to the normalization monocase binary map to extract, and obtains eigenvectors matrix;
The eigenvectors matrix is matched with multiple Character mother plates, multiple similarity parameters are obtained, according to the phase
The images to be recognized is identified like degree parameter completion, reads Bale No. information.
6. the Bale No. identifying system under a kind of steel scene characterized by comprising
Image collection module constructs sample for acquiring standard picture, original image and sample image, and according to the sample set
Notebook data collection;
Processing module obtains image to be detected for pre-processing to the original image;And to described image to be detected into
Row multidomain treat-ment obtains target image;
Training module for being trained to the sample data set, and constructs Bale No. position mark network;
Bale No. position labeling module is obtained for being handled using Bale No. position mark network the target image
Images to be recognized;
Picture recognition module for identifying to the images to be recognized, and reads Bale No. information.
7. according to the Bale No. identifying system under claim 6 steel scene, which is characterized in that the processing module is also used to:
Obtain the pixel coordinate and standard gray angle value of each pixel of the standard picture;Obtain the original image
The pixel coordinate and actual grey value of each pixel;Obtain the picture of the corresponding original image of the pixel coordinate
The difference of the standard gray angle value of the pixel of the actual grey value and standard picture of vegetarian refreshments;And
Judge whether the difference is greater than threshold value;If the difference is greater than the threshold value, the original image is mapping to be checked
Picture obtains described image to be detected.
8. according to the Bale No. identifying system under claim 7 steel scene, which is characterized in that the processing module is also used to root
According to the difference of the standard gray angle value of the pixel of the actual grey value and standard picture of the pixel of described image to be detected
Set greater than the pixel of described image to be detected of threshold value divides described image to be detected into target area and background area
Domain;
The target image, the target are obtained according to the target area of described image to be detected and the background area
Image includes the target area and the background area.
9. according to the Bale No. identifying system under claim 8 steel scene, which is characterized in that Bale No. position labeling module
Location information for the target area to the target image is labeled, and acquisition has the target area and described
The images to be recognized of the location information of target area.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The Bale No. recognition methods under steel scene described in any one of claims 1 to 5 is realized when execution.
11. a kind of electric terminal characterized by comprising processor and memory;
The memory is used to execute the computer journey of the memory storage for storing computer program, the processor
Sequence, so that the terminal executes the Bale No. recognition methods under the steel scene as described in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910476054.8A CN110222629A (en) | 2019-06-03 | 2019-06-03 | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910476054.8A CN110222629A (en) | 2019-06-03 | 2019-06-03 | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110222629A true CN110222629A (en) | 2019-09-10 |
Family
ID=67819055
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910476054.8A Pending CN110222629A (en) | 2019-06-03 | 2019-06-03 | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110222629A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111046848A (en) * | 2019-12-30 | 2020-04-21 | 广东省实验动物监测所 | Gait monitoring method and system based on animal running platform |
CN111126392A (en) * | 2019-12-25 | 2020-05-08 | 江苏恒创软件有限公司 | Digital image rapid identification method and device for ladle label |
CN111353494A (en) * | 2020-04-09 | 2020-06-30 | 成都睿琪科技有限责任公司 | Steel product code identification system and method |
CN111524112A (en) * | 2020-04-17 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Steel chasing identification method, system, equipment and medium |
CN111652541A (en) * | 2020-05-07 | 2020-09-11 | 美的集团股份有限公司 | Industrial production monitoring method, system and computer readable storage medium |
CN112818980A (en) * | 2021-01-15 | 2021-05-18 | 湖南千盟物联信息技术有限公司 | Steel ladle number detection and identification method based on Yolov3 algorithm |
CN113344878A (en) * | 2021-06-09 | 2021-09-03 | 北京容联易通信息技术有限公司 | Image processing method and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107067002A (en) * | 2017-03-09 | 2017-08-18 | 华东师范大学 | Road licence plate recognition method in a kind of dynamic video |
US20180018533A1 (en) * | 2016-07-15 | 2018-01-18 | University Of Central Florida Research Foundation, Inc. | Synthetic data generation of time series data |
CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
CN108629378A (en) * | 2018-05-10 | 2018-10-09 | 上海鹰瞳医疗科技有限公司 | Image-recognizing method and equipment |
CN108875722A (en) * | 2017-12-27 | 2018-11-23 | 北京旷视科技有限公司 | Character recognition and identification model training method, device and system and storage medium |
US20190095739A1 (en) * | 2017-09-27 | 2019-03-28 | Harbin Institute Of Technology | Adaptive Auto Meter Detection Method based on Character Segmentation and Cascade Classifier |
CN109598200A (en) * | 2018-11-01 | 2019-04-09 | 云南昆钢电子信息科技有限公司 | A kind of digital image recognition system and method for hot-metal bottle tank number |
-
2019
- 2019-06-03 CN CN201910476054.8A patent/CN110222629A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180018533A1 (en) * | 2016-07-15 | 2018-01-18 | University Of Central Florida Research Foundation, Inc. | Synthetic data generation of time series data |
CN107067002A (en) * | 2017-03-09 | 2017-08-18 | 华东师范大学 | Road licence plate recognition method in a kind of dynamic video |
US20190095739A1 (en) * | 2017-09-27 | 2019-03-28 | Harbin Institute Of Technology | Adaptive Auto Meter Detection Method based on Character Segmentation and Cascade Classifier |
CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
CN108875722A (en) * | 2017-12-27 | 2018-11-23 | 北京旷视科技有限公司 | Character recognition and identification model training method, device and system and storage medium |
CN108629378A (en) * | 2018-05-10 | 2018-10-09 | 上海鹰瞳医疗科技有限公司 | Image-recognizing method and equipment |
CN109598200A (en) * | 2018-11-01 | 2019-04-09 | 云南昆钢电子信息科技有限公司 | A kind of digital image recognition system and method for hot-metal bottle tank number |
Non-Patent Citations (6)
Title |
---|
MAHFUDI,I: "Indonesian sign language numer recognition using SIFT algorithm", 《2ND INTERNATIONAL CONFERENCE ON VOCATIONAL EDUCATION AND ELECTRIAL ENGINEERING》 * |
MAHFUDI,I: "Indonesian sign language numer recognition using SIFT algorithm", 《2ND INTERNATIONAL CONFERENCE ON VOCATIONAL EDUCATION AND ELECTRIAL ENGINEERING》, vol. 336, 31 December 2018 (2018-12-31) * |
刘智: "径向基神经网络算法在车牌字符识别中的应用", 《华侨大学学报(自然科学版)》 * |
刘智: "径向基神经网络算法在车牌字符识别中的应用", 《华侨大学学报(自然科学版)》, 20 January 2017 (2017-01-20) * |
董峻妃等: "基于卷积神经网络的车牌字符识别", 《计算机应用》 * |
董峻妃等: "基于卷积神经网络的车牌字符识别", 《计算机应用》, no. 07, 10 July 2017 (2017-07-10) * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126392A (en) * | 2019-12-25 | 2020-05-08 | 江苏恒创软件有限公司 | Digital image rapid identification method and device for ladle label |
CN111046848A (en) * | 2019-12-30 | 2020-04-21 | 广东省实验动物监测所 | Gait monitoring method and system based on animal running platform |
CN111353494A (en) * | 2020-04-09 | 2020-06-30 | 成都睿琪科技有限责任公司 | Steel product code identification system and method |
CN111524112A (en) * | 2020-04-17 | 2020-08-11 | 中冶赛迪重庆信息技术有限公司 | Steel chasing identification method, system, equipment and medium |
CN111524112B (en) * | 2020-04-17 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Steel chasing identification method, system, equipment and medium |
CN111652541A (en) * | 2020-05-07 | 2020-09-11 | 美的集团股份有限公司 | Industrial production monitoring method, system and computer readable storage medium |
CN111652541B (en) * | 2020-05-07 | 2022-11-01 | 美的集团股份有限公司 | Industrial production monitoring method, system and computer readable storage medium |
CN112818980A (en) * | 2021-01-15 | 2021-05-18 | 湖南千盟物联信息技术有限公司 | Steel ladle number detection and identification method based on Yolov3 algorithm |
CN113344878A (en) * | 2021-06-09 | 2021-09-03 | 北京容联易通信息技术有限公司 | Image processing method and system |
CN113344878B (en) * | 2021-06-09 | 2022-03-18 | 北京容联易通信息技术有限公司 | Image processing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222629A (en) | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene | |
US11734851B2 (en) | Face key point detection method and apparatus, storage medium, and electronic device | |
CN108154105B (en) | Underwater biological detection and identification method and device, server and terminal equipment | |
CN111054080B (en) | Method, device and equipment for intelligently detecting perspective plug-in and storage medium thereof | |
CN113822951B (en) | Image processing method, device, electronic equipment and storage medium | |
CN109389589A (en) | Method and apparatus for statistical number of person | |
CN103839042A (en) | Human face recognition method and human face recognition system | |
CN112989995B (en) | Text detection method and device and electronic equipment | |
CN112949437A (en) | Gesture recognition method, gesture recognition device and intelligent equipment | |
CN110399760A (en) | A kind of batch two dimensional code localization method, device, electronic equipment and storage medium | |
CN112164086A (en) | Refined image edge information determining method and system and electronic equipment | |
CN113515655A (en) | Fault identification method and device based on image classification | |
CN114777792A (en) | Path planning method and device, computer readable medium and electronic equipment | |
CN108900895B (en) | Method and device for shielding target area of video stream | |
CN102713974A (en) | Learning device, identification device, learning identification system and learning identification device | |
CN112233161B (en) | Hand image depth determination method and device, electronic equipment and storage medium | |
CN115272923B (en) | Intelligent identification method and system based on big data platform | |
KR101391667B1 (en) | A model learning and recognition method for object category recognition robust to scale changes | |
CN112634382B (en) | Method and device for identifying and replacing images of unnatural objects | |
CN111723614A (en) | Traffic signal lamp identification method and device | |
CN115861162A (en) | Method, device and computer readable storage medium for positioning target area | |
Li et al. | Container keyhole positioning based on deep neural network | |
CN113591838A (en) | Target detection method, target detection device, electronic equipment and storage medium | |
CN110796050A (en) | Target object identification method and related device in unmanned aerial vehicle inspection process | |
CN114419451B (en) | Method and device for identifying inside and outside of elevator, electronic equipment and storage medium |
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 | ||
CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: 401122 No. 11 Huijin Road, North New District of Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information |