CN107832767A - Container number identification method, device and electronic equipment - Google Patents
Container number identification method, device and electronic equipment Download PDFInfo
- Publication number
- CN107832767A CN107832767A CN201711125985.0A CN201711125985A CN107832767A CN 107832767 A CN107832767 A CN 107832767A CN 201711125985 A CN201711125985 A CN 201711125985A CN 107832767 A CN107832767 A CN 107832767A
- Authority
- CN
- China
- Prior art keywords
- case number
- image
- container
- identified
- character
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiments of the invention provide a kind of container number identification method, device and electronic equipment, this method includes obtaining the case number (CN) image of container to be identified, and the case number (CN) image is pre-processed to obtain pretreated case number (CN) image;Character segmentation processing is carried out to pretreated case number (CN) image by rank scanning method, obtains multiple character pictures, and record order of the character picture in the case number (CN) of container to be identified;Corresponding character feature in each character picture is extracted according to default deep learning model respectively, the default deep learning model includes the deep learning model based on convolutional neural networks;The character feature of each character picture is identified respectively using the grader based on default deep learning model training;Recognition result corresponding to each character picture is combined, obtains the case number (CN) of container to be identified.So alleviate and manually the case number (CN) of container is registered, the problem of accuracy is low, labor intensity is big, improve recognition accuracy.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of container number identification method, device and electricity
Sub- equipment.
Background technology
Container Transport is a kind of state-of-the-art modernization transport that cargo transport is carried out using container as traffic unit
Mode.It has the characteristics of " safe, rapid, easy, inexpensive ", advantageously reduces transit link, can be by comprehensively utilizing iron
The various forms of transport such as road, highway, water route and aviation, multimodal transport is carried out, realized " door t door ".
With the development of Management of Modern Physical Distribution technology, accelerate the management automation of cargo channel has turned into very urgent times
Business.For harbour, the container throughput at harbour drastically influence the benefit of harbour.At present, used mostly on harbour
It is the handling of artificial commander's container, ID symbol of the container number as unique mark container, in Container Transport process
In links, by manually being registered to the case number (CN) of container, exist low data inputting accuracy, Data duplication typing,
The problem of labor intensity is big, the handling speed of container is influenceed, be unfavorable for the working at high speed at whole harbour.
The content of the invention
In view of this, it is an object of the invention to provide a kind of container number identification method, device and electronic equipment, with
The case number (CN) and automatic identification for all kinds of containers that automatic capture accesses to the ports, alleviate and manually the case number (CN) of container are stepped on
Note, accuracy is low, the big problem of labor intensity, reduces disengaging ETA estimated time of arrival, improves operating efficiency.
In a first aspect, the embodiments of the invention provide a kind of container number identification method, including:
The case number (CN) image of container to be identified is obtained, and the case number (CN) image is pre-processed, is obtained pretreated
Case number (CN) image;
Character segmentation processing is carried out to the pretreated case number (CN) image by rank scanning method, obtains multiple character figures
Picture, and record order of the character picture in the case number (CN) of the container to be identified;
Extracted respectively according to default deep learning model and the container to be identified is corresponded in each character picture
The character feature of case number (CN), the default deep learning model include the deep learning model based on convolutional neural networks;
Using the grader based on the default deep learning model training respectively to the institute of each character picture
State character feature to be identified, and generate recognition result corresponding to each character picture;
, will each character picture pair according to order of the character picture in the case number (CN) of the container to be identified
The recognition result answered is combined, and obtains the case number (CN) of the container to be identified.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the first of first aspect, wherein, institute
State and obtain the case number (CN) image of container to be identified and include:
The general image of container to be identified is gathered, the casing frame searched in the general image;
Slant Rectify is carried out according to the casing frame, intercepts the case number (CN) image in the casing frame.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of second of first aspect, wherein, institute
State and pretreatment is carried out to the case number (CN) image included:
Smoothing denoising is carried out to the case number (CN) image of the container to be identified of collection using neighborhood averaging, obtains smoothing denoising
Case number (CN) image afterwards;
The marginal information of the case number (CN) image after the smoothing denoising is strengthened using histogram equalization method, obtains pre- place
Case number (CN) image after reason.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the third of first aspect, wherein, institute
State and pretreatment is carried out to the case number (CN) image included:
The case number (CN) image is divided into according to the gamma characteristic of the case number (CN) image of the container to be identified by background and template
Two classes, the variance made between two classes is obtained into maximum parameter as optimal threshold;
Binary image is obtained using the Optimal-threshold segmentation, using the binary image as pretreated case number (CN)
Image.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the 4th of first aspect kind, wherein, institute
It is that the case number (CN) sample data for exceeding certain threshold value by quantity trains to obtain to state the deep learning model based on convolutional neural networks
, the case number (CN) sample data includes different angle, different illumination conditions, the case number (CN) picture of different background.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the 5th of first aspect kind, wherein, institute
Stating the training process of grader includes:
Utilize the depth characteristic of the deep learning model extraction case number (CN) sample data based on convolutional neural networks;
Based on machine learning algorithm, grader is trained to the depth characteristic;
Wherein described case number (CN) sample data include the different types of case number (CN) picture that user specifies.
Second aspect, the embodiment of the present invention also provide a kind of container number identification device, including:
Pretreatment module, pre-processed for obtaining the case number (CN) image of container to be identified, and to the case number (CN) image,
Obtain pretreated case number (CN) image;
Character segmentation module, for being carried out by rank scanning method to the pretreated case number (CN) image at Character segmentation
Reason, obtains multiple character pictures, and record order of the character picture in the case number (CN) of the container to be identified;
Characteristic extracting module, it is corresponding in each character picture for being extracted respectively according to default deep learning model
The character feature of the container number to be identified, the default deep learning model include the depth based on convolutional neural networks
Spend learning model;
As a result identification module, for utilizing the grader based on the default deep learning model training respectively to each
The character feature of the character picture is identified, and generates recognition result corresponding to each character picture;
Character combination module, will for the order according to the character picture in the case number (CN) of the container to be identified
Recognition result corresponding to each character picture is combined, and obtains the case number (CN) of the container to be identified.
With reference to second aspect, the embodiments of the invention provide the possible embodiment of the first of second aspect, wherein, institute
It is that the case number (CN) sample data for exceeding certain threshold value by quantity trains to obtain to state the deep learning model based on convolutional neural networks
, the case number (CN) sample data includes different angle, different illumination conditions, the case number (CN) picture of different background.
The third aspect, the embodiment of the present invention, which also provides one kind, includes memory, processor, and being stored with the memory can
The computer program run on the processor, above-mentioned first aspect is realized described in the computing device during computer program
And its method described in any possible embodiment.
Fourth aspect, the embodiment of the present invention also provide a kind of meter for the non-volatile program code that can perform with processor
Calculation machine computer-readable recording medium, described program code make first aspect described in the computing device and its any possible embodiment
Methods described.
The embodiment of the present invention brings following beneficial effect:
The embodiments of the invention provide a kind of container number identification method, device and electronic equipment, wherein this method bag
The case number (CN) image for obtaining container to be identified is included, and the case number (CN) image is pre-processed, obtains pretreated case number (CN) image;
Character segmentation processing is carried out to pretreated case number (CN) image by rank scanning method, obtains multiple character pictures, and record word
Accord with order of the image in the case number (CN) of container to be identified;Each character picture is extracted according to default deep learning model respectively
The character feature of middle correspondence container to be identified, the default deep learning model include the depth based on convolutional neural networks
Practise model;The character feature of each character picture is carried out respectively using the grader based on default deep learning model training
Identification, generates recognition result corresponding to each character picture;According to order of the character picture in the case number (CN) of container to be identified,
Recognition result corresponding to each character picture is combined, obtains the case number (CN) of container to be identified.Carried in the embodiment of the present invention
In the technical scheme of confession, reduce the influence of outside environmental elements first with pretreatment, then by based on convolutional neural networks
Deep learning model extraction character feature, and using the deep learning model training grader to the case of container to be identified
Number it is identified, has been achieved in that the case number (CN) and automatic identification of all kinds of containers that automatic capture accesses to the ports, alleviates artificial
The case number (CN) of container is registered, accuracy is low, the big problem of labor intensity, reduces disengaging ETA estimated time of arrival, improves work effect
Rate.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in accompanying drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The required accompanying drawing used is briefly described in embodiment or description of the prior art, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of container number identification method provided in an embodiment of the present invention;
Fig. 2 is the schematic flow sheet of classifier training process provided in an embodiment of the present invention;
Fig. 3 is the structural representation of container number identification device provided in an embodiment of the present invention;
Fig. 4 is the structural representation of electronic equipment provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Links during Container Transport at present, by manually being registered to the case number (CN) of container, number be present
According to typing accuracy is low, Data duplication typing, labor intensity is big the problem of, influence the handling speed of container, be unfavorable for whole
The working at high speed at harbour.Based on this, a kind of container number identification method, device and electronics provided in an embodiment of the present invention are set
It is standby, the case number (CN) and automatic identification of all kinds of containers that can be accessed to the ports with automatic capture, alleviate manually to the case number (CN) of container
Registered, accuracy is low, the big problem of labor intensity, reduces disengaging ETA estimated time of arrival, improves operating efficiency.
For ease of understanding the present embodiment, a kind of container number disclosed in the embodiment of the present invention is identified first
Method describes in detail.
Embodiment one:
Fig. 1 shows the schematic flow sheet of container number identification method provided in an embodiment of the present invention.As shown in figure 1,
The container number identification method includes:
Step S101, the case number (CN) image of container to be identified is obtained, and the case number (CN) image is pre-processed, obtain pre- place
Case number (CN) image after reason.
The problems such as in view of due to shooting angle or casing inclination, after the image that these complex situations obtain can increase
The complexity of continuous identification, certainly will be impacted to recognition result.Based on this, in an optional embodiment, in step S101,
Obtaining the case number (CN) image of container to be identified includes:The general image of container to be identified is gathered, is searched in the general image
Casing frame;Slant Rectify is carried out according to the casing frame, intercepts the case number (CN) image in casing frame.
Specifically, video camera can be arranged on the gantry crane linking beam at harbour or the saddle beam of gantry crane both sides, so as to right
The container passed through captures the general image of clearly container to be identified.After general image is obtained, grabbed by Hough transform
The straight line of casing frame is taken, generally chooses casing coboundary and right margin, and slant correction is done using this casing frame as line of reference,
Lower section extends into prescribed level to the left on the basis of two borders again, after Slant Rectify, intercepts the case number (CN) image in casing frame.
In view of the rust staining on noise class such as casing, spot, paint stain on container be present, the noise class is retained in case number (CN)
The region at place can influence subsequently to identify.Based on this, in an optional embodiment, the pretreatment operation of use mainly includes
Image enhaucament and denoising, in above-mentioned steps S101, carrying out pretreatment to the case number (CN) image includes:
Smoothing denoising is carried out to the case number (CN) image of the container to be identified of collection using neighborhood averaging, obtains smoothing denoising
Case number (CN) image afterwards;
The marginal information of the case number (CN) image after smoothing denoising is strengthened using histogram equalization method, after obtaining pretreatment
Case number (CN) image.
By above-mentioned preprocess method, the part edge information in image can be strengthened, eliminate make an uproar to a certain extent
The influence of sound, it is more beneficial for the feature extraction and expression in later stage.
In another optional embodiment, in order to simple and handle characteristics of image rapidly, in above-mentioned steps S101, to this
Case number (CN) image, which carries out pretreatment, to be included:
Case number (CN) image is divided into according to the gamma characteristic of the case number (CN) image of container to be identified by background and the class of template two, will be made
Variance between two classes obtains maximum parameter as optimal threshold;
Binary image is obtained using Optimal-threshold segmentation, using the binary image as pretreated case number (CN) image.
In various threshold optimization dividing methods, OTSU algorithms propose that maximizing split plot design based on inter-class variance is acknowledged as
It is Optimal-threshold segmentation algorithm, it divides the image into background and the class of target two according to the gamma characteristic of image, then calculates and allows two
Variance between class obtains maximum parameter as optimal threshold, the binary picture for recycling Optimal-threshold segmentation to be worked well
Picture.
Thus, by above-mentioned binary conversion treatment, the gray value of the pixel on image is arranged to 0 or 255, in image
Data volume is greatly reduced, and image processing speed can substantially reduce.
In another optional embodiment, pixel can be described using the standard deviation characteristic of image, eliminate image
In illumination influence, provide effective data for subsequent characteristics, implementation process is as follows:
Another R represents M × N image block, and for any pixel P (I, j) on image block R, I (P) represents the picture
The gray value of vegetarian refreshments, image block R standard deviation characteristic can be defined as:
Wherein, μ be image block weighted mean, then using color space (such as RGB (RGB) color spaces or
HSV (Hue-Saturation-Value, tone-saturation degree-lightness) color space) tentatively eliminate caused by illumination difference and do
Disturb.
Step S102, Character segmentation processing is carried out to above-mentioned pretreated case number (CN) image by rank scanning method, obtained
Multiple character pictures, and record order of the character picture in the case number (CN) of container to be identified.
Wherein character includes letter and number.In one embodiment, using projection histogram method to pretreated
Case number (CN) image is split.Carry out carrying out projection histogram division to pretreated case number (CN) image first, and calculate Nogata
The Wave crest and wave trough projection relation presented in figure between the number of pixels of the number of pixels and character of character and inter-character space.So
Afterwards, above-mentioned projection histogram is analyzed, chooses and is highly less than the cut-point of " low ebb " of a certain threshold value as intercharacter in histogram,
And ensureing the half for being more than case number (CN) height with individual spacing of horizontal case number (CN), the segmentation spacing of longitudinal case number (CN) is more than the width of case number (CN).
After Character segmentation, the order of obtained character picture in the case number (CN) of container to be identified is recorded, in order to subsequent words
Symbol combination.
Step S103, extracted respectively according to default deep learning model and container to be identified is corresponded in each character picture
The character feature of case number (CN), the default deep learning model include the deep learning model based on convolutional neural networks.
Wherein, the above-mentioned deep learning model based on convolutional neural networks is the case number (CN) sample for exceeding certain threshold value by quantity
Notebook data trains what is obtained, and the case number (CN) sample data includes different angle, different illumination conditions, the case number (CN) picture of different background.
The case number (CN) picture of above-mentioned different background includes the case number (CN) on concave and convex plane, case number (CN) on the casing of unlike material etc..Specifically, case
The quantity of number picture is The more the better, and data are more, train generation the deep learning model based on convolutional neural networks it is general
Property is better, is so advantageous to accurately identifying for the follow-up case number (CN) to container to be identified, overcomes the influence of outside environmental elements, carry
Height is somebody's turn to do the recognition capability of the deep learning model based on convolutional neural networks.
Step S103 is specifically included:Character picture is included as input picture in default deep learning model
Features training is carried out in multiple basic units successively, after the completion of training, the full articulamentum in multiple integrate is extracted or other is specified
Character feature of the characteristic vector of basic unit's output as the case number (CN) that container to be identified is corresponded in character picture.
Step S104, using the grader based on above-mentioned default deep learning model training respectively to each character picture
Character feature be identified, and generate recognition result corresponding to each character picture.
I.e. using the character feature extracted in step 103 as the defeated of the grader based on default deep learning model training
Enter, after being identified by the grader, obtain final recognition result.Specifically, recognition result is character or numeral.
In an optional embodiment, referring to Fig. 2, the training process for the grader applied in step 104 includes:
Step S201, it is special using the depth of the deep learning model extraction case number (CN) sample data based on convolutional neural networks
Sign.
Step S202, based on machine learning algorithm, grader is trained to above-mentioned depth characteristic.
Wherein above-mentioned case number (CN) sample data include the different types of case number (CN) picture that user specifies.The different types of figure
Piece is the poor case number (CN) picture of the preferable case number (CN) picture of picture quality that user specifies, picture quality and does not include case number (CN) region
Case number (CN) picture.In training, by different types of case number (CN) picture, the contrast of different images quality can be carried out, further
Enhance the recognition capability of grader.
Above-mentioned machine learning algorithm can be nearest neighbor algorithm, EM algorithm and algorithm of support vector machine etc., specifically calculate
Method can select as the case may be, be not construed as limiting here.The specific extraction process of the depth characteristic be referred to step S101,
Step S102, step S103.
Step S105, it is according to order of the character picture in the case number (CN) of container to be identified, each character picture is corresponding
Recognition result be combined, obtain the case number (CN) of container to be identified.
Specifically, because container number is made up of 11 characters, preceding 4 characters are English character, rear 7 characters for Ah
Arabic numbers.After recognition result corresponding to each character picture after splitting is obtained, according to its original in container to be identified
Case number (CN) in order be combined, to obtain the case number (CN) of container to be identified.
In technical scheme provided in an embodiment of the present invention, reduce the influence of outside environmental elements first with pretreatment,
Then by the deep learning model extraction character feature based on convolutional neural networks, and the deep learning model training is utilized
The case number (CN) of container to be identified is identified grader, has been achieved in that the case for all kinds of containers that automatic capture accesses to the ports
Number and automatic identification, alleviate and manually the case number (CN) of container registered, accuracy is low, the big problem of labor intensity, reduces
ETA estimated time of arrival is passed in and out, improves operating efficiency.
Embodiment two:
Fig. 3 shows the structural representation of container number identification device provided in an embodiment of the present invention.As shown in figure 3,
The container number identification device includes:
Pretreatment module 11, pre-processed for obtaining the case number (CN) image of container to be identified, and to the case number (CN) image,
Obtain pretreated case number (CN) image;
Character segmentation module 12, for carrying out Character segmentation to above-mentioned pretreated case number (CN) image by rank scanning method
Processing, obtains multiple character pictures, and record order of the character picture in the case number (CN) of container to be identified;
Characteristic extracting module 13, correspondingly treated for being extracted respectively in each character picture according to default deep learning model
The character feature of container number is identified, the default deep learning model includes the deep learning mould based on convolutional neural networks
Type;
As a result identification module 14, for utilizing the grader based on above-mentioned default deep learning model training respectively to every
The character feature of individual character picture is identified, and generates recognition result corresponding to each character picture;
Character combination module 15, for the order according to character picture in the case number (CN) of container to be identified, by each word
Recognition result corresponding to symbol image is combined, and obtains the case number (CN) of container to be identified.
Further, the deep learning model based on convolutional neural networks is to exceed certain threshold by quantity in said apparatus
The case number (CN) sample data of value trains what is obtained, and the case number (CN) sample data includes different angle, different illumination conditions, different background
Case number (CN) picture.
In technical scheme provided in an embodiment of the present invention, reduce the influence of outside environmental elements first with pretreatment,
Then by the deep learning model extraction character feature based on convolutional neural networks, and the deep learning model training is utilized
The case number (CN) of container to be identified is identified grader, has been achieved in that the case for all kinds of containers that automatic capture accesses to the ports
Number and automatic identification, alleviate and manually the case number (CN) of container registered, accuracy is low, the big problem of labor intensity, reduces
ETA estimated time of arrival is passed in and out, improves operating efficiency.
Embodiment three:
Referring to Fig. 4, the embodiment of the present invention also provides a kind of electronic equipment 100, including:Processor 40, memory 41, bus
42 and communication interface 43, the processor 40, communication interface 43 and memory 41 connected by bus 42;Processor 40 is used to hold
The executable module stored in line storage 41, such as computer program.
Wherein, memory 41 may include high-speed random access memory (RAM, Random Access Memory),
Non-labile memory (non-volatile memory), for example, at least a magnetic disk storage may also be included.By extremely
A few communication interface 43 (can be wired or wireless) is realized logical between the system network element and at least one other network element
Letter connection, can use internet, wide area network, LAN, Metropolitan Area Network (MAN) etc..
Bus 42 can be isa bus, pci bus or eisa bus etc..The bus can be divided into address bus, data
Bus, controlling bus etc..Only represented for ease of representing, in Fig. 4 with a four-headed arrow, it is not intended that an only bus or
A type of bus.
Wherein, memory 41 is used for storage program, and the processor 40 performs the journey after execute instruction is received
Sequence, the method performed by device that the stream process that foregoing any embodiment of the embodiment of the present invention discloses defines can apply to handle
In device 40, or realized by processor 40.
Processor 40 is probably a kind of IC chip, has the disposal ability of signal.In implementation process, above-mentioned side
Each step of method can be completed by the integrated logic circuit of the hardware in processor 40 or the instruction of software form.Above-mentioned
Processor 40 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network
Processor (Network Processor, abbreviation NP) etc.;It can also be digital signal processor (Digital Signal
Processing, abbreviation DSP), application specific integrated circuit (Application Specific Integrated Circuit, referred to as
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.It can realize or perform in the embodiment of the present invention
Disclosed each method, step and logic diagram.General processor can be microprocessor or the processor can also be appointed
What conventional processor etc..The step of method with reference to disclosed in the embodiment of the present invention, can be embodied directly in hardware decoding processing
Device performs completion, or performs completion with the hardware in decoding processor and software module combination.Software module can be located at
Machine memory, flash memory, read-only storage, programmable read only memory or electrically erasable programmable memory, register etc. are originally
In the ripe storage medium in field.The storage medium is located at memory 41, and processor 40 reads the information in memory 41, with reference to
Its hardware completes the step of above method.
Container number identification device and electronic equipment provided in an embodiment of the present invention, the packaging provided with above-described embodiment
Case number identification method has identical technical characteristic, so can also solve identical technical problem, reaches identical technology effect
Fruit.
The computer program product for the progress container number identification method that the embodiment of the present invention is provided, including store
The computer-readable recording medium of the executable non-volatile program code of processor, the instruction that described program code includes can use
In the method described in previous methods embodiment that performs, specific implementation can be found in embodiment of the method, will not be repeated here.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description
And the specific work process of electronic equipment, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
Flow chart and block diagram in accompanying drawing show multiple embodiment method and computer program products according to the present invention
Architectural framework in the cards, function and operation.At this point, each square frame in flow chart or block diagram can represent one
A part for module, program segment or code, a part for the module, program segment or code include one or more and are used to realize
The executable instruction of defined logic function.It should also be noted that at some as the work(in the realization replaced, marked in square frame
Energy can also be with different from the order marked in accompanying drawing generation.For example, two continuous square frames can essentially be substantially parallel
Ground is performed, and they can also be performed in the opposite order sometimes, and this is depending on involved function.It is also noted that block diagram
And/or the combination of each square frame and block diagram in flow chart and/or the square frame in flow chart, work(as defined in performing can be used
Can or the special hardware based system of action realize, or the combination of specialized hardware and computer instruction can be used come reality
It is existing.
In the description of the invention, it is necessary to explanation, term " " center ", " on ", " under ", "left", "right", " vertical ",
The orientation or position relationship of the instruction such as " level ", " interior ", " outer " be based on orientation shown in the drawings or position relationship, merely to
Be easy to the description present invention and simplify description, rather than instruction or imply signified device or element must have specific orientation,
With specific azimuth configuration and operation, therefore it is not considered as limiting the invention.In addition, term " first ", " second ",
" the 3rd " is only used for describing purpose, and it is not intended that instruction or hint relative importance.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, can be with
Realize by another way.Device embodiment described above is only schematical, for example, the division of the unit,
Only a kind of division of logic function, can there is other dividing mode when actually realizing, in another example, multiple units or component can
To combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or beg for
The mutual coupling of opinion or direct-coupling or communication connection can be by some communication interfaces, device or unit it is indirect
Coupling or communication connection, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in the executable non-volatile computer read/write memory medium of a processor.Based on such understanding, the present invention
The part that is substantially contributed in other words to prior art of technical scheme or the part of the technical scheme can be with software
The form of product is embodied, and the computer software product is stored in a storage medium, including some instructions are causing
One computer equipment (can be personal computer, server, or network equipment etc.) performs each embodiment institute of the present invention
State all or part of step of method.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with
The medium of store program codes.
Finally it should be noted that:Embodiment described above, it is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that:Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic;And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
- A kind of 1. container number identification method, it is characterised in that including:The case number (CN) image of container to be identified is obtained, and the case number (CN) image is pre-processed, obtains pretreated case number (CN) Image;Character segmentation processing is carried out to the pretreated case number (CN) image by rank scanning method, obtains multiple character pictures, And record order of the character picture in the case number (CN) of the container to be identified;Extracted respectively according to default deep learning model and the container number to be identified is corresponded in each character picture Character feature, the default deep learning model includes the deep learning model based on convolutional neural networks;Using the grader based on the default deep learning model training respectively to the word of each character picture Symbol feature is identified, and generates recognition result corresponding to each character picture;According to order of the character picture in the case number (CN) of the container to be identified, by corresponding to each character picture Recognition result is combined, and obtains the case number (CN) of the container to be identified.
- 2. according to the method for claim 1, it is characterised in that the case number (CN) image for obtaining container to be identified includes:The general image of container to be identified is gathered, the casing frame searched in the general image;Slant Rectify is carried out according to the casing frame, intercepts the case number (CN) image in the casing frame.
- 3. according to the method for claim 1, it is characterised in that described pretreatment is carried out to the case number (CN) image to include:Smoothing denoising is carried out to the case number (CN) image of the container to be identified of collection using neighborhood averaging, after obtaining smoothing denoising Case number (CN) image;The marginal information of the case number (CN) image after the smoothing denoising is strengthened using histogram equalization method, after obtaining pretreatment Case number (CN) image.
- 4. according to the method for claim 1, it is characterised in that described pretreatment is carried out to the case number (CN) image to include:The case number (CN) image is divided into according to the gamma characteristic of the case number (CN) image of the container to be identified by background and the class of template two, The variance made between two classes is obtained into maximum parameter as optimal threshold;Binary image is obtained using the Optimal-threshold segmentation, using the binary image as pretreated case number (CN) figure Picture.
- 5. according to the method for claim 1, it is characterised in that the deep learning model based on convolutional neural networks is The case number (CN) sample data for exceeding certain threshold value by quantity trains what is obtained, and the case number (CN) sample data includes different angle, no The case number (CN) picture of same illumination condition, different background.
- 6. according to the method for claim 1, it is characterised in that the training process of the grader includes:Utilize the depth characteristic of the deep learning model extraction case number (CN) sample data based on convolutional neural networks;Based on machine learning algorithm, grader is trained to the depth characteristic;Wherein described case number (CN) sample data include the different types of case number (CN) picture that user specifies.
- A kind of 7. container number identification device, it is characterised in that including:Pretreatment module, pre-process, obtain for obtaining the case number (CN) image of container to be identified, and to the case number (CN) image Pretreated case number (CN) image;Character segmentation module, for carrying out Character segmentation processing to the pretreated case number (CN) image by rank scanning method, Multiple character pictures are obtained, and record order of the character picture in the case number (CN) of the container to be identified;Characteristic extracting module, described in extracting correspondence in each character picture respectively according to default deep learning model The character feature of container number to be identified, the default deep learning model include the depth based on convolutional neural networks Practise model;As a result identification module, for utilizing the grader based on the default deep learning model training respectively to each described The character feature of character picture is identified, and generates recognition result corresponding to each character picture;Character combination module, will be each for the order according to the character picture in the case number (CN) of the container to be identified Recognition result corresponding to the character picture is combined, and obtains the case number (CN) of the container to be identified.
- 8. device according to claim 7, it is characterised in that the deep learning model based on convolutional neural networks is The case number (CN) sample data for exceeding certain threshold value by quantity trains what is obtained, and the case number (CN) sample data includes different angle, no The case number (CN) picture of same illumination condition, different background.
- 9. a kind of electronic equipment, including memory, processor, it is stored with what can be run on the processor on the memory Computer program, it is characterised in that realize that the claims 1 to 6 are any during computer program described in the computing device Method described in.
- 10. a kind of computer-readable medium for the non-volatile program code that can perform with processor, it is characterised in that described Program code makes any one of claim 1 to 6 described in computing device methods described.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711125985.0A CN107832767A (en) | 2017-11-14 | 2017-11-14 | Container number identification method, device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711125985.0A CN107832767A (en) | 2017-11-14 | 2017-11-14 | Container number identification method, device and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107832767A true CN107832767A (en) | 2018-03-23 |
Family
ID=61655452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711125985.0A Pending CN107832767A (en) | 2017-11-14 | 2017-11-14 | Container number identification method, device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107832767A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108470366A (en) * | 2018-03-28 | 2018-08-31 | 同方威视技术股份有限公司 | Analog image generation method and device and computer readable storage medium |
CN108596166A (en) * | 2018-04-13 | 2018-09-28 | 华南师范大学 | A kind of container number identification method based on convolutional neural networks classification |
CN110210433A (en) * | 2019-06-10 | 2019-09-06 | 南京大学 | A kind of container number detection and recognition methods based on deep learning |
CN110222629A (en) * | 2019-06-03 | 2019-09-10 | 中冶赛迪重庆信息技术有限公司 | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene |
CN110276371A (en) * | 2019-05-05 | 2019-09-24 | 杭州电子科技大学 | A kind of container angle recognition methods based on deep learning |
CN110348451A (en) * | 2019-07-18 | 2019-10-18 | 西南交通大学 | Case number (CN) automatic collection and recognition methods in railway container cargo handling process |
CN110647784A (en) * | 2018-06-27 | 2020-01-03 | 中国移动通信集团浙江有限公司 | Equipment asset management method and device based on deep learning |
CN110659643A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN110969054A (en) * | 2018-09-29 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN111178143A (en) * | 2019-12-06 | 2020-05-19 | 国电南瑞科技股份有限公司 | Container temperature information acquisition method, device and system |
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 |
CN111382733A (en) * | 2018-12-28 | 2020-07-07 | 同方威视技术股份有限公司 | Multichannel container number identification method, device and system |
CN111507316A (en) * | 2020-01-17 | 2020-08-07 | 杭州东方通信软件技术有限公司 | Intelligent identification method and system for optical cable cross connecting box |
CN111833302A (en) * | 2020-06-05 | 2020-10-27 | 中铁武汉勘察设计研究院有限公司 | Car number and case number identification association system |
CN112119397A (en) * | 2018-04-05 | 2020-12-22 | 雪佛龙美国公司 | Classification of pipe and meter flow chart information using machine learning |
CN113076838A (en) * | 2021-03-25 | 2021-07-06 | 中国铁路北京局集团有限公司北京科学技术研究所 | Method, system, equipment and storage medium for identifying marshalling sequence of railway container station box numbers |
CN113673608A (en) * | 2021-06-03 | 2021-11-19 | 厦门锐特信息技术有限公司 | Container number recognition system and method based on PaddleOCR framework |
CN113807244A (en) * | 2021-09-16 | 2021-12-17 | 中国电信集团系统集成有限责任公司 | Deep learning-based cabinet layout drawing method |
CN114359762A (en) * | 2021-12-31 | 2022-04-15 | 哪吒港航智慧科技(上海)有限公司 | Container top hole identification method and system, storage medium and terminal |
CN115527209A (en) * | 2022-09-22 | 2022-12-27 | 宁波港信息通信有限公司 | Method, device and system for identifying shore bridge box number and computer equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101650780A (en) * | 2009-09-08 | 2010-02-17 | 宁波中科集成电路设计中心有限公司 | Identification method of container number |
CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
US20150371100A1 (en) * | 2014-06-23 | 2015-12-24 | Xerox Corporation | Character recognition method and system using digit segmentation and recombination |
CN106909941A (en) * | 2017-02-27 | 2017-06-30 | 广东工业大学 | Multilist character recognition system and method based on machine vision |
-
2017
- 2017-11-14 CN CN201711125985.0A patent/CN107832767A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101650780A (en) * | 2009-09-08 | 2010-02-17 | 宁波中科集成电路设计中心有限公司 | Identification method of container number |
CN102024144A (en) * | 2010-11-23 | 2011-04-20 | 上海海事大学 | Container number identification method |
CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
US20150371100A1 (en) * | 2014-06-23 | 2015-12-24 | Xerox Corporation | Character recognition method and system using digit segmentation and recombination |
CN106909941A (en) * | 2017-02-27 | 2017-06-30 | 广东工业大学 | Multilist character recognition system and method based on machine vision |
Non-Patent Citations (1)
Title |
---|
王嘉梅: "《基于MATLAB的数字信号处理与实践开发》", 31 December 2007, 西安电子科技大学出版社 * |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108470366A (en) * | 2018-03-28 | 2018-08-31 | 同方威视技术股份有限公司 | Analog image generation method and device and computer readable storage medium |
CN112119397A (en) * | 2018-04-05 | 2020-12-22 | 雪佛龙美国公司 | Classification of pipe and meter flow chart information using machine learning |
CN108596166A (en) * | 2018-04-13 | 2018-09-28 | 华南师范大学 | A kind of container number identification method based on convolutional neural networks classification |
CN108596166B (en) * | 2018-04-13 | 2021-10-26 | 华南师范大学 | Container number identification method based on convolutional neural network classification |
CN110647784A (en) * | 2018-06-27 | 2020-01-03 | 中国移动通信集团浙江有限公司 | Equipment asset management method and device based on deep learning |
CN110659643A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN110659643B (en) * | 2018-06-29 | 2022-08-26 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN110969054B (en) * | 2018-09-29 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN110969054A (en) * | 2018-09-29 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Container number identification method and device |
CN111382733A (en) * | 2018-12-28 | 2020-07-07 | 同方威视技术股份有限公司 | Multichannel container number identification method, device and system |
CN111382733B (en) * | 2018-12-28 | 2023-09-15 | 同方威视技术股份有限公司 | Multichannel container number identification method, device and system |
CN110276371A (en) * | 2019-05-05 | 2019-09-24 | 杭州电子科技大学 | A kind of container angle recognition methods based on deep learning |
CN110276371B (en) * | 2019-05-05 | 2021-05-07 | 杭州电子科技大学 | Container corner fitting identification method based on deep learning |
CN110222629A (en) * | 2019-06-03 | 2019-09-10 | 中冶赛迪重庆信息技术有限公司 | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene |
CN110210433A (en) * | 2019-06-10 | 2019-09-06 | 南京大学 | A kind of container number detection and recognition methods based on deep learning |
CN110348451A (en) * | 2019-07-18 | 2019-10-18 | 西南交通大学 | Case number (CN) automatic collection and recognition methods in railway container cargo handling process |
CN111178143B (en) * | 2019-12-06 | 2022-11-04 | 国电南瑞科技股份有限公司 | Container temperature information acquisition method, device and system |
CN111178143A (en) * | 2019-12-06 | 2020-05-19 | 国电南瑞科技股份有限公司 | Container temperature information acquisition method, device and system |
CN111507316A (en) * | 2020-01-17 | 2020-08-07 | 杭州东方通信软件技术有限公司 | Intelligent identification method and system for optical cable cross connecting box |
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 |
CN111353494B (en) * | 2020-04-09 | 2023-06-23 | 成都睿琪科技有限责任公司 | Steel code recognition system and method |
CN111833302A (en) * | 2020-06-05 | 2020-10-27 | 中铁武汉勘察设计研究院有限公司 | Car number and case number identification association system |
CN113076838A (en) * | 2021-03-25 | 2021-07-06 | 中国铁路北京局集团有限公司北京科学技术研究所 | Method, system, equipment and storage medium for identifying marshalling sequence of railway container station box numbers |
CN113673608A (en) * | 2021-06-03 | 2021-11-19 | 厦门锐特信息技术有限公司 | Container number recognition system and method based on PaddleOCR framework |
CN113807244A (en) * | 2021-09-16 | 2021-12-17 | 中国电信集团系统集成有限责任公司 | Deep learning-based cabinet layout drawing method |
CN113807244B (en) * | 2021-09-16 | 2024-02-27 | 中电信数智科技有限公司 | Cabinet layout drawing method based on deep learning |
CN114359762A (en) * | 2021-12-31 | 2022-04-15 | 哪吒港航智慧科技(上海)有限公司 | Container top hole identification method and system, storage medium and terminal |
CN115527209A (en) * | 2022-09-22 | 2022-12-27 | 宁波港信息通信有限公司 | Method, device and system for identifying shore bridge box number and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107832767A (en) | Container number identification method, device and electronic equipment | |
CN109902622B (en) | Character detection and identification method for boarding check information verification | |
Saxena | Niblack’s binarization method and its modifications to real-time applications: a review | |
CN107871125A (en) | Architecture against regulations recognition methods, device and electronic equipment | |
CN111414906B (en) | Data synthesis and text recognition method for paper bill pictures | |
CN103049763B (en) | Context-constraint-based target identification method | |
CN107679531A (en) | Licence plate recognition method, device, equipment and storage medium based on deep learning | |
Xu et al. | Page segmentation for historical handwritten documents using fully convolutional networks | |
CN107292311A (en) | A kind of recognition methods of the Characters Stuck identifying code based on neutral net | |
CN107784301A (en) | Method and apparatus for identifying character area in image | |
CN104751142A (en) | Natural scene text detection algorithm based on stroke features | |
CN103208004A (en) | Automatic recognition and extraction method and device for bill information area | |
CN104915972A (en) | Image processing apparatus, image processing method and program | |
CN103824373B (en) | A kind of bill images amount of money sorting technique and system | |
D’souza et al. | Offline handwritten mathematical expression recognition using convolutional neural network | |
CN110503100A (en) | A kind of medical document recognition methods, device, computer installation and computer readable storage medium | |
CN109685065A (en) | Printed page analysis method, the system of paper automatic content classification | |
CN110598566A (en) | Image processing method, device, terminal and computer readable storage medium | |
CN112069900A (en) | Bill character recognition method and system based on convolutional neural network | |
CN113191358B (en) | Metal part surface text detection method and system | |
CN112052845A (en) | Image recognition method, device, equipment and storage medium | |
CN105404868A (en) | Interaction platform based method for rapidly detecting text in complex background | |
CN111967286A (en) | Method and device for identifying information bearing medium, computer equipment and medium | |
CN109741273A (en) | A kind of mobile phone photograph low-quality images automatically process and methods of marking | |
CN116597466A (en) | Engineering drawing text detection and recognition method and system based on improved YOLOv5s |
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 |
Application publication date: 20180323 |
|
RJ01 | Rejection of invention patent application after publication |