CN105046657B - A kind of image stretch distortion self-adapting correction method - Google Patents
A kind of image stretch distortion self-adapting correction method Download PDFInfo
- Publication number
- CN105046657B CN105046657B CN201510354230.2A CN201510354230A CN105046657B CN 105046657 B CN105046657 B CN 105046657B CN 201510354230 A CN201510354230 A CN 201510354230A CN 105046657 B CN105046657 B CN 105046657B
- Authority
- CN
- China
- Prior art keywords
- constraint
- energy function
- coordinates
- image
- grid
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims 1
- 238000005452 bending Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 3
- 238000000844 transformation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000009877 rendering Methods 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
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/10052—Images from lightfield camera
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of image stretch distortion self-adapting correction method.Uniform square grid is divided an image into first and establishes input and output coordinate；People's object area and background area are determined secondly by Face datection algorithm, respectively regional establishes homography constraint, to correct the stretch distortion occurred in people's object area, and establishes homography compatibility restriction for adjacent area, ensures the continuity of regional；Linearity region is determined by line detection algorithm, establishing straight line for linearity region keeps constraint, to ensure that the straight line after correcting occurs without bending；Smoothly constrain with uniformity by world coordinates and ensure entire image congruous continuity.Above-mentioned constraint is expressed as energy function again, and adds weight, each energy equation is added.Coordinate value during energy minimum is calculated using least square method, that is, the image coordinate value after being corrected.Finally rendered to obtain correction of a final proof image using bilinear map.
Description
Technical Field
The invention relates to a digital image processing technology, in particular to an image stretching distortion self-adaptive correction method.
Background
Wide-angle lenses of cameras can capture images over a large field of view, but are also prone to introduce image distortion. One of the distortions is that when the wide-angle lens performs imaging following a pinhole imaging model, and an object in an imaging scene is close to the camera and at the edge of the field of view, the object in the captured image is severely stretched due to the perspective effect, which causes distortion of the geometric shape of the object. Especially when the object is a human face or a person, the stretching distortion is more obvious because human eyes are sensitive to the distortion of the human face and the person image. Therefore, it is necessary to correct the image in which the object stretch distortion occurs so that the image conforms to the vision of human eyes.
However, straight lines in an image scene may be subject to warping due to stretching that corrects for objects, and therefore, it is desirable to correct for stretching distortion while leaving other scenes or objects unaffected.
In addition, the panoramic image is also a kind of wide-angle image in nature. When a panoramic image is projected in a linear perspective, the image also exhibits stretching distortion.
In the prior art, there are a global projection correction method by changing a projection center, a method of separating an image background from a person and correcting the image background and the person separately, and a projection correction method of optimally maintaining image contents.
Disclosure of Invention
The invention aims to provide an image stretching distortion self-adaptive correction method, aiming at overcoming the defects of the prior art, and correcting the stretching distortion of an object, particularly a person in an image while keeping a straight background line in the image straight.
The purpose of the invention is realized by the following technical scheme: a method for adaptive correction of image stretching distortion, the method comprising the steps of:
step A: an image with object stretch distortion is input.
And B: establishing grids and coordinates, dividing an image with object stretching distortion into square uniform grids, and recording the coordinates of grid intersection points as xi,j＝(xi,j,yi,j) I, j are grid intersection point serial numbers; let grid intersection point coordinate xi,jThe corrected coordinate is ui,j＝(ui,j,vi,j)。
And C: structure ui,jThe constraint energy function of (2).
Step C1: a homography constraining energy function is constructed. Calculating the angle of the figure region to the center of the visual fieldThe calculation formula is as follows:
wherein L is the horizontal offset distance from the center of the human area to the center of the field of view, f is the focal length, and L and f are converted into units of pixel numbers. The homography transformation of the character area can be written as:
the homography described by the above equation is denoted as H (x)i,j) Then an energy function of the homography constraint for the person region grid points may be defined:
wherein, P1A set of human area grid points.
The homography constraint energy function of the background region grid points is defined as:
wherein, P2Is a set of background area grid points.
The total homography constraint energy function is
Step C2: a homography compatibility constraint energy function is constructed.
Definition PhcGrid points for common boundaries between human and background regions, H1、H2Homography transformations of the background region and the person region, respectively. The energy function of the homography compatibility constraint is then:
step C3: constructing a straight line preserves the constraint energy function. First, a straight-line segment detection algorithm is used to detect straight-line segments in a background region of the image except for a human figure. The set of detected straight lines is defined as L.
Defining a virtual point in each grid with straight lines passing through
The coefficients a, b, c and d are obtained by bilinear interpolation calculation of x-y coordinate values corresponding to u-v coordinates. The calculation formula is as follows:
wherein,taken as the midpoint of the line segment within the grid block.
For any straight line, defining the starting point and the end point of the straight line as ustartAnd uend。
Calculating the point u on the curvei,jAnd the distance D from the point to the projected point on the straight line, and the constraint D is zero. The distance D is calculated from the geometric relationship
D＝|n(ui,j-ustart)T|
Wherein n ═ n (n)1,n2) Is the unit normal vector of the straight line. The distance D is calculated as an energy function which defines a line hold constraint as
Step C4: a global coordinate smoothing constraint energy function is constructed. Defining a Jacobian matrix of u-v coordinates as
When the terms in the jacobian matrix satisfy the cauchy-riemann equation:
when the temperature of the water is higher than the set temperature,
continuous smoothing of the coordinates can be achieved. Discretizing the above formula to obtain:
the coordinate smoothing constraint energy function can be calculated by the above equation:
Es＝∑((ui+1，j-ui，j)-(vi，j+1-vi，j))2+∑((vi+1，j-vi，j)+(ui，j+1-ui，j))2；
step C5: and constructing a global coordinate uniform constraint energy function. Discretizing the Laplace operator, an energy function defining a uniform constraint on global coordinates can be defined as
Step D: and (5) solving linear least squares. Adding a weight coefficient to each energy function and adding the energy functions to obtain a total energy function as follows:
if E is equal to 0, then Eh,Ehc,El,Es,EuAre all required to be 0, so that a linear equation system can be constructed
Ax＝b
Wherein A is a constraint matrix containing u in a constraint energy functioni,jThe previous coefficients. x is a value containing the unknown quantity u to be determinedi,jAnd vi,jB contains constant terms of the respective equations.
Solving x by linear least square method to obtain the formula
x＝(ATA)-1ATb
Step E: solving the coordinates u of the grid pointsi,jAnd vi,jThen, the bilinear mapping is adopted to calculate the coordinates of any point (x, y) except the grid point after correction into
(u，v)＝(1-x)(l-y)pl+x(l-y)p2+(1-x)yp3+xyp4。
Wherein p1, p2, p3 and p4 are respectively coordinates of 4 grid points of a grid where the point (x, y) is located, p1 is coordinates of a grid point at the upper left corner, p2 is coordinates of a grid point at the upper right corner, p3 is coordinates of a grid point at the lower left corner, and p4 is coordinates of a grid point at the lower right corner.
Step F: after the corrected coordinates (u, v) are calculated. The corrected image is obtained by remapping and interpolating from the input coordinate values (x, y) to the calculated coordinate values (u, v).
Compared with the existing correction method, the method disclosed by the invention has the following characteristics: (1) not only can the stretching distortion of an object at the edge of a view field be corrected, but also the straight line of the background can be kept from being bent; (2) the image content of the correction result is continuous and consistent, and no cutting imagination appears; (3) the loss of the field of view of the corrected image is small; (4) the correction method is automatically completed without manual intervention.
Drawings
FIG. 1 is a flow chart of a method of image stretch distortion correction according to the present invention;
FIG. 2 is an exemplary image with stretch distortion as described in the present disclosure;
FIG. 3 is a schematic diagram of the creation of a grid and the definition of coordinates;
FIG. 4 is a schematic diagram of the division of an image region;
FIG. 5 is a schematic diagram of the definition of a virtual point;
FIG. 6 is a schematic diagram of the calculation of distance D;
FIG. 7 is a schematic diagram of a bilinear map;
FIG. 8 is an exemplary image corrected by the method of the present invention;
FIG. 9 is an image of an exemplary image corrected by the method of the present invention as a rectangle.
Detailed Description
The self-adaptive correction method of the image stretching distortion comprises the steps of receiving an image with object stretching distortion; dividing the image by using a uniform grid and establishing an input and output coordinate system; detecting the position and size of a face of an input image through a face detection algorithm, and determining a rectangular region where a person is located and a remaining background region through the information; respectively establishing homography constraints for each region to correct stretching distortion in the character region, establishing homography compatibility constraints for adjacent regions to ensure the continuity of each region; determining a straight line area through a straight line detection algorithm, and establishing straight line holding constraint for the straight line area to ensure that the corrected straight line is not bent; establishing global coordinate smoothness and uniformity constraint to ensure that the whole image is consistent and continuous; expressing the constraints as energy functions, adding weights, and adding energy equations; minimizing the energy function to construct a linear equation set, and calculating the linear equation set by using a least square method to obtain a corrected image coordinate value; and rendering by using bilinear texture mapping to obtain a final image.
For better understanding of the implementation process of the present invention, an adaptive correction method for image stretching distortion according to the present invention will be described in detail below with reference to the accompanying drawings. Referring to fig. 1, the method of the present invention for correcting stretching distortion of an image includes the following steps:
step A: an image with object stretch distortion is input. Fig. 2 is an example of an image with human stretch distortion, the distortion location being indicated by a double arrow.
And B: and establishing grids and coordinates. To be provided withFIG. 2 is an example, as shown in FIG. 3, the image is divided into a square uniform grid, and the grid intersection coordinates are marked as xi,j＝(xi,j,yi,j) And i and j are grid intersection point serial numbers. After image distortion, the coordinate to be solved is recorded as ui,j＝(ui,j,vi,j)。
And C: a constraint energy function is constructed.
Step C1: a homography constraining energy function is constructed. The reason for the tensile distortion is that the object is at the edge of the field of view of the image, and when the camera is rotated to face the object and the object is in the center of the field of view, the object is free of tensile distortion. Therefore, it is necessary to change the angle of view of a partial region of an image by a homography transform (perspective transform) to correct the stretching distortion of an object in the region. First, the image face detection algorithm is used to detect the face position and size, and the rectangular region where the person is located and the remaining background region are determined by this information, and the person region and the background region determined by taking fig. 2 as an example are shown in fig. 4. Calculating the angle of the figure region to the center of the visual fieldThe calculation formula is as follows:
wherein L is the horizontal offset distance from the center of the human area to the center of the field of view, f is the focal length, and L and f are converted into units of pixel numbers. The homography transformation of the character area can be written as:
the homography described by the above equation is denoted as H (x)i,j) Then an energy function of the homography constraint for the person region grid points may be defined:
wherein P is1A set of human area grid points. The background region does not need homography transformation, so the homography constraint energy function of the region grid points is defined as:
wherein P is2Is a set of background area grid points. The total homography constraint energy function is
Step C2: a homography compatibility constraint energy function is constructed. The character area and the background area have a common edge. In order to prevent the dislocation phenomenon of the connected parts of the regions after the regions are subjected to the homography transformation, the homography compatibility constraint must be added to the adjacent parts of the regions. Definition PhcGrid points, H, which are boundaries shared between regions1、H2Homography transformations for the person and background regions, respectively. The energy function of the homography compatibility constraint is then:
said homographic transformation H1Comprises the following steps:
said homographic transformation H2Is a 3 × 3 identity matrix.
Step C3: constructing a straight line preserves the constraint energy function. And (4) ensuring that the straight line in the image is still kept straight after being corrected, and adding a straight line keeping constraint. First, a straight line segment detection algorithm is used for detecting straight line segments of background areas except human figures in the image. The set of detected straight lines is defined as L.
Since no straight line passes through the grid points, a virtual point is defined in each grid through which a straight line passes, as shown in fig. 5
The coefficients a, b, c and d are obtained by bilinear interpolation calculation of x-y coordinate values corresponding to u-v coordinates. The calculation formula is as follows:
wherein,taken as the midpoint of the line segment within the grid block.
For any straight line, defining the starting point and the end point of the straight line as ustartAnd uend. As shown in fig. 6, in order to straighten the curve into a straight line, it is necessary to calculate a point u on the curvei,jAnd the distance D from the point to the projected point on the straight line, and the constraint D is zero. The distance D is calculated from the geometric relationship
D＝|n(ui,j-ustart)T|
Wherein n ═ n (n)1,n2) Is the unit normal vector of the straight line. The distance D is calculated as an energy function which defines a line hold constraint as
Step C4: a global coordinate smoothing constraint energy function is constructed. To make the image content consistent and continuous, a global coordinate smoothing constraint is defined, and a Jacobian matrix of u-v coordinates is defined as
When the terms in the jacobian matrix satisfy the cauchy-riemann equation:
continuous smoothing of the coordinates can be achieved. Since the grid is discrete, the above formula is discretized
ui+1,j-ui,j＝vi,j+1-vi,j
ui,j+1-ui,j＝-(vi+1,j-vi,j)
The coordinate smoothing constraint energy function can be calculated by the above equation:
Es＝∑((ui+1,j-ui,j)-(vi,j+1-vi,j))2+∑((vi+1,j-vi,j)+(ui,j+1-ui,j))2
step C5: and constructing a global coordinate uniform constraint energy function. Considering only the coordinate smoothing constraint would make the final corrected image peripheral grid much larger than the image central grid. Therefore, it is necessary to add global coordinate uniformity constraints so that the grid scales inside and outside the image remain consistent. The solution to the laplace equation is of a uniform nature, so the laplace operator is used here. Discretizing the Laplace operator, an energy function defining a coordinate uniformity constraint can be defined as
Step D: and (5) solving linear least squares. Adding a weight coefficient to each energy function and adding the energy functions to obtain a total energy function as follows:
to minimize the energy function, E is 0. E is 0, then Eh,Ehc,El,Es,EuAre all required to be 0, so that a linear equation system can be constructed
Ax＝b
Wherein A is a constraint matrix containing u in a constraint energy functioni,jThe previous coefficients.xTo contain the unknown quantity u to be soughti,jAnd vi,jB contains constant terms of the respective equations. Since the system of linear equations is overdetermined, a linear least squares pair can be usedxSolving is carried out, the solving formula is
x＝(ATA)-1ATb
Step E: solving the coordinates u of the grid pointsi,jAnd vi,jThen, the coordinates except the grid points need to be calculated by using bilinear mapping. As shown in FIG. 7, knowing the coordinates of grid points p1, p2, p3, p4, the calculation formula for any point (u, v) in the grid is
(u，v)＝(1-x)(1-y)p1+x(1-y)p2+(1-x)yp3+xyp4
Step F: after the corrected coordinates (u, v) are calculated. The final corrected image is obtained by remapping and interpolating from the input coordinate values to the calculated coordinate values, as shown in fig. 8. The corrected image has irregular boundaries and needs to be cut into rectangles for output, as shown in fig. 9.
Claims (1)
1. An adaptive correction method for image stretching distortion, characterized in that the method comprises the following steps:
step A: inputting an image with object stretching distortion;
and B: establishing grids and coordinates, dividing an image with object stretching distortion into square uniform grids, and recording the coordinates of grid intersection points as xi,j＝(xi,j,yi,j) I, j are grid intersection point serial numbers; let grid intersection point coordinate xi,jThe corrected coordinate is ui,j＝(ui,j,vi,j)；
And C: structure ui,jThe constraint energy function of (1);
step C1: constructing a homography constraint energy function; calculating the angle of the figure region to the center of the visual fieldThe calculation formula is as follows:
wherein L is the horizontal offset distance from the center of the human object area to the center of the visual field, f is the focal length, and L and f are converted into units of pixel numbers; the homography transformation of the character area can be written as:
the homography described by the above equation is denoted as H (x)i,j) Then an energy function of the homography constraint for the person region grid points may be defined:
wherein, P1A set of person region grid points;
the homography constraint energy function of the background region grid points is defined as:
wherein, P2A set of background region grid points;
the total homography constraint energy function is
Step C2: constructing a homography compatibility constraint energy function;
definition PhcGrid points for common boundaries between human and background regions, H1、H2Homography transformation of a background area and a character area respectively; the energy function of the homography compatibility constraint is then:
step C3: constructing a straight line maintenance constraint energy function; firstly, detecting straight line segments in a background area except for a person in an image by using a straight line segment detection algorithm; defining the detected straight line set as L;
defining a virtual point in each grid with straight lines passing through
The coefficients a, b, c and d are obtained by carrying out bilinear interpolation calculation on the x-y coordinate values corresponding to the u-v coordinates; the calculation formula is as follows:
wherein,taking the midpoint of a line segment in the grid block;
for any straight line, defining the starting point and the end point of the straight line as ustartAnd uend；
Calculating the point u on the curvei,jThe distance D from the point to the projected point on the straight line, and the D is restricted to be zero; the distance D is calculated from the geometric relationship
D＝|n(ui,j-ustart)T|
Wherein n ═ n (n)1,n2) A unit normal vector that is a straight line; the distance D is calculated as an energy function which defines a line hold constraint as
Step C4: constructing a global coordinate smooth constraint energy function; defining a Jacobian matrix of u-v coordinates as
When the terms in the jacobian matrix satisfy the cauchy-riemann equation:
when the temperature of the water is higher than the set temperature,
continuous smoothing of coordinates can be realized; discretizing the above formula to obtain:
the coordinate smoothing constraint energy function can be calculated by the above equation:
Es＝∑((ui+1,j-ui,j)-(vi,j+1-vi,j))2+∑((vi+1,j-vi,j)+(ui,j+1-ui,j))2；
step C5: constructing a global coordinate uniform constraint energy function; discretizing the Laplace operator, an energy function defining a uniform constraint on global coordinates can be defined as
Step D: solving linear least squares; adding a weight coefficient to each energy function and adding the energy functions to obtain a total energy function as follows:
if E is equal to 0, then Eh,Ehc,El,Es,EuAre all required to be 0, so that a linear equation system can be constructed
Ax＝b
Wherein A is a constraint matrix containing u in a constraint energy functioni,jPrevious coefficients; x is a value containing the unknown quantity u to be determinedi,jAnd vi,jB contains constant terms of the respective equations;
solving x by linear least square method to obtain the formula
x＝(ATA)-1ATb
Step E: solving the coordinates u of the grid pointsi,jAnd vi,jThen, the bilinear mapping is adopted to calculate the coordinates of any point (x, y) except the grid point after correction into
(u,v)＝(1-x)(1-y)p1+x(1-y)p2+(1-x)yp3+xyp4；
Wherein p1, p2, p3 and p4 are respectively coordinates of 4 grid points of a grid where the point (x, y) is located, p1 is coordinates of a grid point at the upper left corner, p2 is coordinates of a grid point at the upper right corner, p3 is coordinates of a grid point at the lower left corner, and p4 is coordinates of a grid point at the lower right corner;
step F: after the corrected coordinates (u, v) are calculated; the corrected image is obtained by remapping and interpolating from the input coordinate values (x, y) to the calculated coordinate values (u, v).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510354230.2A CN105046657B (en) | 2015-06-23 | 2015-06-23 | A kind of image stretch distortion self-adapting correction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510354230.2A CN105046657B (en) | 2015-06-23 | 2015-06-23 | A kind of image stretch distortion self-adapting correction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105046657A CN105046657A (en) | 2015-11-11 |
| CN105046657B true CN105046657B (en) | 2018-02-09 |
Family
ID=54453177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510354230.2A Expired - Fee Related CN105046657B (en) | 2015-06-23 | 2015-06-23 | A kind of image stretch distortion self-adapting correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105046657B (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528758B (en) * | 2016-01-12 | 2018-12-14 | 武汉精测电子集团股份有限公司 | Image based on programmable logic device remaps method and device |
| KR102500715B1 (en) * | 2016-07-28 | 2023-02-17 | 삼성전자주식회사 | Electronic apparatus and controlling method thereof |
| CN106506970B (en) * | 2016-11-30 | 2019-10-11 | 宇龙计算机通信科技(深圳)有限公司 | A kind of image pickup method and terminal |
| CN107155017B (en) * | 2017-06-30 | 2021-01-22 | 上海兆芯集成电路有限公司 | Image acquisition method and device |
| GB2559639B (en) * | 2017-09-08 | 2021-01-06 | Anthropics Tech Limited | Image manipulation |
| CN109544460A (en) * | 2017-09-22 | 2019-03-29 | 宝沃汽车（中国）有限公司 | Image correction method, device and vehicle |
| KR20230065365A (en) * | 2018-05-07 | 2023-05-11 | 구글 엘엘씨 | Perspective distortion correction on faces |
| CN109146808B (en) * | 2018-08-01 | 2022-02-18 | 成都品果科技有限公司 | Portrait beauty method and system |
| CN110232667B (en) * | 2019-06-17 | 2021-06-04 | 厦门美图之家科技有限公司 | Image distortion correction method, device, electronic equipment and readable storage medium |
| CN110276734B (en) * | 2019-06-24 | 2021-03-23 | Oppo广东移动通信有限公司 | Image distortion correction method and device |
| CN112529784B (en) * | 2019-09-18 | 2024-05-28 | 华为技术有限公司 | Image distortion correction method and device |
| CN110689501B (en) | 2019-09-29 | 2022-07-22 | 京东方科技集团股份有限公司 | Distortion correction method and device, electronic equipment and computer readable storage medium |
| CN111091507A (en) * | 2019-12-09 | 2020-05-01 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN111008947B (en) * | 2019-12-09 | 2024-05-07 | Oppo广东移动通信有限公司 | Image processing method and device, terminal equipment and storage medium |
| CN111008605B (en) * | 2019-12-09 | 2023-08-11 | Oppo广东移动通信有限公司 | Linear processing method and device in face image, terminal equipment and storage medium |
| CN112686824A (en) * | 2020-12-30 | 2021-04-20 | 北京迈格威科技有限公司 | Image correction method, image correction device, electronic equipment and computer readable medium |
| CN113052900A (en) * | 2021-04-23 | 2021-06-29 | 深圳市商汤科技有限公司 | Position determination method and device, electronic equipment and storage medium |
| CN114049281B (en) * | 2021-12-23 | 2024-08-20 | 厦门大学 | Wide-angle portrait photo distortion correction method based on self-adaptive grid |
| CN115527215A (en) * | 2022-10-10 | 2022-12-27 | 杭州睿胜软件有限公司 | Image processing method, system and storage medium containing text |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101131435A (en) * | 2006-08-23 | 2008-02-27 | 中国石油集团东方地球物理勘探有限责任公司 | NMO correction stacking method preventing NMO stretching |
| US8447078B2 (en) * | 2006-05-08 | 2013-05-21 | Siemens Aktiengesellschaft | X-ray diagnostic device |
| CN103258328A (en) * | 2013-04-27 | 2013-08-21 | 浙江大学 | Method for locating distorted center of wide-field lens |
| CN103283214A (en) * | 2011-01-06 | 2013-09-04 | 松下电器产业株式会社 | Camera, distortion correction device and distortion correction method |
-
2015
- 2015-06-23 CN CN201510354230.2A patent/CN105046657B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447078B2 (en) * | 2006-05-08 | 2013-05-21 | Siemens Aktiengesellschaft | X-ray diagnostic device |
| CN101131435A (en) * | 2006-08-23 | 2008-02-27 | 中国石油集团东方地球物理勘探有限责任公司 | NMO correction stacking method preventing NMO stretching |
| CN103283214A (en) * | 2011-01-06 | 2013-09-04 | 松下电器产业株式会社 | Camera, distortion correction device and distortion correction method |
| CN103258328A (en) * | 2013-04-27 | 2013-08-21 | 浙江大学 | Method for locating distorted center of wide-field lens |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105046657A (en) | 2015-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105046657B (en) | A kind of image stretch distortion self-adapting correction method | |
| US10609282B2 (en) | Wide-area image acquiring method and apparatus | |
| US9094672B2 (en) | Stereo picture generating device, and stereo picture generating method | |
| JP5437311B2 (en) | Image correction method, image correction system, angle estimation method, and angle estimation device | |
| KR101956149B1 (en) | Efficient Determination of Optical Flow Between Images | |
| WO2020259271A1 (en) | Image distortion correction method and apparatus | |
| US9262807B2 (en) | Method and system for correcting a distorted input image | |
| Wei et al. | Fisheye video correction | |
| CN110264426B (en) | Image distortion correction method and device | |
| CN106875339A (en) | A kind of fish eye images joining method based on strip scaling board | |
| CN102436671B (en) | Virtual viewpoint drawing method based on depth value non-linear transformation | |
| KR20120021149A (en) | Image correcting apparatus, correction image generating method, correction table generating apparatus, correction table generating method, computer readable recording medium storing a correction table generating program, computer readable recording medium storing a correction image generating program | |
| US8965105B2 (en) | Image processing device and method | |
| CN104580933A (en) | Multi-scale real-time monitoring video stitching device based on feature points and multi-scale real-time monitoring video stitching method | |
| CN109859137B (en) | Wide-angle camera irregular distortion global correction method | |
| CN110246161B (en) | Method for seamless splicing of 360-degree panoramic images | |
| CN110660034B (en) | Image correction method and device and electronic equipment | |
| TWI517094B (en) | Image calibration method and image calibration circuit | |
| KR101597915B1 (en) | Image processing apparatus and image processing method | |
| TWI443604B (en) | Image correction method and image correction apparatus | |
| CN116152121B (en) | Curved surface screen generating method and correcting method based on distortion parameters | |
| CN117058183A (en) | Image processing method and device based on double cameras, electronic equipment and storage medium | |
| CN106162125A (en) | A kind of gentle curve projection correction method and system thereof | |
| EP3229106A1 (en) | Efficient determination of optical flow between images | |
| CN114998496A (en) | Orthoimage rapid generation method based on scene aerial photography image and sparse point cloud |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180209 Termination date: 20210623 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |