CN112785514A - Rapid bar code image motion reduction method - Google Patents
Rapid bar code image motion reduction method Download PDFInfo
- Publication number
- CN112785514A CN112785514A CN202011621274.4A CN202011621274A CN112785514A CN 112785514 A CN112785514 A CN 112785514A CN 202011621274 A CN202011621274 A CN 202011621274A CN 112785514 A CN112785514 A CN 112785514A
- Authority
- CN
- China
- Prior art keywords
- image
- bar code
- lobe
- candidate
- motion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000009467 reduction Effects 0.000 title claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000004044 response Effects 0.000 claims description 12
- 230000003595 spectral effect Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000000903 blocking effect Effects 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000011410 subtraction method Methods 0.000 claims 2
- 238000005457 optimization Methods 0.000 claims 1
- 238000011426 transformation method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000005530 etching Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a quick bar code image motion reduction method, belonging to the technical field of image processing and comprising the following steps: the method comprises the steps of extracting a bar code image based on direction consistency, conducting blind deblurring processing on the extracted bar code image, obtaining a motion blur direction and a motion blur length according to the image to obtain a motion blur point spread function, adopting wiener filtering to recover the bar code image according to the motion blur length and the blur angle obtained by a blur image, obtaining the motion blur direction and the motion blur length according to a positioning bar code image, and then using the wiener filtering to recover the bar code image, so that the clear bar code image can be obtained in a mobile scene, the working efficiency and the user experience are improved, and the bar code technology can be applied to more complex and changeable scenes.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a quick bar code image motion reduction method.
Background
Most of the bar code images acquired in the daily bar code scanning process are fuzzy bar code images, for the fuzzy bar code images, the traditional decoding method cannot correctly identify bar code information in the bar code images, long-time static and focusing needs to be manually kept, and people cannot acquire clear bar code images in a moving scene, so that the working efficiency is greatly influenced, and the user experience is reduced. In order to better apply the bar code to a complex and changeable scene and aim at the situation of motion blur, a deblurring method for a bar code image is particularly provided, and the blurred bar code image can be restored into a recognizable clear bar code image.
Because the analysis and the deblurring processing of the whole image need to consume much time, and the requirement on timeliness of the bar code identification is high, the deblurring processing is only carried out on the bar code area, so that the algorithm efficiency is improved. Aiming at the analysis of a bar code image, the bar code image has two characteristics, firstly, bars and spaces in a bar code area are arranged in parallel, and the directions tend to be consistent; secondly, in order to improve the readability of the bar code, the bar code has a large difference in reflectivity between the bars and spaces during the manufacture, so that the gray scale contrast in the bar code area is large and the edge information is rich. And combining the characteristics of the bar code, providing a bar code positioning method based on bar code consistency, acquiring a motion blur direction and a motion blur length according to a positioning image, and then recovering the bar code image by using wiener filtering.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a quick bar code image motion reduction method.
The technical scheme adopted by the invention for solving the technical problems is as follows: a quick bar code image motion reduction method comprises the following steps:
A. extracting a bar code image based on the direction consistency;
B. blind deblurring processing is carried out on the extracted bar code image, and a motion blur direction and a motion blur length are obtained according to the image to obtain a motion blur point spread function;
C. and restoring the bar code image by adopting wiener filtering according to the motion blur length and the blur angle acquired by the blurred image.
Preferably, the step A specifically comprises image preprocessing, image blocking for direction consistency evaluation, candidate image block connected domain analysis, barcode region screening and positioning and barcode inclination correction;
a1, preprocessing an image, performing median filtering on the acquired image, and calculating gradients corresponding to all pixel points in the image by using a sobel operator;
a2, dividing the image into image blocks of image blocks, recording the image blocks after division as W, and obtaining a set of image blocks { P }1，P2，...PNWhere N is the total number of image blocks, direction uniformity Coh (P) of an image block is calculated using equation (1)i)；
A3, candidate image block PiCalculating the image block P by the formula (2) using the formulaiAverage gradient direction of thetaiAs PiEstimating the gradient direction of the target object;
wherein the content of the first and second substances,
a4, for each candidate image block PiAnd counting the number of candidate image blocks in the eight neighborhood range. If there is more than2 groups are candidate image blocks, then PiReserving; otherwise, cancel PiThe candidate target of (2) can be filtered out the interference lines and the local background by the corrosion operation.
And A5, judging the adjacency relation between all the candidate image blocks and the eight neighborhoods according to the growth principle, and combining all the candidate image blocks which are mutually communicated by using a local area growth algorithm to obtain candidate bar code areas.
Defining the connectivity (growing rule) of the candidate image blocks as candidate image blocks PiAnd candidate image block PjAdjacent to each other and having an average gradient direction of thetaiAnd thetajAnd if the condition is satisfied:
|θi-θj|＜ε0 or|θi-θj|＜π-ε0 (3)
then candidate image block PiAnd candidate image block PjAre interconnected, wherein epsilonaIs an angular deviation threshold.
A6, calculating the direction consistency of the candidate bar code area P according to the formula (4), and obtaining the direction consistency Coh (P) and the dimension Width (P) of the bar codei) And edge number Edges (P)i) Then, whether the candidate area is valid is judged according to the formula (5).
Where M is the total number of candidate image blocks in the barcode region.
Wherein sigmacohThe setting range is 0.9-0.98, sigmawThe minimum recognizable length of the bar code is set to be 95-125, sigmaeThe threshold value of the number of edges is set within the range of 45-95.
Preferably, in the step B, a modified randon transform method is adopted to extract the motion blur angle;
3) firstly, selecting 1 degree as a step length, calculating random transformation of a frequency spectrum on 0-180 degrees, and selecting an angle theta' corresponding to the maximum value of the random transformation;
4) calculating randon transformation on theta '-3-theta' +3 degrees by taking 0.5 degrees as step length, and solving the angle theta corresponding to the maximum value, namely solving the angle theta;
after the motion blur direction is obtained, the step of obtaining the blur length is as follows:
1) clockwise rotating the motion blurred image G by theta degrees to obtain G _ x;
2) separating the three primary colors R, G, B of the obtained image G _ x;
3) extracting the vertical central part of the motion blur for pixel value verification;
4) finding out the maximum pixel value in each longitudinal row, accumulating to obtain a one-dimensional matrix H, and then drawing a point line graph of H;
5) finding the first turning point on any side of the central lobe, wherein the pixel value of the turning point is the main lobe width (W) of the Fourier spectrumc)；
6) Respectively finding out widths of a second lobe, a third lobe and a fourth lobe on the left side and the right side of the central lobe according to the method, and respectively recording the widths as Wright1，Wright2，Wright3，Wleft1，Wleft2，Wleft3；
7) Screening each lobe, if the pixel difference between the width of the lobe and the width of any lobe is more than 3 pixel values, discarding the lobe, otherwise, keeping the lobe and considering the lobe as a fuzzy scale;
8) calculating the average lobe width of all reserved lobes;
for example, if all of the lobes remain, then,
9) the motion blur length can be obtained by dividing the width of the image by the average lobe width D;
thereby, a point spread function of the moving image can be calculated:
preferably, in the step C, a spatial expression of a point spread function of the motion blur may be obtained according to the motion direction (i.e. the obtained motion blur direction) and the blur length, and then the barcode image is deblurred by using wiener filtering;
the transfer function M (u, v) of the wiener filter is:
where H (u, v) is the frequency domain response of the blur kernel, Snn(u, v) is the frequency spectral density, S, corresponding to noiseff(u, v) is the frequency spectral density of the image;
the frequency response F of the restored image F obtained after wiener filtering is:
wherein G (u, v) is the frequency response of the blurred image;
1) carrying out Fourier transform on the blurred image to obtain G (u, v);
2) obtaining a two-dimensional Fourier transform H (u, v) according to the point spread function calculated by the formula (3);
3) calculating the spectral density S of the noisenn(u, v) and spectral density S of the imageffThe ratio K of (u, v);
4) calculating the frequency response of the restored image by a formula (5);
5) and obtaining a restored image by utilizing inverse Fourier transform.
The invention has the beneficial effects that: the motion blur direction and the motion blur length are obtained according to the positioning bar code image, and then the wiener filtering is used for recovering the bar code image, so that a clear bar code image can be obtained in a mobile scene, the working efficiency and the user experience are improved, and the bar code technology can be applied to more complex and changeable scenes.
Drawings
FIG. 1 is an exemplary original barcode image in an embodiment of the present invention;
FIG. 2 is an edge image after extraction according to an embodiment of the present invention;
FIG. 3 is a result of chunking in an example of an embodiment of the present invention;
FIG. 4 shows the results of an etching operation in an example of an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a process of selecting a barcode region according to an embodiment of the present invention;
FIG. 6 is a barcode region located in an example of an embodiment of the present invention;
FIG. 7 is a bar code region of an original image according to an embodiment of the present invention;
FIG. 8 illustrates a barcode region after wiener filtering recovery in an example embodiment of the invention;
FIG. 9 is a schematic diagram illustrating steps in an embodiment of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in the attached drawings, the quick bar code image motion reduction method provided by the invention comprises the following steps:
A. extracting a bar code image based on the direction consistency;
B. blind deblurring processing is carried out on the extracted bar code image, and a motion blur direction and a motion blur length are obtained according to the image to obtain a motion blur point spread function;
C. and restoring the bar code image by adopting wiener filtering according to the motion blur length and the blur angle acquired by the blurred image.
Preferably, the step A specifically comprises image preprocessing, image blocking for direction consistency evaluation, candidate image block connected domain analysis, barcode region screening and positioning and barcode inclination correction;
a1, preprocessing an image, performing median filtering on the acquired image, and calculating gradients corresponding to all pixel points in the image by using a sobel operator;
a2, dividing the image into image blocks of image blocks, recording the image blocks after division as W, and obtaining a set of image blocks { P }1，P2，...PNWhere N is the total number of image blocks, direction uniformity Coh (P) of an image block is calculated using equation (1)i)；
A3, candidate image block PiCalculating the image block P by the formula (2) using the formulaiAverage gradient direction of thetaiAs PiEstimating the gradient direction of the target object;
wherein the content of the first and second substances,
a4, for each candidate image block PiAnd counting the number of candidate image blocks in the eight neighborhood range. If more than 2 groups are candidate image blocks, PiReserving; otherwise, cancel PiThe candidate target of (2) can be filtered out the interference lines and the local background by the corrosion operation.
And A5, judging the adjacency relation between all the candidate image blocks and the eight neighborhoods according to the growth principle, and combining all the candidate image blocks which are mutually communicated by using a local area growth algorithm to obtain candidate bar code areas.
Defining the connectivity (growing rule) of the candidate image blocks as candidate image blocks PiAnd candidate image block PjAdjacent to each other and having an average gradient direction of thetaiAnd thetajAnd if the condition is satisfied:
|θi-θj|＜ε0 or |θi-θj|＜π-ε0 (3)
then candidate image block PiAnd candidate image block PjAre interconnected, wherein epsilonaIs an angular deviation threshold.
A6, calculating the direction consistency of the candidate bar code area P according to the formula (4), and obtaining the direction consistency Coh (P) and the dimension Width (P) of the bar codei) And edge number Edges (P)i) Then, whether the candidate area is valid is judged according to the formula (5).
Where M is the total number of candidate image blocks in the barcode region.
The setting range is 0.9-0.98, in this embodiment, the setting range is 0.96, the minimum recognizable length of the barcode is 95-125, in this embodiment, the number of modules 95 set as the barcode is an edge number threshold value, the setting range is 45-95, in this embodiment, the value can be smaller than the edge number of the standard barcode and is set as 45 in consideration of the influence of various interference factors.
Preferably, in the step B, a modified randon transform method is adopted to extract the motion blur angle;
5) firstly, selecting 1 degree as a step length, calculating random transformation of a frequency spectrum on 0-180 degrees, and selecting an angle theta' corresponding to the maximum value of the random transformation;
6) calculating randon transformation on theta '-3-theta' +3 degrees by taking 0.5 degrees as step length, and solving the angle theta corresponding to the maximum value, namely solving the angle theta;
after the motion blur direction is obtained, the step of obtaining the blur length is as follows:
1) clockwise rotating the motion blurred image G by theta degrees to obtain G _ x;
2) separating the three primary colors R, G, B of the obtained image G _ x;
3) extracting the vertical central part of the motion blur for pixel value verification;
4) finding out the maximum pixel value in each longitudinal row, accumulating to obtain a one-dimensional matrix H, and then drawing a point line graph of H;
5) finding the first turning point on any side of the central lobe, wherein the pixel value of the turning point is the main lobe width (W) of the Fourier spectrumc)；
6) Respectively finding out widths of a second lobe, a third lobe and a fourth lobe on the left side and the right side of the central lobe according to the method, and respectively recording the widths as Wright1，Wright2，Wright3，Wleft1，Wleft2，Wleft3；
7) Screening each lobe, if the pixel difference between the width of the lobe and the width of any lobe is more than 3 pixel values, discarding the lobe, otherwise, keeping the lobe and considering the lobe as a fuzzy scale;
8) calculating the average lobe width of all reserved lobes;
for example, if all of the lobes remain, then,
9) the motion blur length can be obtained by dividing the width of the image by the average lobe width D;
thereby, a point spread function of the moving image can be calculated:
preferably, in the step C, a spatial expression of a point spread function of the motion blur may be obtained according to the motion direction (i.e. the obtained motion blur direction) and the blur length, and then the barcode image is deblurred by using wiener filtering;
the transfer function M (u, v) of the wiener filter is:
where H (u, v) is the frequency domain response of the blur kernel, Snn(u, v) is the frequency spectral density, S, corresponding to noiseff(u, v) is the frequency spectral density of the image;
the frequency response F of the restored image F obtained after wiener filtering is:
wherein G (u, v) is the frequency response of the blurred image;
1) carrying out Fourier transform on the blurred image to obtain G (u, v);
2) obtaining a two-dimensional Fourier transform H (u, v) according to the point spread function calculated by the formula (3);
3) calculating the spectral density S of the noisenn(u, v) and spectral density S of the imageffThe ratio K of (u, v);
4) calculating the frequency response of the restored image by a formula (5);
5) and obtaining a restored image by utilizing inverse Fourier transform.
Specifically, an actual example is used for demonstration, and fig. 1 is an original barcode image, fig. 2 is an extracted edge image, fig. 3 is a blocking result, wherein a thin-line frame in the diagram is an image blocking result satisfying direction consistency, fig. 4 is an etching operation result, fig. 5 is a selection process of a barcode region, a line frame in the diagram is a selected barcode region, and fig. 6 is a positioned barcode region;
taking the above-mentioned figures as examples, the blur angle θ is 5 ° and the blur length L is 5, that is, a spatial domain expression of a point spread function of the motion blur can be obtained according to the motion direction and the blur length, and then the wiener filtering is adopted to recover the image, where fig. 7 is a barcode region in the original image, and fig. 8 is a barcode region after the wiener filtering is recovered.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (4)
1. A quick bar code image motion reduction method is characterized by comprising the following steps:
A. extracting a bar code image based on the direction consistency;
B. blind deblurring processing is carried out on the extracted bar code image, and a motion blur direction and a motion blur length are obtained according to the image to obtain a motion blur point spread function;
C. and restoring the bar code image by adopting wiener filtering according to the motion blur length and the blur angle acquired by the blurred image.
2. The quick barcode image motion subtraction method according to claim 1, wherein the step a specifically comprises image preprocessing, image blocking for direction consistency evaluation, candidate image block connected domain analysis, barcode region screening and positioning, and barcode tilt correction;
a1, preprocessing an image, performing median filtering on the acquired image, and calculating gradients corresponding to all pixel points in the image by using a sobel operator;
a2, dividing the image into image blocks of image blocks, recording the image blocks after division as W, and obtaining a set of image blocks { P }1，P2，...PNWhere N is the total number of image blocks, direction uniformity Coh (P) of an image block is calculated using equation (1)i)；
A3, candidate image block PiCalculating the image block P by the formula (2) using the formulaiAverage gradient direction of thetaiAs PiEstimating the gradient direction of the target object;
wherein the content of the first and second substances,
a4, for each candidate image block PiCounting the number of candidate image blocks in the eight neighborhood range, if more than 2 groups are candidate image blocks, PiReserving; otherwise, cancel PiThe candidate targets of (1) can filter out interference lines and local backgrounds through corrosion operation;
a5, judging the adjacency relation between all candidate image blocks and eight neighborhoods according to the growth principle, and merging all the mutually communicated candidate image blocks by using a local area growth algorithm to obtain candidate bar code areas;
defining the connectivity of the candidate image blocks as the candidate image blocks PiAnd candidate image block PjAdjacent to each other and having an average gradient direction of thetaiAnd thetajAnd if the condition is satisfied:
|θi-θj|＜εaor|θi-θj|＜π-εa (3)
then candidate image block PiAnd candidate image block PjAre interconnected, wherein epsilonaIs an angular deviation threshold;
a6, calculating the direction consistency of the candidate bar code area P according to the formula (4), and obtaining the direction consistency Coh (P) and the dimension Width (P) of the bar codei) And edge number Edges (P)i) Then, judging whether the candidate area is effective according to a formula (5);
where M is the total number of candidate image blocks in the barcode region;
wherein sigmacohThe setting range is 0.9-0.98, sigmawThe minimum recognizable length of the bar code is set to be 95-125, sigmaeThe threshold value of the number of edges is set within the range of 45-95.
3. The fast barcode image motion reduction method according to claim 1, wherein in the step B, a modified randon transformation method is adopted to extract the motion blur angle;
1) firstly, selecting 1 degree as a step length, calculating random transformation of a frequency spectrum on 0-180 degrees, and selecting an angle theta' corresponding to the maximum value of the random transformation;
2) calculating randon transformation on theta '-3-theta' +3 degrees by taking 0.5 degrees as step length, and solving the angle theta corresponding to the maximum value, namely solving the angle theta;
after the motion blur direction is obtained, the step of obtaining the blur length is as follows:
1) clockwise rotating the motion blurred image G by theta degrees to obtain G _ x;
2) separating the three primary colors R, G, B of the obtained image G _ x;
3) extracting the vertical central part of the motion blur for pixel value verification;
4) finding out the maximum pixel value in each longitudinal row, accumulating to obtain a one-dimensional matrix H, and then drawing a point line graph of H;
5) finding the first turning point on any side of the central lobe, wherein the pixel value of the turning point is the main lobe width (W) of the Fourier spectrumc)；
6) Respectively finding out widths of a second lobe, a third lobe and a fourth lobe on the left side and the right side of the central lobe according to the method, and respectively recording the widths as Wright1，Wright2，Wright3，Wleft1，Wleft2，Wleft3；
7) Screening each lobe, if the pixel difference between the width of the lobe and the width of any lobe is more than 3 pixel values, discarding the lobe, otherwise, keeping the lobe and considering the lobe as a fuzzy scale;
8) calculating the average lobe width of all reserved lobes;
for example, if all of the lobes remain, then,
9) the motion blur length can be obtained by dividing the width of the image by the average lobe width D;
thereby, a point spread function of the moving image can be calculated:
4. the quick barcode image motion subtraction method according to claim 1, wherein, as an optimization, in the step C, a spatial expression of a point spread function of motion blur is obtained according to a motion direction and a blur length, and then barcode image deblurring is performed by using wiener filtering;
the transfer function M (u, v) of the wiener filter is:
where H (u, v) is the frequency domain response of the blur kernel, Snn(u, v) is the frequency spectral density, S, corresponding to noiseff(u, v) is the frequency spectral density of the image;
the frequency response F of the restored image F obtained after wiener filtering is:
wherein G (u, v) is the frequency response of the blurred image;
1) carrying out Fourier transform on the blurred image to obtain G (u, v);
2) obtaining a two-dimensional Fourier transform H (u, v) according to the point spread function calculated by the formula (3);
3) calculating the spectral density S of the noisenn(u, v) and spectral density S of the imageffThe ratio K of (u, v);
4) calculating the frequency response of the restored image by a formula (5);
5) and obtaining a restored image by utilizing inverse Fourier transform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011621274.4A CN112785514A (en) | 2020-12-31 | 2020-12-31 | Rapid bar code image motion reduction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011621274.4A CN112785514A (en) | 2020-12-31 | 2020-12-31 | Rapid bar code image motion reduction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112785514A true CN112785514A (en) | 2021-05-11 |
Family
ID=75753312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011621274.4A Pending CN112785514A (en) | 2020-12-31 | 2020-12-31 | Rapid bar code image motion reduction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112785514A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331269A (en) * | 2022-10-13 | 2022-11-11 | 天津新视光技术有限公司 | Fingerprint identification method based on gradient vector field and application |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329725A (en) * | 2008-07-30 | 2008-12-24 | 电子科技大学 | Method for dividing fingerprint image based on gradient projection and morphology |
| CN102708552A (en) * | 2012-05-24 | 2012-10-03 | 中山大学 | Rapid two-dimensional barcode image motion deblurring method |
| CN104636706A (en) * | 2015-03-04 | 2015-05-20 | 深圳市金准生物医学工程有限公司 | Complicated background bar code image automatic partitioning method based on gradient direction consistency |
| CN104732217A (en) * | 2015-03-27 | 2015-06-24 | 电子科技大学 | Self-adaptive template size fingerprint direction field calculating method |
-
2020
- 2020-12-31 CN CN202011621274.4A patent/CN112785514A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329725A (en) * | 2008-07-30 | 2008-12-24 | 电子科技大学 | Method for dividing fingerprint image based on gradient projection and morphology |
| CN102708552A (en) * | 2012-05-24 | 2012-10-03 | 中山大学 | Rapid two-dimensional barcode image motion deblurring method |
| CN104636706A (en) * | 2015-03-04 | 2015-05-20 | 深圳市金准生物医学工程有限公司 | Complicated background bar code image automatic partitioning method based on gradient direction consistency |
| CN104732217A (en) * | 2015-03-27 | 2015-06-24 | 电子科技大学 | Self-adaptive template size fingerprint direction field calculating method |
Non-Patent Citations (2)
| Title |
|---|
| SHAMIK TIWARI，ET.AL: "Review of Motion Blur Estimation Techniques", 《JOURNAL OF IMAGE AND GRAPHICS》 * |
| 景晓军，等: "《图像处理技术及其应用》", 31 August 2005, 国防工业出版 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331269A (en) * | 2022-10-13 | 2022-11-11 | 天津新视光技术有限公司 | Fingerprint identification method based on gradient vector field and application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | Iterative filter adaptive network for single image defocus deblurring | |
| CN108765325B (en) | Small unmanned aerial vehicle blurred image restoration method | |
| Dauwe et al. | A fast non-local image denoising algorithm | |
| US8712114B2 (en) | Elegant solutions for fingerprint image enhancement | |
| US7751641B2 (en) | Method and system for digital image enhancement | |
| US7103234B2 (en) | Method for blind cross-spectral image registration | |
| Sada et al. | Image deblurring techniques—a detail review | |
| CN112580385B (en) | Bar code decoding method based on multi-frame image fusion and non-local mean filtering | |
| CN112200742A (en) | Filtering and denoising method applied to edge detection | |
| CN111696064B (en) | Image processing method, device, electronic equipment and computer readable medium | |
| CN112381742A (en) | Single image motion blur removing method and system | |
| CN108335268B (en) | Color image deblurring method based on blind deconvolution | |
| CN112785514A (en) | Rapid bar code image motion reduction method | |
| Basso et al. | Combining morphological filtering, anisotropic diffusion and block-based data replication for automatically detecting and recovering unscanned gaps in remote sensing images | |
| CN113012061A (en) | Noise reduction processing method and device and electronic equipment | |
| Robinson et al. | Gaussian blur identification using scale-space theory | |
| Zehtabian et al. | Adaptive restoration of multispectral datasets used for SVM classification | |
| CN115294035B (en) | Bright spot positioning method, bright spot positioning device, electronic equipment and storage medium | |
| Duran et al. | A Novel Framework for Nonlocal Vectorial Total Variation Based on ℓ p, q, r− norms | |
| CN114662519B (en) | QR code blind deblurring method based on position detection graph gradient and intensity prior | |
| Zhang et al. | A new image filtering method: Nonlocal image guided averaging | |
| Banerjee et al. | Bacterial foraging-fuzzy synergism based image Dehazing | |
| CN113436116A (en) | Night image deblurring method based on multi-standard light stripe selection in bipartite graph | |
| RU2405200C2 (en) | Method and device for fast noise filtration in digital images | |
| CN110728686B (en) | Voronoi-based vehicle-mounted lamp image segmentation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210511 |
|
| RJ01 | Rejection of invention patent application after publication |