CN107358138A - Bearing calibration, mobile terminal and the storage device of nonlinear distortion EAN bar codes - Google Patents
Bearing calibration, mobile terminal and the storage device of nonlinear distortion EAN bar codes Download PDFInfo
- Publication number
- CN107358138A CN107358138A CN201710424250.1A CN201710424250A CN107358138A CN 107358138 A CN107358138 A CN 107358138A CN 201710424250 A CN201710424250 A CN 201710424250A CN 107358138 A CN107358138 A CN 107358138A
- Authority
- CN
- China
- Prior art keywords
- lines
- bearing calibration
- refinement
- nonlinear distortion
- bar codes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000012937 correction Methods 0.000 claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract description 5
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 4
- 239000013256 coordination polymer Substances 0.000 description 13
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- IYLGZMTXKJYONK-ACLXAEORSA-N (12s,15r)-15-hydroxy-11,16-dioxo-15,20-dihydrosenecionan-12-yl acetate Chemical compound O1C(=O)[C@](CC)(O)C[C@@H](C)[C@](C)(OC(C)=O)C(=O)OCC2=CCN3[C@H]2[C@H]1CC3 IYLGZMTXKJYONK-ACLXAEORSA-N 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- IYLGZMTXKJYONK-UHFFFAOYSA-N ruwenine Natural products O1C(=O)C(CC)(O)CC(C)C(C)(OC(C)=O)C(=O)OCC2=CCN3C2C1CC3 IYLGZMTXKJYONK-UHFFFAOYSA-N 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
- G06K7/1452—Methods for optical code recognition including a method step for retrieval of the optical code detecting bar code edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/146—Methods for optical code recognition the method including quality enhancement steps
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of bearing calibration, mobile terminal and the storage device of nonlinear distortion EAN bar codes.Wherein, bearing calibration includes:Step S1, binary conversion treatment and inverse processing are carried out successively to nonlinear distortion EAN bar code images, obtains the inverse image comprising background area and foreground area;Step S2, the striped in foreground area is screened and extracted according to particular screen rule, micronization processes then are carried out to the striped of reservation using skeletal extraction technology, obtain the refinement lines set of single pixel;Step S3, the refinement lines to adjacent single pixel carry out collimation two-by-two in order, obtain parallel refinement lines set;Step S4, sampled using piecemeal and regional correction is carried out to parallel refinement lines with bilinear interpolation technique, obtain the EAN bar code correction chart pictures of identical size.The EAN bar codes bearing calibration of the present invention is progressively corrected using piecemeal sampling and interpolation technique, and stability and precision are high, and amount of calculation is small.
Description
Technical field
The present invention relates to graph and image processing field, more particularly to a kind of bearing calibration of nonlinear distortion EAN bar codes, shifting
Dynamic terminal and storage device.
Background technology
EAN (European Article Number Bar Code) is a kind of commodity that International Article Numbering Association formulates
With bar code, obtain extensively should in various fields such as commodity circulation, taking care of books, communications and transportation, health care, Bank Danamons
With.Under actual application environment, the bar code of camera capture is frequently subjected to the influences such as shooting angle, bar code attaching surface deformation and made
Into bar code image Quality Down, so as to seriously reduce bar code identification accuracy.
So-called EAN bar codes aberration correction technique, it is after bar code region is isolated, to its angle rotation, bird caging etc.
The process that nonlinear geometry distortion is corrected.
Existing bar code aberration correction technique mainly has two classes:(1) the bar code bearing calibration based on straight-line detection.By means of
Hough transform isoline detection method, using the spatial distribution statistical property of bar code black and white strip, to rotational deformation or affine
The linear distortion bar codes such as deformation are corrected.(2) the bar code bearing calibration based on geometric space conversion.By gathering some controls
Point is to information and solves solution of equations, and then utilization space transformation matrix is corrected to distortion bar code.
Existing bar code bearing calibration, has the following disadvantages:(1) straight-line detection class method is merely able to processing due to shooting angle
The linear distortions such as rigid body translation or the affine transformation of different introducings are spent, the nonlinear distortions such as bird caging can not be handled, are applied
It is limited in scope.(2) geometric space transformation classes method solves equation group using matrix operation mode, solves computationally intensive and complicated.
Under some specific environments, equation group there may be the situation without solution or infinite multiresolution in itself, cause its reliability not high, real
When property is also poor.
Therefore, prior art has yet to be improved and developed.
The content of the invention
In view of above-mentioned the deficiencies in the prior art, it is an object of the invention to provide a kind of school of nonlinear distortion EAN bar codes
Correction method, mobile terminal and storage device, it is intended to which the nonlinear distortions such as bird caging can not be handled and can by solving prior art
By the problem of property is high, poor real.
Technical scheme is as follows:
A kind of bearing calibration of nonlinear distortion EAN bar codes, including:
Step S1, binary conversion treatment and inverse processing are carried out successively to nonlinear distortion EAN bar code images, is obtained comprising the back of the body
The inverse image of scene area and foreground area;
Step S2, the striped in foreground area is screened and extracted according to particular screen rule, then utilize skeleton
Extractive technique carries out micronization processes to the striped of reservation, obtains the refinement lines set of single pixel;
Step S3, the refinement lines to adjacent single pixel carry out collimation two-by-two in order, obtain parallel refinement
Lines set;
Step S4, sampled using piecemeal and regional correction is carried out to parallel refinement lines with bilinear interpolation technique, obtained
The EAN bar code correction chart pictures of identical size.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, in the step S1, the binary conversion treatment
Method is global Binarization methods or local auto-adaptive Binarization methods.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, in the step S1, the mistake of the inverse processing
Journey is specially:Light and shade striped difference respective pixel value 0 and 255 in binary image, region corresponding to pixel value 0 is referred to as to carry on the back
Scene area, region corresponding to pixel value 255 are referred to as foreground area.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, in the step S2, the screening rule is:Meter
The elemental area of each foreground area is calculated, if single region area is more than the average value of all foreground area areas, retaining should
Foreground area, otherwise delete.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, the step S3 is specifically included:
Step S31, the refinement lines of two adjacent single pixels are selected in order, are designated as L respectivelyleftWith
LrightThe statistical distance between the refinement lines of single pixel is calculated using Hausdorff distance metrics method:Wherein l1, l2L is represented respectivelyleftAnd LrightOn point, d (*, *) represent two dimension
Euclidean distance;
Step S32, the refinement lines of single pixel are depicted as straightway, the spacing of adjacent straightway is institute in step S31
D (the L statedleft,Lright);
Step S33, repeat step S31 and step S32, it is successively that the refinement striped progress of remaining single pixel is parallel in order
Correction, obtains parallel refinement striped set.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, the step S4 is specifically included:
Step S41, by the line one by one of corresponding sampled point on two adjacent parallel refinement lines, using bilinear interpolation
Pixel on line is mapped on the corresponding intersegmental corresponding line of parallel lines by technology;
Step S42, traversal repeats said process pixel-by-pixel from top to bottom, corrects all positions between this two adjacent refinement lines
The pixel put, then travel through all adjacent refinement lines in order again, complete the school of all position pixels between intermediate line
Just;
Step S43, to starting refinement lines and refinement lines progress single line bar sample area correction is terminated.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, in the step S41, pixel on line with
Point mapping relations are corresponding to parallel lines is intersegmental:
Wherein (xleft,yleft) it is left side hachure
Upper PleftCoordinate, (xright,yright) it is corresponding point P on the hachure of the rightrightCoordinate, (xS,yS) it is PleftWith
PrightThe coordinate of a certain pixel on line, (x, y) are the coordinate of the intersegmental corresponding points of parallel lines.
The bearing calibration of described nonlinear distortion EAN bar codes, wherein, the step S43 is specially:Calculate edge lines
The normal orientation of point is up-sampled, the Euclidean distance between normal and the intersection point and sampled point of image boundary is calculated, then by straight line
Put corresponding to Duan Shangyu sampled points to the horizontal-extending above-mentioned Euclidean distance in image boundary direction, that is, obtain corresponding mapped boundaries
Point, according to this method completion starting refinement lines and termination refine the regional correction of lines.
A kind of mobile terminal, including processor and the memory that is connected with the processor communication, the memory storage
There is computer program, as above any described nonlinear distortion EAN bar codes are realized when the computer program is executed by processor
Bearing calibration;The processor is used to call computer program in the memory, any of the above-described described non-to perform
The bearing calibration of linear distortion EAN bar codes.
A kind of storage device, the storage device are stored with computer program, and the computer program can be loaded and held
The bearing calibration of capable described nonlinear distortion EAN bar codes any as described above.
Beneficial effect:The invention provides a kind of bearing calibration of nonlinear distortion EAN bar codes, mobile terminal and storage to set
Standby, EAN bar code bearing calibrations of the invention are the extractions of the shape facility based on bar code itself, do not make any limit to distortion type
System, can handle any nonlinear distortion deformation, and versatility is high.In addition, the present invention is sampled with interpolation technique progressively using piecemeal
Correction, stability and precision are high, and amount of calculation is small.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the bearing calibration of nonlinear distortion EAN bar codes of the present invention.
Fig. 2 a are to take a schematic diagram on adjacent refinement lines in the adjacent lines region correction step of the present invention.
Fig. 2 b are that a schematic diagram is correspondingly taken on parallel segment in the adjacent lines region correction step of the present invention.
Fig. 3 a are normal to curve direction calculating schematic diagram in single line bar region correction step of the invention.
Fig. 3 b are that sampled point is mapped to schematic diagram in the figure after calibration in single line bar region correction step of the invention.
Fig. 4 is a kind of principle of work and power frame of mobile terminal based on nonlinear distortion EAN bar code bearing calibrations of the present invention
Figure.
Fig. 5 is to nonlinear distortion EAN bar code image binaryzations in nonlinear distortion EAN bar code bearing calibrations of the invention
With the design sketch after inverse processing.
Fig. 6 be the present invention nonlinear distortion EAN bar code bearing calibrations in nonlinear distortion EAN bar code images screening and
Design sketch after micronization processes.
Fig. 7 is to refine lines regional correction result to adjacent in the nonlinear distortion EAN bar code bearing calibrations of the present invention
Design sketch.
Fig. 8 is the design sketch of the nonlinear distortion EAN bar code bearing calibration correction of a final proof results of the present invention.
Embodiment
The invention provides a kind of bearing calibration, mobile terminal and the storage device of nonlinear distortion EAN bar codes, to make this
The purpose of invention, technical scheme and effect are clearer, clear and definite, and the present invention is described in more detail below.It should be appreciated that this
The specific embodiment of place description is not intended to limit the present invention only to explain the present invention.
The invention provides a kind of preferred embodiment of the bearing calibration of nonlinear distortion EAN bar codes, correcting process such as Fig. 1
Shown, aligning step includes:
Step S1, binary conversion treatment and inverse processing are carried out successively to nonlinear distortion EAN bar code images, is obtained comprising the back of the body
The inverse image of scene area and foreground area.
Specifically, binary conversion treatment is carried out to bar code image first.According to the acquisition quality of actual bar code image, binaryzation
Algorithm can select fixed threshold the method either global Binarization methods such as Da-Jin algorithm or local auto-adaptive Binarization methods.Then
Inverse processing is done to obtained binary image.After inverse, original light and shade striped difference respective pixel value 0 and 255.Usual feelings
Under condition, region corresponding to pixel 0 is referred to as background area, and region corresponding to pixel 255 is referred to as foreground area.
Step S2, the striped in foreground area is screened and extracted according to particular screen rule, then utilize skeleton
Extractive technique carries out micronization processes to the striped of reservation, obtains the refinement lines set of single pixel.
Specifically, the boundary profile of foreground area is extracted using Freeman chain code technologies, and calculates each isolated foreground zone
The elemental area in domain (is designated as Si, i=1,2,3 ...) and the mean pixel area of all foreground areas (be designated as S0), if Si≥
S0, then retain the foreground area, otherwise delete.So, striped screening step is just completed.
Find out from above-mentioned screening rule, the foreground area set of reservation is all that relative area is larger, non-single pixel width
Striped, so being refined using skeletal extraction technology to foreground area, finally give the lines set of single pixel wide.
It should be noted that the present invention is corresponding less than the foreground area of all foreground area mean pixel areas without extraction
Narrow strips, be to prevent extraction process from producing larger error, influence final correction accuracy, narrow strips will be in subsequent sections school
Directly be corrected in positive step, and traditional rigid body translation or affine transformation etc. be to the processing method of linear distortion can not
Wide striped and stria are handled respectively with different methods.
Step S3, the refinement lines to adjacent single pixel carry out collimation two-by-two in order, obtain parallel refinement
Lines set.
After obtaining the refinement lines set of single pixel, additionally create one group and the refinement Stripe Size identical of single pixel is straight
Line segment.Specifically, (from left to right or from right to left, " in order " of the invention should be understood that) selects two phases in order
Adjacent refinement lines, are designated as L respectivelyleftAnd Lright.Due to the influence of nonlinear distortion, lines LleftAnd LrightNot
It is parallel line segment again.Statistical distance between lines is calculated using Hausdorff distance metrics method:
Wherein l1, l2Lines L is represented respectivelyleftAnd LrightOn point.D (*, *) represents two-dimentional Euclidean distance.
It is assumed that level is x directions, vertical is y directions, and the vertical line segment CL after correction is drawn according to following ruleleftWith
CLright, below with CLleftExemplified by illustrate:
The first step, by CLleftHorizontal direction coordinate definition be lines LleftMiddle horizontal direction x coordinate a little is averaged
Value.The vertical direction y-coordinate of its upper extreme point is defined as lines LleftUpper extreme point vertical direction y-coordinate.
Second step, the vertical direction y-coordinate value of lower extreme point are defined as CLleftUpper extreme point vertical direction y-coordinate value and lines
LleftLength in pixels (sums of 255 pixels) summation.
3rd step, CLleftThe pixel value of line segment uses L successively according to order from top to bottomleftPixel value assignment.
CLrightHorizontal direction coordinate definition be CLleftHorizontal direction x coordinate add D (Lleft,Lright).Other coordinates
Information definition mode and CLleftIt is completely the same.
According to above step, single pixel refinement lines are depicted as to the vertical element of same length, in order successively will be all
Refinement lines be corrected to parallel refinement lines, the spacing between adjacent, parallel lines is D (L recited aboveleft,Lright)。
Step S4, sampled using piecemeal and regional correction is carried out to parallel refinement lines with bilinear interpolation technique, obtained
The EAN bar code correction chart pictures of identical size.
Two-wire bar regional correction is carried out first, i.e., sampled point is correspondingly taken on two adjacent refinement lines, by sampled point
Line is corresponded, such as by LleftUpper first pixel and LrightUpper first pixel line, LleftUpper second picture
Vegetarian refreshments and LrightUpper second pixel point line, LleftUpper 3rd pixel and LrightUpper 3rd pixel line, successively
Analogize.The pixel on line is mapped on the corresponding intersegmental corresponding line of parallel lines using bilinear interpolation technique.
Specifically, such as since the left side, two adjacent refinement lines L are selectedleftAnd LrightIf after corresponding correction
Line Segment is CLleftAnd CLright。LleftAnd CLleftEqual length, LrightAnd CLrightEqual length, be designated as respectively
LengthleftAnd Lengthright.Assuming that PleftIt is LleftOn sort from top to bottom k-th of coordinate points, then it is in LrightOn
Corresponding points PrightIt is defined as being ordered as from top to bottomCoordinate points.PleftAnd PrightIn correction chart as on
Corresponding points CPleftAnd CPrightBe defined as sorting from top to bottom be ordered as k andCoordinate points.Such as Fig. 2 a and figure
Shown in 2b.
Regional correction process between adjacent refinement lines is as follows:
It is assumed that PleftCoordinate be (xleft,yleft), PrightCoordinate be (xright,yright),CPleftCoordinate be
(cxleft,cyleft),CPrightCoordinate be (cxright,cyright).Line segment CPleft CPrightUpper any point CP (x, y), its
Corresponding coordinate P (x on original imageS,yS) calculated by equation below:
So CP (x, y) pixel value is just entered as P (xS,yS) pixel value.
Traversal repeats said process pixel-by-pixel from top to bottom, can be with the interregional all positions of two adjacent lines of correction
Pixel.Method travels through all adjacent lines in order according to this, can complete the correction of all position pixels between lines.
What above-mentioned bearing calibration was directed to is all the correction of intermediate region, not only includes the correction of extracted striped, also
Direct correction including undrawn stria.But the region that the leftmost side lines where starting lines and termination lines are turned left
, it is necessary to carry out single line bar sample area school to the thinning lines of edge two in the region turned right with rightmost side lines is not included in
Just.Bearing calibration is to calculate the normal orientation of edge lines up-sampling point, calculates normal and the intersection point and sampled point of image boundary
Between Euclidean distance, then by straightway it is corresponding with sampled point put to the horizontal-extending above-mentioned Euclidean in image boundary direction away from
From, that is, obtain corresponding mapped boundaries point, according to this method can complete starting refinement lines and terminate refinement lines regional correction.
Below by taking the lines of the rightmost side as an example, the method that single line bar sample area corrects is illustrated.
It is that single line bar does not have side corresponding to right side with two-wire bar difference.As defined in abovementioned steps, it is assumed that
PleftCoordinate be (xleft,yleft),CPleftCoordinate be (cxleft,cyleft).Virtual P is given belowrightCoordinate side
Method, as shown in Figure 3 a and Figure 3 b shows.
Point P is calculated firstleftThe normal orientation at place, the specific method of curve normal direction direction calculating are:Given curve is according to y
Coordinate size carries out ascending sort, is designated as { Curve [i], i=1,2 ..., N }.Any point P on curve, serial number p, is divided into two
Kind situation:
(1) point P falls in the head of curve or tail region, i.e. sequence number p≤5 of P or p >=N-4.Fallen with point P in head
Exemplified by portion, then sampled point set Curve [0], Curve [1] .., Curve [p+5] are taken.Collective data fitting is in line
FitL, fitL direction is taken then to calculate approximate normal direction of the method direction on its deviation right side as point P as the tangential of the point.
(2) point P falls among curve.Sampling point set is combined into Curve [p-5] ..., Curve [p] .., Curve [p+5].
Remaining calculation is identical with step (1).Here is omitted.
Ray is taken then along normal orientation, and the intersection point of ray and image boundary is designated as Pright.Calculate its Euclidean distance
Lengthleft.Due to CLleftItself it is vertical direction line segment, so CPrightValue be CPleftExtended distance to the right
LengthleftCoordinate.So far, Pleft, PrightCorresponding CPleftAnd CPrightAll obtain.Calculated according to this
Journey, the region that rightmost side lines are turned right can be corrected.Similarly, the region that leftmost side lines are turned left can be corrected.
Present invention also offers a kind of mobile terminal, as shown in figure 4, the mobile terminal includes:Processor
(processor) 10, memory (memory) 20, communication interface (Communications Interface) 30 and bus 40.
Wherein, the processor 10, memory 20, communication interface 30 complete mutual communication by the bus 40;The communication
The information transfer that interface 30 is used between the communication equipment of the mobile terminal;The processor 10 is used to call the memory
Computer program in 20, to perform the method that above-mentioned each method embodiment is provided.
Upon power-up of the system, acquisition for mobile terminal nonlinear distortion EAN bar code images, and successively carry out binary conversion treatment and
Inverse processing, obtains the inverse image comprising background area and foreground area, and the effect after processing is as shown in Figure 5;Then according to
Particular screen rule is screened and extracted to the striped in foreground area, and the striped of reservation is entered using skeletal extraction technology
Row micronization processes, the refinement lines set of single pixel is obtained, as shown in Figure 6;The refinement lines to adjacent single pixel are pressed again
Order carries out collimation two-by-two, obtains parallel refinement lines set, finally using piecemeal sampling and bilinear interpolation technique
Regional correction is carried out to parallel refinement lines, obtains the EAN bar code correction chart pictures of identical size, as shown in Figure 7 and Figure 8.
The present invention also provides a kind of storage device, wherein, the storage device is stored with computer program, the computer
Program can be performed to realize the bearing calibration of the nonlinear distortion EAN bar codes.
In summary, the invention provides a kind of bearing calibration of nonlinear distortion EAN bar codes, mobile terminal and storage to set
Standby, EAN bar code bearing calibrations of the invention are the extractions of the shape facility based on bar code itself, do not make any limit to distortion type
System, can handle any nonlinear distortion deformation, and versatility is high.In addition, the present invention is sampled with interpolation technique progressively using piecemeal
Correction, stability and precision are high, and amount of calculation is small.
Certainly, one of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method,
It is that by computer program related hardware (such as processor, controller etc.) can be instructed to complete, described program can store
In a computer-readable storage medium, the program may include such as the flow of above-mentioned each method embodiment upon execution.Its
Described in storage medium can be memory, magnetic disc, CD etc..
It should be appreciated that the application of the present invention is not limited to above-mentioned citing, for those of ordinary skills, can
To be improved or converted according to the above description, all these modifications and variations should all belong to the guarantor of appended claims of the present invention
Protect scope.
Claims (10)
- A kind of 1. bearing calibration of nonlinear distortion EAN bar codes, it is characterised in that including:Step S1, binary conversion treatment and inverse processing are carried out successively to nonlinear distortion EAN bar code images, obtains including background area Domain and the inverse image of foreground area;Step S2, the striped in foreground area is screened and extracted according to particular screen rule, then utilize skeletal extraction Technology carries out micronization processes to the striped of reservation, obtains the refinement lines set of single pixel;Step S3, the refinement lines to adjacent single pixel carry out collimation two-by-two in order, obtain parallel refinement lines Set;Step S4, sampled using piecemeal and regional correction is carried out to parallel refinement lines with bilinear interpolation technique, obtained identical The EAN bar code correction chart pictures of size.
- 2. the bearing calibration of nonlinear distortion EAN bar codes according to claim 1, it is characterised in that in the step S1, The method of the binary conversion treatment is global Binarization methods or local auto-adaptive Binarization methods.
- 3. the bearing calibration of nonlinear distortion EAN bar codes according to claim 1, it is characterised in that in the step S1, The process of inverse processing is specially:Light and shade striped difference respective pixel value 0 and 255 in binary image, pixel value 0 is right The region answered is referred to as background area, and region corresponding to pixel value 255 is referred to as foreground area.
- 4. the bearing calibration of nonlinear distortion EAN bar codes according to claim 1, it is characterised in that in the step S2, The screening rule is:The elemental area of each foreground area is calculated, if single region area is more than all foreground area areas Average value, then retain the foreground area, otherwise delete.
- 5. the bearing calibration of nonlinear distortion EAN bar codes according to claim 1, it is characterised in that the step S3 tools Body includes:Step S31, the refinement lines of two adjacent single pixels are selected in order, are designated as L respectivelyleftWith LrightThe statistical distance between the refinement lines of single pixel is calculated using Hausdorff distance metrics method:Wherein l1, l2L is represented respectivelyleftAnd LrightOn point, d (*, *) represent two dimension Euclidean distance;Step S32, the refinement lines of single pixel are depicted as straightway, the spacing of adjacent straightway is the D described in step S31 (Lleft,Lright);Step S33, repeat step S31 and step S32, the refinement striped of remaining single pixel is subjected to parallel school successively in order Just, parallel refinement striped set is obtained.
- 6. the bearing calibration of nonlinear distortion EAN bar codes according to claim 1, it is characterised in that the step S4 tools Body includes:Step S41, by the line one by one of corresponding sampled point on two adjacent parallel refinement lines, using bilinear interpolation technique Pixel on line is mapped on the corresponding intersegmental corresponding line of parallel lines;Step S42, traversal repeats said process pixel-by-pixel from top to bottom, corrects all positions between this two adjacent refinement lines Pixel, then travel through all adjacent refinement lines in order again, complete the correction of all position pixels between intermediate line;Step S43, to starting refinement lines and refinement lines progress single line bar sample area correction is terminated.
- 7. the bearing calibration of nonlinear distortion EAN bar codes according to claim 6, it is characterised in that the step S41 In, the pixel on line is with the intersegmental corresponding point mapping relations of parallel lines:Wherein (xleft,yleft) it is point on the hachure of the left side PleftCoordinate, (xright,yright) it is corresponding point P on the hachure of the rightrightCoordinate, (xS,yS) it is PleftAnd PrightEven The coordinate of a certain pixel on line, (x, y) are the coordinate of the intersegmental corresponding points of parallel lines.
- 8. the bearing calibration of nonlinear distortion EAN bar codes according to claim 6, it is characterised in that the step S43 tools Body is:The normal orientation of edge lines up-sampling point is calculated, calculates the Europe between normal and the intersection point and sampled point of image boundary Family name's distance, then put to the horizontal-extending above-mentioned Euclidean distance in image boundary direction, produce by corresponding with sampled point on straightway To corresponding mapped boundaries point, method completion starting refinement lines and termination according to this refines the regional correction of lines.
- A kind of 9. mobile terminal, it is characterised in that the memory being connected including processor and with the processor communication, it is described to deposit Reservoir is stored with computer program, and the computer program realizes that claim 1-8 is any described non-when being executed by processor The bearing calibration of linear distortion EAN bar codes;The processor is used to call the computer program in the memory, with execution State the bearing calibration of any described nonlinear distortion EAN bar codes of claim 1-8.
- 10. a kind of storage device, it is characterised in that the storage device is stored with computer program, the computer program energy Enough load and perform the bearing calibration of the nonlinear distortion EAN bar codes as described in claim 1-8 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710424250.1A CN107358138B (en) | 2017-06-07 | 2017-06-07 | Correction method of nonlinear distortion EAN bar code, mobile terminal and storage device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710424250.1A CN107358138B (en) | 2017-06-07 | 2017-06-07 | Correction method of nonlinear distortion EAN bar code, mobile terminal and storage device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107358138A true CN107358138A (en) | 2017-11-17 |
CN107358138B CN107358138B (en) | 2020-03-24 |
Family
ID=60273532
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710424250.1A Expired - Fee Related CN107358138B (en) | 2017-06-07 | 2017-06-07 | Correction method of nonlinear distortion EAN bar code, mobile terminal and storage device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107358138B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113592782A (en) * | 2021-07-07 | 2021-11-02 | 山东大学 | Method and system for extracting X-ray image defects of composite carbon fiber core rod |
CN116804532A (en) * | 2023-08-24 | 2023-09-26 | 苏州中科行智智能科技有限公司 | 3D measurement method for distance between parallel line segments |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096795A (en) * | 2010-11-25 | 2011-06-15 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
CN102799850A (en) * | 2012-06-30 | 2012-11-28 | 北京百度网讯科技有限公司 | Bar code recognition method and device |
US20130069003A1 (en) * | 2009-04-02 | 2013-03-21 | Sicpa Holding Sa | Identification and authentication using polymeric liquid crystal material markings |
CN102156970B (en) * | 2011-04-14 | 2013-04-10 | 复旦大学 | Fisheye image correction method based on distorted straight slope calculation |
-
2017
- 2017-06-07 CN CN201710424250.1A patent/CN107358138B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130069003A1 (en) * | 2009-04-02 | 2013-03-21 | Sicpa Holding Sa | Identification and authentication using polymeric liquid crystal material markings |
CN102096795A (en) * | 2010-11-25 | 2011-06-15 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
CN102156970B (en) * | 2011-04-14 | 2013-04-10 | 复旦大学 | Fisheye image correction method based on distorted straight slope calculation |
CN102799850A (en) * | 2012-06-30 | 2012-11-28 | 北京百度网讯科技有限公司 | Bar code recognition method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113592782A (en) * | 2021-07-07 | 2021-11-02 | 山东大学 | Method and system for extracting X-ray image defects of composite carbon fiber core rod |
CN113592782B (en) * | 2021-07-07 | 2023-07-28 | 山东大学 | Method and system for extracting X-ray image defects of composite material carbon fiber core rod |
CN116804532A (en) * | 2023-08-24 | 2023-09-26 | 苏州中科行智智能科技有限公司 | 3D measurement method for distance between parallel line segments |
CN116804532B (en) * | 2023-08-24 | 2023-11-28 | 苏州中科行智智能科技有限公司 | 3D measurement method for distance between parallel line segments |
Also Published As
Publication number | Publication date |
---|---|
CN107358138B (en) | 2020-03-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112348815B (en) | Image processing method, image processing apparatus, and non-transitory storage medium | |
CN108898610B (en) | Object contour extraction method based on mask-RCNN | |
CN111583097A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN109858325B (en) | Table detection method and device | |
CN114529459B (en) | Method, system and medium for enhancing image edge | |
CN106934806B (en) | It is a kind of based on text structure without with reference to figure fuzzy region dividing method out of focus | |
CN110930411B (en) | Human body segmentation method and system based on depth camera | |
CN108257155B (en) | Extended target stable tracking point extraction method based on local and global coupling | |
CN110400278A (en) | A kind of full-automatic bearing calibration, device and the equipment of color of image and geometric distortion | |
CN105335952B (en) | Matching power flow computational methods and device and parallax value calculating method and equipment | |
CN113744142B (en) | Image restoration method, electronic device and storage medium | |
CN108346148A (en) | A kind of high density flexible IC substrate oxide regions detecting systems and method | |
CN112767270A (en) | Fold document image correction system | |
WO2021168703A1 (en) | Character processing and identifying methods, storage medium, and terminal device | |
CN112991374A (en) | Canny algorithm-based edge enhancement method, device, equipment and storage medium | |
CN112183517A (en) | Certificate card edge detection method, equipment and storage medium | |
CN107358138A (en) | Bearing calibration, mobile terminal and the storage device of nonlinear distortion EAN bar codes | |
CN115082935A (en) | Method, apparatus and storage medium for correcting document image | |
CN110163910B (en) | Object positioning method, device, computer equipment and storage medium | |
CN112200822A (en) | Table reconstruction method and device, computer equipment and storage medium | |
US11908108B2 (en) | Image correction method and processor | |
Shibayama et al. | Reconstruction of 3D surface and restoration of flat document image from monocular image sequence | |
CN115937839A (en) | Large-angle license plate image recognition method, calculation equipment and storage medium | |
CN115619678A (en) | Image deformation correction method and device, computer equipment and storage medium | |
CN114332890A (en) | Table structure extraction method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200324 |
|
CF01 | Termination of patent right due to non-payment of annual fee |