A kind of electronic certificate recognition methods, apparatus and systemTechnical field
The present invention relates to field of image processing more particularly to a kind of electronic certificate recognition methods, apparatus and system.
Background technique
Currently, existing electronic certificate identification device only has acquisition and the transfer function of image, without any image dataProcessing capacity.After electronic certificate identification device collects raw image data, it is transferred to external PC machine, then by outsidePC machine completes whole image processing process.In the process, PC machine needs to carry out a large amount of image data operation, to obtain mostRequired result images eventually (i.e. with the result images of human eye visual picture effect).The processing of raw image data has a large amount ofSimple concurrent operation, cause this kind of electronic certificate identification device more demanding to the function of PC machine, therefore, carried out using PC machineThe efficiency of image procossing is lower, can no longer meet the demand of current electronic certificate identification.
High and identification is required to imitate in view of function of the existing electronic certificate identification device for being only completed Image Acquisition to PC machineThe lower problem of rate, electronic certificate identification device relatively advanced at present have begun using with general image processing functionCamera, this kind of camera includes USB camera and network shooting head etc..This electronic certificate identification device is carrying out certificateDuring identification, first passes through applied to the camera on existing electronic certificate identification device, complete some general imagesProcessing, such as sharpenings, noise reduction, Gamma are corrected etc., then by the image transmitting Jing Guo preliminary treatment to outer PC.However, bySolidify in current used camera function, so can not be demonstrate,proved in the integrated electronics that is exclusively used in of existing electronic certificate identification deviceIt is lower to customize degree for the image processing algorithm of part identification, i.e. electronics.So this kind of electronic certificate identification device is for currentThe applicability of electronic certificate identification is poor.
Therefore, with the diversification of certificate identification client, existing electronic certificate identification device can no longer meet clientDemand, thus limit electronic certificate identification field technology development.
It should be noted that the above description of the technical background be intended merely to it is convenient to technical solution of the present invention carry out it is clear,Complete explanation, and facilitate the understanding of those skilled in the art and illustrate.Cannot merely because these schemes of the inventionBackground technology part is expounded and thinks that above-mentioned technical proposal is known to those skilled in the art.
Summary of the invention
The embodiment of the present invention provides a kind of electronic certificate recognition methods, apparatus and system, to solve existing electronic certificateThe poor problem of the applicability of identification device identification.
In a first aspect, the embodiment of the present invention provides a kind of electronic certificate recognition methods, comprising: acquire the original of electronic certificateImage data；The raw image data is pre-processed, result images data are generated；The result images data are transmittedTo outer PC, the PC machine carries out image recognition processing based on the result images data received.
Second aspect, the embodiment of the present invention provide a kind of electronic certificate recognition methods, are applied to PC machine end, comprising: obtainElectronic certificate identifies the result images data that equipment is sent；Image recognition processing is carried out to the result images data；Wherein, instituteStating result images data is raw image data of the electronic certificate identification equipment by acquisition electronic certificate, and to the originalBeginning image data is generated after being pre-processed.
The third aspect, the embodiment of the present invention provide a kind of electronic certificate identification device, comprising: image capture module is used forAcquire the raw image data of electronic certificate；Image processing module is generated for pre-processing to the raw image dataResult images data；Image transmission module, for the result images data to be transferred to outer PC, the PC machine is based on connecingThe result images data received carry out image recognition processing.
Fourth aspect, the embodiment of the present invention provide a kind of pattern recognition device, are applied to PC machine end, comprising: module is obtained,The result images data sent for obtaining electronic certificate identification equipment；Picture recognition module, for the result images numberAccording to progress image recognition processing；Wherein, the result images data are that the electronic certificate identifies that equipment passes through acquisition electronics cardThe raw image data of part, and generated after being pre-processed to the raw image data.
5th aspect, the embodiment of the present invention provide a kind of electronic certificate identification device, comprising: collector, for acquiring electricityThe raw image data of sub- certificate；Processor generates result images number for pre-processing to the raw image dataAccording to；Transmitter, for the result images data to be transferred to outer PC, the PC machine is based on the result figure receivedAs data carry out image recognition processing.
6th aspect, the embodiment of the present invention provide a kind of electronic certificate identifying system, including electronic certificate identification device andPC machine, in which: the electronic certificate identification device is the electronic certificate identification device as described in the aforementioned third aspect；The PC machineIncluding the pattern recognition device as described in aforementioned fourth aspect.
Electronic certificate recognition methods, apparatus and system disclosed in the embodiment of the present invention, are integrated with image processing function, willThe pretreatment work of image data is removed from PC machine, has been liberated PC machine energy, has been reduced the system delay in PC machine, improve PC machineThe efficiency for identifying the result images makes certificate identification have very high real-time；Meanwhile, it is capable to execute the image procossing of customizationAlgorithm, treated that result images effect is able to satisfy client couple for the electronic certificate identification device for making by the combination image procossingIn the functional requirement of certificate identification, the customization of electronic certificate identification device and the applicability for customer demand are improved.
Referring to following description and accompanying drawings, only certain exemplary embodiments of this invention is disclosed in detail, specifies original of the inventionReason can be in a manner of adopted.It should be understood that embodiments of the present invention are not so limited in range.In appended powerIn the range of the spirit and terms that benefit requires, embodiments of the present invention include many changes, modifications and are equal.
The feature for describing and/or showing for a kind of embodiment can be in a manner of same or similar one or moreIt uses in a other embodiment, is combined with the feature in other embodiment, or the feature in substitution other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when using herein, but simultaneouslyIt is not excluded for the presence or additional of one or more other features, one integral piece, step or component.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show belowThere is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only thisSome embodiments of invention for those skilled in the art without any creative labor, can be with rootOther attached drawings are obtained according to these attached drawings.
Fig. 1 is the process flow diagram of the electronic certificate recognition methods of one embodiment of the invention；
Fig. 2 is the method flow diagram of the step S102 in embodiment illustrated in fig. 1；
Fig. 3 is the process flow diagram of the interpolation method of the embodiment of the present invention；
Fig. 4 is the process flow diagram of the JPEG compression processing method of the embodiment of the present invention；
Fig. 5 is the process flow diagram of the electronic certificate recognition methods of another embodiment of the present invention；
Fig. 6 is the process flow diagram of the electronic certificate recognition methods of yet another embodiment of the invention；
Fig. 7 is the structural schematic diagram of the electronic certificate identification device of the embodiment of the present invention；
Fig. 8 is the structural schematic diagram of the image processing module 102 in embodiment illustrated in fig. 7；
Fig. 9 is the structural schematic diagram of an embodiment of interpolation process unit 1021 of the invention；
Figure 10 is the structural schematic diagram of another embodiment of interpolation process unit 1021 of the invention；
Figure 11 is the structural schematic diagram of the compression processing unit 1022 of the embodiment of the present invention；
Figure 12 is the structural schematic diagram of the electronic certificate identification device of another embodiment of the present invention；
Figure 13 is the structural schematic diagram of the electronic certificate identification device of further embodiment of this invention；
Figure 14 is the process flow diagram of the electronic certificate recognition methods of yet another embodiment of the invention；
Figure 15 is the structural representation of the pattern recognition device of the electronic certificate recognition methods corresponding to embodiment illustrated in fig. 14Figure；
Figure 16 is the hardware structural diagram of the electronic certificate identification device of one embodiment of the invention；
Figure 17 is the hardware structural diagram of the electronic certificate identification device of another embodiment of the present invention；
Figure 18 is the structural schematic diagram of the electronic certificate identifying system of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, completeSite preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based onEmbodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every otherEmbodiment shall fall within the protection scope of the present invention.
Those skilled in the art will understand that embodiments of the present invention can be implemented as a kind of system, device, equipment,Method or computer program product.Therefore, the present disclosure may be embodied in the following forms, it may be assumed that complete hardware, complete softThe form that part (including firmware, resident software, microcode etc.) or hardware and software combine.
Below with reference to several representative embodiments of the invention, the principle and spirit of the present invention are explained in detail.
The embodiment of the present invention is applied in the identification field of electronic certificate, by by the acquisition of electronic certificate image, pretreatmentIt is integrated on electronic certificate identification device with transfer function, to liberate the PC machine energy of periphery, reduces the system in PC machineDelay, substantially increases the efficiency that PC machine identifies the result images, and certificate identification is made to have very high real-time.In addition, pre- placeReason operation can be realized by fpga chip or dsp chip, therefore be able to carry out the image processing algorithm of customization, be made by knotClosing the electronic certificate identification device of image procossing, treated that result images effect is able to satisfy the function that client identifies certificateDemand improves the customization of electronic certificate identification device and the applicability for customer demand.
Fig. 1 is the process flow diagram of the electronic certificate recognition methods of one embodiment of the invention.As shown in Figure 1, the embodimentElectronic certificate recognition methods include:
Step S101 acquires the raw image data of electronic certificate；
Step S102 pre-processes the raw image data, generates result images data；
The result images data are transferred to outer PC by step S103, and the PC machine is based on the knot receivedFruit image data carries out image recognition processing.
It should be noted that the electronic certificate recognition methods of the present embodiment is applied in electronic certificate identification terminal, PC machine isIndependently of the peripheral system of the terminal.In the embodiment of the present invention, PC machine no longer carries out image pretreatment operation, when its get throughAfter crossing pretreated result images data, progress certificate classification first learns the type of specific electronic certificate, then uses thingFirst scheduled recognition template is by sequence of operations such as zone location, row positioning, recognition unit positioning, character cutting, OCR, mostThe character that cutting obtains is identified eventually, to complete the identification to electronic certificate.
When it is implemented, in step s101, the original image number of electronic certificate can be acquired by image acquisition deviceAccording to.For example, image acquisition device can be digital camera, camera, scanner etc..The present invention does not obtain raw image dataMode is taken to be limited, as long as the original image obtained by such as imaging sensor, this is also not wound of the inventionWhere new.
When it is implemented, as shown in Fig. 2, in step s 102, it is described that raw image data is pre-processed, it is specific to wrapIt includes:
Step S1021 carries out real-time interpolation processing to the raw image data, reconstructs corresponding RGB image；
Step S1022 carries out JPEG compression processing to the RGB image after reconstruct, generates the result images data.
In the embodiment of the present invention, step S1021 calculates loss for realizing the interpolation processing to raw image dataRGB data.Under normal conditions, nearest field interpolation algorithm is generally used, this algorithm is relatively simple, in the RGB for calculating lossWhen data, the average value of closest pixel value is only used.Such calculation amount very little, speed also quickly, but recoverRGB image texture it is relatively fuzzy, overall feeling is not sharp keen enough, and has biggish color lump to be distorted at texture edge.
In order to solve the problems, such as that nearest field interpolation algorithm is fuzzy to image bring and edge distortion, the embodiment of the present invention are adoptedWith interpolation process method as shown in Figure 3.
As shown in figure 3, the revealed interpolation method of the present embodiment includes following 3 steps:
Step S301, green component angle detecting: since the Bayer array Green pixel quantity of imaging sensor is than redBlue pixel is more, arranges than comparatively dense, so using green pixel as the reference in interpolation direction.According to the existing green picture in peripheryThe brightness change trend of element calculates the substantially locating grain direction of each pixel, is classified as horizontal and vertical two class.
Green component interpolation: step S302 according to the categorization results of step S301, counts each pixel and its periphery 8The both horizontally and vertically quantity of a pixel determines three kinds of interpolation methods for the green pixel of each missing, respectively horizontal,Vertical and surrounding is average, and finally restores the green pixel values of missing.
Red and blue components interpolation: step S303 due to green pixel full recovery, equalizes principle by region color differenceThe red blue pixel value of missing can be calculated.
In addition, during interpolation processing, can also additionally increase the drop of bad point in another embodiment of the present inventionIt makes an uproar function, keeps final image effect more preferable.
It goes bad point: due to the technological reason of imaging sensor, can inevitably have some defective pixels, show as" being always on " or " often dark ", is commonly called as " bad point ".To the method that the removal of bad point generally uses average threshold, in Bayer array, such asFruit center pixel and the mean difference of periphery same color pixel are excessive, then it is believed that center pixel is bad point, need with weekThe average value of side same color pixel replaces.
Noise reduction: decrease of noise functions is only used for green pixel.In Bayer array, 2 are separately included in a 4x4 pixel regionA green pixel, 1 red pixel and 1 blue pixel, and wherein this 2 green pixels are respectively by different gain amplifiersIt goes to obtain brightness value, even if the light luminance being radiated on 2 green pixels is consistent, due to gain amplifier technique,The two green pixel values got are devious, so this deviation is enough to interfere with interpolation side if being not processedTo judgement, show that on final image be that noise increases, texture edge distortion.The processing means of this programme are, in BayerIn array 4x4 pixel region, one of green pixel uses original value, another then uses the draw with periphery green pixelValue, can obviously inhibit the quantity of noise in this way, and keep image texture transition more natural.
In the embodiment of the present invention, step S1022 is used to carry out JPEG compression processing to the RGB image after reconstruct, withRealize high efficiency of transmission.In the prior art, image data generally is transmitted using RAW mode or use similar H264 video flowing modeTransmit image data.Wherein, RAW data refer to the initial data obtained from imaging sensor, due to without any compressionProcessing, data volume is bigger, so efficiency of the image in transmission is lower, is generally unable to reach the largest frames of imaging sensorRate.Although H264 video flowing mode is less than JPEG compression mode to the pressure of transmission bandwidth, for picture quality stillJPEG compression mode is more preferable.And what H264 video flowing mode was mainly directed towards is video data, with individual bat in certificate identificationIt is still less matched according to mode.
In the embodiment of the present invention, the image obtained from imaging sensor is done into JPEG compression, in unobvious image quality lossUnder the premise of, it is effectively reduced transmission bandwidth pressure, the transmission speed for making image faster, can reach the largest frames speed of sensor.
As shown in figure 4, the method stream for carrying out JPEG compression processing to the RGB image after reconstruct of the embodiment of the present inventionJourney is as follows:
The RGB image after reconstruct is carried out color space conversion, generates YUV color space image by step S401.YUV is a kind of colour coding method, wherein " Y " indicates brightness (Luminance or Luma), that is, grayscale value；" U " andThat " V " is indicated is then coloration (Chrominance, Chroma), and effect is description colors of image and saturation degree, is used for specified pixelColor.Research has shown that human eye is more than coloration to the sensitivity of brightness, using this principle, chrominance information can be reduced a bit,Human eye can not also find this point, so the yuv data size with piece image is always smaller than rgb format.YUV is compilingThe type of true-color color space (colorspace), Y'UV, YUV, the proper nouns such as YCbCr, YPbPr can be known asYUV has overlapping each other.
The YUV color space image is carried out two-dimension discrete cosine transform (Discrete Cosine by step S402Transform, DCT), generate two-dimensional dct image.
Step S403 quantifies the picture frequency data of the two-dimensional dct image, removes high-frequency information and reduces numberAccording to amount；
Picture frequency data after quantization are carried out Huffman encoding, are further reduced data volume, and generate by step S404Jpeg bytestream, i.e. generation jpeg compressed image.
When specific operation, after electronic certificate identification device is started to work, as long as receiving photographing instruction, above workflowIt will start automatically, not need manual intervention, the jpeg image finally compressed can be transferred in computer by usb bus.TogetherWhen, the software of computer end is needed jpeg data decoding is received, and final decompression obtains RGB image and does at subsequent certificate identificationReason.
The revealed JPEG image compression method of the embodiment of the present invention, under the premise of the loss of not obvious image quality, effectivelyTransmission bandwidth pressure is alleviated, the transmission speed for making image faster, can reach the largest frames speed of sensor.
When it is implemented, to the pretreatment of raw image data in addition to including interpolation processing and jpeg image compression processingOutside, further include the noise reduction to raw image data, Gamma correction, image enhancement, go background and go the pretreatment operations such as hot spot.It is due to these pretreated implementation methods and almost consistent in the prior art, expansion is not done in the present invention and is repeated.
Fig. 5 is the process flow diagram of the electronic certificate recognition methods of another embodiment of the present invention.As shown in figure 5, itself and Fig. 1Illustrated embodiment the difference is that, embodiment illustrated in fig. 5 further includes step S104, by the raw image data and resultImage data is stored.That is, raw image data is deposited after step S101 collects raw image dataStorage；After step S102 obtains result images data, result images data are stored.In present embodiment, which isAn independent step, as long as collecting raw image data and generating result images data, this step will start automatically, willRaw image data and the result images data of generation all save, and to facilitate, the later period is searched and while needing to handle again is not required toIt to take pictures repeatedly.
Fig. 6 is the process flow diagram of the electronic certificate recognition methods of yet another embodiment of the invention.As shown in fig. 6, itself and Fig. 1Illustrated embodiment the difference is that, embodiment illustrated in fig. 6 further includes step S105, when generating result images data, togetherShi Shengcheng controls signal；In step s 103, it is controlled the result images data transmission by the control signal to described outerPortion's PC machine.In the present embodiment, step S105 is behind step S102, and if there is control signal generates, then step S103 is then by controllingThe transmission of signal control data processed.
Although the embodiment of Fig. 5 and the embodiment of Fig. 6 respectively illustrate storing step S104 and rate-determining steps S105, in factStoring step S104 and rate-determining steps S105 can also simultaneously in one embodiment, i.e. in a specific embodiment, Ke YitongWhen include step S101-step S105.
Electronic certificate recognition methods illustrated in the above embodiments shells the pretreatment work of image data from PC machine endFrom having liberated PC machine energy, reduced the system delay in PC machine, improved the efficiency that PC machine identifies the result images, make certificateIdentification has very high real-time.
It should be noted that although describing the operation of the method for the present invention in the accompanying drawings with particular order, this is not required thatOr hint must execute these operations in this particular order, or have to carry out operation shown in whole and be just able to achieve the phaseThe result of prestige.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or willOne step is decomposed into execution of multiple steps.
After describing the method for exemplary embodiment of the invention, next, with reference to Fig. 7 to the exemplary reality of the present inventionThe electronic certificate identification device for applying mode is introduced.Based on same design, the implementation of the device may refer to the above methodImplement, overlaps will not be repeated.Term " module " used below and " unit " can be the software for realizing predetermined functionAnd/or hardware.Although module described in following embodiment is preferably realized with software, hardware or software and hardThe realization of the combination of part is also that may and be contemplated.
Fig. 7 is the structural schematic diagram of the electronic certificate identification device of the embodiment of the present invention.As shown in figure 8, comprising: imageAcquisition module 101, for acquiring the raw image data of electronic certificate；Image processing module 102, for the original imageData are pre-processed, and result images data are generated；Image transmission module 103, for being transferred to the result images dataOuter PC, the PC machine carry out image recognition processing based on the result images data received.
In one embodiment, as shown in figure 8, described image processing module 102 is used to pre-process raw image data,It is specifically included:
Interpolation process unit 1021 reconstructs corresponding for carrying out real-time interpolation processing to the raw image dataRGB image；
Compression processing unit 1022 generates the knot for carrying out JPEG compression processing to the RGB image after reconstructFruit image data.
In one embodiment, as shown in figure 9, the interpolation process unit 1021 specifically includes:
Green component angle detecting unit 10211, for carrying out green component angle detecting to the raw image data,Use green pixel to calculate grain direction locating for each pixel as the reference in interpolation direction, and is classified as horizontal and verticalStraight two class；
Green component interpolating unit 10212, for carrying out green component interpolation processing according to classification results, reduction is fallen vacantThe green pixel values of mistake；
Red and blue components interpolating unit 10213, for carrying out at red and blue components interpolation after the green pixel values lackedReason calculates the red blue pixel value of missing.
In one embodiment, as shown in Figure 10, the interpolation process unit 1021 further include:
Bad point unit 10214 is removed, for carrying out the figure after green component interpolation processing and red and blue components interpolation processingIt is handled as carrying out bad point.
In one embodiment, as shown in figure 11, the compression processing unit 1022 is specifically included:
Color space conversion module 10221 carries out color space conversion for the RGB image after reconstructing, generatesYUV color space image；
Two-dimension discrete cosine transform module 10222, for the YUV color space image to be carried out 2-D discrete cosine changeIt changes (Discrete Cosine Transform, DCT), generates two-dimension discrete cosine transform image；
Quantization modules 10223 are gone for quantifying the picture frequency data of the two-dimension discrete cosine transform imageExcept high-frequency information and reduce data volume；
Huffman encoding module 10224 carries out Huffman encoding for the picture frequency data after quantifying, further subtractsFew data volume, and generate jpeg bytestream.
In another embodiment, as shown in figure 12, electronic certificate identification device further include:
Data memory module 104 connects described image acquisition module 101 and image processing module 102, described for storingRaw image data and result images data.
In another embodiment, as shown in figure 13, electronic certificate identification device further include:
Control module 105 connects described image processing module 102 and image transmission module 103, for generating result figureWhen as data, control signal is also generated；The control signal is for controlling the result images data transmission to the outsidePC machine.
In one embodiment, described image processing module 102 is also used to carry out noise reduction, Gamma to the raw image dataCorrection, image enhancement go background and go the pretreatment operations such as hot spot.
In addition, although being referred to several units of electronic certificate identification device in the above detailed description, this strokeDivide only not enforceable.In fact, embodiment according to the present invention, the feature of two or more above-described unitsIt can be embodied in a unit with function.Equally, the feature and function of an above-described unit can also be furtherIt is divided by multiple units and embodies.
Figure 14 is the process flow diagram of the electronic certificate recognition methods of yet another embodiment of the invention.As shown in figure 14, it wrapsIt includes:
Step S701 obtains the result images data that electronic certificate identification equipment is sent；Wherein, the result images dataIdentify that equipment is carried out by the raw image data of acquisition electronic certificate, and to the raw image data for the electronic certificateIt is generated after pretreatment；
Step S702 carries out image recognition processing to the result images data.
It should be noted that the electronic certificate recognition methods of embodiment illustrated in fig. 14 is applied in peripheral system, i.e. PC machine end,It is accomplished that the process that pretreated result images data are carried out with image recognition processing, such as type of credential classification, areaThe sequence of operations such as domain positioning, row positioning, recognition unit positioning, character cutting, OCR.
Based on same design, Figure 15 is the image recognition dress of the electronic certificate recognition methods corresponding to embodiment illustrated in fig. 14The structural schematic diagram set, the pattern recognition device are applied to peripheral system, i.e. PC machine end.
As shown in figure 15, pattern recognition device disclosed in the present embodiment includes:
Module 201 is obtained, the result images data sent for obtaining electronic certificate identification equipment；Wherein, the resultImage data is raw image data of the electronic certificate identification equipment by acquisition electronic certificate, and to the original imageData are generated after being pre-processed.
Picture recognition module 202, for carrying out image recognition processing to the result images data.Image recognition processing toolBody includes: type of credential classification, zone location, row positioning, recognition unit positioning, character cutting, OCR etc..
The image recognition that the electronic certificate recognition methods and embodiment illustrated in fig. 15 that embodiment illustrated in fig. 14 discloses discloseDevice is applied in independent peripheral system, i.e. PC machine end.As can be seen that PC machine end no longer carries out the operation of image preprocessing, solutionPC machine energy has been put, the system delay in PC machine is reduced, has improved the efficiency that PC machine identifies the result images, so that certificate identifiesWith very high real-time.
Figure 16 is the hardware structural diagram of the electronic certificate identification device of the embodiment of the present invention.As shown in figure 16, comprising:
Collector 11, for acquiring the raw image data of electronic certificate；
Processor 12 generates result images data for pre-processing to the raw image data；
Transmitter 13, for the result images data to be transferred to outer PC, the PC machine is based on the institute receivedIt states result images data and carries out image recognition processing.
When it is implemented, the collector 11 can be imaging sensor, be also possible to such as digital camera, camera orThe hardware devices such as person's scanner.Collector 11 the collected raw image data for electronic certificate.
When it is implemented, the processor 12 can be fpga chip or dsp chip.Fpga chip or dsp chip are responsible forCarry out real-time pre-processing image data, comprising interpolation processing, Gamma correction, noise reduction, image enhancement, go background, go hot spot,The functions such as JPEG picture compression processing.
In one embodiment, as shown in figure 17, other than collector, processor and transmitter, electronic certificate identificationDevice further includes master cpu chip 14, pin-saving chip 15.Wherein, cpu chip connection processor 12 and transmitter 13, numberCollector 11 and processor 12 are connected according to storage chip 15.When it is implemented, collector 11 is responsible for acquisition raw image data；Fpga chip or dsp chip are responsible for carrying out real-time pre-processing image data, increase comprising interpolation, Gamma correction, noise reduction, imageBy force, it goes background, go the functions such as hot spot, picture compression；Master cpu chip 14 takes charge the workflow of whole system, coordinatesData between fpga chip and transmitter 13 are carried；Pin-saving chip 15 is responsible for the figure of temporal cache before and after treatmentAs data；Transmitter 13 is responsible for final image data being transferred to periphery by data link (such as USB or TCP/IP network)System (such as PC machine).
Wherein, it should be noted that if processor uses dsp chip, master cpu chip 14 can be omitted, becauseData processing and WorkFlow Managerment can be usually combined for dsp chip.But the parallelization processing capacity of dsp chip does not haveFpga chip is powerful, so DSP scheme and FPGA scheme difference are little in the system of middle and small scale data volume, but is advising greatlyGeneral or preferred FPGA scheme in mould data volume system.
Figure 18 is the structural schematic diagram of the electronic certificate identifying system of the embodiment of the present invention.As shown in figure 18, electronic certificateIdentifying system includes electronic certificate identification device 1 and PC machine 2, wherein electronic certificate identification device 1 can be as Fig. 7-Figure 13,Electronic certificate identification device described in Figure 16-Figure 17 any embodiment；The PC machine includes described in embodiment as shown in figure 15Pattern recognition device.
In the present embodiment, the electronic certificate identification device for being integrated with image processing function is connected by USB line or cableEnter PC machine end, the software at PC machine end initiates operating process, and electronic certificate identification device acquires original image and according to the behaviour at the end PCIt being required and completes specific image procossing, electronic certificate identification device passes the image that processing is completed or data result back PC machine,PC machine carries out final image recognition processing, as type of credential classification, zone location, row positioning, recognition unit positioning, character are cutPoint, OCR etc..
Electronic certificate recognition methods, apparatus and system disclosed in the embodiment of the present invention, by the pretreatment work of image dataMake to remove from PC machine end, has liberated PC machine energy, reduced the system delay in PC machine, improved PC machine and identify the result imagesEfficiency makes certificate identification have very high real-time；Meanwhile image preprocessing is carried out using FPGA or DSP, it is able to carry outThe image processing algorithm of customization, the electronic certificate identification device for making by the combination image procossing treated result imagesEffect is able to satisfy the functional requirement that client identifies certificate, improves the customization of electronic certificate identification device and for visitorThe applicability of family demand.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer programProduct.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present inventionApply 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.) producesThe form of product.
In the present embodiment, the memory includes but is not limited to random access memory (Random AccessMemory, RAM), read-only memory (Read-Only Memory, ROM), caching (Cache), hard disk (Hard DiskDrive, HDD) or storage card (Memory Card).
In the present embodiment, the processor can be implemented in any suitable manner.For example, the processor can be withTake such as microprocessor or processor and storage can by (micro-) processor execute computer readable program code (such asSoftware or firmware) computer-readable medium, logic gate, switch, specific integrated circuit (Application SpecificIntegrated Circuit, ASIC), programmable logic controller (PLC) and the form etc. for being embedded in microcontroller.
The concrete function that the comment processing system that this specification embodiment provides, memory and processor are realized, canTo contrast explanation with the aforementioned embodiments in this specification, and the technical effect of aforementioned embodiments can be reached, hereJust it repeats no more.
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 productFigure 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 instructionsThe combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programsInstruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produceA raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for realThe 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 spyDetermine 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 orThe 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 countingSeries of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer orThe instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram oneThe step of function of being specified in a box or multiple boxes.
Specific embodiment is applied in the present invention, and principle and implementation of the present invention are described, above embodimentsExplanation be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art,According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion in this specificationAppearance should not be construed as limiting the invention.