CN113034405B - Fine geometric correction method for remote sensing image - Google Patents
Fine geometric correction method for remote sensing image Download PDFInfo
- Publication number
- CN113034405B CN113034405B CN202110450682.6A CN202110450682A CN113034405B CN 113034405 B CN113034405 B CN 113034405B CN 202110450682 A CN202110450682 A CN 202110450682A CN 113034405 B CN113034405 B CN 113034405B
- Authority
- CN
- China
- Prior art keywords
- image
- coordinates
- pixel
- output image
- pixel point
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 230000001186 cumulative effect Effects 0.000 claims description 5
- JXASPPWQHFOWPL-UHFFFAOYSA-N Tamarixin Natural products C1=C(O)C(OC)=CC=C1C1=C(OC2C(C(O)C(O)C(CO)O2)O)C(=O)C2=C(O)C=C(O)C=C2O1 JXASPPWQHFOWPL-UHFFFAOYSA-N 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000007670 refining Methods 0.000 claims 1
- 238000013507 mapping Methods 0.000 abstract description 6
- 238000012952 Resampling Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The application relates to a remote sensing image refined geometric correction method, which comprises the steps of firstly determining the coordinates and the row number of pixel points at the upper left corner of an output image grid, then converting the coordinates of the pixel points of an original remote sensing image into grid coordinates in an output image coordinate system, then distributing the brightness values of the pixel points of the original image based on weights, and finally determining the brightness values of the pixel points of the grid of the output image. The application establishes a method for quantitatively determining the contribution degree of the configuration of the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image, and determines the brightness value of the grid pixel point of the output image by quantitatively describing the weight value distributed from the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image, thereby realizing the geometric correction method of the remote sensing image, having direct calculation process and avoiding the technical problem that the pixel point value of the output remote sensing image is empty caused by the forward mapping geometric correction method.
Description
Technical Field
The application relates to the technical field of remote sensing image optimization, in particular to a method for correcting the refinement geometry of a remote sensing image.
Background
The progress of the remote sensing technology greatly improves the scientific application potential of remote sensing data products, and satellite remote sensing data are increasingly widely applied to various fields of national production and construction. The remote sensing data has the concept of a spatial geographic position as spatial data. Before the remote sensing data can be applied, it must be projected into the required geographical coordinate system. Geometric correction is an important step in the geometric processing of remote sensing data. The geometric correction of the remote sensing image is to eliminate geometric deformation in the image and produce a new image meeting the requirement of certain map projection or graphic expression. It comprises two links: firstly, transforming pixel coordinates, namely converting image coordinates into map or ground coordinates; and secondly, resampling the pixel brightness value after the coordinate transformation.
The forward mapping geometry correction method from input to output may result in a null output image grid value. Most remote sensing images are geometrically corrected in a reverse mapping manner from output to input. When resampling the image luminance values, the weight of the surrounding pixel luminance values contribution to the sampled points can be expressed by a resampling function. In the prior art, three common resampling algorithms exist in the remote sensing image processing process: nearest neighbor pel sampling, bilinear interpolation, and bicubic convolution interpolation.
However, the three resampling algorithms have the following technical problems: the nearest pixel sampling method is simple, the brightness value is better in fidelity, but the pixel point is displaced within a pixel range, and the geometric accuracy is poor; the bilinear interpolation method is simpler to calculate, has certain brightness sampling precision and average filtering effect, but slightly blurs an image; the double-three convolution interpolation method has the effects of equalization and definition of images, and has high geometric accuracy but large calculated amount.
The information disclosed in this background section is only for enhancement of understanding of the general background of the application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art.
Disclosure of Invention
In order to solve the technical problems of the nearest neighbor pixel sampling method, the bilinear interpolation method and the bicubic convolution interpolation method in the prior art, the application provides a remote sensing image refinement geometric correction method, and particularly relates to a geometric correction method for forward mapping of a remote sensing image. The method has simple calculation process, can keep the equalization and the definition of the image, and can avoid the condition that the pixel value of the output image is empty.
The method for geometrically correcting the remote sensing image provided by the application comprises the following steps of:
step one, determining coordinates (X) of the upper left corner pixel point of the output image grid 0 ,Y 0 ) And rank numbers M and N.
The coordinates of the upper left corner of the output image grid (X 0 ,Y 0 ) The rank numbers M and N have the following two determination modes:
(1) Determining the coordinates (X) of the upper left corner of the output image grid from the original image pixel coordinate information, and the horizontal and vertical spatial resolutions DeltaX and DeltaY 0 ,Y 0 ) The number of ranks M and N.
The coordinates of four corner points of the original image are read to obtain 4 pairs of coordinate values, and the minimum values (X 1 ,Y 1 ) Sum maximum (X) 2 ,Y 2 ) Let X 1 ，Y 1 ，X 2 ，Y 2 To output coordinate values of four boundaries of the image range. The coordinates of the upper left corner of the output image grid (X 0 ,Y 0 ) The rank numbers M and N are determined by the following formula:
X 0 ＝X 2
Y 0 ＝Y 1
(2) The coordinates (X) of the upper left corner of the output image grid are customized as needed 0 ,Y 0 ) The number of ranks M and N.
To this end, in the output image coordinate system A-x ', y', each pixel may be located by its row and column number. The range of values of the row and column numbers is as follows:
x′＝1,2,…,M
y′＝1,2,…,N
and step two, converting the coordinates of the pixel points of the original remote sensing image into grid coordinates in an output image coordinate system.
The horizontal coordinate of the original image pixel point is X, the vertical coordinate is Y, and the positions of the original image pixel point coordinates in the output image coordinate system A-X ', Y' are as follows:
to this end, the position coordinates of the pixel coordinates of the original image, whose rank numbers are L and C, respectively, corresponding to the output image may be expressed as:
and thirdly, distributing the brightness values of the pixel points of the original image based on the weights.
(1) Parameter calculation
The influence range of the brightness value of the pixel points of the original image with the row and column numbers of i and j is in an elliptical range taking the pixel points as the center, and an elliptical function is as follows:
f(u,v)＝au 2 +buv+cv 2
wherein a, b and c are ellipse parameters; 1< i < L,1< j < C.
The elliptic function satisfies the following condition:
f(u x ,v x )＝1
f(u y ,v y )＝1
where g is an amplification factor, which may be generally set to 1.0, and may be adjusted according to actual conditions to reduce the case where the output image grid is empty. a. b, c is solved as follows:
if it isOr v y =0, then a=g, b=0, c=g.
Up to this point, the pixel point related parameter a, b, c, u del 、v del All are solved. And taking the parameters of the nearest adjacent pixel points for the pixel points of the image edge.
(2) Determining weights for contributions of luminance values of pixels in an original image to the luminance of an output image
Brightness value T of original image pixels with rank numbers i and j, respectively i,j The brightness values of the pixel points in the u 1-u 2 columns of the output images are assigned to the v 1-v 2 rows according to different weights, and the calculation process of v1, v2, u1 and u2 is as follows:
v1=rounding (x' i,j -v del )
v2=rounding (x' i,j +v del )
u1=rounding (y' i,j -u del )
u2=rounding (y' i,j +u del )
The pixel points with the row and column numbers q and p of the output image are assigned the weight w, and the brightness value of the pixel point of the original image is assigned as T' q,p The calculation formula is as follows:
k＝a(p-y′ i,j ) 2 +b(p-y′ i,j )(q-x′ i,j )+c(q-x′ i,j ) 2
w＝exp(-f×k)
T′ q,p ＝w×T i,j
where f is given a positive constant, f >2.0.
And step four, determining brightness values of grid pixel points of the output image.
And after the brightness values of all the original image pixels are assigned, calculating the brightness values of the output image pixels. The cumulative value of the brightness value assigned to any one of the output image pixels is T' a The weight cumulative value is w a The final brightness value T 'of the pixel point' f The method comprises the following steps:
thus, the configuration process from the brightness value of one pixel point of the original image to the pixel point of the output image is realized. After all the gray values of the pixel points of the output image are determined, the image correction process is completed.
The application determines the brightness value of the grid pixel point of the output image by quantitatively describing the weight distributed from the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image, thereby realizing the geometric correction method of the remote sensing image. The calculation process is direct, and the condition that the pixel point of the output image is empty can be avoided. Compared with the prior art, the method for quantitatively determining the contribution degree from the configuration of the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image is established in the technical scheme provided by the application, and the problem that the pixel point value of the output remote sensing image is empty possibly caused by the forward mapping geometric correction method is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a main flow chart of a method for geometric correction of a remote sensing image according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by a person skilled in the art based on the embodiments of the application without any inventive effort, are intended to fall within the scope of the application.
As shown in fig. 1, the method for geometric correction of a remote sensing image provided by the application comprises the following steps:
step one, determining coordinates (X) of the upper left corner pixel point of the output image grid 0 ,Y 0 ) And rank numbers M and N.
The coordinates of the upper left corner of the output image grid (X 0 ,Y 0 ) The rank numbers M and N are determined in two ways:
(1) And determining according to the coordinate information of the pixel points of the original image and the spatial resolutions delta X and delta Y in the horizontal and vertical directions.
The coordinates of four corner points of the original image are read to obtain 4 pairs of coordinate values, and the minimum values (X 1 ,Y 1 ) Sum maximum (X) 2 ,Y 2 ) Let X 1 ，Y 1 ，X 2 ，Y 2 To output coordinate values of four boundaries of the image range. The coordinates of the upper left corner of the output image grid (X 0 ,Y 0 ) The rank numbers M and N are determined by the following formula:
X 0 ＝X 2
Y 0 ＝Y 1
(2) The coordinates (X) of the upper left corner of the output image grid are customized as needed 0 ,Y 0 ) The number of ranks M and N.
To this end, in the output image coordinate system A-x ', y', each pixel may be located by its row and column number. The range of values of the row and column numbers can be:
x′＝1,2,…,M
y′＝1,2,…,N
and step two, converting the coordinates of the pixel points of the original remote sensing image into grid coordinates in an output image coordinate system.
The horizontal coordinate of the original image pixel point is X, the vertical coordinate is Y, and the positions of the original image pixel point coordinates in the output image coordinate system A-X ', Y' are as follows:
to this end, the position coordinates of the pixel coordinates of the original image, whose rank numbers are L and C, respectively, corresponding to the output image may be expressed as:
and thirdly, distributing brightness values of the original image pixel points based on the weights.
(1) Parameter calculation
The influence range of the brightness values of the pixel points of the original image with row and column numbers of i and j is in an elliptical range taking the pixel points as the center, and an elliptical function is as follows:
f(u,v)＝au 2 +buv+cv 2
wherein a, b and c are ellipse parameters; 1< i < L,1< j < C.
The elliptic function satisfies the following condition:
f(u x ,v x )＝1
f(u y ,v y )＝1
where g is an amplification factor, which may be generally set to 1.0, and may be adjusted according to actual conditions to reduce the case where the output image grid is empty. a. b, c is solved as follows:
if it isOr v y =0, then a=g, b=0, c=g.
Up to this point, the pixel point related parameter a, b, c, u del 、v del All are solved. And taking the parameters of the nearest adjacent pixel points for the pixel points of the image edge.
(2) Weighting of the contribution of the luminance value of a pixel in an original image to the luminance of an output image
Brightness value T of original image pixels with row and column numbers i and j i,j The brightness values of the pixel points in the u 1-u 2 columns of the output images are assigned to the v 1-v 2 rows according to different weights, and the calculation process of v1, v2, u1 and u2 is as follows:
v1=rounding (x' i,j -v del )
v2=rounding (x' i,j +v del )
u1=rounding (y' i,j -u del )
u2=rounding (y' i,j +u del )
The pixel points with the row and column numbers q and p of the output image are assigned the weight w, and the brightness value of the pixel point of the original image is assigned as T' q,p The calculation formula is as follows:
k＝a(p-y′ i,j ) 2 +b(p-y′ i,j )(q-x′ i,j )+c(q-x′ i,j ) 2
w＝exp(-f×k)
T′ q,p ＝w×T i,j
where f is given a positive constant, f >2.0.
And step four, determining brightness values of grid pixel points of the output image.
And after the brightness values of all the original image pixels are assigned, calculating the brightness values of the output image pixels. The cumulative value of the brightness value assigned to any one of the output image pixels is T' a The weight cumulative value is w a The final brightness value T 'of the pixel point' f The method comprises the following steps:
thus, the configuration process from the brightness value of one pixel point of the original image to the pixel point of the output image is realized. After the gray values of all the pixel points of the output image are determined, the geometric correction process is completed.
The application determines the brightness value of the grid pixel point of the output image by quantitatively describing the weight distributed from the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image, thereby realizing the geometric correction method of the remote sensing image. The calculation process is direct, and the condition that the pixel point of the output image is empty can be avoided.
Compared with the prior art, the method for quantitatively determining the contribution degree from the configuration of the brightness value of the pixel point of the input remote sensing image to the pixel point of the output image is established in the technical scheme provided by the application, and the problem that the pixel point value of the output remote sensing image is empty possibly caused by the forward mapping geometric correction method is avoided.
The preferred embodiments of the present application have been described in detail with reference to the accompanying drawings, but the present application is not limited thereto. The technical solution of the application can be subjected to a plurality of simple variants within the scope of the technical idea of the application. The application is not described in any way with respect to the possible simple variants in order to avoid unnecessary repetition. Such simple variations are to be regarded as a matter of the present disclosure and all such variations are intended to be included within the scope of the present disclosure.
Claims (5)
1. The method for correcting the geometry of the remote sensing image in a refined way is characterized by comprising the following steps of:
step one, determining coordinates (X) of the upper left corner pixel point of the output image grid 0 ，Y 0 ) And rank numbers M and N;
step two, converting the coordinates of the pixel points of the original remote sensing image into grid coordinates in an output image coordinate system;
thirdly, distributing the brightness value of the pixel point of the original image based on the weight of the contribution of the brightness value of the pixel in the original image to the brightness of the output image; the specific method of the third step is as follows:
(1) Parameter calculation
The influence range of the brightness values of the pixel points of the original image with row and column numbers of i and j is in an elliptical range taking the pixel points as the center, and an elliptical function is as follows:
f(u，v)＝au 2 +buv+cv 2
wherein a, b and c are ellipse parameters;
the elliptic function satisfies the following condition:
f(u x ，v x )＝1
f(u y ，v y )＝1
wherein g is the amplification factor, x' i,j Is the transverse coordinate, y 'of the pixel point coordinate of the original image with the row and column number of the ith row and the jth column in the output image coordinate system' i,j The method is characterized in that the vertical coordinates of the pixel point coordinates of the original image with the row and column numbers of the ith row and the jth column in an output image coordinate system are obtained by solving a, b and c as follows:
if it isOr v y =0, a=g, b=0, c=g,
for the pixel points at the edge of the image, the parameters of the nearest pixel point are taken
(2) Weighting of the contribution of the luminance value of a pixel in an original image to the luminance of an output image
The brightness value T of the original image pixels with the row and column numbers of i and j i，j The brightness values of the pixel points in the u 1-u 2 columns of the output images are assigned to the v 1-v 2 rows according to different weights, and the calculation process of v1, v2, u1 and u2 is as follows:
v1=rounding (x' i，j -v del )
v2=rounding (x' i，j +v del )
u1=rounding (y' i，j -u del )
u2=rounding (y' i，j +u del )
The pixel points with the row and column numbers q and p of the output image are assigned the weight w, and the brightness value of the pixel point of the original image is assigned as T' q，p The calculation formula is as follows:
k＝a(p-y′ i，j ) 2 +b(p-y′ i，j )(q-x′ i，j )+c(q-x′ i，j ) 2
w＝exp(-f×k)
T′ q，p ＝w×T i，j
wherein f is a given positive constant;
and step four, determining brightness values of grid pixel points of the output image.
2. The method according to claim 1, wherein in the first step, the coordinates (X 0 ，Y 0 ) And the rank numbers M and N are as follows: determining the coordinates (X) of the upper left corner of the output image grid from the original image pixel coordinate information, and the horizontal and vertical spatial resolutions DeltaX and DeltaY 0 ，Y 0 ) A rank number M and N; the coordinates of four corner points of the original image are read to obtain 4 pairs of coordinate values, and the minimum values (X 1 ，Y 1 ) Sum maximum (X) 2 ，Y 2 ) Let X 1 ，Y 1 ，X 2 ，Y 2 To output the coordinate values of the four boundaries of the image range, the coordinates (X 0 ，Y 0 ) The rank numbers M and N are determined by the following formula:
X 0 ＝X 2
Y 0 ＝Y 1
3. the method according to claim 2, wherein in the first step, the coordinates (X 0 ，Y 0 ) Sum of the rank number MThe method of N is as follows: in the output image coordinate system A-x ', y', each pixel can determine its position according to the row and column number, and the range of values of the row and column numbers is:
x′＝1，2，…，M；
y′＝1，2，…，N。
4. the method for refining geometric correction of remote sensing image according to claim 1, wherein the method for converting the coordinates of the pixels of the original remote sensing image into grid coordinates in the coordinate system of the output image in the second step is as follows:
the horizontal coordinate of the original image pixel point is X, the vertical coordinate is Y, and the positions of the original image pixel point coordinates in the output image coordinate system A-X ', Y' are as follows:
wherein DeltaX and DeltaY respectively represent the spatial resolution of the pixel point of the original image in the horizontal and vertical directions,
up to this point, the position coordinates of the pixel coordinates of the original image, where the number of rows and columns is L and C, respectively, in the output image are expressed as:
5. the method for fine geometry correction of remote sensing image according to claim 1, wherein the method for determining the brightness value of the grid pixel point of the output image in the fourth step is as follows:
after the brightness values of all the original image pixels are assigned, calculating the brightness values of the output image pixels, wherein the accumulated value of the assigned brightness values of any output image pixel is T' a The weight cumulative value is w a The final brightness value T 'of the pixel point' f The method comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450682.6A CN113034405B (en) | 2021-04-25 | 2021-04-25 | Fine geometric correction method for remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110450682.6A CN113034405B (en) | 2021-04-25 | 2021-04-25 | Fine geometric correction method for remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034405A CN113034405A (en) | 2021-06-25 |
| CN113034405B true CN113034405B (en) | 2023-12-12 |
Family
ID=76454534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110450682.6A Active CN113034405B (en) | 2021-04-25 | 2021-04-25 | Fine geometric correction method for remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034405B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005266042A (en) * | 2004-03-17 | 2005-09-29 | Seiko Epson Corp | Geometric correction method of image and correction apparatus |
| CN1790051A (en) * | 2005-12-16 | 2006-06-21 | 中国科学院上海技术物理研究所 | Automatic assimilation method for multi-source thermal infrared wave band data of polar-orbit meteorological satellite |
| CN103822615A (en) * | 2014-02-25 | 2014-05-28 | 北京航空航天大学 | Unmanned aerial vehicle ground target real-time positioning method with automatic extraction and gathering of multiple control points |
| US9756303B1 (en) * | 2016-12-30 | 2017-09-05 | Texas Instruments Incorporated | Camera-assisted automatic screen fitting |
| CN111339483A (en) * | 2020-01-19 | 2020-06-26 | 武汉大学 | GNSS image generation method based on trend-removing cross-correlation analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8917336B2 (en) * | 2012-05-31 | 2014-12-23 | Apple Inc. | Image signal processing involving geometric distortion correction |
-
2021
- 2021-04-25 CN CN202110450682.6A patent/CN113034405B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005266042A (en) * | 2004-03-17 | 2005-09-29 | Seiko Epson Corp | Geometric correction method of image and correction apparatus |
| CN1790051A (en) * | 2005-12-16 | 2006-06-21 | 中国科学院上海技术物理研究所 | Automatic assimilation method for multi-source thermal infrared wave band data of polar-orbit meteorological satellite |
| CN103822615A (en) * | 2014-02-25 | 2014-05-28 | 北京航空航天大学 | Unmanned aerial vehicle ground target real-time positioning method with automatic extraction and gathering of multiple control points |
| US9756303B1 (en) * | 2016-12-30 | 2017-09-05 | Texas Instruments Incorporated | Camera-assisted automatic screen fitting |
| CN111339483A (en) * | 2020-01-19 | 2020-06-26 | 武汉大学 | GNSS image generation method based on trend-removing cross-correlation analysis |
Non-Patent Citations (3)
| Title |
|---|
| 几何校正中重采样方法研究;陈灿;《中国知网硕士电子期刊》(第5期);全文 * |
| 风云卫星数据在中国农业监测中的应用进展;许淇等;《气象科技进展》;第9卷(第5期);全文 * |
| 高分二号卫星遥感影像几何精校正方法研究;王磊;《中国知网硕士电子期刊》(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034405A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103034973B (en) | Based on the adaptive image scaling method of bicubic interpolation | |
| CN107644398B (en) | Image interpolation method and related image interpolation device | |
| CN110738707A (en) | Distortion correction method, device, equipment and storage medium for cameras | |
| CN107342037B (en) | Data conversion method, device and computer readable storage medium | |
| CN112562576B (en) | Display screen optical external compensation method, device and storage medium | |
| EP4207051A1 (en) | Image super-resolution method and electronic device | |
| CN112801904B (en) | Hybrid degraded image enhancement method based on convolutional neural network | |
| CN113034405B (en) | Fine geometric correction method for remote sensing image | |
| US20170195520A1 (en) | Image processing method, apparatus, and image forming device | |
| CN111695554B (en) | Text correction method and device, electronic equipment and storage medium | |
| CN107516291B (en) | Night scene image ortho-rectification processing method | |
| CN109996085B (en) | Model training method, image processing method and device and electronic equipment | |
| CN115619678B (en) | Correction method and device for image deformation, computer equipment and storage medium | |
| CN111009208B (en) | Optimization method of panel display, display panel and storage medium | |
| JP2016115318A (en) | Blurring correction device, super-resolution device, and program | |
| US6529642B1 (en) | Method for enlarging/reducing digital images | |
| CN110390642A (en) | A kind of method of pair of woodcut Tibetan language geometric correction of imagery | |
| CN114299516A (en) | Processing method of table or text line, bill processing method, bill processing device and storage medium | |
| CN116843555B (en) | Image interpolation method, device, electronic equipment and storage medium | |
| US20200272689A1 (en) | Vector-Based Glyph Style Transfer | |
| JP4930860B2 (en) | Graphic drawing apparatus, antialiasing method and program | |
| CN110608723A (en) | Real-time remote sensing image geographical reference method based on FPGA | |
| KR20160069452A (en) | Image processing device, image processing method and program | |
| CN111093045A (en) | Method and device for scaling video sequence resolution | |
| CN116309058B (en) | Human body infrared image amplification processing 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |