CN105260986A - Anti-fuzzy image amplification method - Google Patents
Anti-fuzzy image amplification method Download PDFInfo
- Publication number
- CN105260986A CN105260986A CN201510669656.7A CN201510669656A CN105260986A CN 105260986 A CN105260986 A CN 105260986A CN 201510669656 A CN201510669656 A CN 201510669656A CN 105260986 A CN105260986 A CN 105260986A
- Authority
- CN
- China
- Prior art keywords
- image
- sharpening
- input picture
- interpolation
- amplification
- 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 title claims abstract description 42
- 230000003321 amplification Effects 0.000 title claims abstract description 26
- 238000003199 nucleic acid amplification method Methods 0.000 title claims abstract description 26
- 238000001914 filtration Methods 0.000 claims description 5
- 241000233855 Orchidaceae Species 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000009452 underexpressoin Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 238000003707 image sharpening Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001235689 Hemifusus ternatanus Species 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 239000007799 cork Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4084—Scaling of whole images or parts thereof, e.g. expanding or contracting in the transform domain, e.g. fast Fourier transform [FFT] domain scaling
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20172—Image enhancement details
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The invention discloses an anti-fuzzy image amplification method which comprises the steps of acquiring an evaluating index for an image fuzzy degree according to the gradient of an input image, calculating an image sharpening intensity parameter according to an amplification factor and an image resolution, and performing sharpening which corresponds with the quality grade of an input image through control of the parameter; and furthermore decomposing an overall amplifying process of the image into a plurality of small-factor step-by-step amplifications, and amplifying the width and the height of the image by 1.2 times according to a common interpolation method until the a total amplification factor requirement is satisfied. The anti-fuzzy image amplification method has advantages of effectively eliminating an inherent fuzzy effect of an interpolation method and remarkably improving definition of an amplified image under a precondition that computing complexity is not remarkably increased.
Description
Technical field
The invention belongs to technical field of image processing, relate to a kind of image interpolate enlarge method, be specifically related to a kind of image magnification method of anti.
Technical background
Current, digital camera or camera can take high-resolution video like a cork, but for saving the consideration of storage or transmission cost, still there is a large amount of low resolution video content in application scenarios such as video monitoring, video conference and Web TVs.Thus video amplifier technology is widely used in the spatial resolution promoting image, to adapt to the requirement in screen actual displayed region.Some special application, such as video monitoring, also relate to and amplify so that the detail content of energy recognisable image image local area.
A large amount of video image zooming technology is grown up, from being simply interpolated into complicated image super-resolution.Although image super-resolution technology can obtain amplification effect more clearly, computational complexity remains high; More inconvenient, image super-resolution generally all wants prior training sample database, lacks universality and operability in actual applications.Therefore, the Nonlinear magnify technology adopted in current Video Applications software or media player mainly based on simply, interpolation method fast, such as bilinear interpolation (Bilinear), bi-cubic interpolation (Bicubic), orchid be interpolation (Lanczos) etc. hereby.But, the interpolation amplification method defect that also existence one is serious simultaneously of these classics, when original image sharpness not high (such as through the image of overcompression) or enlargement factor is excessive time, there is obvious blurring effect in the image after interpolation amplification, affects the subjective experience of beholder.
Space sharpening filter is a kind of Hi-pass filter, can strengthen the high fdrequency component of digital picture, just contrary with the low-pass effect of filtering interpolation.Therefore, if assigned a sharpening operation before image interpolate enlarge, likely the blurring effect brought of interpolation will be offset to a certain extent.In addition, the multiple that image single amplifies is got over Gao Yueyi and is caused fuzzy, and on the contrary, enlargement factor is lower fuzzy lighter.Therefore, if high multiple amplification process to be converted to the amplification step by step of several low multiples, the lifting of enlarged image quality will be contributed to.Based on these two angles, the present invention proposes a kind of image magnification method of anti.
Summary of the invention
In order to solve the problems of the technologies described above, image sharpening computing and interpolation arithmetic are cascaded into an entirety by the present invention, strengthened the profile details of image by sharpening pre-service, be the signal source that interpolation arithmetic contribution radio-frequency component promotes, thus eliminate the low pass blurring effect impact of Interpolation Process.
The technical solution adopted in the present invention is: a kind of image magnification method of anti, is characterized in that, comprises the following steps:
Step 1: adopt the Gradient Features of image to weigh image blurring degree, the blur level index of calculating input image;
Step 2: blur level index, overall magnification, image resolution ratio three key elements of comprehensive input picture, the sharpening intensities parameter of calculating input image;
Step 3: according to the sharpening intensities constant calculated, calls sharpening algorithm and carries out sharpening to input picture;
Step 4: be the amplification step by step that the amplifieroperation of R is decomposed into several little multiplying powers by overall magnification, determine the execution frequency n of amplifying step by step;
Step 5: perform n interpolation amplification computing step by step.
As preferably, the calculating of the blur level index described in step 1, adopt with the following method:
Blur level index Fb is defined as the gradient of energy normalized:
Wherein, Gx, Gy represent horizontal and vertical gradient map respectively, are asked for by Sobel, Roberts or Prewitt gradient operator; E is the energy of input picture, calculates with input image pixels I
" .* " representing matrix dot-product operation.
As preferably, the calculating of the sharpening intensities parameter lambda described in step 2, adopt with the following method:
Wherein, Fb is blur level index, and R is overall magnification, and S is the area of input picture, equals long and takes advantage of height, S
cifthe constant be one being benchmark with CIF format-pattern area.
As preferably, the sharpening operation described in step 3, be the high-pass filtered version of input picture be added to after adjustment on original input picture, computing formula is:
y(n,m)=x(n,m)+λz(n,m);
Here, x, y represent the input picture after original input picture and sharpening respectively, and z represents the input picture after high-pass filtering, and obtain by two-dimentional Laplacian differentiating operator, λ is sharpening intensities parameter.
As preferably, the execution frequency n that the determination described in step 4 is amplified step by step, adopts following rule:
At every turn by the width of image and highly amplification 1.2 times, if overall magnification is R, then amplification 1.2 times at every turn, gradual magnification are calculated as to the execution frequency n of R times
symbol
round under expression.
As preferably, n the interpolation amplification computing step by step of the execution described in step 5, its interpolation method includes but not limited to bilinear interpolation, bi-cubic interpolation method, orchid hereby method of interpolation.
Compared with existing Nonlinear magnify scheme, the present invention has the following advantages and good effect:
(1) the present invention applies a sharpening pre-service before simple interpolation method, under the prerequisite of not obvious increase computational complexity, effectively eliminates the blurring effect that interpolation method is intrinsic, significantly improves the sharpness of enlarged image;
(2) compared with the super-resolution scheme of complexity, the inventive method does not involve sample image training, and have and realize simply, treatment effeciency is high, the advantage that universality is strong;
(3) the inventive method based on sharpening algorithm and interpolation algorithm all from mature technology, be convenient to assemble existing module integration and realize.
Accompanying drawing explanation
Fig. 1: the processing flow chart of the embodiment of the present invention;
Fig. 2: the amplification effect comparative examples figure of the embodiment of the present invention, wherein (a) is for original image is through common double Linear Amplifer 4 times of design sketchs, b () amplifies 4 times of design sketchs through method of the present invention for original image, c (), for decoded picture is through common double Linear Amplifer 4 times of design sketchs, (d) amplifies 4 times of design sketchs through method of the present invention for decoded picture.
Embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, below in conjunction with drawings and Examples, the present invention is described in further detail, should be appreciated that exemplifying embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
The image magnification method of a kind of anti provided by the invention, is cascaded into an entirety by image sharpening computing and interpolation arithmetic.The intensity of sharpening operation should adapt with input picture sole mass, image should weak sharpening clearly, and fuzzy image should sharpening by force, otherwise, sharpening not only can not provide radio-frequency component to strengthen pretreatment image for follow-up interpolation operation, on the contrary can damage image, reduction eye fidelity.Cause image blurring factor from many aspects, the motion blur that the relative motion as target and video camera produces, camera lens defocuses, atmospheric scattering, the filterings such as compression of images, noise reduction and resampling, etc.These processes cause image detail to lose bar none and weaken object edge profile gradients, and therefore, adopt the fog-level of the Gradient Features picture engraving of image, the gradient map of picture rich in detail is sharp keen, and the gradient map of blurred picture is smooth.
Image Sharpening Algorithm uses a sharpening intensities state modulator sharpness usually, input picture is applied to the sharpening of much degree is minimum should consider three factors.First, be also the fog-level that the most important thing is image, available blur level index is weighed; Next is the enlargement factor of image, and enlargement factor is more high more easily causes Low-pass interpolation blurring effect, correspondingly should perform stronger sharpening to compensate the blurring effect of amplification; Be finally the resolution of input picture self, the Hemifusus ternatanus degree of the image that resolution is lower is poorer, more needs to strengthen details by sharpening.
Based on above consideration, the complete treatment scheme of the inventive method as shown in Figure 1, comprises following steps:
Step 1: adopt the Gradient Features of image to weigh image blurring degree, the blur level index of calculating input image;
The impact of integrating image intensity, is defined as the gradient of energy normalized by blur level index Fb
Here, Gx, Gy represent horizontal and vertical gradient map respectively, and the gradient operator classical by Sobel, Roberts, Prewitt etc. is asked for, and E is the energy of input picture, calculates with input image pixels I
" .* " representing matrix dot-product operation.
Step 2: blur level index, overall magnification, image resolution ratio three key elements of comprehensive input picture, the sharpening intensities parameter of calculating input image;
In conjunction with empirical data, the calculating of sharpening intensities parameter lambda, adopt with the following method:
Wherein, Fb is blur level index, and R is overall magnification, and S is the area of input picture, equals long and takes advantage of height, S
cifthe constant be one being benchmark with CIF format-pattern area (352x288).
Step 3: according to the sharpening intensities constant calculated, calls sharpening algorithm and carries out sharpening to input picture;
The sharpening algorithm that the present invention adopts is that the high-pass filtered version of input picture image be added to after adjustment on original input picture image, computing formula is
y(n,m)=x(n,m)+λz(n,m);
Here, x, y represent the input picture image after original input picture image and sharpening respectively, and z represents the input picture image after high-pass filtering, and obtain by two-dimentional Laplacian differentiating operator, λ is sharpening intensities parameter.
Step 4: be the amplification step by step that the amplifieroperation of R is decomposed into several little multiplying powers by overall magnification, determine the execution frequency n of amplifying step by step;
At every turn by the width of image and highly amplification 1.2 times, if overall magnification is R, then amplification 1.2 times at every turn, gradual magnification are calculated as to the execution frequency n of R times
symbol
round under expression.
Step 5: perform n interpolation arithmetic step by step, alternative interpolation method includes but not limited to bilinear interpolation, bi-cubic interpolation, orchid hereby interpolation.
Should be understood that, the part that this instructions does not elaborate all belongs to prior art.
Should be understood that; the above-mentioned description for preferred embodiment is comparatively detailed; therefore the restriction to scope of patent protection of the present invention can not be thought; those of ordinary skill in the art is under enlightenment of the present invention; do not departing under the ambit that the claims in the present invention protect; can also make and replacing or distortion, all fall within protection scope of the present invention, request protection domain of the present invention should be as the criterion with claims.
Claims (6)
1. an image magnification method for anti, is characterized in that, comprises the following steps:
Step 1: adopt the Gradient Features of image to weigh image blurring degree, the blur level index of calculating input image;
Step 2: blur level index, overall magnification, image resolution ratio three key elements of comprehensive input picture, the sharpening intensities parameter of calculating input image;
Step 3: according to the sharpening intensities constant calculated, calls sharpening algorithm and carries out sharpening to input picture;
Step 4: be the amplification step by step that the amplifieroperation of R is decomposed into several little multiplying powers by overall magnification, determine the execution frequency n of amplifying step by step;
Step 5: perform n interpolation amplification computing step by step.
2. the image magnification method of anti according to claim 1, is characterized in that: the calculating of the blur level index described in step 1, adopts with the following method:
Blur level index Fb is defined as the gradient of energy normalized:
Wherein, Gx, Gy represent horizontal and vertical gradient map respectively, are asked for by Sobel, Roberts or Prewitt gradient operator; E is the energy of input picture, calculates with input image pixels I
" .* " representing matrix dot-product operation.
3. the image magnification method of anti according to claim 1, is characterized in that: the calculating of the sharpening intensities parameter lambda described in step 2, adopts with the following method:
Wherein, Fb is blur level index, and R is overall magnification, and S is the area of input picture, equals long and takes advantage of height, S
cifthe constant be one being benchmark with CIF format-pattern area.
4. the image magnification method of anti according to claim 1, is characterized in that: the sharpening operation described in step 3, is the high-pass filtered version of input picture to be added to after adjustment on original input picture, and computing formula is:
y(n,m)=x(n,m)+λz(n,m);
Here, x, y represent the input picture after original input picture and sharpening respectively, and z represents the input picture after high-pass filtering, and obtain by two-dimentional Laplacian differentiating operator, λ is sharpening intensities parameter.
5. the image magnification method of anti according to claim 1, is characterized in that: the execution frequency n that the determination described in step 4 is amplified step by step, adopts following rule:
At every turn by the width of image and highly amplification 1.2 times, if overall magnification is R, then amplification 1.2 times at every turn, gradual magnification are calculated as to the execution frequency n of R times
symbol
round under expression.
6. the image magnification method of anti according to claim 1, is characterized in that: n the interpolation amplification computing step by step of the execution described in step 5, and its interpolation method includes but not limited to bilinear interpolation, bi-cubic interpolation method, orchid hereby method of interpolation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510669656.7A CN105260986B (en) | 2015-10-13 | 2015-10-13 | A kind of image magnification method of anti |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510669656.7A CN105260986B (en) | 2015-10-13 | 2015-10-13 | A kind of image magnification method of anti |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105260986A true CN105260986A (en) | 2016-01-20 |
CN105260986B CN105260986B (en) | 2018-06-29 |
Family
ID=55100661
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510669656.7A Active CN105260986B (en) | 2015-10-13 | 2015-10-13 | A kind of image magnification method of anti |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105260986B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106709873A (en) * | 2016-11-11 | 2017-05-24 | 浙江师范大学 | Super-resolution method based on cubic spline interpolation and iterative updating |
CN106875350A (en) * | 2017-01-05 | 2017-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and the terminal of sharpening treatment are carried out to blurred picture |
CN110446071A (en) * | 2019-08-13 | 2019-11-12 | 腾讯科技(深圳)有限公司 | Multi-media processing method, device, equipment and medium neural network based |
CN111028182A (en) * | 2019-12-24 | 2020-04-17 | 北京金山云网络技术有限公司 | Image sharpening method and device, electronic equipment and computer-readable storage medium |
CN111245816A (en) * | 2020-01-08 | 2020-06-05 | 窦翠云 | Data uploading system and method based on content detection |
CN111654627A (en) * | 2020-06-09 | 2020-09-11 | 展讯通信(上海)有限公司 | Digital zooming method, device, equipment and storage medium |
CN111737665A (en) * | 2019-04-27 | 2020-10-02 | 常英梅 | Grading display method for handheld mobile terminal |
CN112037135A (en) * | 2020-09-11 | 2020-12-04 | 上海瞳观智能科技有限公司 | Method for selecting image key main body to be amplified and displayed |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6421468B1 (en) * | 1999-01-06 | 2002-07-16 | Seiko Epson Corporation | Method and apparatus for sharpening an image by scaling elements of a frequency-domain representation |
WO2007027893A2 (en) * | 2005-08-30 | 2007-03-08 | The Regents Of The University Of California, Santa Cruz | Kernel regression for image processing and reconstruction |
CN102547067A (en) * | 2011-12-31 | 2012-07-04 | 中山大学 | Improved bicubic interpolation video scaling method |
CN102844786A (en) * | 2010-03-01 | 2012-12-26 | 夏普株式会社 | Image enlargement device, image enlargement program, memory medium on which image enlargement program is stored, and display device |
CN103299609A (en) * | 2011-01-07 | 2013-09-11 | Tp视觉控股有限公司 | Method for converting input image data into output image data, image conversion unit for converting input image data into output image data, image processing apparatus, display device |
CN104933679A (en) * | 2015-07-06 | 2015-09-23 | 福州瑞芯微电子有限公司 | A method for enlarging an image and a system corresponding to the method |
-
2015
- 2015-10-13 CN CN201510669656.7A patent/CN105260986B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6421468B1 (en) * | 1999-01-06 | 2002-07-16 | Seiko Epson Corporation | Method and apparatus for sharpening an image by scaling elements of a frequency-domain representation |
WO2007027893A2 (en) * | 2005-08-30 | 2007-03-08 | The Regents Of The University Of California, Santa Cruz | Kernel regression for image processing and reconstruction |
CN102844786A (en) * | 2010-03-01 | 2012-12-26 | 夏普株式会社 | Image enlargement device, image enlargement program, memory medium on which image enlargement program is stored, and display device |
CN103299609A (en) * | 2011-01-07 | 2013-09-11 | Tp视觉控股有限公司 | Method for converting input image data into output image data, image conversion unit for converting input image data into output image data, image processing apparatus, display device |
CN102547067A (en) * | 2011-12-31 | 2012-07-04 | 中山大学 | Improved bicubic interpolation video scaling method |
CN104933679A (en) * | 2015-07-06 | 2015-09-23 | 福州瑞芯微电子有限公司 | A method for enlarging an image and a system corresponding to the method |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106709873A (en) * | 2016-11-11 | 2017-05-24 | 浙江师范大学 | Super-resolution method based on cubic spline interpolation and iterative updating |
CN106709873B (en) * | 2016-11-11 | 2020-12-18 | 浙江师范大学 | Super-resolution method based on cubic spline interpolation and iterative updating |
CN106875350A (en) * | 2017-01-05 | 2017-06-20 | 宇龙计算机通信科技(深圳)有限公司 | Method, device and the terminal of sharpening treatment are carried out to blurred picture |
CN111737665A (en) * | 2019-04-27 | 2020-10-02 | 常英梅 | Grading display method for handheld mobile terminal |
CN110446071A (en) * | 2019-08-13 | 2019-11-12 | 腾讯科技(深圳)有限公司 | Multi-media processing method, device, equipment and medium neural network based |
CN111028182A (en) * | 2019-12-24 | 2020-04-17 | 北京金山云网络技术有限公司 | Image sharpening method and device, electronic equipment and computer-readable storage medium |
CN111028182B (en) * | 2019-12-24 | 2024-04-26 | 北京金山云网络技术有限公司 | Image sharpening method, device, electronic equipment and computer readable storage medium |
CN111245816A (en) * | 2020-01-08 | 2020-06-05 | 窦翠云 | Data uploading system and method based on content detection |
CN111654627A (en) * | 2020-06-09 | 2020-09-11 | 展讯通信(上海)有限公司 | Digital zooming method, device, equipment and storage medium |
CN111654627B (en) * | 2020-06-09 | 2021-11-26 | 展讯通信(上海)有限公司 | Digital zooming method, device, equipment and storage medium |
CN112037135A (en) * | 2020-09-11 | 2020-12-04 | 上海瞳观智能科技有限公司 | Method for selecting image key main body to be amplified and displayed |
CN112037135B (en) * | 2020-09-11 | 2023-06-09 | 上海瞳观智能科技有限公司 | Method for magnifying and displaying selected image key main body |
Also Published As
Publication number | Publication date |
---|---|
CN105260986B (en) | 2018-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105260986A (en) | Anti-fuzzy image amplification method | |
DE602004002618T2 (en) | Method and system for edge enhancement | |
JP3786910B2 (en) | Apparatus and method for enhancing contour line of video | |
CN101981911B (en) | Image processing method and device | |
CN100388755C (en) | Method for reducing noise in images | |
FI104521B (en) | Procedure for improving contrast in image sequences | |
CN102201109B (en) | Image processing method and radiographic apparatus using the same | |
US20100239173A1 (en) | Image output apparatus, edge enhancement method, and recording medium | |
CN101188671A (en) | Video image sharpening method | |
US11574391B2 (en) | Median based frequency separation local area contrast enhancement | |
WO2014102876A1 (en) | Image processing device and image processing method | |
CN101272452B (en) | Apparatus and method for reducing motion blur in a video signal | |
US9848163B2 (en) | Image processing apparatus and image processing method | |
US9495732B2 (en) | Image enhancing device and image enhancement method | |
WO2012124591A1 (en) | Signal processing device, control program, and integrated circuit | |
JP5403450B1 (en) | Image processing apparatus and image processing method | |
CN101316320B (en) | Image processing process for image processing system and correlated image processing apparatus | |
US9734563B2 (en) | Image processing apparatus and image processing method | |
US20240193734A1 (en) | Display device system and method for adaptively enhancing image quality | |
Cımtay | Towards Real Time Image Dehazing on Android Operating System | |
CN104992413A (en) | Face and/or license plate image processing method | |
CN112132749A (en) | Image processing method and device applying parameterized Thiele continuous fractional interpolation | |
CN104378531A (en) | Special image gain amplifier for high-definition film camera | |
Wang et al. | An algorithm for repairing low-quality video enhancement techniques based on trained filter | |
CN104335568A (en) | Image emphasizing device and image emphasizing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200930 Address after: 519000 unit 1, No. 33, Haihe street, Hengqin New District, Zhuhai City, Guangdong Province Patentee after: ZHUHAI DAHENGQIN TECHNOLOGY DEVELOPMENT Co.,Ltd. Address before: 430072 Hubei Province, Wuhan city Wuchang District of Wuhan University Luojiashan Patentee before: WUHAN University |
|
TR01 | Transfer of patent right |