A method, apparatus and medium for generating a poster fission

Abstract

The application discloses a poster fission generation method and device and a medium. The method comprises the following steps: constructing a poster fission template of a fission poster, wherein the poster fission template comprises a picture, text and a preset element region; performing key feature extraction on the poster fission template to obtain key region information and reserved position information of the poster fission template; adjusting a to-be-fissioned poster content according to size information in the reserved position information to obtain adjusted to-be-fissioned poster content; and embedding the adjusted to-be-fissioned poster content into the poster fission template based on the reserved position information and the key region information to generate a fission poster.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet, and more particularly, to a poster fission generation method and device and medium. BACKGROUND

[0002] In an Internet project, it is often necessary to create some poster texts and business cards according to the characteristics of the project and the needs of publicity, so as to achieve the marketing purpose of the project through the propagation and sharing among users. Therefore, the system will promote the fission poster activity every quarter to invite more users by lecturers. Since the poster fission template is different each time, the position of the picture needs to be manually drawn every time, which consumes a lot of time. Therefore, there is a technical problem of low efficiency of poster fission. SUMMARY

[0003] In view of the deficiencies of the prior art, the present application provides a poster fission generation method, device and medium.

[0004] According to one aspect of the present application, a poster fission generation method is provided, comprising:

[0005] Constructing a poster fission template of a fission poster, wherein the poster fission template comprises a picture, a text and a preset element region;

[0006] Extracting key features of the poster fission template to obtain key region information and reserved position information of the poster fission template;

[0007] Adjusting the content of the poster to be fissured according to the size information in the reserved position information to obtain the adjusted content of the poster to be fissured;

[0008] Embedding the adjusted content of the poster to be fissured into the poster fission template based on the reserved position information and the key region information to generate a fission poster.

[0009] Optionally, the key features of the poster fission template are extracted to obtain the key region information and the reserved position information of the poster fission template, comprising:

[0010] Performing grayscale, binarization, denoising and filtering operations on the picture of the poster fission template to obtain a picture region in the key region;

[0011] Using an edge detection algorithm to identify the graphic boundary and line structure of the poster fission template to determine the key region and the reserved position of the poster fission template;

[0012] Calculating the coordinate information of the identified key region, reserved position and key region to determine the key region information and the reserved position information, wherein the coordinate information comprises a top-left corner coordinate point, a width and a height.

[0013] Optionally, the graphic boundary and line structure of the poster fission template are identified by using an edge detection algorithm, key areas and reserved positions of the poster fission template are determined, and the method comprises the following steps:

[0014] An edge image of the graphic boundary and line structure of the poster fission template is detected by using a Canny algorithm.

[0015] All contour information is obtained by applying contour detection on the edge image.

[0016] The poster fission template is subjected to semantic segmentation based on the contour information by using a deep learning model, and key areas and reserved positions are identified.

[0017] Optionally, the edge image of the graphic boundary and line structure of the poster fission template is detected by using a Canny algorithm, and the method comprises the following steps:

[0018] The poster fission template is subjected to Gaussian filtering to obtain a filtered image.

[0019] Gradient information of each pixel in the filtered image is calculated, wherein the gradient information comprises gradient amplitude and gradient angle.

[0020] Non-maximum suppression is performed on the gradient amplitude to obtain edge information.

[0021] The edge information is processed by using a double-threshold method to obtain an edge image.

[0022] According to another aspect of the present application, a poster fission generation device is provided, which comprises:

[0023] A construction module is configured to construct a poster fission template of a fission poster, wherein the poster fission template comprises a picture, text and a preset element area.

[0024] An extraction module is configured to extract key features of the poster fission template to obtain key area information and reserved position information of the poster fission template.

[0025] An adjustment module is configured to adjust a to-be-fissioned poster content according to size information in the reserved position information to obtain an adjusted to-be-fissioned poster content.

[0026] A generation module is configured to embed the adjusted to-be-fissioned poster content into the poster fission template based on the reserved position information and the key area information to generate a fission poster.

[0027] According to still another aspect of the present application, a computer readable storage medium is provided, and the storage medium stores a computer program, wherein the computer program is used to execute the method according to any one of the aspects of the present application.

[0028] According to a further aspect of the present application, there is provided an electronic device comprising: a processor; a memory for storing instructions executable by the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of the above aspects of the present application.

[0029] Thus, BRIEF DESCRIPTION OF DRAWINGS

[0030] The exemplary embodiments of this application will be better understood with a casual reference to the following drawings:

[0031] Figure 1 is a flowchart of a method for generating a poster fission provided by an exemplary embodiment of the present application;

[0032] Figure 2 is a structural diagram of a poster fission generating apparatus provided by an exemplary embodiment of the present application;

[0033] Figure 3 is a structure of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0034] Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent to those skilled in the art that the following described embodiments are only part of the embodiments of the present application and are not intended to limit the present application, and a variety of modifications can be made without departing from the spirit of the present application.

[0035] It should be noted that the relative arrangement of the components and steps, numerical expressions, and numerical values set forth in these embodiments are not limiting to the scope of the present application unless otherwise specifically stated.

[0036] Those skilled in the art can understand that the terms "first", "second", and the like in the embodiments of the present application are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they represent the inevitable logical sequence between them.

[0037] It should also be understood that in the embodiments of the present application, "a plurality of" can mean two or more, and "at least one" can mean one, two, or more.

[0038] It should also be understood that for any component, data, or structure mentioned in the embodiments of the present application, unless specifically limited or unless the context clearly indicates otherwise, it can be understood as one or more.

[0039] In addition, the term "and / or" in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0040] It should also be understood that the description of the application focuses on the differences between various embodiments, and the same or similar parts can be referred to each other, and for the sake of brevity, will not be repeated.

[0041] At the same time, it should be understood that, for the convenience of description, the size of each part shown in the drawings is not drawn according to the actual proportional relationship.

[0042] The following description of at least one example embodiment is merely illustrative in nature and is in no way intended to limit the application or its application or use.

[0043] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification where appropriate.

[0044] It should be noted that similar reference numbers and letters refer to similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0045] Embodiments of the present application can be applied to terminal devices, computer systems, servers and other electronic devices, which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with terminal devices, computer systems, servers and other electronic devices include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, mainframe computer systems and distributed cloud computing technology environments including any of the above systems.

[0046] Electronic devices such as terminal devices, computer systems, servers, and the like can be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules can include routines, programs, objects, components, logic, data structures, and the like that perform particular tasks or implement particular abstract data types. Computer systems / servers can be practiced in distributed cloud-computing environments with remote processing devices that are linked through a communications network. In a distributed cloud-computing environment, program modules can be located in local and / or remote computer system storage media including storage devices.

[0047] Exemplary method

[0048] Figure 1 FIG. 1 is a flowchart of a method for generating a poster fission according to an exemplary embodiment of the present disclosure. The present embodiment can be applied to an electronic device, such as a computer system, a server, a terminal device, and the like. Figure 1 As shown in FIG. 1, the method 100 for generating a poster fission includes the following steps:

[0049] Step 101, constructing a poster fission template of a fission poster, wherein the poster fission template includes pictures, texts, and preset element regions;

[0050] Step 102, performing key feature extraction on the poster fission template to obtain key region information and reserved position information of the poster fission template;

[0051] Step 103, adjusting a content of a poster to be fissured according to size information in the reserved position information to obtain an adjusted content of the poster to be fissured;

[0052] Step 104, embedding the adjusted content of the poster to be fissured into the poster fission template based on the reserved position information and the key region information to generate a fission poster.

[0053] Specifically, the present disclosure detects by automatically recognizing and extracting key features in a poster fission template, locates a boundary of a reserved position in the poster fission template, aligns a user-uploaded content with the reserved position in the poster fission template, and generates a poster. The specific implementation is as follows:

[0054] 1. Preparing a poster fission template of a poster fission:

[0055] Designing a template of a fission poster and reserving positions of pictures, texts, and other elements in the template.

[0056] 2. Key feature extraction of the poster fission template:

[0057] 1) Image preprocessing: performing operations such as graying, binarization, denoising, and filtering on a template image to reduce image complexity and highlight features of reserved positions of pictures.

[0058] 2) Feature Detection: Use edge detection algorithms (such as Canny, Hough Transform) to identify the graphical boundaries and line structures in the template, determine the key areas of the template and the bounding boxes of the reserved positions.

[0059] Algorithm flow:

[0060] 1. Use Canny algorithm to detect edges in the image, formula: edges = cv2.Canny(image, threshold1, threshold2);

[0061] 2. Apply contour detection (such as cv2.findContours) on the edge image to obtain all contour information. Formula: contours, hierarchy = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

[0062] Calculate the bounding box of each contour. Formula: bounding_boxes = [cv2.boundingRect(cnt) for cnt in contours if cv2.contourArea(cnt) > min_area]

[0063] 3. Use deep learning models for semantic segmentation, such as U-Net or Mask R-CNN, to perform pixel-level classification on the template and automatically identify key areas and reserved positions. This method can more accurately locate and identify the bounding boxes of complex structures.

[0064] The parameters used in the Canny algorithm include:

[0065] Gaussian filter parameters;

[0066] Gaussian kernel size: k_{\text{size}};

[0067] Gaussian kernel standard deviation: \sigma;

[0068] Gradient calculation parameters;

[0069] Sobel operator convolution kernel size: k_{\text{size}};

[0070] Pixel difference precision used for gradient calculation: k_{\text{size}};

[0071] Non-maximum suppression parameters;

[0072] Gradient angle threshold: \theta;

[0073] Double threshold processing parameter;

[0074] Low threshold: \text{low_threshold};

[0075] High threshold: \text{high_threshold}.

[0076] According to the above parameters, the edge detection process of the Canny algorithm can be summarized as the following steps:

[0077] Apply a Gaussian filter to the image to reduce noise:

[0078] Input image: \text{input_image};

[0079] Output image: \text{blurred_image} = \text{GaussianBlur}(\text{input_image}, k_{\text{size}}, \sigma).

[0080] Calculate the gradient and angle of each pixel in the image:

[0081] Sobel operator is used to calculate the gradient of the image in x and y directions. The convolution kernels of Sobel operator in x direction and y direction are respectively:

[0082]

[0083] X direction gradient: \text{gradient_x} = \text{Sobel}(\text{blurred_image}, k_{\text{size}}, k_{\text{size}}, 1, 0, k_{\text{size}});

[0084] Y direction gradient: \text{gradient_y} = \text{Sobel}(\text{blurred_image}, k_{\text{size}}, k_{\text{size}}, 0, 1, k_{\text{size}});

[0085] Gradient magnitude: \text{gradient_magnitude} = \sqrt{\text{gradient_x}^2 + \text{gradient_y}^2};

[0086] Gradient angle: \text{gradient_angle} = \text{arctan2}(\text{gradient_y},\text{gradient_x}).

[0087] Non-maximum suppression is performed on the gradient magnitude to preserve edge details:

[0088] Input gradient magnitude image: \text{gradient_magnitude};

[0089] Input gradient angle image: \text{gradient_angle};

[0090] Output suppressed gradient magnitude image: \text{non_max_suppressed} = \text{NonMaxSuppression}(\text{gradient_magnitude},\text{gradient_angle},\theta).

[0091] A double thresholding process is used to determine the true edges:

[0092] Input suppressed gradient magnitude image: \text{non_max_suppressed};

[0093] Low threshold thresholding: \text{low_threshold_mask} = (\text{non_max_suppressed} > \text{low_threshold});

[0094] High threshold thresholding: \text{high_threshold_mask} = (\text{non_max_suppressed} > \text{high_threshold});

[0095] Output binary edge image: \text{edge_image} = \text{hysteresis}(\text{low_threshold_mask},\text{high_threshold_mask}).

[0096] The Canny algorithm is a classic edge detection algorithm with the following innovations and technical effects:

[0097] Multi-step edge detection process: The Canny algorithm extracts edges in an image through a multi-step process. These steps include Gaussian filtering, gradient calculation, non-maximum suppression, and double thresholding. Through the combination of these steps, the Canny algorithm can extract detailed and accurate edges with less noise influence.

[0098] Double thresholding with adaptive threshold: The Canny algorithm uses double thresholding to determine true edges. Compared to single thresholding, double thresholding can adaptively select thresholds according to the gradient intensity of pixels. This can better distinguish edges from noise and produce more accurate edge images.

[0099] Non-maximum suppression: The Canny algorithm applies non-maximum suppression after gradient calculation to preserve edge details. This step suppresses non-edge pixels by interpolating in the gradient direction, thus extracting thin lines of edges.

[0100] The Canny algorithm achieves the following technical effects through the above innovations:

[0101] High-accuracy edge detection: The Canny algorithm can accurately detect edges in an image, including thin lines and curved edges. It improves the accuracy and stability of edge detection through multiple steps of processing.

[0102] Strong anti-noise ability: The Gaussian filtering step of the Canny algorithm can reduce noise interference in the image, thus improving the robustness and anti-noise ability of edge detection.

[0103] Strong detail preservation ability: The Canny algorithm preserves the details of the edge information through non-maximum suppression and double thresholding. This can effectively remove noise and irrelevant details while maintaining clear edges.

[0104] 3) Coordinate calculation: For each identified replaceable area, calculate its top-left corner coordinates, width, and height, forming a rectangular bounding box in the coordinate system as metadata for saving.

[0105] 3、User uploaded content processing:

[0106] According to the size requirements of the reserved positions in the template, the user's content is scaled, cropped, rotated, and other adaptive adjustments are made to ensure that it can be perfectly embedded in the specified area.

[0107] 4、Generate poster: Output the completed personalized poster as a high-quality image file.

[0108] 5、Feedback and optimization: Collect feedback from users during use, continuously optimize template recognition accuracy, content embedding effect, and system performance, and improve user experience.

[0109] Therefore, by the poster fission generation method provided by the application, only the designed poster fission template needs to be uploaded, the coordinates of the reserved positions of the template are automatically recognized and extracted, the user uploaded content is embedded into the template area to generate a poster, the time for developing manual matching of pictures and poster fission templates is reduced, and thus the development efficiency is improved.

[0110] Exemplary apparatus

[0111] Figure 2 is a structural schematic diagram of a poster fission generation device provided by an exemplary embodiment of the application. As shown in Figure 2 , the device 200 comprises:

[0112] a construction module 210, configured to construct a poster fission template of a fission poster, wherein the poster fission template comprises pictures, texts and preset element areas;

[0113] an extraction module 220, configured to perform key feature extraction on the poster fission template to obtain key area information and reserved position information of the poster fission template;

[0114] an adjustment module 230, configured to adjust a to-be-fissioned poster content according to size information in the reserved position information to obtain an adjusted to-be-fissioned poster content;

[0115] a generation module 240, configured to embed the adjusted to-be-fissioned poster content into the poster fission template based on the reserved position information and the key area information to generate a fission poster.

[0116] Optionally, the extraction module 220 comprises:

[0117] a preprocessing sub-module, configured to perform grayscale, binarization, denoising and filtering operations on pictures of the poster fission template to obtain picture areas in the key areas;

[0118] an identification sub-module, configured to identify graph boundaries and line structures of the poster fission template by using an edge detection algorithm to determine the key areas and the reserved positions of the poster fission template;

[0119] a calculation sub-module, configured to calculate coordinate information of the identified key areas, reserved positions and key areas to determine the key area information and the reserved position information, wherein the coordinate information comprises a top-left corner coordinate point, a width and a height.

[0120] Optionally, the identification sub-module comprises:

[0121] a detection unit, configured to detect edge images of the graph boundaries and the line structures of the poster fission template by using a Canny algorithm;

[0122] The acquisition unit is configured to acquire all contour information by applying contour detection on the edge image;

[0123] The recognition unit is configured to perform semantic segmentation on the poster fission template based on the contour information by using a deep learning model, to identify a key region and a reserved position.

[0124] Optionally, the detection unit comprises:

[0125] The filtering sub-unit is configured to perform Gaussian filtering on the poster fission template to obtain a filtered image.

[0126] The calculation sub-unit is configured to calculate gradient information of each pixel in the filtered image, wherein the gradient information comprises a gradient magnitude and a gradient angle.

[0127] The suppression sub-unit is configured to perform non-maximum suppression on the gradient magnitude to obtain edge information.

[0128] The processing sub-unit is configured to process the edge information by using a double-threshold method to obtain an edge image.

[0129] Exemplary electronic device

[0130] Figure 3 is a structure of an electronic device provided by an exemplary embodiment of the present application. As shown in Figure 3 The electronic device 30 comprises one or more processors 31 and a memory 32.

[0131] The processor 31 can be a central processing unit (CPU) or other forms of processing units having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.

[0132] The memory 32 can comprise one or more computer program products, which can comprise various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can comprise, for example, random access memory (RAM), cache memory and / or the like. The non-volatile memory can comprise, for example, read-only memory (ROM), hard disk, flash memory and / or the like. One or more computer program instructions can be stored on the computer readable storage media, and the processor 31 can run the program instructions to implement the methods of the software programs of various embodiments of the present application described above and / or other desired functions. In one example, the electronic device can further comprise an input device 33 and an output device 34, which are interconnected by a bus system and / or other forms of connection mechanism (not shown).

[0133] In addition, the input device 33 can further comprise, for example, a keyboard, a mouse and / or the like.

[0134] The output device 34 can output various information to the outside. The output device 34 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0135] Of course, in order to simplify, Figure 3 Only some of the components of the electronic device related to the present application are shown in FIG. 1, and components such as a bus, an input / output interface, and the like are omitted. In addition to this, the electronic device can include any other appropriate components according to the specific application.

[0136] Exemplary computer program product and computer readable storage medium

[0137] In addition to the above-mentioned methods and devices, embodiments of the present application can also be a computer program product including computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0138] The computer program product can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, and the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

[0139] In addition, embodiments of the present application can also be a computer readable storage medium having stored thereon computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the method of information mining on the history change record according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0140] The computer readable storage medium can be any combination of one or more computer readable medium(s). The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or apparatus or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] The above describes the basic principles of the present application in conjunction with specific embodiments, but it should be noted that the advantages, benefits, effects and the like mentioned in the present application are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as necessary for each embodiment of the present application. In addition, the above specific details disclosed are only for the purpose of example and understanding, and are not limiting, and the above details do not limit the present application to the above specific details.

[0142] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between each embodiment can be understood by mutual reference. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple, and the relevant parts can be understood by referring to the part of the method embodiment.

[0143] The block diagrams of the devices, systems, apparatuses, systems involved in the present application are only illustrative examples and are not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagram. As those skilled in the art will recognize, these devices, systems, apparatuses, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have" and the like are open-ended words, mean "include but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0144] The methods and systems of the present application can be implemented in a number of ways. For example, the methods and systems of the present application can be implemented via software, hardware, firmware, or any combination of software, hardware, and firmware. The above described order of steps for the methods is merely illustrative, and the steps of the methods of the present application are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present application can also be implemented as a program recorded on a recording medium, which includes machine readable instructions for implementing the methods according to the present application. Thus, the present application also covers recording media storing programs for executing the methods according to the present application.

[0145] It is also important to note that the systems, devices and methods of the present application can be embodied in a variety of forms without departing from the spirit of the application. Specifically, the systems, devices and methods of the present application can be implemented using hardware, software, firmware, or any combination thereof. In some embodiments, the systems, devices and methods of the present application can be implemented as a program tangibly embodied on a program carrier. It is therefore intended that the present application covers all such variations and modifications that fall within the scope of the application. It is also intended that the pre sent application covers all of the generic and specific substitutional groups of the members of the genera and species herein disclosed. Furthermore, the disclosure of multiple herein disclosed aspects does not preclude a claim comprising at least one of the aspects; that is, any one of the aspects can also include any additional aspect or aspects.

[0146] The above description has been presented for the purposes of illustration and description. Further, this description is not intended to limit embodiments of the present application to the forms disclosed herein. Although several example aspects and embodiments have been discussed, those skilled in the art will recognize certain modifications, permutations, additions, and sub-combinations thereof.

Claims

1. A method for generating a poster fission, characterized by, The method comprises the following steps: constructing a poster fission template of a fission poster, wherein the poster fission template comprises pictures, texts and preset element regions; extracting key features of the poster fission template to obtain key region information and reserved position information of the poster fission template; adjusting a to-be-fissioned poster content according to size information in the reserved position information to obtain an adjusted to-be-fissioned poster content; embedding the adjusted to-be-fissioned poster content into the poster fission template based on the reserved position information and the key region information to generate a fission poster. extracting key features of the poster fission template to obtain key region information and reserved position information of the poster fission template, comprising: performing grayscale, binarization, denoising and filtering operations on pictures of the poster fission template to obtain picture regions in the key regions; identifying graph boundaries and line structures of the poster fission template by using an edge detection algorithm to determine the key regions and the reserved positions of the poster fission template; calculating coordinate information of the identified key regions, the reserved positions and the key regions to determine the key region information and the reserved position information, wherein the coordinate information comprises a top-left corner coordinate point, a width and a height; identifying graph boundaries and line structures of the poster fission template by using an edge detection algorithm to determine the key regions and the reserved positions of the poster fission template, comprising: detecting edge images of the graph boundaries and the line structures of the poster fission template by using a Canny algorithm; applying contour detection on the edge images to obtain all contour information; performing semantic segmentation on the poster fission template based on the contour information by using a deep learning model to identify the key regions and the reserved positions; detecting edge images of the graph boundaries and the line structures of the poster fission template by using a Canny algorithm, comprising: performing Gaussian filtering on the poster fission template to obtain a filtered image; calculating gradient information of each pixel in the filtered image, wherein the gradient information comprises a gradient amplitude and a gradient angle; performing non-maximum suppression on the gradient amplitude to obtain edge information; processing the edge information by using a double-threshold method to obtain the edge images.

2. An apparatus for generating a poster fission, for implementing the method for generating a poster fission according to claim 1, characterized in that, The method comprises the following steps: constructing a poster fission template of a fission poster, wherein the poster fission template comprises pictures, texts and preset element regions; extracting key features of the poster fission template to obtain key region information and reserved position information of the poster fission template; adjusting a to-be-fissioned poster content according to size information in the reserved position information to obtain an adjusted to-be-fissioned poster content; embedding the adjusted to-be-fissioned poster content into the poster fission template based on the reserved position information and the key region information to generate a fission poster.

3. The apparatus of claim 2, wherein, The extraction module comprises: a preprocessing submodule configured to perform grayscale, binarization, denoising and filtering operations on pictures of the poster fission template to obtain picture regions in the key regions; The identification sub-module is configured to identify the graphic boundary and line structure of the poster fission template by using an edge detection algorithm, and determine a key region and a reserved position of the poster fission template. The calculation sub-module is configured to calculate the identified key region, reserved position and coordinate information of the key region, and determine key region information and reserved position information, wherein the coordinate information comprises a top-left corner coordinate point, a width and a height.

4. The apparatus of claim 3, wherein, The identification sub-module comprises: The detection unit is configured to detect an edge image of the graphic boundary and line structure of the poster fission template by using a Canny algorithm. The acquisition unit is configured to acquire all contour information by applying contour detection on the edge image. The identification unit is configured to perform semantic segmentation on the poster fission template based on the contour information by using a deep learning model, and identify a key region and a reserved position.

5. The apparatus of claim 4, wherein, The detection unit comprises: The filtering sub-unit is configured to perform Gaussian filtering on the poster fission template to acquire a filtered image. The calculation sub-unit is configured to calculate gradient information of each pixel in the filtered image, wherein the gradient information comprises a gradient amplitude and a gradient angle. The suppression sub-unit is configured to perform non-maximum suppression on the gradient amplitude to acquire edge information. The processing sub-unit is configured to process the edge information by using a double-threshold method to acquire the edge image.

6. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is configured to execute the method in claim 1.

7. An electronic device, comprising: The electronic device comprises: a processor; a memory configured to store executable instructions of the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method in claim 1.

Images