CN104616257A - Recovery evidence obtaining method for blurred degraded digital images in administration of justice - Google Patents
Recovery evidence obtaining method for blurred degraded digital images in administration of justice Download PDFInfo
- Publication number
- CN104616257A CN104616257A CN201510037693.6A CN201510037693A CN104616257A CN 104616257 A CN104616257 A CN 104616257A CN 201510037693 A CN201510037693 A CN 201510037693A CN 104616257 A CN104616257 A CN 104616257A
- Authority
- CN
- China
- Prior art keywords
- image
- blurred
- motion
- blur
- images
- 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 56
- 238000011084 recovery Methods 0.000 title claims abstract description 12
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims abstract description 7
- 239000000654 additive Substances 0.000 claims description 10
- 230000000996 additive effect Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 230000015556 catabolic process Effects 0.000 claims description 5
- 238000006731 degradation reaction Methods 0.000 claims description 5
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 3
- 238000005352 clarification Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a recovery evidence obtaining method for blurred degraded digital images in administration of justice. The recovery evidence obtaining method comprises the following steps: a), judging motion or out-of-focus blur; b), performing sharp processing by adopting a FORMULA; c), judging whether blur limited by shooting conditions exists or not; d) performing sharp processing on blurred images; e), judging blurs at a low resolution; f) adopting a blur-removing and de-noising ultra-solution image reconstructing method to obtain an ultra-solution image of the burred images, and performing a step g); g), after image processing, obtaining images which are scientific and reasonable recovered images of original burred images. According to the recovery evidence obtaining method for blurred degraded digital images in administration of justice, image blurred caused by movement or out-of-focus blur and a bad shooting condition and image blur caused by low resolution can be eliminated, so that vivid recovery of the original burred images is scientifically and reasonably realized, image tamper behaviors do not exist, and powerful image guarantee is provided as the basis of administration of justice.
Description
Technical Field
The invention relates to a recovery and evidence-obtaining method of a blurred and degraded digital image in judicial works, in particular to a recovery and evidence-obtaining method of a blurred and degraded digital image in judicial works, which can effectively eliminate the image blurring caused by the bad motion, shooting environment and low resolution.
Background
Digital image content forensics techniques mainly determine the accuracy, integrity and originality of image content by analyzing the statistical properties of digital images. Various images are likely to be after one or more types of tampering, which, although not directly perceptible by human vision, inevitably alter certain data characteristics of the image. The key to digital image forensics is to use scientific and reasonable image processing means to detect the change of data characteristics caused by human tampering.
In judicial review, situations are often encountered in which the digital image provided is blurred and insufficient to provide full evidence of the content being attested, at which point it is necessary to restore the blurred and degraded image to be valid evidence in the judicial process. In summary, there are three main types of causes for image blur degradation: (1) firstly, the image is blurred due to the bad shooting environment (such as heavy rain, heavy fog, heavy snow or haze); (2) secondly, the image fineness is not enough due to the low resolution of the image acquisition equipment; (3) thirdly, image blurring due to relative motion between the image capturing apparatus and the capturing object.
For the first category, if the key objects in the image are blurred, the details of the image cannot be clearly observed, convincing useful information cannot be provided, and the image is not proved to be strong enough. In the second category, the digital images with low resolution can display limited details of the target of interest, and if the key objects in the images cannot be clearly displayed through scientific means, the images which originally include the effective proof content may be lost. In some cases, in order to make an originally clearly recognizable image lose its function as an evidence, the resolution of the image may be artificially reduced, so that the evidence of law violation or crime cannot be obtained. For the third kind of situations, since sudden shaking or fast movement occurs to the object or the image capturing device at the moment of capturing the digital image, a motion-blurred or out-of-focus-blurred digital image is generated, and the motion-blurred or out-of-focus-blurred image is cleared, which is also the key for digital image forensics.
Disclosure of Invention
The invention provides a recovery evidence-obtaining method of a fuzzy degraded digital image in judicial works in order to overcome the defects of the technical problems.
The recovery evidence obtaining method of the fuzzy degraded digital image in judicial works is characterized by comprising the following steps: a) judging motion blur or defocus blur, and for a blur degraded digital image to be clarified, firstly, artificially judging whether the motion blur or defocus blur exists, and if so, executing the step b); if not, executing step c); b) motion or defocus blur, for a digital image to be sharpened, using formula (1) to sharpen it:
（1）
for the original imageIs estimated by the above-mentioned method,as a function of the degradation of the image,additive noise for the image;andthe more accurate the acquisition is, the more accurate,the closer to；Determining the fuzzy motion direction and the motion length; carrying out sharpening processing on the image by using the acquired blurred motion direction and length, and removing additive noise of the blurred image to acquire a sharp image; performing step c); c) judgment ofJudging whether the image to be clarified has the image blur caused by poor shooting conditions or not, and if so, executing the step d); if not, executing step e); d) sharpening the blurred image by setting the pixel points in the image to be processedR, G, B values of、、The value ranges of R, G, B values of all the pixel points in the image are respectively、、，0≤≤255，0≤≤255，0≤255, and performing clarification treatment by using a formula (2):
（2）
using derived、、Value replacement pixel pointThe value of R, G, B, the graph can be clearly processed; wherein,，，(ii) a Performing step e); e) judging whether the image is blurred due to low resolution, and if not, executing the step g); if so, performing step f); f) sharpening the low-resolution image by: f-1), obtaining a plurality of low-resolution images, and if the image to be clarified is a video frame image, obtaining a plurality of low-resolution images with consistent pictures through processing the video frame; if the image to be clarified is a single digital image, acquiring a plurality of low-resolution images with consistent pictures by adopting an interpolation method; setting the number of the acquired low-resolution images to be N; f-2), performing super-resolution reconstruction on the images, and acquiring super-resolution images of the blurred images by adopting a deblurring and noise reduction super-resolution image reconstruction method according to the N low-resolution images acquired in the step f-1); performing step g); g) after the graph processing is finished, the restoring processing of the fuzzy degraded digital graph is finished, the image blurring caused by the motion or defocusing blurring and poor shooting conditions and the image blurring caused by low resolution can be eliminated, and the finally obtained image is an original blurred imageThe displayed detail content of the image can be used as evidence.
The invention relates to a recovering and evidence-obtaining method of a fuzzy degraded digital image in judicial science, wherein the process of sharpening the motion or defocus blur in the step b) is realized by the following steps: b-1), estimating the motion direction of the blurred image by adopting the motion blur direction based on a rotation difference operator, and performing linear convolution operation on the difference operator and the blurred image by adopting a formula (3) to realize the difference operation on the blurred image:
（3）
wherein,which represents the original blurred image, is,a directional difference operator is represented as a function of,representing a difference result acted by a difference operator; b-2) determination of the direction of movementAccording to=Are sequentially changed and the correspondingAnd each is obtained according to the formula (4)Sum of absolute values of medium pixels:
（4）
during the operation, if inequality (5) is satisfiedIt appears that the user has, at the time of the day,
（5）
then makeThe angle value with the minimum value is the motion direction of the blurred image, and the motion direction is set as(ii) a b-3), solving motion blur parameters, and estimating the motion length of the motion blur image by adopting a blurred image point spread function parameter estimation method;
the motion blur parameter is obtained by adopting the formula (6)：
（6）
As the initial modulus motion parameter(s),for step size of motion, D is searchTimes of 1 or lessD is less than or equal to D; b-4) obtaining the blurred image again, using the blur parametersFor the original blurred imageThe blurring process results in a blurred image again，The calculation is performed by equation (7):
（7）
b-5) determination of the length of the fuzzy motion, calculating the errorTo makeHaving a minimum valueI.e. the blur motion step.
The invention relates to a method for recovering and evidence-obtaining a fuzzy degraded digital image in judicial science, wherein additive noise is added in step b)The removal of (2) is realized by a mean filtering method, a median filtering method or a frequency domain low-pass filtering method.
The invention relates to the recovery and fetching of fuzzy degraded digital image in judicial practiceThe method comprises the step d), if the acquired image is a gray value image, setting pixel pointsHas a gray value ofThe gray value range of all pixels in the image is,0≤Less than or equal to 255; the sharpening process of the blurred image is implemented by equation (8):
（8）
using derivedValue replacement pixel pointIs/are as followsThe figure can be clearly processed; wherein,。
the invention has the beneficial effects that: the method for recovering and evidence-obtaining the blurred and degraded digital image in judicial works is to pass the degradation function under the condition that the original blurred image has motion or defocusing blurAdditive noiseThe maximum estimation of the original image is realized, so that the restoration of the image is realized to the maximum extent; when the blurred image has image blurring caused by bad shooting environment, such as an image acquired under the conditions of heavy rain, heavy fog or heavy snow weather, a clear image is acquired by adopting a pixel value expansion method; when the blurred image is blurred due to low resolution, a super-resolution image reconstruction method is adopted to acquire the super-resolution image of the blurred image, the acquired image is a scientific and reasonable restored image of the original blurred image, and displayed detail content can be used as evidence.
The method for recovering and evidence-obtaining the blurred and degraded digital image in the judicial works can eliminate the image blurring caused by the motion or defocusing blurring, the image blurring caused by the bad shooting conditions and the low resolution, scientifically and reasonably realize the vivid restoration of the original blurred image, has no image tampering behaviors, and provides powerful guarantee for the image as the judicial basis.
Drawings
FIG. 1 is a flow chart of an in-jurisdictional restoration forensic method for a blurred, degraded digital image in accordance with the present invention;
FIG. 2 is an original blurred image in the present invention;
FIG. 3 is an image of an original blurred image after motion blur sharpening processing in the present invention;
FIG. 4 is the image of FIG. 3 after pixel equalization;
fig. 5 is an image of the image in fig. 4 after the super-resolution image reconstruction processing.
Detailed Description
The invention is further described with reference to the following figures and examples.
As shown in fig. 1, a flow chart of the recovering and evidence obtaining method of the fuzzy degraded digital image in judicial law is given, which is realized by the following method:
a) judging motion blur or defocus blur, and for a blur degraded digital image to be clarified, firstly, artificially judging whether the motion blur or defocus blur exists, and if so, executing the step b); if not, executing step c);
as shown in fig. 2, an original blurred image is given, and the blurred image shown has not only motion blur but also image blur due to poor shooting environment and image blur due to low resolution. Due to the blurring of the original image, the license plate number in the monitoring picture cannot be obtained at all.
b) Motion or defocus blur, for a digital image to be sharpened, using formula (1) to sharpen it:
（1）
for the original imageIs estimated by the above-mentioned method,as a function of the degradation of the image,additive noise for the image;andthe more accurate the acquisition is, the more accurate,the closer to；Determining the fuzzy motion direction and the motion length;
carrying out sharpening processing on the image by using the acquired blurred motion direction and length, and removing additive noise of the blurred image to acquire a sharp image; performing step c);
in this step, the motion or defocus blur sharpening process is implemented by the following steps:
b-1), estimating the motion direction of the blurred image by adopting the motion blur direction based on a rotation difference operator, and performing linear convolution operation on the difference operator and the blurred image by adopting a formula (3) to realize the difference operation on the blurred image:
（3）
wherein,which represents the original blurred image, is,a directional difference operator is represented as a function of,representing a difference result acted by a difference operator;
b-2) determination of the direction of movementAccording to=Are sequentially changed and the correspondingAnd each is obtained according to the formula (4)Sum of absolute values of medium pixels:
（4）
during the operation, if inequality (5) is satisfiedIt appears that the user has, at the time of the day,
（5）
then makeThe angle value with the minimum value is the motion direction of the blurred image, and the motion direction is set as；
b-3), solving motion blur parameters, and estimating the motion length of the motion blur image by adopting a blurred image point spread function parameter estimation method;
the motion blur parameter is obtained by adopting the formula (6)：
（6）
As the initial modulus motion parameter(s),the motion step length is adopted, D is the search frequency, and 1 is less than or equal to≤D；
b-4) obtaining the blurred image again, using the blur parametersFor the original blurred imageThe blurring process results in a blurred image again，The calculation is performed by equation (7):
（7）
b-5) determination of the length of the fuzzy motion, calculating the errorTo makeHaving a minimum valueI.e. the blur motion step.
In this step, additive noiseThe removal of (2) is realized by a mean filtering method, a median filtering method or a frequency domain low-pass filtering method.
As shown in fig. 3, the image processed in step b) is shown, so that the motion blur of the image is eliminated after the processing in step b), but the acquired image is blurred due to bad shooting conditions, and the license plate number cannot be identified.
c) Judging whether the image to be clarified has image blurring caused by poor shooting conditions or not, and if so, executing the step d); if not, executing step e);
d) sharpening the blurred image by setting the pixel points in the image to be processedR, G, B values of、、The value ranges of R, G, B values of all the pixel points in the image are respectively、、，0≤≤255，0≤≤255，0≤255, and performing clarification treatment by using a formula (2):
（2）
using derived、、Value replacement pixel pointThe value of R, G, B, the graph can be clearly processed; wherein,，，(ii) a Performing step e);
if the obtained image is a gray value image, setting pixel pointsHas a gray value ofThe gray value range of all pixels in the image is,0≤Less than or equal to 255; the sharpening process of the blurred image is implemented by equation (8):
（8）
using derivedValue replacement pixel pointIs/are as followsThe figure can be clearly processed; wherein,。
as shown in fig. 4, the image of fig. 3 is obtained after the pixel equalization processing, and compared with the monitoring picture of fig. 3, the image of fig. 4 has no motion and no image blur caused by bad shooting environment, but the resolution of the image itself is low, and the license plate number cannot be obtained.
e) Judging whether the image is blurred due to low resolution, and if not, executing the step g); if so, performing step f);
f) sharpening the low-resolution image by:
f-1), obtaining a plurality of low-resolution images, and if the image to be clarified is a video frame image, obtaining a plurality of low-resolution images with consistent pictures through processing the video frame; if the image to be clarified is a single digital image, acquiring a plurality of low-resolution images with consistent pictures by adopting an interpolation method; setting the number of the acquired low-resolution images to be N;
f-2), performing super-resolution reconstruction on the images, and acquiring super-resolution images of the blurred images by adopting a deblurring and noise reduction super-resolution image reconstruction method according to the N low-resolution images acquired in the step f-1); performing step g);
as shown in fig. 5, the image obtained by reconstructing the super-resolution image from the image in fig. 4 is given, and the license plate number in the monitoring picture is clear and distinguishable because the motion blur, the shooting environment harsh blur, and the low resolution blur of the original image are eliminated.
g) After the image processing is finished, the restoration processing of the fuzzy degraded digital image is finished, the image blurring caused by motion or defocusing blurring and poor shooting conditions and the image blurring caused by low resolution can be eliminated, the finally obtained image is a scientific and reasonable restored image of the original blurred image, and the displayed detail content can be used as evidence.
Claims (4)
1. A recovery evidence obtaining method of a fuzzy degraded digital image in judicial law is characterized by comprising the following steps:
a) judging motion blur or defocus blur, and for a blur degraded digital image to be clarified, firstly, artificially judging whether the motion blur or defocus blur exists, and if so, executing the step b); if not, executing step c);
b) motion or defocus blur, for a digital image to be sharpened, using formula (1) to sharpen it:
（1）
for the original imageIs estimated by the above-mentioned method,as a function of the degradation of the image,additive noise for the image;andthe more accurate the acquisition is, the more accurate,the closer to；Determining the fuzzy motion direction and the motion length;
carrying out sharpening processing on the image by using the acquired blurred motion direction and length, and removing additive noise of the blurred image to acquire a sharp image; performing step c);
c) judging whether the image to be clarified has image blurring caused by poor shooting conditions or not, and if so, executing the step d); if not, executing step e);
d) sharpening the blurred image by setting the pixel points in the image to be processedR, G, B values of、、The value ranges of R, G, B values of all the pixel points in the image are respectively、、，0≤≤255，0≤≤255，0≤255, and performing clarification treatment by using a formula (2):
（2）
using derived、、Value replacement pixel pointThe value of R, G, B, the graph can be clearly processed; wherein,，，(ii) a Performing step e);
e) judging whether the image is blurred due to low resolution, and if not, executing the step g); if so, performing step f);
f) sharpening the low-resolution image by:
f-1), obtaining a plurality of low-resolution images, and if the image to be clarified is a video frame image, obtaining a plurality of low-resolution images with consistent pictures through processing the video frame; if the image to be clarified is a single digital image, acquiring a plurality of low-resolution images with consistent pictures by adopting an interpolation method; setting the number of the acquired low-resolution images to be N;
f-2), performing super-resolution reconstruction on the images, and acquiring super-resolution images of the blurred images by adopting a deblurring and noise reduction super-resolution image reconstruction method according to the N low-resolution images acquired in the step f-1); performing step g);
g) after the image processing is finished, the restoration processing of the fuzzy degraded digital image is finished, the image blurring caused by motion or defocusing blurring and poor shooting conditions and the image blurring caused by low resolution can be eliminated, the finally obtained image is a scientific and reasonable restored image of the original blurred image, and the displayed detail content can be used as evidence.
2. The in-judicial restoration forensic method of blurred, degraded digital images as defined in claim 1, wherein: the motion or defocus blur sharpening process described in step b) is implemented by the following steps:
b-1), estimating the motion direction of the blurred image by adopting the motion blur direction based on a rotation difference operator, and performing linear convolution operation on the difference operator and the blurred image by adopting a formula (3) to realize the difference operation on the blurred image:
（3）
wherein,which represents the original blurred image, is,a directional difference operator is represented as a function of,representing a difference result acted by a difference operator;
b-2) determination of the direction of movementAccording to=Are sequentially changed and the correspondingAnd each is obtained according to the formula (4)Sum of absolute values of medium pixels:
（4）
during the operation, if inequality (5) is satisfiedIt appears that the user has, at the time of the day,
（5）
then makeThe angle value with the minimum value is the motion direction of the blurred image, and the motion direction is set as；
b-3), solving motion blur parameters, and estimating the motion length of the motion blur image by adopting a blurred image point spread function parameter estimation method;
the motion blur parameter is obtained by adopting the formula (6)：
（6）
As the initial modulus motion parameter(s),the motion step length is adopted, D is the search frequency, and 1 is less than or equal to≤D；
b-4) obtaining the blurred image again, using the blur parametersFor the original blurred imageThe blurring process results in a blurred image again，The calculation is performed by equation (7):
（7）
b-5) determination of the length of the fuzzy motion, calculating the errorTo makeHaving a minimum valueI.e. the blur motion step.
3. The in-judicial restoration forensic method of blurred, degraded digital images as claimed in claim 1 or claim 2, wherein: additive noise in step b)The removal of (2) is realized by a mean filtering method, a median filtering method or a frequency domain low-pass filtering method.
4. The in-judicial restoration forensic method of blurred, degraded digital images as claimed in claim 1 or claim 2, wherein: in step d), if the acquired image is a gray value image, setting pixel pointsHas a gray value ofThe gray value range of all pixels in the image is,0≤Less than or equal to 255; the sharpening process of the blurred image is implemented by equation (8):
（8）
using derivedValue replacement pixel pointIs/are as followsThe figure can be clearly processed; wherein,。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510037693.6A CN104616257A (en) | 2015-01-26 | 2015-01-26 | Recovery evidence obtaining method for blurred degraded digital images in administration of justice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510037693.6A CN104616257A (en) | 2015-01-26 | 2015-01-26 | Recovery evidence obtaining method for blurred degraded digital images in administration of justice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104616257A true CN104616257A (en) | 2015-05-13 |
Family
ID=53150690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510037693.6A Pending CN104616257A (en) | 2015-01-26 | 2015-01-26 | Recovery evidence obtaining method for blurred degraded digital images in administration of justice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104616257A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913392A (en) * | 2016-04-08 | 2016-08-31 | 西安电子科技大学昆山创新研究院 | Degraded image overall quality improving method in complex environment |
| CN106097267A (en) * | 2016-06-08 | 2016-11-09 | 浙江传媒学院 | A kind of image deblurring method based on Fourier transformation |
| CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
| CN110264415A (en) * | 2019-05-24 | 2019-09-20 | 北京爱诺斯科技有限公司 | It is a kind of to eliminate the fuzzy image processing method of shake |
| CN112652000A (en) * | 2020-12-30 | 2021-04-13 | 南京航空航天大学 | Method for judging small-scale motion direction of image |
| CN112700386A (en) * | 2020-12-30 | 2021-04-23 | 江苏奥格视特信息科技有限公司 | Fuzzy image ultrahigh-definition transformation method and system based on artificial intelligence |
| CN113014822A (en) * | 2021-03-24 | 2021-06-22 | 深圳市蔚来芯科技有限公司 | Image enhancement processing system and method based on camera image processing chip |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079149A (en) * | 2006-09-08 | 2007-11-28 | 浙江师范大学 | Noise-possessing movement fuzzy image restoration method based on radial basis nerve network |
| US20080232707A1 (en) * | 2007-03-23 | 2008-09-25 | Industrial Technology Research Institute | Motion blurred image restoring method |
| CN101441765A (en) * | 2008-11-19 | 2009-05-27 | 西安电子科技大学 | Self-adapting regular super resolution image reconstruction method for maintaining edge clear |
| CN101968881A (en) * | 2010-10-27 | 2011-02-09 | 东南大学 | Motion blurring and defocusing composite blurring image restoration method |
| CN102170526A (en) * | 2011-03-22 | 2011-08-31 | 公安部第三研究所 | Method for calculation of defocus fuzzy core and sharp processing of defocus fuzzy image of defocus fuzzy core |
| CN102236887A (en) * | 2011-03-11 | 2011-11-09 | 贵州大学 | Motion-blurred image restoration method based on rotary difference and weighted total variation |
-
2015
- 2015-01-26 CN CN201510037693.6A patent/CN104616257A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079149A (en) * | 2006-09-08 | 2007-11-28 | 浙江师范大学 | Noise-possessing movement fuzzy image restoration method based on radial basis nerve network |
| US20080232707A1 (en) * | 2007-03-23 | 2008-09-25 | Industrial Technology Research Institute | Motion blurred image restoring method |
| CN101441765A (en) * | 2008-11-19 | 2009-05-27 | 西安电子科技大学 | Self-adapting regular super resolution image reconstruction method for maintaining edge clear |
| CN101968881A (en) * | 2010-10-27 | 2011-02-09 | 东南大学 | Motion blurring and defocusing composite blurring image restoration method |
| CN102236887A (en) * | 2011-03-11 | 2011-11-09 | 贵州大学 | Motion-blurred image restoration method based on rotary difference and weighted total variation |
| CN102170526A (en) * | 2011-03-22 | 2011-08-31 | 公安部第三研究所 | Method for calculation of defocus fuzzy core and sharp processing of defocus fuzzy image of defocus fuzzy core |
Non-Patent Citations (4)
| Title |
|---|
| 方永选等: "《模糊图像处理技术在刑事侦查中的应用》", 《中国公共安全 学术版》 * |
| 杨洪臣等: "《模糊图像处理技术概述》", 《警察技术》 * |
| 武彬: "《一种有效的图像复原方法》", 《图像分析》 * |
| 计岑: "《一种低分辨率散焦模糊图像的超分辨率重建复原方法》", 《广播电视信息》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913392A (en) * | 2016-04-08 | 2016-08-31 | 西安电子科技大学昆山创新研究院 | Degraded image overall quality improving method in complex environment |
| CN106097267A (en) * | 2016-06-08 | 2016-11-09 | 浙江传媒学院 | A kind of image deblurring method based on Fourier transformation |
| CN106097267B (en) * | 2016-06-08 | 2019-04-02 | 浙江传媒学院 | A kind of image deblurring method based on Fourier transformation |
| CN108961186A (en) * | 2018-06-29 | 2018-12-07 | 赵岩 | A kind of old film reparation recasting method based on deep learning |
| CN108961186B (en) * | 2018-06-29 | 2022-02-15 | 福建帝视信息科技有限公司 | Old film repairing and reproducing method based on deep learning |
| CN110264415A (en) * | 2019-05-24 | 2019-09-20 | 北京爱诺斯科技有限公司 | It is a kind of to eliminate the fuzzy image processing method of shake |
| CN112652000A (en) * | 2020-12-30 | 2021-04-13 | 南京航空航天大学 | Method for judging small-scale motion direction of image |
| CN112700386A (en) * | 2020-12-30 | 2021-04-23 | 江苏奥格视特信息科技有限公司 | Fuzzy image ultrahigh-definition transformation method and system based on artificial intelligence |
| CN112652000B (en) * | 2020-12-30 | 2024-05-24 | 南京航空航天大学 | Method for judging small-scale movement direction of image |
| CN113014822A (en) * | 2021-03-24 | 2021-06-22 | 深圳市蔚来芯科技有限公司 | Image enhancement processing system and method based on camera image processing chip |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104616257A (en) | Recovery evidence obtaining method for blurred degraded digital images in administration of justice | |
| CN102147915B (en) | Method for restoring weighting sparse edge regularization image | |
| CN111275626A (en) | Video deblurring method, device and equipment based on ambiguity | |
| Ramya et al. | Restoration of blurred images using Blind Deconvolution Algorithm | |
| KR101684990B1 (en) | Method for deblurring vehicle image using sigma variation of Bilateral Filter | |
| CN112862753B (en) | Noise intensity estimation method and device and electronic equipment | |
| Mishra et al. | Digital image restoration using image filtering techniques | |
| CN108122209B (en) | License plate deblurring method based on countermeasure generation network | |
| US20080025628A1 (en) | Enhancement of Blurred Image Portions | |
| Jain et al. | A comparative study of various image restoration techniques with different types of blur | |
| CN110111392B (en) | High-resolution optical imaging method based on nanoparticle calibration | |
| CN105741255A (en) | Image fusion method and device | |
| El Abbadi et al. | Improve image de-blurring | |
| Bhagat et al. | Novel Approach to Estimate Motion Blur Kernel Parameters and Comparative Study of Restoration Techniques | |
| Abinaya et al. | Rectify the blurred license plate image from fast moving vehicles using morphological process | |
| He et al. | Joint motion deblurring and superresolution from single blurry image | |
| Patil et al. | Implementation of restoration of blurred image using blind deconvolution algorithm | |
| Selvi et al. | Dehazing of natural images using non-linear wavelet filter | |
| Ansari et al. | A Survey on Blurred Images with Restoration and Transformation Techniques | |
| Kazi et al. | Image Restoration using Blind Deconvolution | |
| Jain et al. | PURPOSE OF BLIND DE-CONVOLUTION ALGORITHM FOR IMAGE RESTORATION | |
| Dong et al. | Analysis and Comparison of Image Restoration Methods | |
| ChaoFeng et al. | Research on fuzzy image enhancement and restoration effect | |
| Sreenivasulu et al. | Classification of unsharp pixels using Gaussian scale mixture (GSM) model | |
| Hridya et al. | Pre-Denoising, Deblurring and Ringing Artifacts Removal of Natural, Text and Grayscale Images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150513 |
|
| RJ01 | Rejection of invention patent application after publication |