WO2019041651A1

WO2019041651A1 - Image correction method, apparatus and device, and computer readable storage medium

Info

Publication number: WO2019041651A1
Application number: PCT/CN2017/116731
Authority: WO
Inventors: 杨铭
Original assignee: 广州视源电子科技股份有限公司
Priority date: 2017-08-30
Filing date: 2017-12-17
Publication date: 2019-03-07
Also published as: CN107516292A

Abstract

Disclosed in the present invention is an image correction method, comprising: obtaining a target image of a writing board by means of a video camera in response to a trigger instruction, wherein a plurality of markers is manufactured on the writing board; obtaining a first coordinate according to a preset algorithm, wherein the first coordinate is a coordinate of the marker in the target image; obtaining, according to a second coordinate and the first coordinate, a coordinate mapping relation between the writing board and an image obtained by the video camera, wherein the second coordinate is a coordinate of the marker on the writing board; correcting the image obtained by the video camera as a blackboard-writing image according to the coordinate mapping relation after confirming that the image obtained by the video camera contains the writing board displaying the blackboard-writing image. Accordingly, also disclosed in the present invention are an image correction apparatus and device, and a computer readable storage medium. Implementing the present invention can solve the problem that the image distortion occurs in automatic capture of the blackboard-writing image to affect reading, and the readability of the captured image can be improved.

Description

Image correction method, device, device and computer readable storage medium

Technical field

The present invention relates to image processing technology, and more particularly to an image correction method, apparatus, device, and computer readable storage medium.

Background technique

The writing board on the electronic whiteboard provided by the touch screen terminal has the advantages of no dust, no effort and easy erasing, so the electronic whiteboard is gradually popularized in the teaching classroom. However, it is not a substitute for the traditional blackboard, because the electronic whiteboard can not restore some details such as the pen, which may result in poor viewing of the saved blackboard, especially for courses that need to restore handwriting details, such as art, calligraphy, and so on. Moreover, it is impossible to exclude the interference of auxiliary educational equipment (such as a triangular board). For example, when using a triangular board to measure on the blackboard, the touch screen will misjudge that the triangular board is the content of the board and display it, resulting in more unnecessary contents of the final displayed board.

Traditional writing boards, such as blackboards and whiteboards, are not convenient for keeping the contents of the board written by the teacher on the writing pad. If the student or teacher needs to record the contents of the board, take a picture of the board. Manually taking photos affects the quality of the class, but if you set up an automatic camera to take an automatic photo, the captured image will be distorted and inconvenient to read.

Summary of the invention

The invention provides an image correction method, device, device and computer readable storage medium, so as to restore the real picture displayed by the writing board after automatically capturing an image of the book content on the classroom, and improve the readable image of the captured image. Sex.

In a first aspect, an embodiment of the present invention provides an image correction method, including:

Acquiring, by the camera, a target image of the tablet in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

Obtaining a first coordinate according to a preset algorithm; wherein the first coordinate is a coordinate of the identifier in the target image;

Obtaining a coordinate mapping relationship between the writing board and an image acquired by the camera according to the second coordinate and the first coordinate; wherein the second coordinate is a coordinate of the identifier on the writing board ;

After confirming that the image acquired by the camera includes the tablet on which the blackboard image is displayed, the image acquired by the camera is corrected to the blackboard image according to the coordinate mapping relationship.

In a second aspect, an embodiment of the present invention further provides an image correction apparatus, where the apparatus includes:

a photographing module, configured to acquire a target image of the writing board by the camera in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

An acquiring module, configured to acquire a first coordinate according to a preset algorithm, where the first coordinate is a coordinate of the identifier in the target image;

a mapping module, configured to obtain, according to the second coordinate and the first coordinate, a coordinate mapping relationship between the writing board and an image acquired by the camera; wherein the second coordinate is that the identifier is in the The coordinates on the writing pad;

The correction module is configured to correct the image acquired by the camera to the blackboard image according to the coordinate mapping relationship after the image obtained by the confirmation camera includes the tablet on which the blackboard image is displayed.

In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:

One or more processors;

a memory for storing one or more programs;

a camera for taking images;

The one or more programs are executed by the one or more processors such that the one or more processors implement the image correction method described above.

In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, the program being implemented by the processor to implement the image correction method described above.

In the embodiment of the present invention, an image of the writing board is acquired by the camera by making the identifier on the writing board, so that the image acquired by the writing board and the camera can be obtained according to the coordinates of the marker on the writing board and the coordinates in the image acquired by the camera. The coordinate mapping relationship between the two can be used to restore the actual picture displayed on the tablet after automatically capturing the image of the board content on the board. Solving the problem of automatic distortion of the image of the book is affected by the distortion of the image, and the effect of improving the readability of the captured image is achieved.

DRAWINGS

1 is a flowchart of an image correction method according to Embodiment 1 of the present invention;

2a is a schematic diagram of an image taken by a camera in Embodiment 1 of the present invention;

2b is a schematic diagram showing an image displayed on a tablet in the first embodiment of the present invention;

3 is a flowchart of an image correction method according to Embodiment 2 of the present invention;

4 is a schematic structural diagram of an image correcting apparatus according to Embodiment 3 of the present invention;

FIG. 5 is a schematic structural diagram of a device according to Embodiment 4 of the present invention.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. It should also be noted that, for ease of description, only some, but not all, of the structures related to the present invention are shown in the drawings.

Embodiment 1

1 is a flowchart of an image correction method according to Embodiment 1 of the present invention. The present embodiment is applicable to a method for performing distortion correction on an image of a board book content captured by a camera. The method may be performed by an image correction device, including The following steps 110 to 130 are performed.

Step 110: Acquire a target image of the writing board by using a camera in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

Wherein, the target image of the writing board is acquired by the camera, that is, the image taken by the camera facing the writing board is as shown in FIG. 2a, and since the camera is facing the writing board, all the display contents on the writing board can be photographed, and the image displayed on the writing board is as Figure 2b shows.

Step 120: Acquire a first coordinate according to a preset algorithm, where the first coordinate is a coordinate of the identifier in the target image.

Step 130: Obtain a coordinate mapping relationship between the writing board and an image acquired by the camera according to the second coordinate and the first coordinate; wherein the second coordinate is the identifier on the writing board The coordinates on the top.

Step 140: After confirming that the image acquired by the camera includes the tablet on which the blackboard image is displayed, correct the image acquired by the camera to the blackboard image according to the coordinate mapping relationship.

How the image correction method works:

A plurality of markers are formed on the tablet, which may be printed on the tablet or inlaid with markers, and the coordinates of the markers on the tablet are known during the design and production of the tablet. Since the tablet displays a picture, the coordinates of the tablet are equivalent to the image coordinates displayed on the tablet. After the target image is captured by the camera, the marker can be detected and the coordinates can be read according to the image detection algorithm. According to the coordinates of the identifier in the two images, the coordinate mapping relationship between the two images can be obtained, and with this relationship, the subsequently captured image can be restored to the image displayed on the tablet. That is, after the image including the board content is captured by the camera, the board image displayed by the tablet may be obtained according to the image acquired by the camera and the coordinate mapping relationship. The specific reduction method is to use the mapping relationship to find the coordinates on the captured image corresponding to the coordinates in the image to be restored, and take the feature values (such as RGB values or gray values to represent the feature values of the colors on the coordinates). ) as the feature value of the coordinates in the image to be restored.

Simply, the marker with the coordinates P _B (u _B , v _B , 0) on the writing board has the coordinates P _I (u _I , v _I , 0) in the captured target image, and P _B (u _B can be set. The conversion function between v _B , 0) and P _I (u _I , v _I , 0) is:

By using the coordinate values of the plurality of markers, the values of the elements of the matrix H can be solved, thereby obtaining the conversion function. In the specific implementation, H is a matrix of 3*3, and one element can be used as the homogeneous coordinate. , at least 4 markers must be combined, and 8 sets of equations can be combined to solve the matrix H. In addition, the coordinate mapping parameters between the writing board and the target image can be obtained by using the Zhang's calibration method, that is, the internal and external parameters of the camera calibration are obtained; other more complicated calibration methods can also be used.

In a specific implementation, the conversion function can be directly used as a coordinate mapping relationship between the tablet and the image acquired by the camera. For each coordinate on the image displayed on the tablet to be restored, the conversion function is used to find a corresponding camera shot. The coordinates in the image.

The identifier of the embodiment of the present invention may be a silk screen with a large contrast difference between the background of the writing board and the background of the writing board, or a silk screen on the special jig, or even a bulb or an infrared diode embedded in the writing board, and the marker is a writing. Intrinsic to the board or fixture, the coordinates will not change easily, so the calibration accuracy is high. The marker is arranged on the border of the writing board so as not to cover the content of the writing board, so that the mapping relationship can be performed under the condition that the writing board is normally used, and can be recalibrated at any time, thereby improving the reliability of saving the image of the blackboard in time.

For a special marker, the corresponding image detection algorithm needs to be set to read the coordinates of the marker. For a marker with a large contrast between the color and the background color of the tablet, the feature value corresponding to each coordinate may be read under a specific color model, and the region pattern corresponding to the set feature value range is extracted by using the binarization method as the identifier. Things. The edge detection method may also be used and the edge is obtained by fitting the edge with the set model, that is, step 120 includes: detecting an edge of the identifier in the target image; and searching for the identifier according to the detected edge The coordinates of the specified corner point are taken as the first coordinate.

Based on the foregoing technical solution, the embodiment further provides a preferred manner to implement step 130.

Specifically, step 130 may obtain an internal parameter of the camera according to the coordinates of the identifier on the tablet and the coordinates of the identifier in the target image by using a Zhang's calibration method or other more complicated algorithms. And the outer parameter is equivalent to obtaining a coordinate mapping relationship between the image displayed by the tablet and the image captured by the camera. According to the internal parameter and the external parameter, the blackboard image displayed by the tablet can be obtained from the image of the board content captured by the camera.

Further, in order to reduce the error, the internal parameters can be corrected. Specifically, after the camera is calibrated according to the first coordinate and the second coordinate, and the internal parameter and the external parameter of the camera are obtained, the method further includes:

Calculating, by the first coordinate, a theoretical coordinate of the identifier according to the inner parameter and the outer parameter;

If the theoretical coordinate of the identifier does not match the second coordinate, modifying the theoretical coordinate of the identifier to match the second coordinate;

Adjusting coordinates are calculated according to the theoretical parameters of the modified identifier according to the external parameters;

Calculating a coordinate mapping parameter between the adjustment coordinate and the first coordinate;

The internal parameters of the camera are replaced with the coordinate mapping parameters.

In the above further solution, wherein the internal parameters of the camera include a camera main point, a focal length, and a distortion parameter, which may be represented by θ; the external parameters of the camera are obtained by the image on the target panel and the distortion caused by the elimination of the internal parameters of the captured image. The homography matrix between images can be represented by M, then H = θ * M. According to the conversion function, the theoretical coordinate P' _{B of the} marker can be obtained from P _I (u _I , v _I , 0). If the theoretical coordinate P' _B and the second coordinate do not match, it is modified to the matched coordinate P _B (ie, the accurate coordinate calculated by P _I from the internal parameter θ and the outer parameter M without error) Value), the adjusted coordinate P _C =MP _B can be obtained from the modified theoretical coordinates according to the external parameter M. The coordinate mapping parameter between P _C and P _I is calculated, and the inner parameter θ is replaced by the coordinate mapping parameter, so that the coordinate mapping relationship between the image displayed by the tablet that reduces the error and the image acquired by the camera is obtained.

In the specific implementation, the correction of the theoretical coordinates can be realized through human-computer interaction, avoiding errors caused by external environmental factors.

Specifically, if the theoretical coordinate of the identifier does not match the second coordinate, the theoretical coordinate of the identifier is modified to match the second coordinate, and specifically includes:

Obtaining an image displayed by the writing board according to an image captured by the camera and an internal parameter and an external parameter of the camera;

Displaying the obtained image through the touch screen terminal, and providing a drag control point at a position corresponding to the theoretical coordinate of the identifier on the image;

Detecting whether the drag control point is dragged by the user to a position corresponding to other coordinates;

If yes, determining that the theoretical coordinate of the identifier does not match the second coordinate; modifying the theoretical coordinate of the identifier to the coordinate of the drag control point;

If not, it is determined that the theoretical coordinates of the marker match the second coordinate.

The above specific scheme allows the user to drag the marker to a position that the user thinks matches the coordinates of the marker on the tablet using an input device such as a mouse or a touch screen, and then correct the internal parameter θ according to the position. This method visualizes the parameters and allows the user to visually evaluate whether the current parameters are accurate enough and to make manual adjustments.

In the technical solution of the embodiment, the image of the writing board is acquired by the camera by making the identifier on the writing board, so that the writing board and the camera can be obtained according to the coordinates of the marker on the writing board and the coordinates in the image acquired by the camera. The coordinate mapping relationship between the acquired images, so that the real picture displayed on the tablet can be restored after automatically capturing the image of the board content contained in the class. Solving the problem of automatic distortion of the image of the book is affected by the distortion of the image, and the effect of improving the readability of the captured image is achieved.

Embodiment 2

FIG. 3 is a flowchart of an image correction method according to Embodiment 2 of the present invention. The present embodiment is applicable to a case where distortion correction is performed on an image of a board book content captured by a camera, and the method may be performed by an image correction device. The difference between this embodiment and the first embodiment is that the first embodiment records the coordinate mapping relationship between the image displayed by the tablet and the image captured by the camera by using a coordinate mapping parameter or a conversion function, and the embodiment records in a list manner. The coordinate mapping relationship. The image correction method provided in this embodiment includes:

Step 310: Acquire a target image of the writing board by the camera in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

Step 320: Acquire a first coordinate according to a preset algorithm, where the first coordinate is a coordinate of the identifier in the target image;

Step 330: Calculate a conversion function between the first coordinate and the second coordinate;

Step 340: Establish a mapping list between each coordinate in the writing board and coordinates in the image acquired by the camera according to the conversion function.

The

above steps

330 and 340 first calculate a conversion function between the coordinates of the marker on the tablet and the coordinates in the captured image, and then establish a mapping list of coordinates according to the conversion function. In this method, when the board image displayed on the tablet is subsequently restored, the coordinates on the captured image corresponding to the coordinate points on the board image can be directly obtained by looking up the table, and the feature value is read as its own feature value. When the image is restored, it is not necessary to calculate according to the conversion function, and the processing speed is increased, that is, after step 340, the method further includes:

Step 350: After confirming that the image acquired by the camera includes the writing board displaying the blackboard image, querying the mapping list to obtain coordinates in the image acquired by the camera corresponding to each coordinate in the blackboard image;

Step 360: Read the feature value of the queried coordinate as the feature value of the corresponding coordinate in the blackboard image.

Steps

350 and 360 enable the captured image to be corrected in time during the teaching process, and further displayed in the classroom through the display terminal in real time.

In the technical solution of the embodiment, the image of the writing board is acquired by the camera by making the identifier on the writing board, so that the writing board and the camera can be obtained according to the coordinates of the marker on the writing board and the coordinates in the image acquired by the camera. Obtaining the conversion function between the images, thereby obtaining a coordinate correspondence list between the two images, so that after automatically capturing the image containing the contents of the blackboard in the classroom, it is not necessary to calculate the corresponding coordinate values according to the conversion function, and only need to check The table and pixel interpolation can restore the real picture displayed on the tablet.

Embodiment 3

4 is a schematic structural diagram of an image correction apparatus according to Embodiment 3 of the present invention, where the apparatus includes:

The photographing module 410 is configured to acquire a target image of the writing board by the camera in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

The obtaining module 420 is configured to acquire a first coordinate according to a preset algorithm, where the first coordinate is a coordinate of the identifier in the target image;

a mapping module 430, configured to obtain, according to the second coordinate and the first coordinate, a coordinate mapping relationship between the writing board and an image acquired by the camera; wherein the second coordinate is that the identifier is in the The coordinates on the writing board;

The correction module 440 is configured to correct the image acquired by the camera to the blackboard image according to the coordinate mapping relationship after the image obtained by the confirmation camera includes the tablet on which the blackboard image is displayed.

As an implementation manner, the mapping module 430 includes:

a calculating unit, configured to calculate a conversion function between the first coordinate and the second coordinate;

a table building unit, configured to establish, according to the conversion function, a mapping list between each coordinate in the writing board and coordinates in an image acquired by the camera;

The image correcting device further includes:

a table lookup unit, configured to query the map list after the image obtained by the confirmation camera includes the tablet with the blackboard image, and obtain coordinates in the image acquired by the camera corresponding to each coordinate in the book image;

And a replacement unit, configured to read the feature value of the queried coordinate as the feature value of the corresponding coordinate in the blackboard image.

Preferably, the obtaining module 420 includes:

a detecting unit, configured to detect an edge of the identifier in the target image;

And a searching unit, configured to search for coordinates of the specified corner point in the identifier as the first coordinate according to the detected edge.

As another implementation manner, the mapping module 430 includes a calibration unit, configured to obtain an internal parameter and an external parameter of the camera according to the first coordinate and the second, calibration camera.

The mapping module 430 further includes:

a prediction unit, configured to calculate, by the first coordinate, a theoretical coordinate of the identifier according to the inner parameter and the outer parameter;

a correction unit, configured to modify a theoretical coordinate of the identifier to match the second coordinate if the theoretical coordinate of the identifier does not match the second coordinate;

An adjusting unit, configured to calculate an adjusted coordinate according to the theoretical parameter of the modified identifier according to the external parameter;

a correction parameter calculation unit, configured to calculate a coordinate mapping parameter between the adjustment coordinate and the first coordinate;

And a second replacement unit, configured to replace the internal parameter of the camera by using the coordinate mapping parameter.

Further, the modifying unit specifically includes:

a display unit, configured to obtain an image displayed by the tablet according to an image captured by the camera and an internal parameter and an external parameter of the camera; display the obtained image through the touch screen terminal, and correspond to a theoretical coordinate of the identifier on the image The location provides a drag handle;

a detecting unit, configured to detect whether the drag control point is dragged by a user to a position corresponding to another coordinate;

a modifying unit, if yes, determining that the theoretical coordinate of the identifier does not match the second coordinate; modifying a theoretical coordinate of the identifier to a coordinate of the drag control point;

And a maintaining unit, if not, determining that the theoretical coordinate of the identifier matches the second coordinate.

The image correction device provided by the embodiment of the present invention may perform an image correction method provided by any embodiment of the present invention, and has a function module and a beneficial effect corresponding to the execution method.

Embodiment 4

FIG. 5 is a schematic structural diagram of a device according to Embodiment 4 of the present invention. As shown in FIG. 5, the device includes a processor 510, a memory 520, an input device 530, an output device 540, and a camera 550 for capturing an image; The number of the processors 510 may be one or more, and one processor 510 is taken as an example in FIG. 5; the processor 510, the memory 520, the input device 530, and the output device 540 in the device may be connected by a bus or other manner. In 5, the bus connection is taken as an example.

The memory 520 is used as a computer readable storage medium, and can be used for storing a software program, a computer executable program, and a module, such as a program instruction/module corresponding to the image correction method in the embodiment of the present invention (for example, a shooting module in the image correction device) 410. An acquisition module 420, a mapping module 430, and a correction module 440). The processor 510 performs various functional applications and data processing of the device by executing software programs, instructions, and modules stored in the memory 520, that is, implementing the image correction method described above.

The memory 520 may mainly include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the terminal, and the like. Further, the memory 520 may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, flash memory device, or other nonvolatile solid state storage device. In some examples, memory 520 can further include memory remotely located relative to processor 510, which can be connected to the device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Input device 530 can be used to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output device 540 can include a display device such as a display screen.

Embodiment 5

A fifth embodiment of the present invention further provides a computer readable storage medium storing a computer program, where the program is implemented by a computer processor to implement an image correction method, the method comprising:

Of course, the computer readable storage medium storing the computer program, the computer executable instructions are not limited to the method operations as described above, and may also perform the image correction method provided by any embodiment of the present invention. Related operations in .

Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by software and necessary general hardware, and can also be implemented by hardware, but in many cases, the former is a better implementation. . Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk of a computer. , Read-Only Memory (ROM), Random Access Memory (RAM), Flash (FLASH), hard disk or optical disk, etc., including a number of instructions to make a computer device (can be a personal computer) The server, or network device, etc.) performs the methods described in various embodiments of the present invention.

It should be noted that, in the embodiment of the image correcting apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above-mentioned partitioning, as long as the corresponding functions can be implemented; The specific names of the functional units are also for convenience of distinguishing from each other and are not intended to limit the scope of the present invention.

Note that the above are only the preferred embodiments of the present invention and the technical principles applied thereto. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments described herein, and that various modifications, changes and substitutions may be made without departing from the scope of the invention. Therefore, the present invention has been described in detail by the above embodiments, but the present invention is not limited to the above embodiments, and other equivalent embodiments may be included without departing from the inventive concept. The scope is determined by the scope of the appended claims.

Claims

An image correction method, comprising:

Acquiring, by the camera, a target image of the tablet in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

Obtaining a first coordinate according to a preset algorithm; wherein the first coordinate is a coordinate of the identifier in the target image;

Obtaining a coordinate mapping relationship between the writing board and an image acquired by the camera according to the second coordinate and the first coordinate; wherein the second coordinate is a coordinate of the identifier on the writing board ;

After confirming that the image acquired by the camera includes the tablet on which the blackboard image is displayed, the image acquired by the camera is corrected to the blackboard image according to the coordinate mapping relationship.
The image correction method according to claim 1, wherein said marker is formed at an edge of said writing board.
The image correction method according to claim 1, wherein the obtaining a mapping relationship between the tablet and the image acquired by the camera according to the second coordinate and the first coordinate comprises:

Calculating a conversion function between the first coordinate and the second coordinate;

Establishing a mapping list between each coordinate in the tablet and coordinates in an image acquired by the camera according to the conversion function;

Then, after the image obtained by the confirmation camera includes the tablet with the blackboard image, the image acquired by the camera is corrected to the blackboard image according to the coordinate mapping relationship, and specifically includes:

After confirming that the image acquired by the camera includes the tablet displaying the blackboard image, querying the mapping list to obtain coordinates in the image acquired by the camera corresponding to each coordinate in the blackboard image;

The feature value of the queried coordinate is read as the feature value of the corresponding coordinate in the blackboard image.
The image correction method according to any one of claims 1 to 3, wherein the acquiring the first coordinate according to the preset algorithm comprises:

Detecting an edge of the identifier in the target image;

Based on the detected edge, the coordinates of the specified corner point in the identifier are searched for as the first coordinate.
The image correction method according to any one of claims 1 to 3, wherein the marker is printed or mounted on the tablet.
An image correction device, comprising:

a photographing module, configured to acquire a target image of the writing board by the camera in response to the triggering instruction; wherein the writing board is formed with a plurality of markers;

An acquiring module, configured to acquire a first coordinate according to a preset algorithm, where the first coordinate is a coordinate of the identifier in the target image;

a mapping module, configured to obtain, according to the second coordinate and the first coordinate, a coordinate mapping relationship between the writing board and an image acquired by the camera; wherein the second coordinate is that the identifier is in the The coordinates on the writing pad;

The correction module is configured to correct the image acquired by the camera to the blackboard image according to the coordinate mapping relationship after the image obtained by the confirmation camera includes the tablet on which the blackboard image is displayed.
The image correction device according to claim 6, wherein the mapping module comprises:

a calculating unit, configured to calculate a conversion function between the first coordinate and the second coordinate;

a table building unit, configured to establish, according to the conversion function, a mapping list between each coordinate in the writing board and coordinates in an image acquired by the camera;

Then the correction module comprises:

a table lookup unit, configured to query the map list after the image obtained by the confirmation camera includes the tablet with the blackboard image, and obtain coordinates in the image acquired by the camera corresponding to each coordinate in the book image;

And a replacement unit, configured to read the feature value of the queried coordinate as the feature value of the corresponding coordinate in the blackboard image.
The image correction device according to claim 7, wherein the acquisition module comprises:

a detecting unit, configured to detect an edge of the identifier in the target image;

And a searching unit, configured to search for coordinates of the specified corner point in the identifier as the first coordinate according to the detected edge.
A device, characterized in that the device comprises:

One or more processors;

a memory for storing one or more programs;

a camera for taking images;

The one or more programs are executed by the one or more processors such that the one or more processors implement the image correction method of any of claims 1-5.
A computer readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor to implement the image correction method according to any one of claims 1-5.