WO2023284313A1

WO2023284313A1 - Automatic slicing method and device for psd picture

Info

Publication number: WO2023284313A1
Application number: PCT/CN2022/080388
Authority: WO
Inventors: 魏陈南; 唐斌
Original assignee: 稿定（厦门）科技有限公司
Priority date: 2021-07-16
Filing date: 2022-03-11
Publication date: 2023-01-19
Also published as: CN113450365B; CN113450365A

Abstract

The present invention relates to an automatic slicing method and device for a PSD picture. The method comprises: obtaining the PSD picture; performing binarization processing on the PSD picture, and determining a foreground and a background in the PSD picture; extracting distribution information of the foreground and the background by means of an image segmentation algorithm; and slicing the PSD picture according to the distribution information of the foreground and the background. According to the solution of the present invention, automatic slicing of the PSD picture can be achieved without depending on a PSD document structured directory and layer naming, the mutual relation of visual elements can be kept by means of the slicing, and the visual elements would not be split to different canvases, so that the integrity of the visual design relation of the PSD picture is guaranteed, and the use complexity of the PSD picture and the use cost of a designer are reduced.

Description

Automatic slicing method and device for PSD pictures

This application claims the priority of the Chinese invention patent application with the application number 202110804654.X and the title "Automatic slicing method and device for PSD pictures" submitted to the China Intellectual Property Office on July 16, 2021, the entire disclosure content of which is incorporated Here for reference.

technical field

The present disclosure relates generally to the field of computer technology. More specifically, the present disclosure relates to a method and device for automatically slicing PSD pictures.

Background technique

At present, webpage designers are used to using Photoshop to participate in webpage design. When using PSD format image files generated by Photoshop, they often need to slice them to facilitate the transfer and use of various elements in the PSD image files.

However, there are currently two ways to slice PSD image files: the first is to split the PSD image files into slices with the same height regardless of the visual structure design of the PSD image file; the second is to split the PSD image file into Use the agreed directory structure and layer file naming in , identify the slice range, and then divide the document according to the area framed by the slice. For these two methods, there are the following problems: the PSD file is simply sliced equally, and the segmented document area will generally destroy the visual design division in the original PSD image file, such as splitting a visually complete object into In the upper and lower slices; Structural conventions and layer naming marks are carried out on the PSD document to identify the slice range. Although the problem of splitting visual design objects can be avoided, due to the existence of the agreed structure naming, the use of documents is greatly improved. The complexity also increases the cost for designers to use.

Therefore, how to obtain an optimized slicing method is a problem to be solved in the prior art.

Contents of the invention

In order to at least partly solve the technical problems mentioned in the background art, the solutions of the present disclosure provide a method and device for automatically slicing PSD pictures.

According to the first aspect of the present disclosure, the present disclosure provides a method for automatically slicing a PSD picture, wherein the method includes: acquiring the PSD picture; performing binarization processing on the PSD picture, and determining the foreground and background; extract the distribution information of the foreground and the background through an image segmentation algorithm; slice the PSD picture according to the distribution information of the foreground and the background.

Optionally, performing binarization processing on the PSD picture, and determining the foreground and background in the PSD picture include: performing preprocessing on the PSD picture; performing binarization processing on the preprocessed PSD picture to determine the foreground and background in the PSD picture.

Optionally, the preprocessing of the PSD picture includes: performing grayscale processing on the PSD picture; performing noise reduction and sharpening processing on the grayscale processed PSD picture.

Optionally, the grayscale processing of the PSD picture includes: taking the average value of the red, yellow and blue values of each pixel in the PSD picture as the grayscale value of each pixel after grayscale. value, or the sum of the red, yellow and blue values of each pixel in the PSD image multiplied by different coefficients as the gray value of each pixel after graying.

Optionally, the denoising and sharpening processing of the grayscaled PSD picture includes: performing noise reduction on the grayscaled PSD picture through Gaussian filtering, and performing high pass filtering on the grayscaled PSD picture PSD images are sharpened.

Optionally, performing binarization processing on the preprocessed PSD picture, and determining the foreground and background in the PSD picture include: obtaining the binarization threshold of the preprocessed PSD picture through the Otsu algorithm; according to the The binarization threshold performs binarization processing on the preprocessed PSD picture.

Optionally, the extracting the distribution information of the foreground and the background through an image segmentation algorithm includes: obtaining the distribution information of the foreground and the background through a projection cutting algorithm.

Optionally, the distribution information is upper and lower boundary lines between the foreground and the background obtained through progressive scanning.

Optionally, the slicing the PSD picture according to the distribution information of the foreground and the background includes: determining a cutting line of the PSD picture according to the distribution information of the foreground and the background; A cutting line cuts out the foreground to slice the PSD picture.

According to a second aspect of the present disclosure, the present disclosure provides an automatic slicing device for a PSD picture, wherein the device includes: an acquisition module configured to acquire the PSD picture; a processing module configured to process the PSD picture The PSD picture is binarized to determine the foreground and background in the PSD picture; the extraction module is configured to extract the distribution information of the foreground and the background through an image segmentation algorithm; the slicing module is configured Slicing the PSD picture is used to slice the PSD picture according to the distribution information of the foreground and the background.

Optionally, the processing module is configured to perform binarization processing on the PSD picture in the following manner to determine the foreground and background in the PSD picture: preprocessing the PSD picture; The image is binarized to determine the foreground and background in the PSD image.

Optionally, the processing module is configured to preprocess the PSD picture in the following manner: perform grayscale processing on the PSD picture; perform noise reduction and sharpening processing on the grayscale processed PSD picture.

Optionally, the processing module is configured to perform grayscale processing on the PSD picture in the following manner: taking the average value of the red, yellow and blue values of each pixel in the PSD picture as the respective values of each pixel The grayscale value after grayscale, or the sum of the red, yellow, and blue color values of each pixel in the PSD image multiplied by different coefficients as the grayscale value of each pixel after grayscale .

Optionally, the processing module is used to perform denoising and sharpening processing on the grayscaled PSD picture in the following manner: denoise the grayscaled PSD picture through Gaussian filtering, and denoise the grayscaled PSD picture through high-pass filtering. The grayscaled PSD image is sharpened.

Optionally, the processing module is used to perform binarization processing on the preprocessed PSD picture in the following manner to determine the foreground and background in the PSD picture: Obtain the binary value of the preprocessed PSD picture by the Otsu algorithm threshold; according to the binarization threshold, the preprocessed PSD picture is binarized.

Optionally, the extraction module is configured to extract the distribution information of the foreground and the background through an image segmentation algorithm in the following manner: obtain the distribution information of the foreground and the background through a projection cutting algorithm.

Optionally, the slicing module is configured to slice the PSD picture according to the distribution information of the foreground and the background in the following manner: determine the PSD picture according to the distribution information of the foreground and the background Cutting line: Cut out the foreground according to the cutting line, so as to slice the PSD picture.

According to a third aspect of the present disclosure, the present disclosure provides a device for automatically slicing PSD pictures, wherein the device includes a memory and a processor, a computer program is stored in the memory, and when the processor executes the computer program , implementing the above-mentioned method of the first aspect of the present disclosure.

According to a fourth aspect of the present disclosure, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed, implements the above-mentioned method of the first aspect of the present disclosure.

Through the automatic slicing method and device for PSD pictures of the present disclosure, the automatic slicing of PSD pictures can be realized without relying on the PSD document structured directory and layer naming, and the slicing can maintain the relationship between visual elements and will not be disassembled. Divide into different canvases, so as to ensure the integrity of the visual design relationship of PSD pictures, and at the same time reduce the complexity of using PSD pictures and the cost of designers.

Description of drawings

The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are shown by way of illustration and not limitation, and the same or corresponding reference numerals indicate the same or corresponding parts wherein:

FIG. 1 is a flow chart illustrating an automatic slicing method of a PSD picture according to an embodiment of the present disclosure;

Fig. 2 is a schematic block diagram illustrating an automatic slicing device for a PSD picture according to an embodiment of the present disclosure.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are part of the embodiments of the present disclosure, not all of them. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present disclosure.

Specific embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings.

The present disclosure provides a method for automatically slicing PSD pictures. Referring to FIG. 1 , FIG. 1 is a flowchart illustrating an automatic slicing method of a PSD picture according to an embodiment of the present disclosure. As shown in Fig. 1, the method includes the following steps S101-S104. Step S101: Acquiring the PSD picture. Step S102: Perform binarization processing on the PSD picture, and determine the foreground and background in the PSD picture. Step S103: extracting the distribution information of the foreground and the background through an image segmentation algorithm. Step S104: slice the PSD picture according to the distribution information of the foreground and the background.

Through the automatic slicing method of PSD pictures disclosed in the present disclosure, automatic slicing of PSD pictures can be realized without relying on the PSD document structured directory and layer naming, and the slices can maintain the mutual relationship of visual elements and will not be split into Different canvases, so as to ensure the integrity of the visual design relationship of PSD pictures, at the same time reduce the complexity of using PSD pictures and the cost of designers.

In step S101, the PSD picture may be acquired.

According to an embodiment of the present disclosure, in order to slice a PSD picture, the PSD picture to be sliced should first be acquired. The PSD image can be obtained through any appropriate means, for example, it can be from a gallery, specially designed by a designer, and so on.

In step S102, the PSD picture may be binarized to determine the foreground and background in the PSD picture.

According to an embodiment of the present disclosure, after the PSD picture is acquired, the foreground and the background in the PSD picture may be determined by means of binarization processing. The foreground refers to the object being targeted or to be used in the picture. The background refers to the area in the picture other than the foreground.

Specifically, performing binarization processing on the PSD picture and determining the foreground and background in the PSD picture may include: performing preprocessing on the PSD picture; performing binarization processing on the preprocessed PSD picture to determine the foreground and background in the PSD picture.

According to an embodiment of the present disclosure, before binarizing the PSD picture, it is necessary to perform preprocessing on the PSD picture, so as to realize the binarization process or have a better effect after the binarization process.

Further, the preprocessing of the PSD picture may include: performing grayscale processing on the PSD picture; performing noise reduction and sharpening processing on the grayscale processed PSD picture.

In order to carry out binarization processing, the PSD image is first grayscaled so as to obtain a grayscale image. The grayscale processing of the PSD picture may include: taking the average value of the red, yellow and blue values of each pixel in the PSD picture as the grayscale value of each pixel after grayscale, Alternatively, the sum of the red, yellow and blue values of each pixel in the PSD image multiplied by different coefficients is used as the gray value of each pixel after graying. When graying an image, the gray value of each pixel after graying can be equal to the average value of the red, yellow, and blue values of the pixel before graying, or the gray value of each pixel after graying The grayscale value may also be equal to the sum of the values of red, yellow, and blue colors before the grayscale of the pixel is multiplied by different coefficients. The present disclosure may adopt any suitable grayscale method, which is not limited here.

After the grayscale processing of the PSD image, noise reduction and sharpening can be performed. Wherein, the denoising and sharpening processing of the grayscaled PSD picture may include: performing noise reduction on the grayscaled PSD picture through Gaussian filtering, and performing high pass filtering on the grayscaled PSD picture. The image is sharpened. Noise reduction can be implemented by using any applicable noise reduction algorithm such as Gaussian filtering, and sharpening can be implemented by using any applicable sharpening algorithm such as high-pass filtering. Image quality can be improved through noise reduction and sharpening.

In addition, performing preprocessing on the PSD picture may also include only performing grayscale processing on the PSD picture. In view of this situation, the PSD image obtained after binarization processing can satisfy applications that do not require high image quality.

After the above preprocessing is performed on the PSD picture, binarization processing may be performed so as to determine the foreground and background in the PSD picture. More specifically, said performing binarization processing on the preprocessed PSD picture, and determining the foreground and background in the PSD picture may include: obtaining the binarization threshold of the preprocessed PSD picture through the Otsu algorithm; The binarization threshold is used to perform binarization processing on the preprocessed PSD picture.

According to an embodiment of the present disclosure, for the preprocessed PSD picture, the binarization threshold can be obtained through the Otsu algorithm. The Otsu algorithm assumes that the picture includes two types of pixels, namely, foreground pixels and background pixels, and calculates the best threshold that can separate the two types of pixels, that is, the binarization threshold. After the binarization threshold is obtained, the preprocessed PSD picture can be binarized to obtain a black and white picture, and the black and white parts in the black and white picture represent the foreground part and the background part respectively. By setting in the Otsu algorithm, black can be set as the background part and white can be set as the foreground part. Of course, white can be set as the background part and black can be set as the foreground part according to the needs.

In addition, the preprocessed PSD picture can also be binarized by any other applicable algorithm, as long as the foreground and background of the picture can be distinguished.

In step S103, distribution information of the foreground and the background may be extracted through an image segmentation algorithm.

According to an embodiment of the present disclosure, after distinguishing the foreground and the background of the PSD picture, the distribution information of the foreground and the background can be extracted through an image segmentation algorithm. The distribution information may include the coordinates, size and the like of the boundary line between the foreground and the background.

Specifically, the extracting the distribution information of the foreground and the background through an image segmentation algorithm may include: obtaining the distribution information of the foreground and the background through a projection cutting algorithm.

According to an embodiment of the present disclosure, the black-and-white picture obtained above can be scanned line by line through the projection cutting algorithm, so that the distribution of foreground (such as white part) and background (such as black part) can be determined according to the pixel grayscale (black or white) information. In this embodiment, the distribution information may be, for example, upper and lower boundary lines between the foreground and the background obtained through progressive scanning. According to the projection cutting algorithm, the upper and lower boundary lines are horizontal boundary lines that run through the entire picture, that is, when the picture is scanned line by line, there are no foreground pixels (white pixels) in the current pixel line and there are foreground pixels in the previous pixel line , then the current pixel row can be used as the lower boundary line; when there are foreground pixels (white pixels) in the current pixel row and there is no foreground pixel in the previous pixel row, the current pixel row can be used as the upper boundary line.

Of course, the distribution information of foreground and background can also be extracted by any other applicable image segmentation algorithm.

In step S104, the PSD picture may be sliced according to the distribution information of the foreground and the background.

According to the embodiments of the present disclosure, after obtaining the distribution information of the foreground and the background, the foreground can be segmented from the background without destroying the integrity of the foreground.

Specifically, the slicing the PSD picture according to the distribution information of the foreground and the background includes: determining the cutting line of the PSD picture according to the distribution information of the foreground and the background; line to cut out the foreground to slice the PSD picture.

According to an embodiment of the present disclosure, the cutting line may be determined according to the distribution information of the foreground and the background, such as the above-mentioned boundary line. Specifically, in the case where there are multiple upper and lower boundary lines (in the case of multiple foregrounds), a line can be taken between adjacent upper and lower boundary lines without foreground pixels in the middle, so that the line is consistent with the upper and lower boundary lines. The lower boundary line is parallel and spaced the same distance from the upper and lower boundary lines, and this line can be used as a cutting line. For the uppermost upper boundary line (corresponding to the uppermost foreground), there is no adjacent lower boundary line above it (there is no foreground above it), so the upper boundary line above the upper boundary line can be separated from the upper boundary line by a predetermined distance. Let the number of rows of pixels be used as cutting lines. For the lower boundary line located at the bottom (corresponding to the bottommost foreground), there is no upper boundary line adjacent to it below it (there is no foreground below it), so the distance between the lower boundary line and the lower boundary line can be preset. number of pixel rows as cutting lines. In the case that there are multiple cutting lines, the PSD picture is cut horizontally (horizontally) along the cutting lines to cut out the foreground, so as to realize the slicing of the PSD picture.

It should be noted that each slice may contain multiple foregrounds, especially when multiple foregrounds are arranged in a horizontal (horizontal) direction (at least one same pixel row passes through multiple foregrounds), the above-mentioned cutting line will Multiple foregrounds are sandwiched in it.

In addition, for the content in the above steps S103 and S104, through a similar method, the black and white pictures obtained above can also be scanned column by column through the projection cutting algorithm to obtain the left and right boundary lines, and then determine the cutting line through the left and right boundary lines, and finally Cut through the cutting line longitudinally (perpendicularly), so as to realize the slicing of the PSD picture.

The present disclosure also provides an automatic slicing device for PSD pictures. The device is used to execute the steps in the embodiment of the method for automatically slicing PSD pictures described above in conjunction with FIG. 1 .

Referring to FIG. 2 , FIG. 2 is a schematic block diagram illustrating an automatic slicing apparatus 100 for PSD pictures according to an embodiment of the present disclosure. The apparatus 100 includes an acquisition module 101 , a processing module 102 , an extraction module 103 and a slicing module 104 . The obtaining module 101 is configured to obtain the PSD picture. The processing module 102 is configured to perform binarization processing on the PSD picture, and determine the foreground and background in the PSD picture. The extraction module 103 is configured to extract the distribution information of the foreground and the background through an image segmentation algorithm. The slicing module 104 is configured to slice the PSD picture according to the distribution information of the foreground and the background.

According to an embodiment of the present disclosure, the processing module 102 is configured to perform binarization processing on the PSD picture in the following manner to determine the foreground and background in the PSD picture: preprocessing the PSD picture; The processed PSD picture is subjected to binarization processing to determine the foreground and background in the PSD picture.

According to an embodiment of the present disclosure, the processing module 102 is configured to preprocess the PSD picture in the following manner: perform grayscale processing on the PSD picture; perform noise reduction and Sharpening.

According to an embodiment of the present disclosure, the processing module 102 is configured to grayscale the PSD picture in the following manner: take the average value of the red, yellow and blue values of each pixel in the PSD picture as The grayscale value of each pixel after grayscale, or the sum of the red, yellow and blue color values of each pixel in the PSD image multiplied by different coefficients as the grayscale value of each pixel gray value of .

According to an embodiment of the present disclosure, the processing module 102 is configured to perform noise reduction and sharpening processing on the grayscaled PSD picture in the following manner: denoise the grayscaled PSD picture by Gaussian filtering, The gray-scaled PSD image is sharpened by high-pass filtering.

According to an embodiment of the present disclosure, the processing module 102 is configured to perform binarization processing on the preprocessed PSD picture in the following manner to determine the foreground and background in the PSD picture: Obtain the preprocessed PSD through the Otsu algorithm The binarization threshold of the picture; performing binarization processing on the preprocessed PSD picture according to the binarization threshold.

According to an embodiment of the present disclosure, the extraction module 103 is configured to extract the distribution information of the foreground and the background through an image segmentation algorithm in the following manner: obtain the distribution information of the foreground and the background through a projection cutting algorithm.

According to an embodiment of the present disclosure, the distribution information is upper and lower boundary lines between the foreground and the background obtained by progressive scanning.

According to an embodiment of the present disclosure, the slicing module 104 is configured to slice the PSD picture according to the distribution information of the foreground and the background in the following manner: determine the PSD picture according to the distribution information of the background Cutting line: cutting out the foreground according to the distribution information of the foreground and the cutting line, so as to slice the PSD picture.

It can be understood that, with regard to the automatic slicing device for PSD pictures in the embodiment described above with reference to FIG. A detailed description is given, so no detailed explanation will be given here.

An embodiment of the present disclosure also provides a device for generating a page component, wherein the device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: obtaining the Described PSD picture; Carry out binarization process to described PSD picture, determine the foreground and background in the described PSD picture; Extract the distribution information of described foreground and described background by image segmentation algorithm; According to described foreground and described background The distribution information of the PSD picture is sliced.

It can be understood that the steps implemented when the processor executes the computer program are basically the same as the implementation of each step in the above method, and the specific method has been described in detail in the embodiment of the automatic slicing method for PSD pictures , which will not be elaborated here.

In another aspect, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed, the following steps are implemented: acquiring the PSD picture; The picture is binarized to determine the foreground and background in the PSD picture; the distribution information of the foreground and the background is extracted by an image segmentation algorithm; according to the distribution information of the foreground and the background, the PSD is processed The picture is sliced.

The embodiments of the present disclosure have been introduced in detail above, and the principles and implementation methods of the present disclosure have been explained by using specific examples in this article. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present disclosure; at the same time, for Those skilled in the art may have changes in specific implementation methods and application scopes based on the idea of the present disclosure. In summary, the contents of this specification should not be construed as limiting the present disclosure.

It should be understood that the terms "first" and "second", etc. in the claims, specification and drawings of the present disclosure are used to distinguish different objects, rather than to describe a specific order. The terms "comprising" and "comprises" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and/or components, but do not exclude one or more other features, integers , steps, operations, elements, components, and/or the presence or addition of collections thereof.

It should also be understood that the terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in this disclosure and the claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise. It should be further understood that the term "and/or" used in the present disclosure and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

The embodiments of the present disclosure have been introduced in detail above, and the principles and implementation modes of the present disclosure have been described by using specific examples in this article. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present disclosure. At the same time, changes or deformations made by those skilled in the art based on the ideas of the present disclosure, specific implementation methods and application scopes of the present disclosure all belong to the scope of protection of the present disclosure. To sum up, the contents of this specification should not be construed as limiting the present disclosure.

Claims

A method for automatically slicing PSD pictures, wherein the method includes:

Obtain the PSD image;

Carry out binarization processing to described PSD picture, determine the foreground and the background in the described PSD picture;

Extracting the distribution information of the foreground and the background through an image segmentation algorithm;

Slice the PSD picture according to the distribution information of the foreground and the background.
The automatic slicing method of a PSD picture according to claim 1, wherein said performing binarization processing on said PSD picture, determining the foreground and background in said PSD picture comprises:

Preprocessing the PSD picture;

Perform binarization processing on the preprocessed PSD picture, and determine the foreground and background in the PSD picture.
The automatic slicing method of the PSD picture according to claim 2, wherein said preprocessing the PSD picture comprises:

Perform grayscale processing on the PSD image;

Noise reduction and sharpening are performed on the grayscaled PSD image.
The method for automatically slicing PSD pictures according to claim 3, wherein said grayscale processing of said PSD pictures comprises:

The average value of the red, yellow, and blue values of each pixel in the PSD picture is used as the gray value of each pixel after graying, or the red, yellow, and blue values of each pixel in the PSD picture are The sum of the values of the three colors multiplied by different coefficients is used as the gray value of each pixel after graying.
The automatic slicing method of the PSD picture according to claim 3, wherein said denoising and sharpening the grayscale processed PSD picture comprises:

The grayscaled PSD image is denoised by Gaussian filtering, and the grayscaled PSD image is sharpened by high pass filtering.
The automatic slicing method of the PSD picture according to claim 3, wherein, said performing binarization processing on the preprocessed PSD picture, and determining the foreground and background in the PSD picture include:

Obtain the binarization threshold of the preprocessed PSD image through the Otsu algorithm;

Perform binarization processing on the preprocessed PSD picture according to the binarization threshold.
The automatic slicing method of the PSD picture according to any one of claims 1 to 6, wherein said extraction of the distribution information of the foreground and the background by an image segmentation algorithm comprises:

The distribution information of the foreground and the background is obtained through a projection cutting algorithm.
The method for automatically slicing PSD pictures according to claim 7, wherein the distribution information is upper and lower boundary lines between the foreground and the background obtained through progressive scanning.
The automatic slicing method of the PSD picture according to any one of claims 1 to 6, wherein said slicing the PSD picture according to the distribution information of the foreground and the background comprises:

determining the cutting line of the PSD picture according to the distribution information of the foreground and the background;

Cut out the foreground according to the cutting line, so as to slice the PSD picture.
A kind of automatic slicing device of PSD picture, wherein, described device comprises:

An acquisition module configured to acquire the PSD picture;

A processing module configured to perform binarization processing on the PSD picture, and determine the foreground and background in the PSD picture;

An extraction module configured to extract the distribution information of the foreground and the background through an image segmentation algorithm;

A slicing module configured to slice the PSD picture according to the distribution information of the foreground and the background.
The automatic slicing device for a PSD picture according to claim 7, wherein the processing module is used to perform binarization processing on the PSD picture in the following manner to determine the foreground and background in the PSD picture:

Preprocessing the PSD picture;

Perform binarization processing on the preprocessed PSD picture, and determine the foreground and background in the PSD picture.
The automatic slicing device for PSD pictures according to claim 8, wherein the processing module is used to preprocess the PSD pictures in the following manner:

Perform grayscale processing on the PSD image;

Noise reduction and sharpening are performed on the grayscaled PSD image.
The automatic slicing device for PSD pictures according to claim 12, wherein the processing module is used to grayscale the PSD pictures in the following manner:

The average value of the red, yellow, and blue values of each pixel in the PSD picture is used as the gray value of each pixel after graying, or the red, yellow, and blue values of each pixel in the PSD picture are The sum of the values of the three colors multiplied by different coefficients is used as the gray value of each pixel after graying.
The automatic slicing device for PSD pictures according to claim 12, wherein the processing module is used to perform noise reduction and sharpening processing on the grayscaled PSD pictures in the following manner:

The grayscaled PSD image is denoised by Gaussian filtering, and the grayscaled PSD image is sharpened by high pass filtering.
The automatic slicing device for a PSD picture according to claim 9, wherein the processing module is used to perform binarization processing on the preprocessed PSD picture in the following manner, to determine the foreground and background in the PSD picture:

Obtain the binarization threshold of the preprocessed PSD image through the Otsu algorithm;

Perform binarization processing on the preprocessed PSD picture according to the binarization threshold.
The automatic slicing device for PSD pictures according to any one of claims 10 to 15, wherein the extraction module is used to extract the distribution information of the foreground and the background through an image segmentation algorithm in the following manner:

The distribution information of the foreground and the background is obtained through a projection cutting algorithm.
The device for automatically slicing PSD pictures according to claim 16, wherein the distribution information is upper and lower boundary lines between the foreground and the background obtained through progressive scanning.
The automatic slicing device for PSD pictures according to any one of claims 10 to 15, wherein the slicing module is used to slice the PSD pictures according to the distribution information of the foreground and the background in the following manner :

determining the cutting line of the PSD picture according to the distribution information of the foreground and the background;

Cut out the foreground according to the cutting line, so as to slice the PSD picture.
A device for automatically slicing PSD pictures, wherein the device includes a memory and a processor, and a computer program is stored in the memory, and when the processor executes the computer program, any one of claims 1 to 9 is realized. method described in the item.
A computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 9 is implemented.