CN114500857A - An image capturing method, device, terminal device and storage medium - Google Patents

Abstract

The embodiment of the invention discloses an image shooting method, an image shooting device, terminal equipment and a storage medium. Be applied to terminal equipment, terminal equipment is including the camera module, but the camera module free rotation is in order to shoot the image in different regions, and the method includes: determining a shooting mode of a target area; controlling the camera module to rotate according to the shooting mode and the pre-divided sub-regions so as to enable the camera module to shoot images of different sub-regions in the rotating process; the sub-area is obtained by dividing a target area in advance; target information is acquired from the image. According to the embodiment of the invention, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can shoot images of different sub-regions. When the shooting scope of camera module has been guaranteed, can reduce the edge distortion of the image of shooing, solved the poor technical problem of learning auxiliary assembly's formation of image effect among the prior art.

Description

An image capturing method, device, terminal device and storage medium

technical field

The embodiments of the present application relate to the field of images, and in particular, to an image capturing method, apparatus, terminal device, and storage medium.

Background technique

At present, in order to assist students in their learning, learning aids have been widely used in teaching. Existing learning aids are generally installed on electronic devices such as tablet computers, with lifting and rotating cameras or mirrors and cameras, so that when the tablet computer is used in a vertical position, the camera can take pictures of objects such as exercise books or books. However, in the actual use process, the photographing effect of this method is relatively poor. For example, limited by the field of view of the camera, the area that the camera can shoot is limited, and limited by the depth of field of the camera, learning aids cannot be applied to scenes with uneven thickness of books, uneven objects, or large-angle shooting of distant scenes; Limited by the distortion of the camera, the edge distortion of the image captured by the camera is relatively serious. In addition, when the size of the target object is large, or the distance from the camera is far, due to the limitation of the optical principle of shooting, in the area close to the tablet computer or the camera, the corresponding camera CMOS pixels are more, and the captured image It is relatively clear and the degree of restoration is relatively high; while in the area far from the tablet computer or the camera, the captured image is obviously deformed, and the captured font is small, which is not easy to distinguish.

To sum up, how to improve the imaging effect of learning aids has become a technical problem that needs to be solved urgently.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide an image capturing method, device, terminal device and storage medium, which can improve the imaging effect of the image and solve the technical problem of poor imaging effect of the learning auxiliary device in the prior art.

In a first aspect, an embodiment of the present invention provides an image capturing method, which is applied to a terminal device. The terminal device includes a camera module, and the camera module can be freely rotated to capture images of different regions. The method include:

Determine the shooting mode of the target area;

According to the shooting mode and the pre-divided sub-regions, the camera module is controlled to rotate, so that the camera module can capture images of different sub-regions during the rotation process; The target area is divided into;

Obtain target information from the image.

Preferably, dividing the target area includes:

Determine the angular range when the camera module rotates according to the target area;

Determine the step size of each rotation of the camera module;

The camera module is controlled to rotate according to the step size within the angle range, and the area captured by the camera module after each rotation is divided into a sub-area.

Preferably, dividing the target area includes:

acquiring a target image, the target image is obtained by photographing the target area;

The boundary of the target object is determined in the target image, a first image corresponding to the range of the boundary is determined in the target image, and the first image is divided to obtain a plurality of sub-regions.

Preferably, the first image is divided to obtain a plurality of sub-regions, including:

The first image is uniformly divided into M columns in the horizontal direction, and each column is non-uniformly divided into N rows in the longitudinal direction to obtain M×N sub-regions.

Preferably, the first image is divided to obtain a plurality of sub-regions, including:

performing character recognition on the first image to obtain characters in the first image;

The size of the text is determined, and the first image is divided according to the size of the text to obtain a plurality of sub-regions.

Preferably, the first image is divided according to the text size to obtain a plurality of sub-regions, including:

The first image is evenly divided into M columns in the horizontal direction, and each column is non-uniformly divided into N rows in the longitudinal direction to obtain M×N sub-regions, and the size of each of the sub-regions is the same as the size of the text. is positively correlated.

Preferably, the first image is divided to obtain a plurality of sub-regions, including:

A template type of the first image is determined, a division rule corresponding to the template type is acquired, and the first image is divided according to the division rule to obtain a plurality of sub-regions.

Preferably, the shooting mode is any one of a global scanning mode, a local scanning mode and a target tracking mode.

Preferably, the shooting mode is a global scanning mode. Correspondingly, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating. images of different sub-areas in the , including:

Determine the path for the camera module to shoot the sub-region according to the pre-divided sub-region, and control the camera module to rotate according to the path, so that the camera module can shoot different sub-regions during the rotation process. image of the area.

Preferably, the shooting mode is a local scanning mode. Correspondingly, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating. images of different sub-areas in the , including:

acquiring a global image of the target area in real time;

determining a first area to be photographed in the global image;

Determine the first sub-area included in the first area, determine the first path for the camera module to shoot the first sub-area, and control the camera module to rotate according to the first path, so that the camera The module captures an image of the first sub-region during the rotation.

Preferably, the shooting mode is a target tracking mode. Correspondingly, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating. images of different sub-areas in the , including:

Determine the position of the target object in the target area, and determine the second sub-area corresponding to the position;

determining that the camera module is rotated to a target angle corresponding to the second sub-area;

The camera module is controlled to rotate to the target angle, so that the camera module captures an image of the second sub-region.

Preferably, the obtaining target information from the image includes:

combining the images to obtain a second image;

Perform character recognition on the second image to obtain a target character, obtain a corresponding standard character in a database according to the target character, compare the target character with the standard character, and obtain a comparison result.

Preferably, the obtaining target information from the image includes:

Perform character recognition on the image to obtain target characters, obtain corresponding standard characters in a database according to the target characters, and compare the target characters with the standard characters to obtain a comparison result.

Preferably, the obtaining target information from the image includes:

Obtaining all images captured within a preset time period, and extracting handwriting information from each of the all images;

Determine the stroke order according to the handwriting information, and obtain the corresponding standard stroke order according to the handwriting information;

The stroke order is compared with the standard stroke order to obtain a comparison result.

In a second aspect, an embodiment of the present invention provides an image capturing apparatus, which is applied to a terminal device. The terminal device includes a camera module, and the camera module can be freely rotated to capture images of different regions. The photographing device includes: a mode determination module, a control module and an information acquisition module;

The mode determination module is used to determine the shooting mode of the target area;

The control module is configured to control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can capture images of different sub-regions during the rotation; The sub-region is obtained by dividing the target region in advance;

The information acquisition module is used for acquiring target information from the image.

In a third aspect, an embodiment of the present invention provides a terminal device, where the terminal device includes a processor and a memory;

the memory is used to store a computer program and transmit the computer program to the processor;

The processor is configured to execute the image capturing method according to the first aspect according to the instructions in the computer program.

In a fourth aspect, an embodiment of the present invention provides a storage medium for storing computer-executable instructions, where the computer-executable instructions are used to execute the image capturing method according to the first aspect when executed by a computer processor.

As described above, the embodiments of the present invention provide an image capturing method, device, terminal device, and storage medium, which are applied to the terminal device. The terminal device includes a camera module, and the camera module can be freely rotated to capture images in different areas. The method Including: determining the shooting mode of the target area; controlling the camera module to rotate according to the shooting mode and the pre-divided sub-areas, so that the camera module can shoot images of different sub-areas during the rotation process; It is obtained by dividing the target area; the target information is obtained from the image. In the embodiment of the present invention, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can capture images of different sub-regions. While ensuring the shooting range of the camera module, it can reduce the edge distortion of the captured image and improve the imaging effect of the image, thereby breaking through the limitations of the field of view, depth of field and distortion of a single-angle camera when taking pictures. The technical problem of poor imaging effect of the learning auxiliary device in the prior art is solved.

Description of drawings

FIG. 1 is a flowchart of an image capturing method according to an embodiment of the present invention.

FIG. 2 is a schematic structural diagram of an image capturing apparatus according to an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of another image capturing apparatus according to an embodiment of the present invention.

FIG. 4 is a schematic diagram of dividing a target area according to an embodiment of the present invention.

FIG. 5 is a schematic diagram of a target area captured by a camera module according to an embodiment of the present invention.

FIG. 6 is a flowchart of dividing a target area according to an embodiment of the present invention.

FIG. 7 is a flowchart of dividing a target area according to an embodiment of the present invention.

FIG. 8 is a schematic diagram of dividing a target area according to a text size according to an embodiment of the present invention.

FIG. 9 is a schematic diagram of dividing a target area according to a text size according to an embodiment of the present invention.

FIG. 10 is a schematic diagram of a path for photographing a sub-area according to an embodiment of the present invention.

FIG. 11 is a schematic diagram of a path for photographing a sub-area according to an embodiment of the present invention.

FIG. 12 is a schematic structural diagram of an image capturing apparatus according to an embodiment of the present invention.

FIG. 13 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.

Detailed ways

The following description and drawings sufficiently illustrate specific embodiments of the application to enable those skilled in the art to practice them. The examples represent only possible variations. Unless expressly required, individual components and functions are optional and the order of operations may vary. Portions and features of some embodiments may be included in or substituted for those of other embodiments. The scope of the embodiments of this application includes the full scope of the claims, along with all available equivalents of the claims. Various embodiments may be referred to herein by the term "invention," individually or collectively, for convenience only, and are not intended to automatically limit the scope of this application to any if more than one invention is in fact disclosed. A single invention or inventive concept. Herein, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation and do not require or imply any actual relationship between these entities or operations or order. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method or terminal device comprising a list of elements includes not only those elements, but also those not expressly listed. other elements. The various embodiments herein are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and it is sufficient to refer to each other for the same and similar parts between the various embodiments. As for the structures, products, etc. disclosed in the embodiments, since they correspond to the parts disclosed in the embodiments, the descriptions are relatively simple, and the related parts can be referred to the descriptions of the methods.

As shown in FIG. 1 , FIG. 1 is a flowchart of an image capturing method according to an embodiment of the present invention. The image capturing method provided by the embodiment of the present invention is applied to a terminal device. The terminal device includes a camera module, and the camera module can be freely rotated to capture images of different regions. Exemplarily, in one embodiment, the camera module is a rotatable camera, as shown in FIG. 2 , the rotatable camera can shoot images of different regions by freely rotating, or the camera module is a mirror and a camera. , the reflector is used to reflect external light into the camera, and the reflector can be freely rotated to adjust the angle of the mirror surface of the reflector relative to the camera, as shown in Figure 3. By controlling the mirror to rotate, the mirror surface of the mirror can reflect images of different areas, and the camera obtains images of different areas by shooting the mirror surface of the mirror. It should be further noted that, in this embodiment, an auxiliary camera may also be set in the camera module, so as to be used for auxiliary shooting. Exemplarily, in one embodiment, a camera with a larger viewing angle field is further set in the camera module to capture a global image, or an event camera (dynamic vision sensor) is further set in the camera module, and the event camera is used to The subject is tracked.

An image capturing method provided by an embodiment of the present invention includes the following steps:

Step 101: Determine the shooting mode of the target area.

First, the shooting mode of the target area needs to be determined, and the shooting mode of the target area determines the rotation mode of the camera module. Exemplarily, in one embodiment, if the shooting mode is the scanning mode, it is necessary to control the camera module to scan each position in the target area by rotating, so as to capture the image of each position in the target area until the target area is photographed. image at all positions in the . In another embodiment, if the shooting mode is the target tracking mode, the position of the pen tip can be tracked in the target area through the event camera, and then the camera module can be controlled to rotate according to the position of the pen tip, so that the camera module can track the position of the pen tip. Shooting, get the user's handwriting image, and realize the tracking of the user's handwriting.

It can be understood that, in this embodiment, the manner of determining the shooting mode may be determined according to the mode selection instruction input by the user, or the terminal device may determine according to the object in the target area. Exemplarily, in one embodiment, the terminal device will display an executable shooting mode on the display screen before shooting, and the user selects the shooting mode by clicking on the display screen, thereby sending a mode selection instruction to the terminal device, The terminal device executes the corresponding shooting mode according to the mode selection instruction sent by the user. In another embodiment, before determining the shooting mode, the terminal device will use a camera with a larger field of view to shoot a global image of the target area in advance, identify the target object in the global image, and determine the shooting mode according to the target object . It can be understood that, in this embodiment, the determination method of the shooting mode can be set according to actual needs, and the determination method of the shooting mode is not specifically limited in this embodiment.

Step 102: Control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module captures images of different sub-regions during the rotation; wherein, the sub-regions are obtained by dividing the target region in advance. .

After the shooting mode is determined, the camera module is further controlled to rotate according to the shooting mode and the pre-divided sub-regions. It should be further explained that, in this embodiment, the target area needs to be divided in advance, and the target area is divided into a plurality of sub-areas. Exemplarily, as shown in FIG. 4 , the length and width of the target area in FIG. 4 are Acm and Bcm, respectively, and the target area is divided into multiple sub-areas 1-1, 1-2, 1-3, . . . By dividing the target area into multiple sub-areas, the rotation angle of the camera module corresponding to each sub-area can be determined. When the camera module rotates the corresponding rotation angle, the corresponding sub-area can be photographed, which is convenient for the camera module The group is quickly positioned to the specified sub-area, as shown in Figure 5. According to the shooting mode, the sub-areas that the camera module needs to be photographed can be determined, and the camera can be controlled to rotate by the rotation angle corresponding to the sub-areas to be photographed, so that the sub-areas to be photographed can be photographed, thereby obtaining different sub-areas. image.

It should be further explained that, in this embodiment, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can focus when capturing images of different sub-regions. The center of each sub-region can obtain a clear image of the sub-region, so that the imaging effect in the global scope of the target region is clearer.

Step 103: Obtain target information from the image.

Finally, the target information can be obtained from the image. It can be understood that in this embodiment, the target information can be set according to actual needs. For example, in an embodiment, the target information is text information, and the text in the image is obtained by performing text recognition on the captured image. information, or the target information is handwriting information, and the handwriting information in the image is obtained by performing image recognition on the image.

As described above, the embodiment of the present invention controls the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can capture images of different sub-regions. Compared with the prior art using a single-angle camera to directly shoot the global image of the target area, while ensuring the shooting range of the camera module, the focus of the camera module can be aimed at the center of each sub-region, which can reduce the amount of shooting. The edge distortion of the obtained image improves the imaging effect of the image, thereby breaking through the limitations of the field of view, depth of field and distortion of a single-angle camera when taking pictures. The technical problem of poor imaging effect of the learning auxiliary device in the prior art is solved.

It should be noted that in this embodiment, there are many ways to divide the target area. In one embodiment, the process of dividing the target area is shown in FIG. 6 , including the following steps:

Step 201: Determine the angular range when the camera module rotates according to the target area.

First, it is necessary to determine the angular range of the camera module when it rotates according to the target area. Exemplarily, in one embodiment, the target area is a rectangular area, the camera module is a rotatable camera, the rotatable camera has a horizontal rotation axis and a vertical rotation axis that are perpendicular to each other, and the rotatable camera can rotate around the horizontal rotation axis and the vertical rotation axis. The shaft rotates. According to the length and width of the target area, determine the angular range when the rotatable camera rotates around the two rotation axes, so that when the rotation angle of the rotatable camera reaches the boundary value of the angle range, the rotatable camera can just shoot the target area. border.

Step 202: Determine the step size of each rotation of the camera module.

After that, the step length of each rotation of the camera module is further determined. Exemplarily, in one embodiment, the first step is set to rotate the rotatable camera by 10° around the lateral rotation axis, and the second step is set to rotate the rotatable camera by 5° around the longitudinal rotation axis, or, respectively, Divide the angular range of the rotatable camera around the rotation axis into several parts, so as to obtain the step size when the rotatable camera rotates around the rotation axis. Exemplarily, in one embodiment, the rotation angle range of the rotatable camera around the lateral rotation axis is ±120°, that is, ±120° is equally divided into 10 parts, that is, the step length of the rotation of the rotating camera around the lateral rotation axis is 24°. .

Step 203 , controlling the camera module to rotate according to the step length within the angle range, and dividing the area photographed by the camera module after each rotation into a sub-area.

After that, the camera module is controlled to rotate by one step each time, and the area captured by the camera module after each rotation is divided into a sub-area. It is understandable that the rotation angle of the camera during the rotation process must not exceed the angle range. And the area captured by the camera module after each rotation is divided into a sub-area. Exemplarily, in one embodiment, the angular range of rotation of the rotatable camera around the lateral rotation axis is ±120°, the first length of the rotation of the rotatable camera around the lateral rotation axis is 10°, and the rotatable camera around the longitudinal rotation axis The rotation angle range is ±60°, and the second step of rotating the rotatable camera around the longitudinal rotation axis is 10°. At the beginning, control the rotatable camera to rotate to (120°, 60°), and set the position of the rotatable camera at this time. The captured area is used as a sub-area. After that, the rotatable camera is controlled to rotate a first step around the horizontal rotation axis. At this time, the rotatable camera is rotated to (110°, 60°), and the The area of is used as a sub-area, ..., when the rotatable camera is rotated to (-120°, 60°), the rotatable camera is controlled to rotate around the longitudinal rotation axis by a second step, and the rotatable camera is rotated to (-120 °, 50°), and then re-control the rotatable camera to rotate a first step around the horizontal rotation axis, and so on, until the rotatable camera has photographed every position in the target area, thereby dividing the target area into multiple sub-regions.

It should be further explained that, in one embodiment, the target area may also be divided into multiple sub-areas according to the rotation time of the camera module, so that the time required for the camera module to rotate to an angle corresponding to each sub-area is equal.

In another embodiment, the process of dividing the target area is shown in FIG. 7 , including the following steps:

Step 301: Acquire a target image, and the target image is obtained by photographing the target area.

In this embodiment, a target image of the target area is obtained first, and the target image can be obtained by photographing the target area by a camera with a larger viewing angle field in the camera module.

Step 302: Determine the boundary of the target object in the target image, determine a first image corresponding to the range of the boundary in the target image, and divide the first image to obtain a plurality of sub-regions.

After the target image is acquired, the boundary of the target object is further determined in the target image, and the target object can be set according to actual needs, such as a textbook or a test paper. After the boundary except the target object is determined, a first image within the boundary range is cut out from the target image, and the first image is divided to obtain a plurality of sub-regions. It can be understood that when the target object moves, the boundary of the target object will change. Therefore, in this embodiment, when the boundary of the target object changes, it is necessary to re-adjust and calibrate the sub-region according to the degree of boundary change.

In this embodiment, there are many ways to divide the first image. In one embodiment, the first image is divided in step 302 to obtain a plurality of sub-regions, which is specifically executed by step 3021, including:

Step 3021: Divide the first image into M columns uniformly in the horizontal direction, and divide each column non-uniformly into N rows in the longitudinal direction to obtain M×N sub-regions.

In one embodiment, the first image may be directly divided, the first image is evenly divided into M columns in the horizontal direction, and each column is non-uniformly divided into M rows in the longitudinal direction to obtain M×N sub-regions, such as shown in Figure 4. It should be further explained that the purpose of dividing each column into M rows non-uniformly in the longitudinal direction is that for the sub-areas close to the lower part of the rotatable camera, the range captured by the rotatable camera will be relatively small, and the rotatable camera will rotate around the longitudinal direction. As the axis rotates, the size of the area captured by the rotatable camera increases. Therefore, each column needs to be non-uniformly divided in the longitudinal direction.

In another embodiment, the first image is divided in step 302 to obtain a plurality of sub-regions, which is specifically performed by steps 3022 to 3023, including:

Step 3022: Perform character recognition on the first image to obtain characters in the first image.

In another embodiment, after the first image is obtained, character recognition is further performed on the first image, so as to obtain the characters in the first image. It can be understood that an existing OCR (Optical Character Recognition, Optical Character Recognition) algorithm may be used for the method of character recognition for the first image, and the character recognition method is not specifically limited in this embodiment.

Step 3023: Determine the size of the text, and divide the first image according to the size of the text to obtain multiple sub-regions.

After the text in the first image is obtained, the size of the text in the first image is further determined, and the first image is divided according to the size of the text, thereby obtaining a plurality of sub-regions. It should be further explained that, in this embodiment, the goal of dividing the first image according to the size of the text is that the size of the text reflects the difficulty of recognizing the content to a certain extent. The thicker the stroke), the easier it is to identify the content, and the smaller the text (the smaller the font or the thinner the stroke), the higher the difficulty of content identification. If the text in the first image is larger, when dividing the first image, the area of each sub-region can be appropriately increased.

On the basis of the above embodiment, in step 3023, the first image is divided according to the text size to obtain a plurality of sub-regions, which is specifically executed by step 30231, including:

Step 30231: Divide the first image into M columns evenly in the horizontal direction, and divide each column into N rows non-uniformly in the longitudinal direction to obtain M×N sub-regions, and the size of each sub-region is positively correlated with the size of the text.

Similarly, in this embodiment, the first image is evenly divided into M columns in the horizontal direction, and each column is non-uniformly divided into N rows in the longitudinal direction to obtain M×N sub-regions, and the first image is divided into M columns. , the size of each subregion is positively related to the size of the text. Exemplarily, as shown in FIG. 8 , if the text in the first image is larger, the area of each sub-region divided is larger. As shown in FIG. 9 , if the text in the first image is smaller, the The smaller the area of each sub-region divided.

It should be further explained that, in this embodiment, there is another way of dividing the first image to obtain multiple sub-regions, which is specifically executed by step 3024, including:

Step 3024: Determine the template type of the first image, obtain a division rule corresponding to the template type, and divide the first image according to the division rule to obtain a plurality of sub-regions.

In another embodiment, after the first image is obtained, a template type of the first image is determined, a division rule corresponding to the template type is obtained, and finally the first image is divided according to the division rule to obtain a plurality of sub-regions. Exemplarily, in one embodiment, the first image is an image of the test paper, then after the first image is obtained, the template type of the test paper is determined, for example, what type of questions the content of the test paper is composed of (multiple-choice questions, fill-in-the-blank questions) etc.) and the positions of different question types, and then obtain the corresponding division rules from the server according to the question types and the position of the question types in the test paper. The division rules include the division methods of the positions corresponding to different question types. For example, for test papers The position of the fill-in-the-blank question corresponds to a division method, the position of the multiple-choice questions in the test paper corresponds to a division method, etc. Finally, the first image is divided according to the division rules, so as to obtain multiple sub-regions, so that the first image can be divided into multiple sub-regions. The division method can be flexibly selected according to actual needs, and the division rules support user-defined settings to meet the needs of various scenarios.

The above is the specific process of dividing the first image in step 302 to obtain multiple sub-regions.

On the basis of the above embodiment, the shooting mode of the target area is any one of the global scanning mode, the local scanning mode and the target tracking mode. Under different shooting modes, the camera module has different shooting modes, so as to satisfy different the needs of the shooting situation.

In one embodiment, the shooting mode is a global scanning mode. Correspondingly, in step 102, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can shoot different sub-regions during the rotation process. The image of the area, specifically executed by step 1021, specifically includes:

Step 1021: Determine a path for the camera module to shoot the sub-region according to the pre-divided sub-regions, and control the camera module to rotate according to the path, so that the camera module captures images of different sub-regions during the rotation.

When the shooting mode is the global scanning mode, it is necessary to shoot the whole image of the target area, or the whole image of the target object in the target area, for example, the whole text in the target area, or the text on the test paper in the target area. At this time, it is necessary to determine the path of the sub-areas captured by the camera in the pre-divided sub-areas. In this embodiment, the path can be set in advance, or the terminal device can automatically calculate the optimal path according to the target object. Exemplarily, in one embodiment, for example, for the sub-areas shown in 2-6...2-1...5-7, as shown in Figure 10. Or, it is determined that the paths of the sub-regions captured by the camera are 1-1, 2-1, ... 5-2, 4-2 ... 1-2 ... 5-7, as shown in FIG. 11 .

After determining the path for the camera module to shoot the sub-regions, the terminal device can control the camera module to rotate according to the path, so that the camera module can shoot each sub-region according to the sequence corresponding to the path, so as to obtain different sub-regions Image.

In another embodiment, the shooting mode is a local scanning mode. Correspondingly, in step 102, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can shoot different pictures during the rotation process. The image of the sub-region is specifically executed by steps 1022 to 1024, including:

Step 1022: Acquire a global image of the target area in real time.

When the shooting mode is the local scanning mode, the camera module needs to scan the local area in the target area. First, a global image of the target area needs to be acquired in real time. The global image can be obtained by photographing a camera with a larger field of view in the camera module, or by globally photographing the target area by a rotatable camera in the camera module in a global scan mode.

Step 1023: Determine the first area to be photographed in the global image.

After the target area is obtained, the first area to be photographed needs to be further determined in the global image. In this embodiment, the first area can be set in advance, for example, a certain area in the global image is fixed as the first area, or, the target feature of the first area can be set in the terminal device in advance, and the terminal device obtains the target feature of the first area in advance. After the global image is obtained, image recognition is automatically performed on the global image, and target features are acquired in the global image, thereby determining the first area to be photographed in the global image. Exemplarily, in one embodiment, when the text content filled in the test paper of the target area is photographed by the partial scanning mode, the target feature is set to the handwriting filled in by the user, and at this time, the global image in the target area is first photographed, Then, the area of the test paper corresponding to the test paper is identified from the global image, and finally, using the image processing algorithm, the area of the handwriting filled in by the user can be identified from the area of the test paper, and this area is used as the first area.

Step 1024: Determine the first sub-region included in the first region, determine the first path for the camera module to shoot the first sub-region, and control the camera module to rotate according to the first path, so that the camera module is in the process of rotating An image of the first sub-region is captured.

After the first area is determined in the global image, the first sub-area included in the first area is further determined, and according to the first sub-area, the first path when the camera module shoots the first sub-area is determined, and then, The camera module can be controlled to rotate according to the first path, so that the camera module can capture an image of the first sub-area during the rotation process. Exemplarily, in one embodiment, the first path of the camera module is determined according to the area of the handwriting filled in by the user, and then the camera module is controlled to rotate according to the first path, so that the camera module can shoot during the rotation process. to the image corresponding to the area of the handwriting filled in by the user.

In one embodiment, the shooting mode is the target tracking mode. Correspondingly, in step 102, the camera module is controlled to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can shoot different sub-regions during the rotation process. The image of the area, which is specifically executed from steps 1025 to 1028, specifically includes:

Step 1025: Determine the position of the target object in the target area, and determine the second sub-area corresponding to the position.

When the shooting mode is the target tracking mode, the position of the target object in the target area needs to be determined. Exemplarily, the target object can be tracked by an event camera (dynamic vision sensor) on the camera module, so as to determine the position of the target object in the target area. Then, according to the position of the target object in the target area, a second sub-area corresponding to the position is determined, that is, the second sub-area where the target object is located. Exemplarily, in one embodiment, the target object is the pen or hand that the user is using, and the event camera is used to track the pen or hand that the user is using, identify the position of the pen or hand that the user is using, and determine the position according to the location. The second sub-area where the pen or hand the user is using.

Step 1026: Determine that the camera module is rotated to a target angle corresponding to the second sub-area.

After the second sub-area where the target object is located is determined, the camera projection module is controlled to rotate to a target angle corresponding to the second sub-area. In this embodiment, the angle of the camera module corresponding to each sub-area can be determined in advance. Exemplarily, for any sub-region in the i-th row and j-column in FIG. 4, an angle (αi, αj) corresponding to the camera module and the sub-region is determined, wherein αi, αj respectively represent the camera module around the horizontal direction. The angle to which the rotation axis needs to be rotated and the angle to which the camera module needs to rotate around the longitudinal rotation axis, so that when the camera module rotates to the angle (αi, αj), the center of the camera module can be aligned with the sub-area the center point.

Step 1027 , controlling the camera module to rotate to the target angle, so that the camera module captures an image of the second sub-region.

After that, the camera module is controlled to rotate to a corresponding target angle, so that the camera module can capture an image of the second sub-region. Exemplarily, when the second sub-area is the pen that the user is using or the area where the user's hand is located, the handwriting filled in by the user can be acquired by taking an image of the second sub-area, so that the subsequent implementation can be realized according to the handwriting filled in by the user. corresponding auxiliary function.

The above is the specific process of controlling the camera module to rotate according to the shooting mode and pre-divided sub-regions in step 102, so that the camera module can capture images of different sub-regions during the rotation process.

It should be further noted that, in this embodiment, there are also various methods for acquiring target information from an image in step 103, so as to meet different needs of users.

In one embodiment, obtaining target information from an image in step 103 is specifically performed by steps 1031 to 1032, including:

Step 1031: Combine the images to obtain a second image.

In one embodiment, after images of different sub-regions are obtained by shooting, the images of different sub-regions are combined to obtain the second image. For example, in the global scanning mode, the images of each sub-region obtained by shooting are combined to obtain a second image, that is, a complete image of the target region. The specific merging manner may be combined according to the shooting time or the shooting path, and the specific merging manner is not limited in this embodiment.

Step 1032: Perform text recognition on the second image to obtain the target text, obtain the corresponding standard text in the database according to the target text, compare the target text with the standard text, and obtain a comparison result.

In one embodiment, the terminal device is further connected to the database, and when objects such as test papers or textbooks are placed in the target area, the second image obtained by combining will include images of the objects corresponding to the test papers or textbooks. Character recognition is performed on the second image, and the target characters on the test paper or textbook are obtained from the second image, and then the database is further retrieved according to the target characters to obtain standard characters corresponding to the target characters. In one embodiment, the corresponding standard text can be obtained from the database according to the coincidence rate of the entire target text and a certain piece of text in the database, and then the target text and the standard text can be compared to obtain a comparison result , and according to the comparison result, execute the corresponding learning auxiliary function. For example, if the question type on the test paper is a fill-in-the-blank question, it can be determined whether the content filled in by the user is correct according to the comparison result. If it is correct, a corresponding prompt can be issued. For the user's reference, and according to the comparison result, find the knowledge point corresponding to the wrong place the user fills in, find the corresponding practice questions according to the knowledge point and push it to the user.

In another embodiment, obtaining target information from the image in step 103, specifically executed by step 1033, includes:

Step 1033: Perform text recognition on the image to obtain the target text, obtain the corresponding standard text in the database according to the target text, compare the target text with the standard text, and obtain a comparison result.

In another embodiment, the images of each sub-region may not be merged, but the images of each sub-region may be directly processed. Exemplarily, when the shooting mode is the local scanning mode, character recognition is performed corresponding to each photographed image to obtain the target text, and the corresponding standard text is obtained in the database according to the target text, and the target text is compared with the standard text. Compare, get the comparison result, and finally execute the corresponding learning auxiliary function according to the comparison result. For the specific process, reference may be made to the specific process in step 1032, which is not repeated in this embodiment.

In another embodiment, obtaining target information from an image in step 103 is specifically performed by steps 1034 to 1036, and specifically includes:

Step 1034: Acquire all images captured within a preset time period, and extract handwriting information from each image of all the images.

In one embodiment, after the images are obtained, all images captured within a preset time period are obtained, and image processing is performed on each image, and the handwriting information filled in by the user is extracted from the images. Exemplarily, when the shooting mode is the target tracking mode and the tracked target object is the pen being used by the user, after capturing the image of the sub-area where the pen being used by the user is located, all images captured over a period of time in the history are obtained. Image, understandably, the preset time period can be set according to actual needs. For example, one minute before the current time point is a preset time period, and the specific time of the preset time period is not limited in this embodiment. After that, the handwriting information filled in by the user is extracted from each image of all the acquired images.

Step 1035: Determine the stroke order according to the handwriting information, and obtain the corresponding standard stroke order according to the handwriting information.

After that, according to the handwriting information extracted from all the graphics, the user's handwriting information can be determined, and by performing text recognition on the handwriting information, the text corresponding to the handwriting information can be determined, thereby determining the text written by the user, According to the text, the standard stroke order of the text can be obtained. Exemplarily, in one embodiment, the terminal device is connected to a server on the Internet, and the terminal device can obtain the standard stroke order of characters from the server on the Internet. It can be understood that, in this embodiment, the method of obtaining the standard stroke order according to the text can be set according to actual needs.

Step 1036: Compare the stroke order with the standard stroke order to obtain a comparison result.

Finally, compare the stroke order filled in by the user with the standard stroke order, and get the comparison result, so as to confirm whether the stroke order is correct in the process of writing the text. If the stroke order is incorrect, you can send a corresponding prompt to It also reminds the wrong strokes in the stroke order and provides the correct marking stroke order for users to refer to and correct, which plays a role in assisting users in learning.

As shown in FIG. 12, FIG. 12 is a schematic structural diagram of an image capturing device provided by an embodiment of the present invention. The image capturing device is applied to a terminal device, and the terminal device includes a camera module, and the camera module can be freely rotated to capture the For images of different regions, the image capturing device includes: a mode determination module 401, a control module 402 and an information acquisition module 403;

The mode determination module 401 is used to determine the shooting mode of the target area.

The control module 402 is used to control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module captures images of different sub-regions during the rotation; divided.

The information acquisition module 403 is used for acquiring target information from the image.

On the basis of the above embodiment, the control module 402 is used to divide the target area, including:

It is used to determine the angle range when the camera module rotates according to the target area; determine the step length of each rotation of the camera module; control the camera module to rotate according to the step length within the angle range, and record the images captured by the camera module after each rotation. The arrived area is divided into a sub-area.

On the basis of the above embodiment, the control module 402 is used to divide the target area, including:

It is used to obtain the target image, and the target image is obtained by shooting the target area; the boundary of the target object is determined in the target image, the first image corresponding to the range of the boundary is determined in the target image, and the first image is divided to obtain multiple sub-regions.

On the basis of the above embodiment, the control module 402 is configured to divide the first image to obtain a plurality of sub-regions, including:

It is used to divide the first image into M columns uniformly in the lateral direction, and divide each column into N rows non-uniformly in the longitudinal direction to obtain M×N sub-regions.

On the basis of the above embodiment, the control module 402 is configured to divide the first image to obtain a plurality of sub-regions, including:

It is used to perform character recognition on the first image to obtain the characters in the first image; determine the size of the characters, and divide the first image according to the size of the characters to obtain a plurality of sub-regions.

On the basis of the above embodiment, the control module 402 is configured to divide the first image according to the text size to obtain a plurality of sub-regions, including:

It is used to evenly divide the first image into M columns in the horizontal direction, and divide each column into N rows non-uniformly in the vertical direction to obtain M×N sub-regions, and the size of each sub-region is positively correlated with the size of the text.

On the basis of the above embodiment, the control module 402 is configured to divide the first image to obtain a plurality of sub-regions, including:

It is used to determine the template type of the first image, obtain a division rule corresponding to the template type, and divide the first image according to the division rule to obtain a plurality of sub-regions.

On the basis of the above embodiment, the shooting mode is any one of the global scanning mode, the local scanning mode and the target tracking mode.

On the basis of the above embodiment, the shooting mode is the global scanning mode. Correspondingly, the control module 402 is used to control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating images of different sub-areas in the , including:

It is used to determine the path of the camera module to shoot the sub-region according to the pre-divided sub-region, and control the camera module to rotate according to the path, so that the camera module can capture images of different sub-regions during the rotation.

On the basis of the above-mentioned embodiment, the shooting mode is the local scanning mode. Correspondingly, the control module 402 is configured to control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating images of different sub-areas in the , including:

For obtaining the global image of the target area in real time; determining the first area to be shot in the global image; determining the first sub-area included in the first area, and determining the first path for the camera module to shoot the first sub-area, according to The first path controls the camera module to rotate, so that the camera module captures an image of the first sub-area during the rotation.

On the basis of the above embodiment, the shooting mode is the target tracking mode. Correspondingly, the control module 402 is used to control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module is in the process of rotating images of different sub-areas in the , including:

It is used to determine the position of the target object in the target area, and determine the second sub-area corresponding to the position; determine that the camera module rotates to the target angle corresponding to the second sub-area; control the camera module to rotate to the target angle to Make the camera module capture images of the second sub-region.

On the basis of the above embodiment, the information acquisition module 403 is used to acquire target information from the image, including:

It is used to combine images to obtain a second image; perform text recognition on the second image to obtain target text, obtain corresponding standard text in the database according to the target text, compare the target text with the standard text, and obtain the comparison result .

On the basis of the above embodiment, the information acquisition module 403 is used to acquire target information from the image, including:

It is used to perform text recognition on the image to obtain the target text, obtain the corresponding standard text in the database according to the target text, compare the target text with the standard text, and obtain the comparison result.

On the basis of the above embodiment, the information acquisition module 403 is used to acquire target information from the image, including:

It is used to obtain all images captured within a preset time period, and extract handwriting information from each image of all images; determine the stroke order according to the handwriting information, and obtain the corresponding standard stroke order according to the handwriting information; The standard stroke order is compared to obtain the comparison result.

This embodiment also provides a terminal device, as shown in FIG. 13 , a terminal device 50 , the terminal device includes a processor 500 and a memory 501;

The memory 501 is used to store the computer program 502 and transmit the computer program 502 to the processor;

The processor 500 is configured to execute the steps in the above-mentioned embodiment of an image capturing method according to the instructions in the computer program 502 .

Exemplarily, the computer program 502 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 501 and executed by the processor 500 to complete the this application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 502 in the terminal device 50 .

The terminal device 50 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device 50 may include, but is not limited to, a processor 500 and a memory 501 . Those skilled in the art can understand that FIG. 13 is only an example of the terminal device 50, and does not constitute a limitation on the terminal device 50. It may include more or less components than the one shown, or combine some components, or different components For example, the terminal device 50 may further include an input and output device, a network access device, a bus, and the like.

The so-called processor 500 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 501 may be an internal storage unit of the terminal device 50 , such as a hard disk or a memory of the terminal device 50 . The memory 501 may also be an external storage terminal device of the terminal device 50, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) equipped on the terminal device 50. card, flash card (Flash Card) and so on. Further, the memory 501 may also include both an internal storage unit of the terminal device 50 and an external storage device. The memory 501 is used to store the computer program and other programs and data required by the terminal device 50 . The memory 501 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above may refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store computer programs.

Embodiments of the present invention further provide a storage medium containing computer-executable instructions, the computer-executable instructions are used to execute an image capturing method when executed by a computer processor, and are applied to a terminal device, where the terminal device includes a camera module, The camera module can be rotated freely to capture images of different areas, and the methods include:

Determine the shooting mode of the target area;

Control the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module can capture images of different sub-regions during the rotation; wherein, the sub-regions are obtained by pre-dividing the target region;

Get target information from the image.

Note that the above are only preferred embodiments and applied technical principles of the embodiments of the present invention. Those skilled in the art will understand that the embodiments of the present invention are not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made to those skilled in the art without departing from the protection scope of the embodiments of the present invention . Therefore, although the embodiments of the present invention have been described in detail through the above embodiments, the embodiments of the present invention are not limited to the above embodiments, and may also include more other equivalents without departing from the concept of the embodiments of the present invention. Examples, the scope of the embodiments of the invention is determined by the scope of the appended claims.

Claims (17)

1. An image shooting method is applied to terminal equipment, and is characterized in that the terminal equipment comprises a camera module which can freely rotate to shoot images in different areas, and the method comprises the following steps:

determining a shooting mode of a target area;

controlling the camera module to rotate according to the shooting mode and the pre-divided sub-regions so as to enable the camera module to shoot images of different sub-regions in the rotating process; the sub-area is obtained by dividing a target area in advance;

target information is obtained from the image.

2. An image capturing method as claimed in claim 1, wherein the dividing of the target area comprises:

determining the angle range of the camera module when rotating according to the target area;

determining the step length of each rotation of the camera module;

and controlling the camera module to rotate within the angle range according to the step length, and dividing the area shot by the camera module after each rotation into a sub-area.

3. An image capturing method as claimed in claim 1, wherein the dividing of the target area comprises:

acquiring a target image, wherein the target image is obtained by shooting the target area;

determining a boundary of a target object in the target image, determining a first image corresponding to the range of the boundary in the target image, and dividing the first image to obtain a plurality of sub-regions.

4. An image capturing method as claimed in claim 3, wherein the dividing the first image into a plurality of sub-regions comprises:

and uniformly dividing the first image into M columns in the transverse direction, and non-uniformly dividing each column into N rows in the longitudinal direction to obtain M multiplied by N sub-regions.

5. An image capturing method as claimed in claim 3, wherein the dividing the first image into a plurality of sub-regions comprises:

performing character recognition on the first image to obtain characters in the first image;

and determining the size of the characters, and dividing the first image according to the size of the characters to obtain a plurality of sub-regions.

6. The image capturing method according to claim 5, wherein the dividing the first image according to the text size to obtain a plurality of sub-regions comprises:

the first image is uniformly divided into M rows in the transverse direction, each row is non-uniformly divided into N rows in the longitudinal direction, M multiplied by N sub-regions are obtained, and the size of each sub-region is positively correlated with the size of the characters.

7. An image capturing method as claimed in claim 3, wherein the dividing the first image into a plurality of sub-regions comprises:

determining the template type of the first image, acquiring a division rule corresponding to the template type, and dividing the first image according to the division rule to obtain a plurality of sub-regions.

8. An image capturing method according to claim 1, wherein the capturing mode is any one of a global scanning mode, a local scanning mode, and a target tracking mode.

9. The image capturing method according to claim 8, wherein the capturing mode is a global scan mode, and accordingly, the controlling the camera module to rotate according to the capturing mode and the pre-divided sub-regions so that the camera module captures images of different sub-regions during the rotation includes:

determining a path of the camera module for shooting the subareas according to the pre-divided subareas, and controlling the camera module to rotate according to the path so as to enable the camera module to shoot images of different subareas in the rotating process.

10. The image capturing method according to claim 8, wherein the capturing mode is a local scanning mode, and accordingly, the controlling the camera module to rotate according to the capturing mode and the pre-divided sub-regions so that the camera module captures images of different sub-regions during the rotation includes:

acquiring a global image of the target area in real time;

determining a first area needing to be shot in the global image;

determining a first sub-area contained in the first area, determining a first path of the camera module for shooting the first sub-area, and controlling the camera module to rotate according to the first path so that the camera module shoots an image of the first sub-area in the rotating process.

11. An image capturing method according to claim 8, wherein the capturing mode is a target tracking mode, and accordingly, the controlling the camera module to rotate according to the capturing mode and the pre-divided sub-regions so that the camera module captures images of different sub-regions during the rotation process includes:

determining the position of a target object in the target area, and determining a second sub-area corresponding to the position;

determining a target angle of the camera module rotating to correspond to the second sub-area;

and controlling the camera module to rotate to the target angle so as to enable the camera module to shoot the image of the second sub-area.

12. An image capturing method according to claim 1, wherein the acquiring of the target information from the image includes:

merging the images to obtain a second image;

and performing character recognition on the second image to obtain a target character, acquiring a corresponding standard character in a database according to the target character, and comparing the target character with the standard character to obtain a comparison result.

13. An image capturing method according to claim 1, wherein the acquiring of the target information from the image includes:

and performing character recognition on the image to obtain a target character, acquiring a corresponding standard character in a database according to the target character, and comparing the target character with the standard character to obtain a comparison result.

14. An image capturing method according to claim 1, wherein the acquiring of the target information from the image includes:

acquiring all images shot in a preset time period, and extracting handwriting information from each image of all the images;

determining a stroke order sequence according to the handwriting information, and acquiring a corresponding standard stroke order sequence according to the handwriting information;

and comparing the stroke order with a standard stroke order to obtain a comparison result.

15. The utility model provides an image shooting device, is applied to terminal equipment, its characterized in that, terminal equipment is including the camera module, but the camera module free rotation is in order to shoot the image in different regions, image shooting device includes: the device comprises a mode determining module, a control module and an information acquiring module;

the mode determining module is used for determining a shooting mode of a target area;

the control module is used for controlling the camera module to rotate according to the shooting mode and the pre-divided sub-regions, so that the camera module shoots images of different sub-regions in the rotating process; the sub-area is obtained by dividing a target area in advance;

the information acquisition module is used for acquiring target information from the image.

16. A terminal device, characterized in that the terminal device comprises a processor and a memory;

the memory is used for storing a computer program and transmitting the computer program to the processor;

the processor is adapted to perform an image capturing method according to any of claims 1-14 according to instructions in the computer program.

17. A storage medium storing computer-executable instructions for performing an image capture method as claimed in any one of claims 1 to 14 when executed by a computer processor.

Images