WO2023005813A1

WO2023005813A1 - Image direction adjustment method and apparatus, and storage medium and electronic device

Info

Publication number: WO2023005813A1
Application number: PCT/CN2022/107240
Authority: WO
Inventors: 郑侠松; 赵佳鹏
Original assignee: 广州视源电子科技股份有限公司; 广州视睿电子科技有限公司
Priority date: 2021-07-30
Filing date: 2022-07-22
Publication date: 2023-02-02
Also published as: CN115696028A

Abstract

Provided in the present application are an image direction adjustment method and apparatus, and a storage medium and an electronic device. The method comprises: acquiring a preview image, which is collected by a camera for a photographed object; recognizing a target object in the preview image, and acquiring at least one text row in the target object; determining the direction of each text row in the at least one text row; and determining a target direction of the preview image on the basis of the directions, and adjusting a display direction of the preview image on the basis of the target direction of the preview image. By means of the present disclosure, the direction of a photographed preview image can conform to the direction required by a user, so as to meet the usage habits of the user, thereby facilitating the usage of the user.

Description

Image orientation adjustment method, device, storage medium and electronic equipment

This application claims the priority of the Chinese patent application with the application number 202110879167.X and the title of the invention "image orientation adjustment method, device, storage medium and electronic equipment" submitted to the China Patent Office on July 30, 2021, the entire content of which Incorporated in this application by reference.

technical field

The present application relates to the field of computer technology, and in particular to an image orientation adjustment method, device, storage medium and electronic equipment.

Background technique

When the mobile terminal takes pictures of the subject, since the camera is only responsible for taking pictures, and the shooting application does not consider whether the mobile terminal will rotate to make a corresponding response, this will occur when the mobile terminal is rotated by 90°, 180° or Rotation at equal angles of 270°, but the image does not follow the rotation, or even if the camera is facing the subject to shoot and the mobile terminal does not rotate after shooting, the captured image still has 90°, 180° Or in the case of rotation at 270° and other angles, the direction of the characters in the acquired image does not match the actual direction of the characters in the subject, which does not conform to the user's usage habits, causing inconvenience to the user.

Contents of the invention

Embodiments of the present application provide an image orientation adjustment method, device, storage medium, and electronic device, which can make the text orientation in the captured image the orientation required by the user, so as to conform to the user's usage habits and facilitate the user's use. This technical scheme is as follows:

In the first aspect, an embodiment of the present application provides a method for adjusting an image direction, the method including:

Obtain the preview image collected by the camera for the subject;

identifying a target object in the preview image, and acquiring at least one text line in the target object;

determining the orientation of each of the at least one line of text;

A target direction of the preview image is determined based on each of the directions, and a display direction of the preview image is adjusted based on the target direction of the preview image.

In a second aspect, an embodiment of the present application provides a method for adjusting an image direction, the method including:

receiving a shooting instruction, and turning on the camera in response to the shooting instruction;

Displaying a preview image collected by the camera for the subject;

determining the orientation of each of the lines of text determined in the preview image;

determining a target direction of the preview image based on each of the directions, adjusting a display direction of the preview image based on the target direction of the preview image, and displaying the adjusted preview image.

In the third aspect, the embodiment of the present application provides an image direction adjustment device, the device includes:

An image acquisition module configured to acquire a preview image collected by the camera for the subject;

A text line acquisition module configured to identify a target object in the preview image, and acquire at least one text line in the target object;

an orientation determination module configured to determine the orientation of each of the at least one text lines;

The angle adjustment module is configured to determine a target direction of the preview image based on each of the directions, and adjust a display direction of the preview image based on the target direction of the preview image.

In a fourth aspect, the embodiment of the present application provides an image orientation adjustment device, the device comprising:

The camera opening module is configured to receive a shooting instruction, and turn on the camera in response to the shooting instruction;

An image display module configured to display a preview image collected by the camera for the subject;

a direction determination module configured to determine the direction of each text line determined in the preview image;

The direction adjustment module is configured to determine the target direction of the preview image for each direction, adjust the display direction of the preview image based on the target direction of the preview image, and display the adjusted preview image.

In a fifth aspect, an embodiment of the present application provides a computer storage medium, where a plurality of instructions are stored in the computer storage medium, and the instructions are adapted to be loaded by a processor and execute the method steps of the first aspect above.

In a sixth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above-mentioned first aspect method steps.

In the seventh aspect, the embodiment of the present application provides an image orientation adjustment program. When the program is executed, operations related to the image orientation adjustment method as described in the first aspect or the second aspect can be realized.

The beneficial effects brought by the technical solutions provided by some embodiments of the present application at least include:

In the embodiment of the present application, the mobile terminal acquires a preview image collected by the camera for the object to be photographed, and when the preview image includes an identified object, recognizes the target object in the preview image, acquires at least one text line in the target object, and determines at least one For the direction of each text line in the text line, the target direction of the preview image is determined based on each direction, and the display direction of the preview image is adjusted based on the target direction of the preview image. Even if the shooting device is rotated or the captured preview image will be rotated randomly, the display direction of the preview image will be rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, the display direction of the preview image will be rotated This rotation angle can make the direction of the text in the captured image match the direction required by the user, so as to conform to the user's usage habits and facilitate the user's use.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present application. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flow chart of an image orientation adjustment method provided in an embodiment of the present application;

Fig. 2a is a system architecture diagram of an image direction adjustment method provided by an embodiment of the present application;

Fig. 2b is a system architecture diagram of an image direction adjustment method provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of a preview image provided by an embodiment of the present application;

FIG. 4 is a schematic flowchart of an image orientation adjustment method provided in an embodiment of the present application;

FIG. 5 is a schematic diagram of a prompt message provided by an embodiment of the present application;

Fig. 6 is a schematic diagram of a target object marking provided by an embodiment of the present application;

Fig. 7 is a schematic diagram of a text line mark provided by an embodiment of the present application;

Fig. 8 is an exemplary schematic diagram of a first pixel distribution histogram provided by an embodiment of the present application;

FIG. 9 is an exemplary schematic diagram of a second pixel distribution histogram provided by an embodiment of the present application;

FIG. 10 is a schematic flowchart of a method for adjusting an image direction provided by an embodiment of the present application;

FIG. 11 is a schematic diagram of a trigger shooting function provided by an embodiment of the present application;

FIG. 12 is a schematic flowchart of a method for adjusting an image direction provided by an embodiment of the present application;

Fig. 13 is a schematic diagram of prompt information provided by the embodiment of the present application;

FIG. 14 is a schematic structural diagram of an image orientation adjustment device provided in an embodiment of the present application;

Fig. 15 is a schematic structural diagram of a text line acquisition module provided by an embodiment of the present application;

Fig. 16 is a schematic structural diagram of a direction determination module provided by an embodiment of the present application;

Fig. 17 is a schematic structural diagram of a direction determining unit provided in an embodiment of the present application;

Fig. 18 is a schematic structural diagram of a direction adjustment module provided by an embodiment of the present application;

FIG. 19 is a schematic structural diagram of an image orientation adjustment device provided in an embodiment of the present application;

Fig. 20 is a schematic structural diagram of an image orientation adjustment device provided by an embodiment of the present application;

Fig. 21 is a schematic structural diagram of a direction adjustment module provided by an embodiment of the present application;

Fig. 22 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

In the description of the present application, it should be understood that the terms "first", "second" and so on are used for descriptive purposes only, and should not be understood as indicating or implying relative importance. Those of ordinary skill in the art can understand the specific meanings of the above terms in this application in specific situations. In addition, in the description of the present application, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone. . The character "/" generally indicates that the contextual objects are an "or" relationship.

The present application will be described in detail below in conjunction with specific embodiments.

The method can be implemented relying on a computer program, and can run on an image orientation adjustment device based on the von Neumann system. The computer program can be integrated in the application, or run as an independent utility application. Wherein, the image orientation adjustment device in the embodiment of the present application may be a mobile terminal, including but not limited to: personal computer, tablet computer, handheld device, vehicle-mounted device, wearable device, computing device or other processing device connected to a wireless modem, etc. . User terminals can be called by different names in different networks, for example: user equipment, access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication Equipment, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), terminal equipment in 5G network or future evolution network, etc.

This method includes but is not limited to application to student learning machines. This learning machine refers to a tablet computer that is generally used for students to take online classes or conduct other learning projects. It has a camera set on the top of the learning machine and has a shooting function.

Please refer to FIG. 1 , which provides a schematic flowchart of a method for adjusting an image direction according to an embodiment of the present application. The embodiment of the present application is described by taking the mobile terminal side as an example, and the image direction adjustment method may include the following steps:

S101, acquiring a preview image collected by the camera for the subject;

Specifically, as shown in Figure 2a, the camera can be a device that communicates with the mobile terminal in a wireless or wired manner, where the wireless manner for the mobile terminal to communicate with the camera includes but is not limited to, for example, a cellular network, a wireless local area network, an infrared network, a near Field communication network or bluetooth network, etc., wired methods include but not limited to Universal Serial Bus (Universal Serial Bus, USB) and so on. As shown in FIG. 2b, the camera may also be a part of the mobile terminal, that is, a device installed on the camera of the mobile terminal.

Wherein, the shooting object may be any object containing text, which is not limited here.

Wherein, the preview image may be a pre-browsing image captured by the camera based on the shooting picture, or may be a pre-browsing image obtained based on the capturing of the shooting picture by the camera installed on the mobile terminal in response to a shooting instruction of the mobile terminal. The preview image can be displayed on the screen.

For example, as shown in FIG. 2a, the user triggers to turn on the camera, and the camera of the camera collects images of the subject to obtain a preview image, and sends the preview image to the mobile terminal. The acquisition of the preview image by the mobile terminal can be based on a preset timing acquisition mechanism, for example, acquisition in the 3rd second after the camera is turned on, or can be acquired in a preset certain step length (eg, once every 2 seconds).

It can be understood that before the orientation of the image is adjusted, the preview image is a preview image that has been rotated by a certain angle or an image that does not follow the rotation of the device. One possible situation is as shown in Figure 3, where the orientation of the subject in the figure is is the direction before the rotation, and the preview image in the mobile terminal is a preview image rotated by a certain angle.

S102. Identify a target object in the preview image, and acquire at least one text line in the target object;

A text line refers to a specific line of text, and the direction of the text can be any direction.

Specifically, the target object is any object containing text information, such as books, certificates, paper, and the like.

To recognize the target object in the preview image, you need to preset the recognition object first, and obtain the recognition object in the preview image. The recognition object is the same as the target object, and can be any object containing text, such as books, certificates, paper, etc.

Specifically, because it is a binary classification task to identify whether the preview image contains an object or not, a binary classification algorithm is used to classify the preview image. Among them, algorithms that can realize binary classification include support vector machines, decision trees, neural networks, and k-nearest neighbors. , classification based on association rules, etc.

The binary classification algorithm in this application can be ResNet-18 in the ResNet (Deep Residual Network, ResNet) series network, the ResNet series network is an algorithm in the field of image classification, and the number 18 in ResNet-18 represents the network Depth, 18 specifies 18 layers with weights, including convolutional layers and fully connected layers, excluding pooling layers and BN (Batch Normalization, BN) layers. Using ResNet-18, preview images can be divided into preview images that include recognized objects and preview images that do not include recognized objects.

When the preview image does not include the identified object, output prompt information, the prompt information is used to remind the user that the preview image does not include the identified object, and the prompt information can be output in the form of audio, text or animation. Multiple prompting methods can be used in parallel. The specific method and content are not limited.

For example, when the preset recognized object is a book, a feasible prompting method may be a voice prompt, and the voice outputs "the book is not recognized in the current image, please shoot again".

When the preview image includes one recognition object, one recognition object is used as the target object, and when the preview image includes multiple recognition objects, the selected recognition object among the multiple recognition objects is used as the target object.

Any text line in the text line can be a text line in the vertical direction, a text line in the horizontal direction, or a text line in any other direction, and there are no restrictions on the character shape, size, language, font and other characteristics contained in the text line.

Because the text lines on the target object may be vertical text lines, horizontal text lines or text lines in any other direction, the Advanced East (An Efficient and Accurate Scene Text Detector, East) algorithm is used to Identify lines of text on a target object. Advanced EAST is an algorithm for scene image text detection, which is essentially an algorithm model for simultaneous detection of target direction and area. Mainly based on the EAST algorithm, the EAST algorithm has been improved in the detection of long texts to make the prediction of long texts more accurate.

After using the Advanced East algorithm to identify all the text lines in the target object, select at least one text line from all the text lines.

When the target object includes a text line, get a text line as at least one text line, when the target object includes multiple text lines, get at least one text line in the target object can be, get all the text in the target object line as at least one text line, and at least one text line may also be randomly obtained as a part of all text lines in the target object.

S103. Determine the direction of each text line in the at least one text line;

After obtaining at least one text line in the target object, the characters in the at least one text line are cut by using a projection method.

Among them, the projection method is an algorithm in the field of text segmentation, including horizontal projection method and vertical projection method. The horizontal projection method can be understood as a beam of light irradiating from the horizontal direction of the image, and each light can be understood as a line of the image. , calculate the black pixels of the image on each line, so that the characters in the text line can be segmented. Similarly, the vertical projection method can be understood as a beam of light shining from the vertical direction of the image, and each light can be understood as the image One column, calculate the black pixels of the image on each column, so that the characters in the text line can be segmented.

The orientation of each of the at least one text line is determined based on the result of character cutting.

S104. Determine a target direction of the preview image based on each of the directions, and adjust a display direction of the preview image based on the target direction of the preview image.

The target orientation of the preview image is a preset orientation conforming to user habits or an image orientation set by the user.

Specifically, calculate the quantity ratio of each text line in each direction; obtain the direction indicated by the highest quantity ratio in the quantity ratio, adjust the display direction of the preview image based on the direction indicated by the highest quantity ratio, and finally obtain and acquire the preview after display adjustment image.

Adjust the display direction of the preview image based on the direction indicated by the highest quantity ratio. There are two adjustment methods. You can adjust the display direction of the preview image to be consistent with the direction indicated by the highest quantity ratio in the quantity ratio, or you can adjust the display direction of the preview image. To a direction that differs by an angle from the direction indicated by the highest number ratio of the number ratios.

In the embodiment of the present application, the mobile terminal acquires a preview image collected by the camera for the object to be photographed, and when the preview image includes the identified object, recognizes the target object in the preview image, and acquires at least one of the target objects The text line determines the direction of each text line in the at least one text line, determines the target direction of the preview image based on each of the directions, and adjusts the display direction of the preview image based on the target direction of the preview image. Even if the shooting device is rotated or the captured preview image will be rotated randomly, the display direction of the preview image will be rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, the display direction of the preview image will be rotated This rotation angle can make the direction of the text in the captured preview image match the direction required by the user, so as to conform to the usage habits of the user and facilitate the use of the user.

Please refer to FIG. 4 , which provides a schematic flowchart of a method for adjusting an image direction according to an embodiment of the present application. The embodiment of the present application is described by taking the mobile terminal side as an example, and the image direction adjustment method may include the following steps:

S201. Obtain a preview image collected by the camera for the shooting object;

Taking the camera as an example of the device installed on the camera on the mobile terminal, the preview image collected by the camera on the mobile terminal for the subject is shown in Figure 3. The preview image has been rotated, which does not match the actual direction of the user, which is inconvenient for the user. use.

For details of obtaining the preview image collected by the camera for the object to be photographed, refer to S106, which will not be repeated here.

S202, using a binary classification algorithm to identify the target object in the preview image; when the preview image includes multiple recognized objects, use the selected recognized object among the multiple recognized objects as the target object;

After the binary classification algorithm is used to identify the target object in the preview image, when the preview image includes multiple recognized objects, a prompt message is output. The prompt message is used to remind the user that the preview image contains multiple recognized objects, and one of the recognized objects needs to be selected as the For the target object, the prompt information can be output in the form of audio, text or animation. Multiple prompting methods can be used in parallel. The specific method and content are not limited.

For example, a feasible prompting method may be a voice prompt, and the voice output "the current image includes multiple recognized objects, please select one of the recognized objects for image direction adjustment".

For example, a feasible prompting method can be a text box prompt, as shown in Figure 5, a text box pops up, and the content of the text box is "The current image includes multiple recognized objects, please select one of the recognized objects for image orientation adjustment! ".

As shown in FIG. 6 , the user's selection signal for the target object is received, and the target object is determined.

S203, identifying all text lines in the target object; selecting at least one text line from all the text lines;

Specifically, the Advanced East algorithm is used to identify all text lines in the target object.

Specifically, because the target object includes a text line or includes multiple text lines, when the target object includes a text line, obtain a text line as at least one text line, and when the target object includes multiple text lines When , all text lines in the target object may be obtained as at least one text line, or any number of text lines or text lines with any proportion in the target object may be obtained. For example, as shown in Figure 7, a book in the figure is the target object, when there are 6 text lines in the target object, randomly obtain several (3) text lines as at least one text line, or, when the target When there are 6 text lines in the object, a certain proportion (50%) of the text lines is obtained, that is, 3 of the text lines are obtained as at least one text line.

S204. Traverse each text line in the at least one text line;

Perform binarization processing on the currently traversed target text line to obtain a binarized image;

The binarized image is processed by the horizontal projection method to obtain the first pixel distribution histogram;

The binarized image is processed by a vertical projection method to obtain a second pixel distribution histogram;

Among them, the binarization of the image is to set the gray value of the pixel on the image to 0 (lowest brightness) or 255 (highest brightness), that is, to present the entire image with a visual effect of only black and white. That is, the grayscale images with 256 brightness levels are selected through appropriate thresholds to obtain a binary image that can still reflect the overall and local features of the image.

The binarized image can also be further image processed. After binarization, the content of the image is only related to the point with a pixel value of 0 or 255 and the position of the point. When the image is processed later, the subsequent image processing process is simplified.

Image binarization processing methods include:

Select an appropriate threshold, the selected threshold should not only preserve the image information as much as possible, but also minimize the interference of background and noise;

If the grayscale value of the pixel in the preview image is equal to or higher than the threshold, the grayscale value is set to 255;

If the gray value of the pixel in the preview image is lower than the threshold, the gray value is set to 0;

The binarized image is processed by the horizontal projection method to obtain the first pixel distribution histogram, as shown in Figure 8. When the binarized image is as shown in the figure, the binarized image is processed by the horizontal projection method to obtain The first pixel distribution histogram of .

As shown in FIG. 9 , the binarized image is processed by a vertical projection method to obtain a second pixel distribution histogram, and a second pixel distribution histogram.

It can be understood that the first pixel distribution histogram and the second pixel distribution histogram respectively obtained after the preview image is binarized, and then the binarized image is processed by the horizontal projection method and the vertical projection method are unique and stable.

Based on the first pixel distribution histogram and the second pixel distribution histogram, the characters in the target text line are segmented to determine the direction of each character.

S205. Calculate the quantity ratio of each of the characters in each direction, and obtain the target direction of the character indicated by the highest quantity ratio among the quantity ratios;

Take the target direction of the character as the direction of the target text line;

The target direction refers to the direction indicated by the highest number ratio among the number ratios.

Because the characters in the traversed text line may have inconsistent character directions, the target text is determined by calculating the quantity ratio of each character in each direction and obtaining the target direction of the character indicated by the highest quantity ratio in the quantity ratio The direction of the line, for example, there are 10 characters in the target text line, and the ratio of the number of 10 characters in each direction is calculated, if the number of characters in the A direction among the 10 characters: the number of characters in the B direction: the number of characters in the C direction If the number of characters is 5:4:1, then obtain the direction indicated by the highest number ratio among the number ratios, that is, the A direction, take the A direction as the target direction, and then use the A direction as the direction of the currently traversed target text line. For another example, there are 10 characters in the target text line, randomly obtain any number (6) or a certain percentage (60%) of characters that exist in the target text line, that is, 6 characters in the 10 characters are placed in each The number ratio in the direction is calculated. If the number of characters in the A direction: the number of characters in the B direction: the number of characters in the C direction among the 6 characters is 3:2:1, then the direction indicated by the highest number ratio among the obtained number ratios is A Direction, take the A direction as the target direction, and then use the A direction as the direction of the currently traversed target text line.

S206. When all the characters in the target text line have the same direction, cut the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determine The direction of any character in the target text line, using the direction of any character as the direction of the target text line;

When all the characters in the target text line have the same direction, in order to reduce the computational workload, after cutting the characters in the target text line, randomly obtain any character in the target text line, and determine any randomly obtained character The direction of any character is used as the direction of the target text line.

until the traversal ends.

S207, calculating the quantity ratios of each of the text lines in each direction;

Each text line refers to each text line in at least one text line. After the traversal, the direction of each text line in at least one text line is determined, and the quantity ratio of each text line in each direction is calculated, for example, as shown in Figure 7 As shown, there are 4 text lines in the figure and at least one text line, and the ratio of the 4 text lines in each direction is calculated, and the ratio is text line 3 in the horizontal direction: text line 1 in the vertical direction.

S208. Acquire the direction indicated by the highest number ratio among the number ratios, and adjust the display direction of the preview image based on the direction indicated by the highest number ratio.

Based on the quantity ratios of each text line in each direction respectively, the direction indicated by the highest quantity ratio in the quantity ratio is obtained, for example, the direction indicated by the highest quantity ratio in at least one text line as shown in Figure 7 is the horizontal direction, therefore, Adjust the display direction of the preview image based on the horizontal direction. If the rotation angle is not 0, rotate the display direction of the preview image by the rotation angle to obtain and obtain the preview image after display adjustment.

In the embodiment of this application, a binary classification algorithm is used to identify the preview image. If the preview image includes multiple identification objects, a prompt message is output to prompt the user to select one of the identification objects as the target object. After the Advanced East algorithm is used, all identification objects will be identified. Text line, when the target object includes multiple text lines, any number of text lines in the target object or any proportion of text lines in the target object can be obtained as at least one text line, and the direction is determined by comparing all text lines , which reduces the computational workload. Cutting the characters by combining the horizontal projection method and the vertical projection method in the projection method can improve the accuracy of the determined character direction. Randomly obtain any number or preset ratio of characters in the target text line traversed, determine the direction of the target text line based on any number of characters, or when all the characters in the target text line have the same direction , randomly obtain any character in the target text line, and determine the direction of any randomly obtained character, which can reduce the computational workload. Calculate the number ratio of each text line in each direction, and adjust the display direction of the preview image based on the direction indicated by the highest number ratio, so as to avoid the direction adjustment of the preview image when the text lines in the target object have inconsistent directions. There is no specific basis for adjusting the direction. confusing question. Even if the shooting device is rotated or the captured preview image will be rotated randomly, the display direction of the preview image will be rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, the display direction of the preview image will be rotated This rotation angle can make the direction of the text in the captured image match the direction required by the user, so as to conform to the user's usage habits and facilitate the user's use.

Please refer to FIG. 10 , which provides a schematic flowchart of a method for adjusting an image direction according to an embodiment of the present application.

The embodiment of the present application is described on the mobile terminal side, and the image direction adjustment method may include the following steps:

S301. Receive a shooting instruction, and turn on the camera in response to the shooting instruction;

As shown in Figure 2a, the camera can be a device that communicates with the mobile terminal wirelessly or wiredly, and as shown in Figure 2b, the camera can also be a part of the mobile terminal, that is, a device installed on the mobile terminal.

Taking the camera as an example of a device installed on a mobile terminal, as shown in Figure 11, when the user triggers the mobile terminal to start the shooting function of the camera (application-camera), that is, to send a shooting instruction, when the mobile terminal receives the shooting instruction, In response to the shooting instruction, the shooting function of the camera is turned on, and the camera shoots the object to be shot.

S302, displaying a preview image collected by the camera for the shooting object;

The preview image refers to the pre-browsing image obtained by the camera based on the capture of the shooting screen in response to the start shooting command sent by the mobile terminal. It can be understood that, as shown in Figure 3, before the shooting angle is adjusted, the mobile terminal obtains the The preview image for is randomly rotated.

Acquiring and displaying the preview image collected by the camera for the object to be photographed. For details of obtaining the preview image collected by the camera for the object to be photographed, refer to S106 , which will not be repeated here.

S303. Determine the direction of each text line determined in the preview image;

For determining the direction of each text line determined in the preview image, reference may be made to S103 and S204-S207, which will not be repeated here.

S304. Determine the target direction of the preview image based on each of the directions, adjust the display direction of the preview image based on the target direction of the preview image, and display the adjusted preview image.

Determine the target direction of the preview image based on each of the directions, adjust the display direction of the preview image based on the target direction of the preview image, and display the adjusted preview image. Refer to S104 and S208, which will not be repeated here.

In this embodiment of the application, even if the shooting device is rotated or the captured preview image will rotate randomly, the display direction of the preview image is rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, then Rotate the display direction of the preview image by this rotation angle, so that the text direction in the captured image can match the direction required by the user, so as to conform to the user's usage habits and facilitate the user's use.

Please refer to FIG. 12 , which provides a schematic flowchart of a method for adjusting an image direction according to an embodiment of the present application.

S401. Receive a shooting instruction, and turn on the camera in response to the shooting instruction;

Display whether to open the prompt information for the direction detection of the target object;

receiving a confirmation instruction for the prompt information, and in response to the confirmation instruction, enabling the function of detecting the direction of the target object;

See S301 for receiving a shooting instruction, and turning on the camera in response to the shooting instruction, which will not be repeated here.

Display whether to enable the prompt information for detecting the direction of the target object. The prompt information is used to prompt the user whether to enable the prompt information for detecting the direction of the target object. The prompt information can be output in the form of audio, text or animation. Multiple prompting methods can be used in parallel. The specific method and content are not limited.

As shown in Figure 13, if the preset recognition object is a book, a feasible prompting method can be a text box prompt, and a text box pops up, and the content of the text box is "whether to enable direction detection for books?".

If the user clicks the "Yes" button, it means that the user also enables the direction detection of the book, the mobile terminal receives the confirmation instruction for the prompt information, and responds to the confirmation instruction to enable the direction detection function of the target object.

S402, displaying a preview image collected by the camera for the shooting object;

When the preview image includes multiple recognized objects, displaying prompt information containing the multiple recognized objects;

As shown in FIG. 5 , when the preview image includes multiple recognized objects, prompt information including the multiple recognized objects is displayed. Refer to S102 and S202 for the manner of displaying the prompt information, which will not be repeated here.

S403. Receive a selection instruction for the target object in the prompt information, and determine the target object in response to the selection instruction.

As shown in FIG. 6 , when the user performs a touch operation on the mobile terminal and selects any of the recognized objects as the target object, the target object is determined in response to the selection instruction. For the identification of the target object, reference may be made to S102 and S202, which will not be repeated here.

S404. Determine the direction of each text line determined in the preview image;

S405. Calculate the quantity ratios of each of the text lines in each direction, and determine the direction indicated by the highest quantity ratio among the quantity ratios;

The process of determining the direction indicated by the highest number ratio among the number ratios can refer to S104 and S208, and will not be repeated here.

S406. Calculate and output a rotation angle based on the direction indicated by the highest quantity ratio;

If the rotation angle is not 0, the preview image is rotated by the rotation angle to display the adjusted preview image.

Specifically, a direction is preset, which is the direction required by the user. If the direction indicated by the highest number ratio is inconsistent with the preset direction, that is, the rotation angle is not 0, the preview image is rotated by this rotation angle, and the preview image can be rotated. Make the direction indicated by the highest quantity ratio consistent with the preset direction, and finally obtain and display the adjusted preview image.

In the embodiment of the present application, when the preview image includes multiple recognized objects, displaying prompt information containing the multiple recognized objects to prompt the user to select any one of the recognized objects as the target object. Use the binary classification algorithm to recognize the preview image. If the preview image includes multiple recognition objects, output a prompt message to remind the user to select one of the recognition objects as the target object. After using the Advanced East algorithm, all text lines will be recognized. When the target object is included When multiple text lines are included, any number of text lines in the target object or any proportion of text lines in the target object can be obtained as at least one text line. Compared with obtaining all text lines for direction determination, the calculation workload can be reduced . Cutting the characters by combining the horizontal projection method and the vertical projection method in the projection method can improve the accuracy of the determined character direction. Randomly obtain any number or preset ratio of characters in the target text line traversed, determine the direction of the target text line based on any number of characters, or when all the characters in the target text line have the same direction , randomly obtain any character in the target text line, and determine the direction of any randomly obtained character, which can reduce the computational workload. Calculate the number ratio of each text line in each direction, and adjust the image direction of the camera based on the direction indicated by the highest number ratio, which can avoid the adjustment of the direction of the image when the direction of the text line in the target object is inconsistent. There is no specific basis for adjusting the direction. question. Even if the shooting device is rotated or the captured preview image will be rotated randomly, the display direction of the preview image will be rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, the display direction of the preview image will be rotated This rotation angle can make the direction of the text in the captured image match the direction required by the user, so as to conform to the user's usage habits and facilitate the user's use.

The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

Please refer to FIG. 14 , which shows a schematic structural diagram of an image orientation adjustment device provided by an exemplary embodiment of the present application. The device for adjusting the image direction can be implemented as all or a part of the terminal through software, hardware or a combination of the two. The device 1 includes an image acquisition module 11 , a text line acquisition module 12 , a direction determination module 13 and an angle adjustment module 14 .

The image acquisition module 11 is configured to acquire a preview image collected by the camera for the subject;

The text line acquisition module 12 is configured to identify the target object in the preview image, and acquire at least one text line in the target object;

a direction determining module 13, configured to determine the direction of each text line in the at least one text line;

The direction adjusting module 14 is configured to determine a target direction of the preview image based on each of the directions, and adjust a display direction of the preview image based on the target direction of the preview image.

Optionally, as shown in Figure 15, the text line acquisition module 12 includes:

The target object recognition unit 121 is configured to use a binary classification algorithm to recognize the target object in the preview image;

A text line identification unit 122 configured to identify all text lines in the target object;

The text line selection unit 123 is configured to select at least one text line from all the text lines.

Optionally, as shown in FIG. 16, the direction determining module 13 includes:

A text line traversing unit 131 configured to traverse each text line in the at least one text line;

The direction determining unit 132 is configured to perform character cutting processing on the currently traversed target text line, and determine the direction of the target text line;

The traversal end unit 133 is configured to wait until the traversal ends.

Optionally, as shown in FIG. 17, the direction determining unit 132 includes:

The image acquisition subunit 1321 is configured to perform binarization processing on the currently traversed target text line to obtain a binarized image;

The first histogram acquisition subunit 1322 is configured to process the binarized image using a horizontal projection method to obtain a first pixel distribution histogram;

The second histogram acquisition subunit 1323 is configured to process the binarized image using a vertical projection method to obtain a second pixel distribution histogram;

The character cutting subunit 1324 is configured to cut the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determine the direction of the target text line.

Optionally, the character cutting subunit 1324 is specifically configured as:

cutting the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determining the direction of each character;

calculating the quantity ratios of the characters in each direction, and obtaining the target direction of the character indicated by the highest quantity ratio among the quantity ratios;

The target direction of the character is used as the direction of the target text line.

Optionally, when all the characters in the target text line have the same direction, the character cutting subunit 1324 is specifically configured as:

The character in the target text line is cut based on the first pixel distribution histogram and the second pixel distribution histogram, the direction of any character in the target text line is determined, and any character in the target text line is determined. The direction of a character is used as the direction of the target text line.

Optionally, as shown in Figure 18, the direction adjustment module 14 includes:

The ratio calculation unit 141 is configured to calculate the quantity ratio of each of the text lines in each direction;

The direction adjusting unit 142 is configured to acquire the direction indicated by the highest number ratio among the number ratios, and adjust the display direction of the preview image based on the direction indicated by the highest number ratio.

Optionally, the text line acquisition module 12 is specifically configured as:

When the preview image includes multiple recognized objects, the selected recognized object among the multiple recognized objects is used as the target object.

In the embodiment of this application, a binary classification algorithm is used to identify the preview image. If the preview image includes multiple identification objects, a prompt message is output to prompt the user to select one of the identification objects as the target object. After the Advanced East algorithm is used, all identification objects will be identified. Text line, when the target object includes multiple text lines, any number of text lines in the target object or any proportion of text lines in the target object can be obtained as at least one text line, and the direction is determined by comparing all text lines , which reduces the computational workload. Cutting the characters by combining the horizontal projection method and the vertical projection method in the projection method can improve the accuracy of the determined character direction. Randomly obtain any number or preset ratio of characters in the target text line traversed, determine the direction of the target text line based on any number of characters, or when all the characters in the target text line have the same direction , randomly obtain any character in the target text line, and determine the direction of any randomly obtained character, which can reduce the computational workload. Calculate the number ratio of each text line in each direction, and adjust the display direction of the preview image based on the direction indicated by the highest number ratio, so as to avoid that there is no specific basis for adjusting the direction of the image when the direction of the text line in the target object is inconsistent, and the direction of the adjustment is confused. The problem. Even if the shooting device is rotated or the captured preview image will be rotated randomly, the display direction of the preview image will be rotated according to the target direction of the preview image. Specifically, if the rotation angle is not 0, the display direction of the preview image will be rotated This rotation angle can make the direction of the text in the captured image match the direction required by the user, so as to conform to the user's usage habits and facilitate the user's use.

Please refer to FIG. 19 , which shows a schematic structural diagram of an image orientation adjustment device provided by an exemplary embodiment of the present application. The device 2 includes a camera opening module 21 , an image display module 22 , a direction determining module 23 and a direction adjusting module 24 .

The camera opening module 21 is configured to receive a shooting instruction, and open the camera in response to the shooting instruction;

The image display module 22 is configured to display the preview image collected by the camera for the subject;

a direction determining module 23, configured to determine the direction of each text line determined in the preview image;

The direction adjustment module 24 is configured to determine the target direction of the preview image based on each of the directions, adjust the display direction of the preview image based on the target direction of the preview image, and display the adjusted preview image.

Optionally, as shown in Figure 20, the device 2 further includes:

The detection prompt display module 25 is configured to display whether to open the prompt information for direction detection of the target object;

The detection enabling module 26 is configured to receive a confirmation instruction for the prompt information, and respond to the confirmation instruction to enable the function of detecting the direction of the target object.

Optionally, as shown in Figure 20, the device 2 further includes:

The information prompt display module 27 is configured to display prompt information including the multiple recognized objects when the preview image includes multiple recognized objects;

The target object determination module 28 is configured to receive a selection instruction for the target object in the prompt information, and determine the target object in response to the selection instruction.

Optionally, as shown in Figure 21, the direction adjustment module 24 includes:

The ratio calculation unit 241 is configured to calculate the quantity ratios of each of the text lines in each direction, and determine the direction indicated by the highest quantity ratio among the quantity ratios;

an angle output unit 242 configured to calculate and output a rotation angle based on the direction indicated by the highest number ratio;

The direction adjusting unit 243 is configured to adjust the display direction of the preview image based on the rotation angle, and display the adjusted preview image.

Optionally, the angle adjustment unit is specifically configured as:

If the rotation angle is not 0, the display direction of the preview image is rotated by the rotation angle to obtain the display direction of the preview image.

It should be noted that, when the image orientation adjustment device provided in the above-mentioned embodiments executes the image orientation adjustment method, the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can be assigned to different function modules as required Module completion means that the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the image orientation adjustment device and the image orientation adjustment method embodiment provided by the above embodiment belong to the same idea, and the implementation process thereof is detailed in the method embodiment, and will not be repeated here.

The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

The embodiment of the present application also provides a computer storage medium, the computer storage medium can store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps of the above-mentioned embodiments shown in Figures 1-13 For the specific execution process, refer to the specific description of the embodiments shown in FIGS. 1-13 , and details are not repeated here.

The present application also provides a computer program product, the computer program product stores at least one instruction, and the at least one instruction is loaded by the processor and executes the method steps of the above-mentioned embodiments shown in Figures 1-13, specifically For the execution process, reference may be made to the specific descriptions of the embodiments shown in FIGS. 1-13 , and details are not repeated here.

Please refer to FIG. 22 , which provides a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in FIG. 22 , the mobile terminal 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

Wherein, the communication bus 1002 is used to realize connection and communication between these components.

Wherein, the user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

Wherein, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

Wherein, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005, execute Various functions of the electronic device 1000 and processing data. Optionally, the processor 1001 may use at least one of Digital Signal Processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). implemented in the form of hardware. The processor 1001 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly handles the operating system, user interface and application programs, etc.; the GPU is used to render and draw the content that needs to be displayed on the display screen; the modem is used to handle wireless communication. It can be understood that the above modem may also not be integrated into the processor 1001, but implemented by a single chip.

Wherein, the memory 1005 may include a random access memory (Random Access Memory, RAM), and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium (non-transitory computer-readable storage medium). The memory 1005 may be used to store instructions, programs, codes, sets of codes or sets of instructions. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), Instructions and the like for implementing the above method embodiments; the storage data area can store the data and the like involved in the above method embodiments. Optionally, the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001 . As shown in FIG. 22 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an image orientation adjustment application program.

In the mobile terminal 1000 shown in FIG. 22 , the user interface 1003 is mainly used to provide the user with an input interface to obtain the data input by the user; and the processor 1001 can be used to call the generated image orientation adjustment application program stored in the memory 1005, And specifically do the following:

Obtain the preview image collected by the camera for the subject;

determining the orientation of each of the at least one line of text;

In one embodiment, when the processor 1001 recognizes the target object in the preview image and acquires at least one text line in the target object, it specifically performs the following operations:

Using a binary classification algorithm to identify the target object in the preview image;

identifying all text lines in said target object;

At least one text line is selected from all the text lines.

In one embodiment, when the processor 1001 determines the direction of each text line in the at least one text line, it specifically performs the following operations:

traversing each of the at least one text line;

Perform character cutting processing on the currently traversed target text line, and determine the direction of the target text line;

until the traversal ends.

In one embodiment, when the processor 1001 performs character cutting processing on the currently traversed target text line and determines the direction of the target text line, it specifically performs the following operations:

Processing the binarized image by using a horizontal projection method to obtain a first pixel distribution histogram;

Processing the binarized image by using a vertical projection method to obtain a second pixel distribution histogram;

Based on the first pixel distribution histogram and the second pixel distribution histogram, the characters in the target text line are cut to determine the direction of the target text line.

In one embodiment, the processor 1001 cuts the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram to determine the target text line In the direction of , specifically perform the following operations:

In one embodiment, when the processor 1001 executes when all characters in the target text line have the same direction, based on the first pixel distribution histogram and the second pixel distribution histogram, the target The characters in the text line are cut, and when the direction of the target text line is determined, the following operations are specifically performed:

In one embodiment, the processor 1001 determines the target direction of the preview image based on each of the directions, adjusts the display direction of the preview image based on the target direction of the preview image, and displays the adjusted preview image. , specifically perform the following operations:

calculating the quantity ratios of each of the text lines in each direction;

Acquiring the direction indicated by the highest number ratio among the number ratios, and adjusting the display direction of the preview image based on the direction indicated by the highest number ratio.

In one embodiment, when the processor 1001 recognizes the target object in the preview image, the following operations are specifically performed:

Optionally, the processor 1001 also performs the following operations:

Displaying a preview image collected by the camera for the subject;

In one embodiment, the processor 1001 also performs the following operations:

A confirmation instruction for the prompt information is received, and a function of detecting the direction of the target object is turned on in response to the confirmation instruction.

In one embodiment, after the processor 1001 executes displaying the preview image captured by the camera for the subject, the following operations are further performed:

A selection instruction for the target object in the prompt information is received, and marking information for the target object is displayed in response to the selection instruction.

In one embodiment, the processor 1001 determines the target direction of the preview image based on each of the directions, adjusts the display direction of the preview image based on the target direction of the preview image, and displays the adjusted preview image. , specifically do the following:

calculating the quantity ratios of each of the text lines in each direction, and determining the direction indicated by the highest quantity ratio among the quantity ratios;

calculating and outputting a rotation angle based on the direction indicated by the highest number ratio;

Adjusting the display direction of the preview image based on the rotation angle, and displaying the adjusted preview image.

In one embodiment, when the processor 1001 adjusts the display direction of the preview image based on the rotation angle, it specifically performs the following operations:

If the rotation angle is not 0, the display direction of the preview image is rotated by the rotation angle.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the programs can be stored in a computer-readable storage medium. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory, and the like.

The above disclosures are only preferred embodiments of the present application, which certainly cannot limit the scope of the present application. Therefore, equivalent changes made according to the claims of the present application still fall within the scope of the present application.

Claims

A method for adjusting an image direction, wherein, applied to a mobile terminal, the method includes:

Obtain the preview image collected by the camera for the subject;

identifying a target object in the preview image, and acquiring at least one text line in the target object;

determining the orientation of each of the at least one line of text;

A target direction of the preview image is determined based on each of the directions, and a display direction of the preview image is adjusted based on the target direction of the preview image.
The method according to claim 1, wherein said identifying the target object in the preview image and obtaining at least one text line in the target object comprises:

Using a binary classification algorithm to identify the target object in the preview image;

identifying all text lines in said target object;

At least one text line is selected from all the text lines.
The method according to claim 1, wherein said determining the direction of each text line in said at least one text line comprises:

traversing each of the at least one text line;

Perform character cutting processing on the currently traversed target text line, and determine the direction of the target text line;

until the traversal ends.
The method according to claim 3, wherein said performing character cutting processing on the currently traversed target text line, and determining the direction of the target text line include:

Perform binarization processing on the currently traversed target text line to obtain a binarized image;

Processing the binarized image by using a horizontal projection method to obtain a first pixel distribution histogram;

Processing the binarized image by using a vertical projection method to obtain a second pixel distribution histogram;

Based on the first pixel distribution histogram and the second pixel distribution histogram, the characters in the target text line are cut to determine the direction of the target text line.
The method according to claim 4, wherein, based on the first pixel distribution histogram and the second pixel distribution histogram, the characters in the target text line are cut to determine the target text line directions, including:

cutting the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determining the direction of each character;

calculating the quantity ratios of the characters in each direction, and obtaining the target direction of the character indicated by the highest quantity ratio among the quantity ratios;

The target direction of the character is used as the direction of the target text line.
The method according to claim 4, wherein, when all characters in the target text line have the same direction, the target The characters in the text line are cut to determine the direction of the target text line, including:

The character in the target text line is cut based on the first pixel distribution histogram and the second pixel distribution histogram, the direction of any character in the target text line is determined, and any character in the target text line is determined. The direction of a character is used as the direction of the target text line.
The method according to claim 1, wherein determining the target direction of the preview image based on each of the directions, and adjusting the display direction of the preview image based on the target direction of the preview image comprises:

calculating the quantity ratios of each of the text lines in each direction;

Acquiring the direction indicated by the highest number ratio among the number ratios, and adjusting the display direction of the preview image based on the direction indicated by the highest number ratio.
The method according to claim 1, wherein the identifying the target object in the preview image comprises:

When the preview image includes multiple recognized objects, the selected recognized object among the multiple recognized objects is used as the target object.
A method for adjusting an image orientation, wherein the method includes:

receiving a shooting instruction, and turning on the camera in response to the shooting instruction;

Displaying a preview image collected by the camera for the subject;

determining the orientation of each of the lines of text determined in the preview image;

determining a target direction of the preview image based on each of the directions, adjusting a display direction of the preview image based on the target direction of the preview image, and displaying the adjusted preview image.
The method according to claim 9, wherein, after turning on the camera, further comprising:

Display whether to open the prompt information for the direction detection of the target object;

A confirmation instruction for the prompt information is received, and a function of detecting the direction of the target object is turned on in response to the confirmation instruction.
The method according to claim 9, wherein, after displaying the preview image collected by the camera for the subject, further comprising:

When the preview image includes multiple recognized objects, displaying prompt information containing the multiple recognized objects;

A selection instruction for the target object in the prompt information is received, and the target object is determined in response to the selection instruction.
The method according to claim 9, wherein determining the target direction of the preview image based on each of the directions, adjusting the display direction of the preview image based on the target direction of the preview image, and displaying the adjusted preview image comprises :

calculating the quantity ratios of each of the text lines in each direction, and determining the direction indicated by the highest quantity ratio among the quantity ratios;

calculating and outputting a rotation angle based on the direction indicated by the highest number ratio;

Adjusting the display direction of the preview image based on the rotation angle, and displaying the adjusted preview image.
The method according to claim 12, wherein the adjusting the display direction of the preview image based on the rotation angle comprises:

If the rotation angle is not 0, the display direction of the preview image is rotated by the rotation angle.
An image orientation adjustment device, wherein the device includes:

An image acquisition module configured to acquire a preview image collected by the camera for the subject;

A text line acquisition module configured to identify a target object in the preview image, and acquire at least one text line in the target object;

an orientation determination module configured to determine the orientation of each of the at least one text lines;

The orientation adjustment module is configured to determine the target orientation of the preview image based on each of the orientations, and adjust the display orientation of the preview image based on the target orientation of the preview image.
The device according to claim 14, wherein the text line acquisition module comprises:

a target object recognition unit configured to use a binary classification algorithm to recognize the target object in the preview image;

a text line identification unit configured to identify all text lines in the target object;

The text line selection unit is configured to select at least one text line from all the text lines.
The device according to claim 14, wherein the direction determining module comprises:

a text line traversing unit configured to traverse each text line in the at least one text line;

a direction determination unit configured to perform character cutting processing on the currently traversed target text line, and determine the direction of the target text line;

The end unit of the traversal is configured until the end of the traversal.
The device according to claim 16, wherein the direction determining unit comprises:

The image acquisition subunit is configured to perform binarization processing on the currently traversed target text line to obtain a binarized image;

The first histogram acquisition subunit is configured to process the binarized image using a horizontal projection method to obtain a first pixel distribution histogram;

The second histogram acquisition subunit is configured to process the binarized image using a vertical projection method to obtain a second pixel distribution histogram;

The character cutting subunit is configured to cut the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determine the direction of the target text line.
The device according to claim 17, wherein the character cutting subunit is specifically configured as:

cutting the characters in the target text line based on the first pixel distribution histogram and the second pixel distribution histogram, and determining the direction of each character;

calculating the quantity ratios of the characters in each direction, and obtaining the target direction of the character indicated by the highest quantity ratio among the quantity ratios;

The target direction of the character is used as the direction of the target text line.
The device according to claim 17, wherein when all the characters in the target text line have the same direction, the character cutting subunit is specifically configured as:

The character in the target text line is cut based on the first pixel distribution histogram and the second pixel distribution histogram, the direction of any character in the target text line is determined, and any character in the target text line is determined. The direction of a character is used as the direction of the target text line.
The device according to claim 14, wherein the direction adjustment module comprises:

A ratio calculation unit configured to calculate the quantity ratio of each of the text lines in each direction;

The angle adjustment unit is configured to obtain the direction indicated by the highest number ratio among the number ratios, and adjust the display direction of the preview image based on the direction indicated by the highest number ratio.
The device according to claim 14, wherein the text line acquisition module is specifically configured as:

When the preview image includes multiple recognized objects, the selected recognized object among the multiple recognized objects is used as the target object.
An image orientation adjustment device, wherein the device includes:

The camera opening module is configured to receive a shooting instruction, and turn on the camera in response to the shooting instruction;

An image display module configured to display a preview image collected by the camera for the subject;

a direction determination module configured to determine the direction of each text line determined in the preview image;

The direction adjustment module is configured to determine the target direction of the preview image based on each of the directions, adjust the display direction of the preview image based on the target direction of the preview image, and display the adjusted preview image.
The apparatus according to claim 22, wherein said apparatus further comprises:

The detection prompt display module is configured to display the prompt information of whether to open the direction detection of the target object;

The detection enabling module is configured to receive a confirmation instruction for the prompt information, and respond to the confirmation instruction to enable the function of detecting the direction of the target object.
The apparatus according to claim 22, wherein said apparatus further comprises:

An information prompt display module configured to display prompt information containing the multiple recognized objects when the preview image includes multiple recognized objects;

The target object determination module is configured to receive a selection instruction for the target object in the prompt information, and determine the target object in response to the selection instruction.
The device according to claim 22, wherein the direction adjustment module comprises:

A ratio calculation unit configured to calculate the quantity ratios of each of the text lines in each direction, and determine the direction indicated by the highest quantity ratio among the quantity ratios;

an angle output unit configured to calculate and output a rotation angle based on the direction indicated by the highest number ratio;

The direction adjusting unit is configured to adjust the display direction of the preview image based on the rotation angle, and display the adjusted preview image.
The device according to claim 25, wherein the angle adjustment unit is specifically configured as:

If the rotation angle is not 0, the display direction of the preview image is rotated by the rotation angle.
A computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1-8 or 9-13.
An electronic device, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing any one of claims 1-8 or 9-13 method steps for the item.