CN109214230A

CN109214230A - Data matrix code recognition methods, device and electronic equipment

Info

Publication number: CN109214230A
Application number: CN201710542181.4A
Authority: CN
Inventors: 吕文
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2017-07-05
Filing date: 2017-07-05
Publication date: 2019-01-15
Anticipated expiration: 2037-07-05
Also published as: CN109214230B

Abstract

The embodiment of the invention provides data matrix code recognition methods, device and electronic equipments, wherein the described method includes: obtaining the data matrix code image comprising data matrix code to be identified；According to black, the white jump rule of pixel in data matrix code image, piecemeal is carried out to data matrix code image；According to black, the white jump rule of pixel in each piecemeal, each module for including in the piecemeal is determined, and according to the corresponding bit value of each module, determine the corresponding bit matrix of the piecemeal；Merge the corresponding bit matrix of each piecemeal, obtains the corresponding bit matrix of data matrix code to be identified.Data matrix code recognition methods, device and the electronic equipment provided through the embodiment of the present invention can be improved recognition accuracy when identification data matrix code.

Description

Data matrix code recognition methods, device and electronic equipment

Technical field

The present invention relates to two dimensional code identification technology fields, more particularly to data matrix code recognition methods, device and electronics Equipment.

Background technique

With the high speed development of information age, bar code is restricted its application because memory capacity is small.And it is two-dimentional Code can in the horizontal and vertical directions simultaneously expressing information, memory capacity is big, and two dimensional code have very strong correcting data error energy Power, it is highly reliable.Data matrix code is as one of two dimensional code, it is characterized in that storage efficiency is high, size is small, error correcting capability By force, therefore in fields such as industrial automation, automatic identifications it has a wide range of applications.Fig. 1 is the structure of common data matrix code Schematic diagram, common data matrix code include correction graph (not shown), positioning pattern 101 and data field.Data field It is made of the white module 102 and black module 103 of random distribution, these white modules 102 and the corresponding ratio of black module 103 The matrix of paricular value composition is the bit matrix of data matrix code data field.Data field bit matrix size is obtained by correction graph Number of modules determines.

Known data matrix code recognition methods predominantly utilizes the boundary of Contour extraction method location data square matrix code and list The average-size size of a module；Then vertical direction makees one group of straight line parallel with code vertical boundary, between adjacent parallel lines Spacing is module width value, wherein first parallel lines and frontier distance are 1.5 times of module width value sizes；Similarly in level side To work one group of parallel lines same as vertical direction；The seat of black module and white module is determined according to the intersection point of two groups of straight lines Mark, according to the bit matrix of the two-value information extraction data field of respective coordinates point, completes the identification of data matrix code.

As can be seen that known data matrix code recognition methods determines each module using equally distributed parallel lines, and And the bit value of respective modules is determined using corresponding two value information of the coordinate of single sampled point.So that working as data matrix When there is deviation on code positioning boundary, deviation can all occur in all sampled points, so that the error rate of the bit matrix extracted is larger, into And make data matrix code recognition accuracy lower.

Summary of the invention

The embodiment of the present invention is designed to provide data matrix code recognition methods, device and electronic equipment, is known with improving Recognition accuracy when other data matrix code.Specific technical solution is as follows:

In a first aspect, the embodiment of the invention provides a kind of data matrix code recognition methods, comprising:

Obtain the data matrix code image comprising data matrix code to be identified；

According to black, the white jump rule of pixel in the data matrix code image, the data matrix code image is carried out Piecemeal；

For each piecemeal, according to black, the white jump rule of pixel in the piecemeal, include in the piecemeal each is determined Module, and according to the corresponding bit value of each module, determine the corresponding bit matrix of the piecemeal；

Merge the corresponding bit matrix of each piecemeal, obtains the corresponding bit square of the data matrix code to be identified Battle array.

Optionally, black, the white jump rule according to pixel in the data matrix code image, to the data matrix Code image carry out piecemeal the step of include:

According to black, the white jump rule of pixel in the data matrix code image, piecemeal boundary is determined；

Piecemeal is carried out to the data matrix code image according to identified piecemeal boundary.

Optionally, black, the white jump rule according to pixel in the data matrix code image, determines piecemeal side The step of boundary includes:

Upright projection is carried out to the black and white trip point of pixel on every row in the data matrix code image, obtains the data The first black and white trip point accumulated value on square matrix code image level direction, chooses the vertical center line of the data matrix code image Corresponding vertical line vertically divides as the first piecemeal at the maximum coordinate of the first black and white trip point accumulated value in preset range Boundary line；

Floor projection is carried out to the black and white trip point of pixel in each column in the data matrix code image, obtains the data The second black and white trip point accumulated value in square matrix code image vertical direction, chooses the horizontal center line of the data matrix code image Corresponding horizontal line divides as the first piecemeal level at the maximum coordinate of the second black and white trip point accumulated value in preset range Boundary line；

Using the vertical line of demarcation of first piecemeal and the first piecemeal horizontal dividing lines as piecemeal boundary.

According to the horizontal center line of the data matrix code image by the data matrix code image be divided into top half and Lower half portion；

Upright projection is carried out to the black and white trip point of pixel on every row in the top half, obtains the data matrix code Third black and white trip point accumulated value on image level direction, the vertical center line for choosing the data matrix code image preset model Corresponding vertical line is enclosed at the maximum coordinate of the interior third black and white trip point accumulated value as the vertical line of demarcation of the second piecemeal；

Upright projection is carried out to the black and white trip point of pixel on every row in the lower half portion, obtains the data matrix code The 4th black and white trip point accumulated value on image level direction, the vertical center line for choosing the data matrix code image preset model Corresponding vertical line is enclosed at the maximum coordinate of the interior 4th black and white trip point accumulated value as the vertical line of demarcation of third piecemeal；

According to the vertical center line of the data matrix code image by the data matrix code image be divided into left-half and Right half part；

Floor projection is carried out to the black and white trip point of pixel in each column in the left-half, obtains the data matrix code The 5th black and white trip point accumulated value in image vertical direction, the vertical center line for choosing the data matrix code image preset model Corresponding vertical line is enclosed at the maximum coordinate of the interior 5th black and white trip point accumulated value as the second piecemeal horizontal dividing lines；

Floor projection is carried out to the black and white trip point of pixel in each column in the right half part, obtains the data matrix code The 6th black and white trip point accumulated value in image vertical direction, the vertical center line for choosing the data matrix code image preset model Corresponding vertical line is enclosed at the maximum coordinate of the interior 6th black and white trip point accumulated value as third piecemeal horizontal dividing lines；

By the vertical line of demarcation of second piecemeal, the vertical line of demarcation of the third piecemeal, the second piecemeal level boundary Line, the third piecemeal horizontal dividing lines are as piecemeal boundary.

Optionally, described to be directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determine this point Each module for including in block, and according to the corresponding bit value of each module, the step of determining the piecemeal corresponding bit matrix include:

The module side of the piecemeal is determined according to black, the white jump rule of pixel in the piecemeal for each piecemeal Boundary, and according to identified module alignment, determine each module for including in the piecemeal；

According to the number of black picture element and white pixel in each module, the corresponding bit value of each module is determined, and by each mould The corresponding bit value combinations of block obtain the corresponding bit matrix of the piecemeal.

Optionally, described to be directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determine this point The step of module alignment of block includes:

For each piecemeal, upright projection is carried out to the black and white trip point of pixel on every row in the piecemeal, black and white is chosen and jumps Corresponding vertical line is as the vertical line of demarcation of module at the Local modulus maxima of height accumulated value；

Floor projection is carried out to the black and white trip point of pixel in each column in the piecemeal, chooses the office of black and white trip point accumulated value Corresponding horizontal line is as module level line of demarcation at portion's maximum point；

Using the vertical line of demarcation of the module and the module level line of demarcation as the module alignment of the piecemeal.

Optionally, after the module alignment of the determination piecemeal, the method also includes:

Upright projection is carried out to the black and white trip point of pixel on every row in the preset range of the module alignment, chooses black and white Module level line of demarcation of the corresponding horizontal line as the module at trip point accumulated value local maximum；

Floor projection is carried out to the black and white trip point of pixel in each column in the preset range of the module alignment, chooses black and white Module vertical line of demarcation of the corresponding vertical line as the module at trip point accumulated value local maximum.

Optionally, the number according to black picture element and white pixel in each module determines the corresponding bit of each module The step of value includes:

For each module, the first number and the white pixel of the black picture element for including in the module are counted Second number, it is corresponding using the corresponding bit value of the corresponding type of pixel of maximum value in the first number and the second number as the module Bit value.

Optionally, black, the white jump rule according to pixel in the data matrix code image, to the data matrix Before code image carries out piecemeal, the method also includes:

The data matrix code to be identified for including in the data matrix code image is positioned, is obtained described wait know The positioning coordinate of other data matrix code；

Perspective transform is carried out according to data matrix code image described in the positioning coordinate pair, and to the data matrix code figure As carrying out binary conversion treatment, target data matrix code image is obtained；

Black, the white jump rule according to pixel in the data matrix code image, to the data matrix code image Carry out piecemeal the step of include:

According to black, the white jump rule of pixel in the target data matrix code image, to the target data matrix code Image carries out piecemeal.

Second aspect, the embodiment of the invention also provides a kind of data matrix code recognition devices, comprising:

Module is obtained, for obtaining the data matrix code image comprising data matrix code to be identified；

Piecemeal module, according to black, the white jump rule of pixel in the data matrix code image, to the data matrix code Image carries out piecemeal；

Determining module, for being directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determining should Each module for including in piecemeal, and according to the corresponding bit value of each module, determine the corresponding bit matrix of the piecemeal；

Merging module obtains the data matrix code to be identified for merging the corresponding bit matrix of each piecemeal Corresponding bit matrix.

Optionally, the piecemeal module includes:

First determines submodule, for black, the white jump rule according to pixel in the data matrix code image, really Determine piecemeal boundary；

Piecemeal submodule, for carrying out piecemeal to the data matrix code image according to identified piecemeal boundary.

Optionally, described first submodule is determined, comprising:

First selection unit carries out vertical for the black and white trip point to pixel on every row in the data matrix code image Projection, obtains the first black and white trip point accumulated value on data matrix code image level direction, chooses the data matrix Corresponding vertical line at the maximum coordinate of the first black and white trip point accumulated value in the vertical center line preset range of code image As the vertical line of demarcation of the first piecemeal；

Second selection unit carries out horizontal for the black and white trip point to pixel in each column in the data matrix code image Projection, obtains the second black and white trip point accumulated value in the data matrix code image vertical direction, chooses the data matrix Corresponding horizontal line at the maximum coordinate of the second black and white trip point accumulated value in the horizontal center line preset range of code image As the first piecemeal horizontal dividing lines；

First determines piecemeal boundary element, for dividing the vertical line of demarcation of first piecemeal and the first piecemeal level Boundary line is as piecemeal boundary.

Optionally, described first submodule is determined, comprising:

First cutting unit, for according to the horizontal center line of the data matrix code image by the data matrix code figure As being divided into top half and lower half portion；

Third selection unit carries out upright projection for the black and white trip point to pixel on every row in the top half, The third black and white trip point accumulated value on data matrix code image level direction is obtained, the data matrix code image is chosen Vertical center line preset range at the maximum coordinate of the third black and white trip point accumulated value corresponding vertical line as The vertical line of demarcation of two piecemeals；

4th selection unit carries out upright projection for the black and white trip point to pixel on every row in the lower half portion, The 4th black and white trip point accumulated value on data matrix code image level direction is obtained, the data matrix code image is chosen Vertical center line preset range at the maximum coordinate of the 4th black and white trip point accumulated value corresponding vertical line as The vertical line of demarcation of three piecemeals；

Second cutting unit, for according to the vertical center line of the data matrix code image by the data matrix code figure As being divided into left-half and right half part；

5th selection unit carries out floor projection for the black and white trip point to pixel in each column in the left-half, The 5th black and white trip point accumulated value in the data matrix code image vertical direction is obtained, the data matrix code image is chosen Vertical center line preset range at the maximum coordinate of the 5th black and white trip point accumulated value corresponding vertical line as Two piecemeal horizontal dividing lines；

6th selection unit carries out floor projection for the black and white trip point to pixel in each column in the right half part, The 6th black and white trip point accumulated value in the data matrix code image vertical direction is obtained, the data matrix code image is chosen Vertical center line preset range at the maximum coordinate of the 6th black and white trip point accumulated value corresponding vertical line as Three piecemeal horizontal dividing lines；

Second determines piecemeal boundary element, for vertically dividing the vertical line of demarcation of second piecemeal, the third piecemeal Boundary line, the second piecemeal horizontal dividing lines, the third piecemeal horizontal dividing lines are as piecemeal boundary.

Optionally, the determining module, comprising:

Second determines submodule, and for being directed to each piecemeal, black, the white jump according to pixel in the piecemeal is regular, It determines the module alignment of the piecemeal, and according to identified module alignment, determines each module for including in the piecemeal；

Third determines submodule, for the number according to black picture element and white pixel in each module, determines each module pair The bit value answered, and the corresponding bit value combinations of each module are obtained into the corresponding bit matrix of the piecemeal.

Optionally, described second determine that submodule includes:

7th selection unit hangs down to the black and white trip point of pixel on every row in the piecemeal for being directed to each piecemeal Shadow is delivered directly, corresponding vertical line is as the vertical line of demarcation of module at the Local modulus maxima of selection black and white trip point accumulated value；

8th selection unit carries out floor projection for the black and white trip point to pixel in each column in the piecemeal, chooses black Corresponding horizontal line is as module level line of demarcation at the Local modulus maxima of white trip point accumulated value；

Determining module boundary element, for using the vertical line of demarcation of the module and the module level line of demarcation as this point The module alignment of block.

Optionally, described device further include:

First chooses module, and the black and white trip point of pixel carries out on every row in the preset range to the module alignment Upright projection chooses corresponding horizontal line at black and white trip point accumulated value local maximum and demarcates as the module level of the module Line；

Second chooses module, and the black and white trip point of pixel carries out in each column in the preset range to the module alignment Floor projection chooses corresponding vertical line at black and white trip point accumulated value local maximum and vertically demarcates as the module of the module Line.

Optionally, the third determines that submodule is specifically used for for each module, counts include in the module described First number of black picture element and the second number of the white pixel, maximum value in the first number and the second number is corresponding The corresponding bit value of type of pixel is as the corresponding bit value of the module.

Optionally, described device further include:

Locating module, for determining the data matrix code to be identified for including in the data matrix code image Position, obtains the positioning coordinate of the data matrix code to be identified；

Binary processing module carries out perspective transform for the data matrix code image according to the positioning coordinate pair, And binary conversion treatment is carried out to the data matrix code image, obtain target data matrix code image；

The piecemeal module is specifically used for black, the white jump rule according to pixel in the target data matrix code image, Piecemeal is carried out to the target data matrix code image.

The third aspect, the embodiment of the invention also provides a kind of electronic equipment, including processor, communication interface, memory And communication bus, wherein the processor, the communication interface, the memory are completed mutual by the communication bus Communication；

The memory, for storing computer program；

The processor when for executing the program stored on the memory, realizes method described in first aspect Step.

Data matrix code recognition methods, device and electronic equipment provided in an embodiment of the present invention, can be according to data matrix Black, the white jump rule of pixel in code image carries out piecemeal to the data matrix code image, and then for determining point of each piecemeal The module for including in block determines the corresponding bit value of each module in each piecemeal, then determines the corresponding ratio of each piecemeal Special matrix finally combines bit matrix corresponding in each piecemeal to obtain the bit matrix of data matrix code image, completion pair The identification of data matrix code to be identified.Data matrix code recognition methods, device and electronic equipment of the present invention, according to data matrix code Black, the white jump rule of image pixel itself, divides data matrix code image, and independent of data matrix code image Positioning boundary, so as to improve to data matrix code identification accuracy rate.Certainly, it implements any of the products of the present invention or square Method must be not necessarily required to reach all the above advantage simultaneously.

Detailed description of the invention

In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.

Fig. 1 is the structural schematic diagram of common data matrix code；

Fig. 2 is the flow chart of data matrix code recognition methods provided in an embodiment of the present invention；

Fig. 3 is the schematic diagram positioned in the embodiment of the present invention to data matrix code to be identified；

Fig. 4 is the effect diagram after pre-processing to pending data square matrix code shown in Fig. 3；

Fig. 5 is drop shadow curve's schematic diagram of upright projection in the embodiment of the present invention；

Fig. 6 is drop shadow curve's schematic diagram of floor projection in the embodiment of the present invention；

Fig. 7 is the schematic diagram on piecemeal boundary in the embodiment of the present invention；

Fig. 8 is the schematic diagram of module alignment in the embodiment of the present invention；

Fig. 9 is the module alignment schematic diagram of the second row third column module in Fig. 8；

Figure 10 is the schematic diagram that process is adjusted to module alignment shown in Fig. 9；

Figure 11 is the schematic diagram after being adjusted to module alignment shown in Fig. 9；

Figure 12 is the schematic diagram of the corresponding bit matrix of piecemeal in the embodiment of the present invention；

Figure 13 is the bit matrix schematic diagram of data matrix code after piecemeal merging in the embodiment of the present invention；

Figure 14 is the structural schematic diagram of data matrix code recognition device provided in an embodiment of the present invention；

Figure 15 is the structural schematic diagram of electronic equipment provided in an 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, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.

In known data matrix code recognition methods, when there is deviation on data matrix code positioning boundary, all sampled points Deviation will occur, eventually lead to lower to the recognition accuracy of data matrix code.As can be seen that known data matrix code is known In other method, the accuracy rate of data matrix code identification depends on the positioning boundary of data matrix code.But actual application process In, there is not deviation in the positioning boundary that not can guarantee data matrix code, in order to avoid position inaccurate is to final data square matrix code The influence of recognition result, the data matrix code recognition methods with robustness that the embodiment of the invention provides a kind of, with raising pair The accuracy rate of data matrix code identification.

Fig. 2 is the flow chart of data matrix code recognition methods provided in an embodiment of the present invention, referring to Fig. 2, to of the invention real The data matrix code recognition methods for applying example offer is described in detail, this method comprises:

Step 201, the data matrix code image comprising data matrix code to be identified is obtained.

Method provided in an embodiment of the present invention can be applied to electronic equipment.Specifically, which can be desk-top Computer, portable computer, intelligent mobile terminal etc..

In embodiments of the present invention, electronic equipment can identify the data matrix code in the place such as product packaging.Tool Body, electronic equipment can be obtained by the picture in scanning product packaging, the modes such as take pictures comprising data square to be identified first The data matrix code image of horizontal and vertical parity check code, to realize the identification to data matrix code by the data matrix code image.

Step 202, according to black, the white jump rule of pixel in data matrix code image, data matrix code image is carried out Piecemeal.

After getting the data matrix code image comprising data matrix code to be identified, electronic equipment can be to data matrix Code image is identified, to obtain the bit matrix of data matrix code, to realize the identification to data matrix code.To data square The identification of horizontal and vertical parity check code, that is, identify the black module that includes in data matrix code and white module, and then according to black module and white The distribution of color module finally obtains the bit matrix of data matrix code.Simply, data matrix code image can also will be identified In the process of each module be interpreted as, cutting is carried out to data matrix code image from big to small, finally obtains each module.

Electronic equipment can carry out piecemeal to data matrix code image first, namely carry out to data matrix code image initial Cutting.Specifically, electronic equipment can be according to black, the white jump rule of pixel in data matrix code image, to data matrix code Image carries out piecemeal.Such as, can either side in the horizontal direction, identify that pixel occurs jump and exists with horizontal center line default The position of distance, and using the corresponding horizontal line in the position as horizontal dividing lines；In vertical direction either side, identify that pixel is sent out Raw jump and there are the positions of pre-determined distance with vertical center line, and using the corresponding vertical line in the position as vertical line of demarcation, And then piecemeal can be carried out according to square matrix code image according to horizontal dividing lines and vertical boundary demand pairs.

Alternatively, electronic equipment can count according to jumping between black picture element and white pixel in data matrix code image, Respectively both horizontally and vertically, the position that jump points are greater than preset threshold between black picture element and white pixel is cut Point, which is subjected to piecemeal.Wherein, it is white that the position that pixel jumps, which is pixel by blacking, or by Leucismus is black position；Black, white jump rule can be the black and white trip point accumulated value of pixel in data matrix code image most The corresponding position of general goal is determined as the line of demarcation of piecemeal.

The embodiment of the present invention does not limit the number of piecemeal, and of piecemeal can be determined according to the demand in practical application Number, specifically can be 4,9 etc..

Step 203, it for each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determines in the piecemeal and includes Each module determine the corresponding bit matrix of the piecemeal and according to the corresponding bit value of each module.

In order to further identify to data matrix code, electronic equipment can divide white in data matrix code image Module and black module.Specifically, electronic equipment can be based on the piecemeal to data matrix code image as a result, being directed to each piecemeal Carry out module division.It should be noted that carrying out piecemeal to data matrix code image and carrying out module division for each piecemeal Based on similar principle, i.e., black, the white jump rule of pixel in data matrix code image.

For each piecemeal, the module in each piecemeal is determined, namely be directed to each piecemeal, determine each mould in the piecemeal Then the boundary of block determines each module that the piecemeal includes according to boundary.Specifically, for each piecemeal, electronic equipment can To determine the boundary of each module in the piecemeal, and then according to the side of each module according to black, the white jump rule of pixel in the piecemeal The piecemeal is divided to obtain each module that the piecemeal includes by boundary.

For example, electronic equipment can be directed to each piecemeal, according to the jump in the piecemeal between black picture element and white pixel Variable point numeral, respectively both horizontally and vertically, jump points are greater than the position of preset threshold between black picture element and white pixel Carry out cutting is set, determines the module in the piecemeal.

After determining each module that the piecemeal includes for each piecemeal, electronic equipment may further determine that this point The corresponding bit value of each module that block includes, for example, electronic equipment can be directed to each piecemeal, according to each in each piecemeal The color of module region determines the corresponding bit value of each module.

The corresponding bit value of each module that the piecemeal includes determined, the corresponding bit value of all modules is in the piecemeal It can combine to obtain the corresponding bit matrix of the piecemeal.

Step 204, merge the corresponding bit matrix of each piecemeal, obtain the corresponding bit square of data matrix code to be identified Battle array.

After obtaining the corresponding bit matrix of each piecemeal, electronic equipment can by all corresponding bit matrixs of piecemeal into Row merges, and obtains the corresponding bit matrix of data matrix code to be identified in data matrix code image, namely realize to data square The identification of horizontal and vertical parity check code.

Data matrix code recognition methods provided in an embodiment of the present invention, according in data matrix code image pixel it is black, white Jump rule carries out piecemeal to the data matrix code image, and then determines the module for including in piecemeal for each piecemeal, determines The corresponding bit value of each module, then determines the corresponding bit matrix of each piecemeal, finally will each divide in each piecemeal Corresponding bit matrix combines to obtain the bit matrix of data matrix code image in block, completes the knowledge to data matrix code to be identified Not.As can be seen that the embodiment of the present invention is black, the white jump rule according to data matrix code image pixel itself, to data square Horizontal and vertical parity check code image is divided, and the positioning boundary independent of data matrix code image, so as to improve to data matrix code The accuracy rate of identification.

It is appreciated that the data matrix code image that electronic equipment is got is gray level image, or sometimes get Data matrix code image may be complexity inclined, that these situations may be such that the identification process of data matrix code becomes, even Influence the recognition result of data matrix code.So a kind of embodiment as the embodiment of the present invention, in order to simplify the mistake of identification To the recognition accuracy of data matrix code, electronic equipment, can be first right before the identification for carrying out data matrix code for journey and raising The data matrix code image got is pre-processed.

For example, can be positioned to data matrix code image, carry out binary conversion treatment and obtain binary image, to data Data matrix code image is transformed into conventional coordinates, to module in data matrix code image by the progress perspective transform of square matrix code image Size be normalized.

Fig. 3 is the schematic diagram positioned in the embodiment of the present invention to data matrix code to be identified, and Fig. 4 is to shown in Fig. 3 Data matrix code pre-processed after effect diagram.Data matrix code is carried out to the embodiment of the present invention referring to Fig. 3 and Fig. 4 Identification before pretreated process carried out to data matrix code image be described in detail.

Electronic equipment can position the data matrix code to be identified for including in data matrix code image, obtain wait know The positioning coordinate of other data matrix code.As shown in figure 3, electronic equipment can be with data square to be identified in location data square matrix code image Four vertex a, b, c, d of horizontal and vertical parity check code obtain the positioning coordinate a (x1, y1) on four vertex according to the coordinate system of building, b (x2, Y2), c (x3, y3), d (x4, y4), and obtained using the positioning coordinate on this four vertex as being positioned from data matrix code image Data matrix code to be identified positioning coordinate.It should be noted that in some cases, the positioning of four vertex a, b, c, d are sat Excessive, position inaccurate may be deviated by indicating, such as the positioning coordinate a (x1, y1) of a point in Fig. 3.

After obtaining the positioning coordinate of data matrix code, electronic equipment can be further according to positioning coordinate pair data matrix code Image carries out perspective transform, and carries out binary conversion treatment to data matrix code image, obtains target data matrix code image, such as schemes Shown in 4.

Perspective transform refers to using the centre of perspectivity, picture point, the condition of target point three point on a straight line, makes to hold by chasles theorem Shadow face (perspective plane) rotates a certain angle around trace (axis of homology), destroys original projected light harness, is still able to maintain on image-bearing surface The constant transformation of perspective geometry figure.It is simple it is also understood that by data matrix code image from a coordinate system transformation to another One conventional coordinates, and then meet human visual system, facilitate processing.

It is 0 or 255 that image binaryzation processing, which is exactly by the grayvalue transition of the pixel on image, that is, will be entire Image, which shows, significantly only has black and white visual effect.Specifically, which can be will be greater than according to preset threshold Pixel grayvalue transition be 255, less than the preset threshold pixel grayvalue transition be 0.To data matrix code After image is pre-processed, next data matrix code to be identified is identified.Data matrix code image is carried out pre- The data matrix code to be identified in target data matrix code image obtained after processing is identified.

By carrying out perspective transform to data matrix code image, data matrix code image geometry can unchangeably be transformed to The conventional coordinates of more convenient processing；Meanwhile binary conversion treatment is carried out to data matrix code image, it is available to be more in line with Actual data matrix code image, and then the recognition accuracy of logarithmic moment square matrix code can be improved, and more convenient processing.

In a kind of embodiment of the embodiment of the present invention, electronic equipment according in data matrix code image pixel it is black, White jump rule, the process that piecemeal is carried out to data matrix code image may include: according to pixel in data matrix code image Black, white jump rule, determines piecemeal boundary；Piecemeal is carried out to data matrix code image according to identified piecemeal boundary.Wherein, According to black, the white jump rule of pixel in data matrix code image, determine that piecemeal boundary is divided data matrix code image The emphasis of block after determining piecemeal boundary, carries out piecemeal to data matrix code image according to piecemeal boundary and is easily achieved.

In a kind of optional embodiment of the embodiment of the present invention, according to black, the white jump of pixel in data matrix code image Rule determines that the process on piecemeal boundary may include:

The first step carries out upright projection to the black and white trip point of pixel on every row in data matrix code image, obtains data The first black and white trip point accumulated value on square matrix code image level direction chooses data matrix code image vertical center line and presets model In enclosing at the maximum coordinate of the first black and white trip point accumulated value corresponding vertical line as the vertical line of demarcation of the first piecemeal.

It should be noted that upright projection refers to that two dimensional image is projected by row to x-axis direction, in application of the embodiment of the present invention In, i.e., data matrix code image is projected by the black and white trip point of pixel on every row to x-axis direction, and the result of upright projection can be seen At being one dimensional image.

Piecemeal boundary is determined according to black, the white trip point drop shadow curve of pixel in data matrix code image.Determine left and right point When boundary line, upright projection is carried out to the row black and white trip point of data matrix code image, i.e., on every row in data matrix code image The black and white trip point of pixel carries out upright projection.Then the corresponding drop shadow curve of upright projection is obtained, as shown in Figure 5.Wherein, it needs It is noted that the coordinate of drop shadow curve and the coordinate of data matrix code image correspond.Finally, choosing data matrix code figure As corresponding vertical line vertically divides as piecemeal at the maximum coordinate of black and white trip point aggregate-value in vertical center line preset range Boundary line, the vertical line of demarcation of the piecemeal be determine to data matrix code image carry out piecemeal when right boundary.

Specifically, the black and white trip point of the every row of data matrix code image can be represented by vectors for 0,1.0 ..., 1,1, 0 ..., 0,1,1 }, jump include from it is black jump to it is white or from it is white jump to it is black, wherein " 0 " indicate do not jump, " 1 " indicate There is jump；Alternatively, " 1 " indicates not jump, " 0 " indicates jump.By the black and white trip point of row every in data matrix code image Upright projection is carried out, the drop shadow curve corresponding to x-axis is obtained, it specifically can be in a vertical direction by the black and white trip point on every row Transition times be added, for example, the transition times of the black and white trip point of row every on first row are added, obtain the of drop shadow curve The transition times of the black and white trip point of row every on all column similarly are added, obtain corresponding all projection values by one value. The black and white trip point accumulated value of every row in data matrix code image, i.e., corresponding projection value can be represented by vectors for 10,15, 17,…,20,15,25,…,17,19,20}.It is black in drop shadow curve in data matrix code image vertical center line preset range White trip point accumulated value is that 25 corresponding projection values are maximum, then choosing black and white trip point accumulated value is hanging down at 25 corresponding coordinates Right boundary when straight line is as piecemeal.

It optionally, can be according to the horizontal centre of data matrix code image in a kind of embodiment of the embodiment of the present invention Data matrix code image is divided into top half and lower half portion by line.The black and white of pixel on row every in top half is jumped and is clicked through Row upright projection obtains the third black and white trip point accumulated value on data matrix code image level direction, chooses data matrix code In the vertical center line preset range of image at the maximum coordinate of third black and white trip point accumulated value corresponding vertical line as The vertical line of demarcation of two piecemeals.Upright projection is carried out to the black and white trip point of pixel on row every in lower half portion, obtains data matrix The 4th black and white trip point accumulated value on code image level direction, chooses the vertical center line preset range of data matrix code image Corresponding vertical line is as the vertical line of demarcation of third piecemeal at the maximum coordinate of interior 4th black and white trip point accumulated value.

Specifically, data matrix code image can be divided into top half and lower half portion according to horizontal center line, for The black and white trip point of pixel on every row in top half and lower half portion is respectively vertically thrown in top half and lower half portion Shadow obtains corresponding drop shadow curve of the corresponding drop shadow curve of top half and lower half portion, and then corresponding according to top half Corresponding drop shadow curve of drop shadow curve and lower half portion determines that the corresponding vertical line of demarcation of top half and lower half portion are corresponding Vertical line of demarcation.Finally using the corresponding vertical line of demarcation of top half as the corresponding right boundary of top half, in Fig. 7 Shown in 701；The corresponding vertical line of demarcation in lower half portion is as the corresponding right boundary in lower half portion, as shown in 702 in Fig. 7.

Second step carries out floor projection to the black and white trip point of pixel in each column in data matrix code image, obtains data The second black and white trip point accumulated value in square matrix code image vertical direction chooses data matrix code image level center line and presets model In enclosing at the maximum coordinate of the second black and white trip point accumulated value corresponding horizontal line as the first piecemeal horizontal dividing lines.

Similarly, when determining line of demarcation up and down, floor projection is carried out to the column black and white trip point of data matrix code image, i.e., Floor projection is carried out to the black and white trip point of pixel in each column in data matrix code image.Then the corresponding throwing of floor projection is obtained Shadow curve.Finally, choosing, projection value in data matrix code image level center line preset range is maximum, i.e. black and white trip point is accumulative Being worth corresponding horizontal line at maximum coordinate, as piecemeal horizontal dividing lines, which is to determine to data Square matrix code image carries out up-and-down boundary when piecemeal.

It should be noted that floor projection refer to two dimensional image by column to y-axis direction projection, in application of the embodiment of the present invention In, i.e., by the black and white trip point of pixel in each column to y-axis direction projection, the result of floor projection can be seen data matrix code image At being one dimensional image.

Specifically, the black and white trip point of data matrix code image each column can be represented by vectors for 0,1.0 ..., 1,1, 0,…,0,1,1}.The black and white trip point of each column in data matrix code image is subjected to floor projection, obtains the throwing corresponding to y-axis The transition times of black and white trip point in each column are added by shadow curve by horizontal direction, for example, by the first row each column it is black The transition times of white trip point are added, and obtain first value of drop shadow curve, and similarly, the black and white of each column on all rows is jumped The transition times of point are added, and obtain corresponding all projection values.The black and white trip point accumulated value of each column in data matrix code image, I.e. corresponding floor projection value can be represented by vectors for 11,17,17 ..., 20,15,29 ..., 16,19,20 }.Drop shadow curve In in data matrix code image level center line preset range, black and white trip point accumulated value be that 29 corresponding projection values are maximum, Then choose black and white trip point accumulated value be 29 corresponding coordinates at horizontal line as piecemeal when up-and-down boundary.

It optionally, will according to the vertical center line of data matrix code image in a kind of embodiment of the embodiment of the present invention Data matrix code image is divided into left-half and right half part.Water is carried out to the black and white trip point of pixel in each column in left-half Flat projection, obtains the 5th black and white trip point accumulated value in data matrix code image vertical direction, chooses data matrix code image Vertical center line preset range at the 5th maximum coordinate of black and white trip point accumulated value corresponding vertical line as second point Block horizontal dividing lines.Floor projection is carried out to the black and white trip point of pixel in each column in right half part, obtains data matrix code figure As the 6th black and white trip point accumulated value in vertical direction, the is chosen in the vertical center line preset range of data matrix code image Corresponding vertical line is as third piecemeal horizontal dividing lines at the six maximum coordinates of black and white trip point accumulated value.

Specifically, data matrix code image can be divided into left-half and right half part according to vertical center line, for Left-half and right half part carry out horizontal throwing to the black and white trip point of pixel in each column in left-half and right half part respectively Shadow obtains the corresponding drop shadow curve of left-half and the corresponding drop shadow curve of right half part, and then corresponding according to left-half Drop shadow curve and the corresponding drop shadow curve of right half part determine that the corresponding horizontal dividing lines of left-half and right half part are corresponding Horizontal dividing lines.Wherein, the corresponding drop shadow curve of right half part is as shown in Figure 6.The corresponding drop shadow curve of left-half and Fig. 6 institute The corresponding drop shadow curve of the right half part shown is similar.It is finally corresponding using the corresponding horizontal dividing lines of left-half as left-half Up-and-down boundary, as shown in 704 in Fig. 7；The corresponding horizontal dividing lines of right half part as the corresponding up-and-down boundary of right half part, As shown in 703 in Fig. 7.

Third step, using the vertical line of demarcation of piecemeal and piecemeal horizontal dividing lines as piecemeal boundary.

It specifically, can be using the vertical line of demarcation of above-mentioned first piecemeal and the first piecemeal horizontal dividing lines as piecemeal boundary. Alternatively, by the vertical line of demarcation of above-mentioned second piecemeal, the vertical line of demarcation of third piecemeal, the second piecemeal horizontal dividing lines, third piecemeal Horizontal dividing lines are as piecemeal boundary.

After determining piecemeal boundary, piecemeal can be carried out to data matrix code image according to identified piecemeal boundary.

Data matrix code recognition methods provided in an embodiment of the present invention, by avoiding whole figure to black and white to image block Trip point carries out upright projection and floor projection, and picture size is big, deformation quantity increases with projected length and it is inclined to project accumulated value It is poor big, the influence that module alignment is determined.Data matrix code image block is operated, can be improved and data matrix code is known Other accuracy rate.

After data matrix code image block, it next can be directed to each piecemeal, determine include in each piecemeal every A module.Generally speaking, for each piecemeal, determine each module for including in each piecemeal with to data matrix code image into The principle of row piecemeal be it is similar, be all based on pixel black, white jump rule.Specifically, for each piecemeal, according to this point Black, the white jump rule of pixel in block, determines the module alignment of the piecemeal, and according to identified module alignment, determines this point Each module for including in block.Specifically, this point is determined according to black, the white jump rule of pixel in the piecemeal for each piecemeal The step of module alignment of block may include:

The first step carries out upright projection to the black and white trip point of pixel on every row in the piecemeal, chooses for each piecemeal Corresponding vertical line is as the vertical line of demarcation of module at the Local modulus maxima of black and white trip point accumulated value.

Second step carries out floor projection to the black and white trip point of pixel in each column in the piecemeal, it is tired to choose black and white trip point Corresponding horizontal line is as module level line of demarcation at value added Local modulus maxima.

Each piecemeal corresponds to a block image, and each module is determined from block image, can be by piecemeal Then each module for including in each piecemeal is determined by module alignment in determining module boundary in image.To each point Block image determining module boundary comprises determining that module row bound and module column boundary, the method for determining boundary can use to point The black and white trip point of pixel carries out upright projection and jumps to the black and white of pixel in each column in block image on every row in block image Point carries out the drop shadow curve that floor projection obtains to determine.Obtained drop shadow curve is the waveform of rule distribution, and upright projection obtains To drop shadow curve at Local modulus maxima corresponding vertical line as the vertical line of demarcation of module, i.e. module column boundary；It is horizontal Corresponding horizontal line is projected in obtained drop shadow curve at Local modulus maxima as module level line of demarcation, i.e. module row side Boundary.Specifically upright projection and floor projection have been carried out detailed description in the above content, just repeat no more here.Certainly, first really Determine row bound, rear determining column boundary or first determines that column boundary, rear determining row bound are all possible.

Third step, using the vertical line of demarcation of the module and the module level line of demarcation as the module alignment of the piecemeal.

Pass through the module alignment of each module in each piecemeal for determining, so that it may determine each of each piecemeal Module.

The module alignment of bottom right piecemeal is as shown in Figure 8 in finally obtained above-mentioned Fig. 7.

In addition, can also be finely adjusted to determining module alignment to keep determining module alignment more accurate.This hair It is cumulative according to the black and white trip point in the module alignment preset range determined in a kind of bright optional embodiment of embodiment Value, is adjusted the module alignment.It can specifically include: after determining the module alignment of the piecemeal, to module alignment The black and white trip point of pixel carries out upright projection on every row in preset range, chooses at black and white trip point accumulated value local maximum Module level line of demarcation of the corresponding horizontal line as the module；To the black and white of pixel in each column in the preset range of module alignment Trip point carries out floor projection, chooses mould of the corresponding vertical line as the module at black and white trip point accumulated value local maximum The vertical line of demarcation of block.

It can be seen that the second row third arranges the coboundary inaccuracy of corresponding module in the Fig. 8 determined by the above process, As shown in Figure 9.The coboundary is adjusted, this can be utilized in the coboundary preset range of the module of above-mentioned determination Determining coboundary is micro-adjusted in the black and white trip point accumulated value of pixel in module.Specifically, the coboundary is calculated separately The black and white trip point accumulated value of all pixels on the lastrow and next line of upper all pixels and the coboundary, for example, the top The pixel value of all pixels is respectively (1,1,1,0,1,1,1,1,1,1,1,0,0,0), institute on the lastrow of the coboundary in boundary The pixel value for having pixel is respectively (1,1,0,1,0,0,0,0,0,0,0,0,0,0), all pixels on the next line of the coboundary Pixel value all 1.The jump of the lastrow of the coboundary and the coboundary be (0,0,1,1,1,1,1,1,1,1,1,0,0, 0), as shown in Figure 10, black and white trip point accumulated value is 9；And the black and white trip point of the next line of the coboundary and the coboundary is tired Value added is 4, then finely tunes the coboundary of the module to the lastrow of coboundary.Coboundary after fine tuning is as shown in figure 11.

In a kind of embodiment of the embodiment of the present invention, determine that the process of the corresponding bit matrix of any piecemeal can wrap It includes: according to the number of black picture element and white pixel in each module, determining the corresponding bit value of each module, and each module is corresponding Bit value combinations obtain the corresponding bit matrix of the piecemeal.Specifically, for each module, it can count in the module and include Black picture element the first number and white pixel the second number, by the corresponding picture of maximum value in the first number and the second number The corresponding bit value of plain type is as the corresponding bit value of the module.

For counting black picture element and white pixel number in the module rectangular area of module alignment composition, by the first number The corresponding bit value of the corresponding type of pixel of maximum value is as the corresponding bit value of the module in mesh and the second number, that is, incites somebody to action Leading pixel value is accounted in module is determined as the corresponding bit matrix value of the module.It can be obtained after extracting the bit value of each module The corresponding bit matrix of the block image.Wherein, piecemeal corresponding bit matrix in bottom right is as shown in figure 12 in above-mentioned piecemeal, In, logos bit value 1, white indicia bit value 0, it is, of course, also possible to white indicia bit value 1, logos bit Value 0.

Leading pixel value is accounted for by counting each module and determines the bit matrix of respective modules, it can be to avoid in module Fractional polar causes to extract the situation of bit value mistake on the contrary, and the modules local extremum such as can reduce hot spot, pollution is opposite Interference, and then dependence of the accuracy rate of data matrix code identification to picture quality can be reduced.

The corresponding bit matrix of the available each piecemeal of above-mentioned processing is carried out for each module, by all piecemeals Corresponding bit matrix, which merges, can be obtained the corresponding bit matrix of data matrix code to be identified in data matrix code image, The identification of complete paired data square matrix code, the data matrix code image that the corresponding bit matrix of aforementioned four piecemeal merges In, the corresponding bit matrix of data matrix code to be identified it is as shown in figure 13.

The embodiment of the invention also provides a kind of data matrix code recognition device, referring to Fig.1 4, the embodiment of the present invention is mentioned The data matrix code recognition device of confession is described in detail, comprising:

Module 1401 is obtained, for obtaining the data matrix code image comprising data matrix code to be identified.

Piecemeal module 1402, according to black, the white jump rule of pixel in data matrix code image, to data matrix code image Carry out piecemeal.

Determining module 1403, for being directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determining should Each module for including in piecemeal, and according to the corresponding bit value of each module, determine the corresponding bit matrix of the piecemeal.

It is corresponding to obtain data matrix code to be identified for merging the corresponding bit matrix of each piecemeal for merging module 1404 Bit matrix.

Data matrix code recognition device provided in an embodiment of the present invention, according in data matrix code image pixel it is black, white Jump rule carries out piecemeal to the data matrix code image, and then determines the module for including in piecemeal for each piecemeal, determines The corresponding bit value of each module, then determines the corresponding bit matrix of each piecemeal, finally will each divide in each piecemeal Corresponding bit matrix combines to obtain the bit matrix of data matrix code image in block, completes the knowledge to data matrix code to be identified Not.As can be seen that being drawn according to black, the white jump of data matrix code image pixel rule itself to data matrix code image Point, and then the identification of complete paired data square matrix code, and the positioning boundary independent of data matrix code image.So it can be improved To the accuracy rate of data matrix code identification.

Optionally, piecemeal module 1402 includes:

First determines submodule, for black, the white jump rule according to pixel in data matrix code image, determines piecemeal side Boundary.

Piecemeal submodule, for carrying out piecemeal to data matrix code image according to identified piecemeal boundary.

Optionally, first submodule is determined, comprising:

First selection unit is vertically thrown for the black and white trip point to pixel on every row in data matrix code image Shadow obtains the first black and white trip point accumulated value on data matrix code image level direction, chooses hanging down for data matrix code image Corresponding vertical line hangs down as the first piecemeal at the first maximum coordinate of black and white trip point accumulated value in straight center line preset range Straight line of demarcation.

Second selection unit carries out horizontal throwing for the black and white trip point to pixel in each column in data matrix code image Shadow obtains the second black and white trip point accumulated value in data matrix code image vertical direction, chooses the water of data matrix code image In flat center line preset range at the second maximum coordinate of black and white trip point accumulated value corresponding horizontal line as the first piecemeal water Divide boundary line equally.

First determines piecemeal boundary element, for using the vertical line of demarcation of the first piecemeal and the first piecemeal horizontal dividing lines as Piecemeal boundary.

Optionally, first submodule is determined, comprising:

First cutting unit, for being divided into data matrix code image according to the horizontal center line of data matrix code image Half part and lower half portion.

Third selection unit carries out upright projection for the black and white trip point to pixel on row every in top half, obtains Third black and white trip point accumulated value on data matrix code image level direction chooses the vertical center line of data matrix code image In preset range at the maximum coordinate of third black and white trip point accumulated value corresponding vertical line as the vertical line of demarcation of the second piecemeal.

4th selection unit carries out upright projection for the black and white trip point to pixel on row every in lower half portion, obtains The 4th black and white trip point accumulated value on data matrix code image level direction chooses the vertical center line of data matrix code image In preset range at the 4th maximum coordinate of black and white trip point accumulated value corresponding vertical line as the vertical line of demarcation of third piecemeal.

Second cutting unit, for data matrix code image to be divided into a left side according to the vertical center line of data matrix code image Half part and right half part.

5th selection unit carries out floor projection for the black and white trip point to pixel in each column in left-half, obtains The 5th black and white trip point accumulated value in data matrix code image vertical direction chooses the vertical center line of data matrix code image In preset range at the 5th maximum coordinate of black and white trip point accumulated value corresponding vertical line as the second piecemeal horizontal dividing lines.

6th selection unit carries out floor projection for the black and white trip point to pixel in each column in right half part, obtains The 6th black and white trip point accumulated value in data matrix code image vertical direction chooses the vertical center line of data matrix code image In preset range at the 6th maximum coordinate of black and white trip point accumulated value corresponding vertical line as third piecemeal horizontal dividing lines.

Second determines piecemeal boundary element, is used for the vertical line of demarcation of the second piecemeal, the vertical line of demarcation of third piecemeal, second Piecemeal horizontal dividing lines, third piecemeal horizontal dividing lines are as piecemeal boundary.

Optionally, determining module 1403 includes:

Second determines submodule, for being directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determines The module alignment of the piecemeal, and according to identified module alignment, determine each module for including in the piecemeal.

Optionally, second determine that submodule includes:

7th selection unit hangs down to the black and white trip point of pixel on every row in the piecemeal for being directed to each piecemeal Shadow is delivered directly, corresponding vertical line is as the vertical line of demarcation of module at the Local modulus maxima of selection black and white trip point accumulated value.

8th selection unit carries out floor projection for the black and white trip point to pixel in each column in the piecemeal, chooses black Corresponding horizontal line is as module level line of demarcation at the Local modulus maxima of white trip point accumulated value.

Determining module boundary element, for using the vertical line of demarcation of module and module level line of demarcation as the module of the piecemeal Boundary.

Optionally, device further include:

First chooses module, and the black and white trip point of pixel carries out vertical on row every in the preset range to module alignment Module level line of demarcation of the corresponding horizontal line as the module at black and white trip point accumulated value local maximum is chosen in projection.

Second chooses module, and the black and white trip point of pixel carries out horizontal in each column in the preset range to module alignment Module vertical line of demarcation of the corresponding vertical line as the module at black and white trip point accumulated value local maximum is chosen in projection.

Optionally, third determines that submodule is specifically used for counting the black picture element for including in the module for each module The first number and white pixel the second number, the corresponding type of pixel of maximum value in the first number and the second number is corresponding Bit value as the corresponding bit value of the module.

Optionally, device further include:

Locating module, for being positioned to the data matrix code to be identified for including in data matrix code image, obtain to Identify the positioning coordinate of data matrix code.

Binary processing module, for carrying out perspective transform according to positioning coordinate pair data matrix code image, and to data Square matrix code image carries out binary conversion treatment, obtains target data matrix code image.

Piecemeal module is specifically used for black, the white jump rule according to pixel in target data matrix code image, to number of targets Piecemeal is carried out according to square matrix code image.

It should be noted that the data matrix code recognition device of the embodiment of the present invention is identified using above-mentioned data matrix code The device of method, then all embodiments of above-mentioned data matrix code recognition methods are suitable for the device, and can reach identical Or similar beneficial effect.

Figure 15 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 15, the embodiment of the present invention The electronic equipment of offer, including processor 1501, communication interface 1502, memory 1503 and communication bus 1504, wherein processing Device, communication interface, memory complete mutual communication by communication bus；

Memory 1503, for storing computer program；

Processor 1501, when for executing the program stored on memory, with the number for executing the embodiment of the present invention According to square matrix code recognition methods, wherein data matrix code recognition methods includes:

According to black, the white jump rule of pixel in data matrix code image, piecemeal is carried out to data matrix code image；

Each mould for including in the piecemeal is determined according to black, the white jump rule of pixel in the piecemeal for each piecemeal Block, and according to the corresponding bit value of each module, determine the corresponding bit matrix of the piecemeal；

Merge the corresponding bit matrix of each piecemeal, obtains the corresponding bit matrix of data matrix code to be identified.

The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.

Communication interface is for the communication between above-mentioned electronic equipment and other equipment.

Memory may include random access memory (Random Access Memory, RAM), also may include non-easy The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also To be storage device that at least one is located remotely from aforementioned processor.

Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete Door or transistor logic, discrete hardware components.

Electronic equipment provided in an embodiment of the present invention, it is right according to black, the white jump rule of pixel in data matrix code image The data matrix code image carries out piecemeal, and then determines the module for including in piecemeal for each piecemeal, determines in each piecemeal The corresponding bit value of each module, then determines the corresponding bit matrix of each piecemeal, finally will be corresponding in each piecemeal Bit matrix combines to obtain the bit matrix of data matrix code image, completes the identification to data matrix code to be identified.It can see Out, according to black, the white jump of data matrix code image pixel rule itself, data matrix code image is divided, and then complete The identification of paired data square matrix code, and the positioning boundary independent of data matrix code image.So it can be improved to data square The accuracy rate of horizontal and vertical parity check code identification.

The embodiment of the invention also provides a kind of computer readable storage medium, it is stored in computer readable storage medium Computer program realizes the data matrix code recognition methods of the embodiment of the present invention when computer program is executed by processor, wherein Data matrix code recognition methods includes:

Computer readable storage medium provided in an embodiment of the present invention, according in data matrix code image pixel it is black, white Jump rule carries out piecemeal to the data matrix code image, and then determines the module for including in piecemeal for each piecemeal, determines The corresponding bit value of each module, then determines the corresponding bit matrix of each piecemeal, finally will each divide in each piecemeal Corresponding bit matrix combines to obtain the bit matrix of data matrix code image in block, completes the knowledge to data matrix code to be identified Not.As can be seen that being black, the white jump rule according to data matrix code image pixel itself in the embodiment of the present invention, to data Square matrix code image is divided, and then the identification of complete paired data square matrix code, and the positioning independent of data matrix code image Boundary.It so can be improved the accuracy rate to data matrix code identification.

It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or equipment including the element.

Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part explanation.

The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention It is interior.

Claims

1. a kind of data matrix code recognition methods characterized by comprising

According to black, the white jump rule of pixel in the data matrix code image, piecemeal is carried out to the data matrix code image；

Merge the corresponding bit matrix of each piecemeal, obtains the corresponding bit matrix of the data matrix code to be identified.

2. the method according to claim 1, wherein described according to pixel in the data matrix code image Black, white jump is regular, includes: to the step of data matrix code image progress piecemeal

3. according to the method described in claim 2, it is characterized in that, the institute according to pixel in the data matrix code image The step of stating black, white jump rule, determining piecemeal boundary include:

Upright projection is carried out to the black and white trip point of pixel on every row in the data matrix code image, obtains the data matrix The first black and white trip point accumulated value on code image level direction, the vertical center line for choosing the data matrix code image are default In range at the maximum coordinate of the first black and white trip point accumulated value corresponding vertical line as the vertical line of demarcation of the first piecemeal；

Floor projection is carried out to the black and white trip point of pixel in each column in the data matrix code image, obtains the data matrix The second black and white trip point accumulated value in code image vertical direction, the horizontal center line for choosing the data matrix code image are default In range at the maximum coordinate of the second black and white trip point accumulated value corresponding horizontal line as the first piecemeal horizontal dividing lines；

4. according to the method described in claim 2, it is characterized in that, the institute according to pixel in the data matrix code image The step of stating black, white jump rule, determining piecemeal boundary include:

The data matrix code image is divided into top half and lower half according to the horizontal center line of the data matrix code image Part；

Upright projection is carried out to the black and white trip point of pixel on every row in the top half, obtains the data matrix code image Third black and white trip point accumulated value in horizontal direction, in the vertical center line preset range for choosing the data matrix code image Corresponding vertical line is as the vertical line of demarcation of the second piecemeal at the maximum coordinate of the third black and white trip point accumulated value；

Upright projection is carried out to the black and white trip point of pixel on every row in the lower half portion, obtains the data matrix code image The 4th black and white trip point accumulated value in horizontal direction, in the vertical center line preset range for choosing the data matrix code image Corresponding vertical line is as the vertical line of demarcation of third piecemeal at the maximum coordinate of the 4th black and white trip point accumulated value；

The data matrix code image is divided into left-half and right half according to the vertical center line of the data matrix code image Part；

Floor projection is carried out to the black and white trip point of pixel in each column in the left-half, obtains the data matrix code image The 5th black and white trip point accumulated value in vertical direction, in the vertical center line preset range for choosing the data matrix code image Corresponding vertical line is as the second piecemeal horizontal dividing lines at the maximum coordinate of the 5th black and white trip point accumulated value；

Floor projection is carried out to the black and white trip point of pixel in each column in the right half part, obtains the data matrix code image The 6th black and white trip point accumulated value in vertical direction, in the vertical center line preset range for choosing the data matrix code image Corresponding vertical line is as third piecemeal horizontal dividing lines at the maximum coordinate of the 6th black and white trip point accumulated value；

By the vertical line of demarcation of second piecemeal, the vertical line of demarcation of the third piecemeal, the second piecemeal horizontal dividing lines, institute Third piecemeal horizontal dividing lines are stated as piecemeal boundary.

5. the method according to claim 1, wherein described be directed to each piecemeal, according to pixel in the piecemeal Black, the white jump rule, determines each module for including in the piecemeal, and according to the corresponding bit value of each module, determines this point The step of block corresponding bit matrix includes:

The module alignment of the piecemeal is determined according to black, the white jump rule of pixel in the piecemeal for each piecemeal, and According to identified module alignment, each module for including in the piecemeal is determined；

According to the number of black picture element and white pixel in each module, the corresponding bit value of each module is determined, and by each module pair The bit value combinations answered obtain the corresponding bit matrix of the piecemeal.

6. according to the method described in claim 5, it is characterized in that, described be directed to each piecemeal, according to pixel in the piecemeal Black, the white jump rule, the step of determining the module alignment of the piecemeal include:

For each piecemeal, upright projection is carried out to the black and white trip point of pixel on every row in the piecemeal, chooses black and white trip point Corresponding vertical line is as the vertical line of demarcation of module at the Local modulus maxima of accumulated value；

Floor projection is carried out to the black and white trip point of pixel in each column in the piecemeal, chooses the local pole of black and white trip point accumulated value Corresponding horizontal line is as module level line of demarcation at big value point；

7. method according to claim 5 or 6, which is characterized in that after the module alignment of the determination piecemeal, institute State method further include:

Upright projection is carried out to the black and white trip point of pixel on every row in the preset range of the module alignment, chooses black and white jump Module level line of demarcation of the corresponding horizontal line as the module at point accumulated value local maximum；

Floor projection is carried out to the black and white trip point of pixel in each column in the preset range of the module alignment, chooses black and white jump Module vertical line of demarcation of the corresponding vertical line as the module at point accumulated value local maximum.

8. method according to claim 5 or 6, which is characterized in that described according to black picture element in each module and white picture The number of element, the step of determining each module corresponding bit value include:

For each module, count the black picture element for including in the module the first number and the white pixel second Number, using the corresponding bit value of the corresponding type of pixel of maximum value in the first number and the second number as the corresponding ratio of the module Paricular value.

9. method according to claim 1-6, which is characterized in that described according in the data matrix code image Black, the white jump rule of pixel, before carrying out piecemeal to the data matrix code image, the method also includes:

The data matrix code to be identified for including in the data matrix code image is positioned, the number to be identified is obtained According to the positioning coordinate of square matrix code；

According to data matrix code image described in the positioning coordinate pair carry out perspective transform, and to the data matrix code image into Row binary conversion treatment obtains target data matrix code image；

Black, the white jump rule according to pixel in the data matrix code image, carries out the data matrix code image The step of piecemeal includes:

According to black, the white jump rule of pixel in the target data matrix code image, to the target data matrix code image Carry out piecemeal.

10. a kind of data matrix code recognition device characterized by comprising

Piecemeal module, according to black, the white jump rule of pixel in the data matrix code image, to the data matrix code image Carry out piecemeal；

Determining module, according to black, the white jump rule of pixel in the piecemeal, determines the piecemeal for being directed to each piecemeal In include each module determine the corresponding bit matrix of the piecemeal and according to the corresponding bit value of each module；

It is corresponding to obtain the data matrix code to be identified for merging the corresponding bit matrix of each piecemeal for merging module Bit matrix.

11. device according to claim 10, which is characterized in that the piecemeal module includes:

First determines submodule, for black, the white jump rule according to pixel in the data matrix code image, determines and divides Block boundary；

12. device according to claim 11, which is characterized in that described first determines submodule, comprising:

First selection unit is vertically thrown for the black and white trip point to pixel on every row in the data matrix code image Shadow obtains the first black and white trip point accumulated value on data matrix code image level direction, chooses the data matrix code Corresponding vertical line is made at the maximum coordinate of the first black and white trip point accumulated value in the vertical center line preset range of image For the vertical line of demarcation of the first piecemeal；

Second selection unit carries out horizontal throwing for the black and white trip point to pixel in each column in the data matrix code image Shadow obtains the second black and white trip point accumulated value in the data matrix code image vertical direction, chooses the data matrix code Corresponding horizontal line is made at the maximum coordinate of the second black and white trip point accumulated value in the horizontal center line preset range of image For the first piecemeal horizontal dividing lines；

First determines piecemeal boundary element, is used for the vertical line of demarcation of first piecemeal and the first piecemeal horizontal dividing lines As piecemeal boundary.

13. device according to claim 11, which is characterized in that described first determines submodule, comprising:

First cutting unit, for being divided the data matrix code image according to the horizontal center line of the data matrix code image For top half and lower half portion；

Third selection unit carries out upright projection for the black and white trip point to pixel on every row in the top half, obtains Third black and white trip point accumulated value on data matrix code image level direction chooses hanging down for the data matrix code image In straight center line preset range at the maximum coordinate of the third black and white trip point accumulated value corresponding vertical line as second point The vertical line of demarcation of block；

4th selection unit carries out upright projection for the black and white trip point to pixel on every row in the lower half portion, obtains The 4th black and white trip point accumulated value on data matrix code image level direction chooses hanging down for the data matrix code image Corresponding vertical line divides as third at the maximum coordinate of the 4th black and white trip point accumulated value in straight center line preset range The vertical line of demarcation of block；

Second cutting unit, for being divided the data matrix code image according to the vertical center line of the data matrix code image For left-half and right half part；

5th selection unit carries out floor projection for the black and white trip point to pixel in each column in the left-half, obtains The 5th black and white trip point accumulated value in the data matrix code image vertical direction chooses hanging down for the data matrix code image In straight center line preset range at the maximum coordinate of the 5th black and white trip point accumulated value corresponding vertical line as second point Block horizontal dividing lines；

6th selection unit carries out floor projection for the black and white trip point to pixel in each column in the right half part, obtains The 6th black and white trip point accumulated value in the data matrix code image vertical direction chooses hanging down for the data matrix code image Corresponding vertical line divides as third at the maximum coordinate of the 6th black and white trip point accumulated value in straight center line preset range Block horizontal dividing lines；

Second determine piecemeal boundary element, for by the vertical line of demarcation of second piecemeal, the vertical line of demarcation of the third piecemeal, The second piecemeal horizontal dividing lines, the third piecemeal horizontal dividing lines are as piecemeal boundary.

14. device according to claim 10, which is characterized in that the determining module, comprising:

Second determines submodule, for being directed to each piecemeal, according to black, the white jump rule of pixel in the piecemeal, determines The module alignment of the piecemeal, and according to identified module alignment, determine each module for including in the piecemeal；

Third determines submodule, for the number according to black picture element and white pixel in each module, determines that each module is corresponding Bit value, and the corresponding bit value combinations of each module are obtained into the corresponding bit matrix of the piecemeal.

15. device according to claim 14, which is characterized in that described second determines that submodule includes:

7th selection unit vertically throws the black and white trip point of pixel on every row in the piecemeal for being directed to each piecemeal Shadow, choose black and white trip point accumulated value Local modulus maxima at corresponding vertical line as the vertical line of demarcation of module；

8th selection unit carries out floor projection for the black and white trip point to pixel in each column in the piecemeal, chooses black and white and jumps Corresponding horizontal line is as module level line of demarcation at the Local modulus maxima of height accumulated value；

Determining module boundary element, for using the vertical line of demarcation of the module and the module level line of demarcation as the piecemeal Module alignment.

16. device according to claim 14 or 15, which is characterized in that described device further include:

First chooses module, and the black and white trip point of pixel carries out vertical on every row in the preset range to the module alignment Module level line of demarcation of the corresponding horizontal line as the module at black and white trip point accumulated value local maximum is chosen in projection；

Second chooses module, and the black and white trip point of pixel carries out horizontal in each column in the preset range to the module alignment Module vertical line of demarcation of the corresponding vertical line as the module at black and white trip point accumulated value local maximum is chosen in projection.

17. device according to claim 14 or 15, which is characterized in that the third determines that submodule is specifically used for being directed to Each module counts the first number of the black picture element for including in the module and the second number of the white pixel, will The corresponding bit value of the corresponding type of pixel of maximum value is as the corresponding bit value of the module in first number and the second number.

18. device described in -15 according to claim 1, which is characterized in that described device further include:

Locating module is obtained for positioning to the data matrix code to be identified for including in the data matrix code image To the positioning coordinate of the data matrix code to be identified；

Binary processing module carries out perspective transform for the data matrix code image according to the positioning coordinate pair, and right The data matrix code image carries out binary conversion treatment, obtains target data matrix code image；

The piecemeal module is specifically used for black, the white jump rule according to pixel in the target data matrix code image, to institute It states target data matrix code image and carries out piecemeal.

19. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein described Processor, the communication interface, the memory complete mutual communication by the communication bus；

The memory, for storing computer program；

The processor when for executing the program stored on the memory, realizes any side claim 1-9 Method step.