CN110827344A - Image composition analysis method and device - Google Patents

Abstract

The application discloses an image composition analysis method and device, wherein the method comprises the following steps: acquiring layer information of a target image, wherein the layer information represents the target image and basic attribute information of a plurality of element images in the target image; determining layout structure information of a plurality of element images in a target image; and performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image. By utilizing the technical scheme provided by the application, image composition analysis can be rapidly and accurately carried out, the cost of composition analysis is greatly reduced, and the accuracy and the processing efficiency of subsequent image screening are improved.

Description

Image composition analysis method and device

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image composition analysis method and apparatus.

Background

The image is the most commonly used information carrier in human social activities and has wide application in the field of information flow application. The composition of the image can reflect the layout structure of the image, and the good composition can enhance the expressive force of the image, better express the image content, make the theme clear and make the intention clear.

In the prior art, in some scenes for information propagation in an image form, in order to screen out an image with a proper composition, related personnel need to select one by one from a large number of images, but the manual processing mode is easy to generate errors, and the problems of high cost and low processing efficiency are caused. Therefore, it is necessary to provide a method for analyzing image composition to accurately analyze the layout structure of an image and improve the accuracy and processing efficiency of subsequent image screening.

Disclosure of Invention

The application provides an image composition analysis method and device, which can be used for rapidly and accurately carrying out image composition analysis, greatly reducing the cost of composition analysis and improving the accuracy and the processing efficiency of subsequent image screening.

In one aspect, the present application provides an image composition analysis method, including:

acquiring layer information of a target image, wherein the layer information represents the target image and basic attribute information of a plurality of element images in the target image;

determining layout structure information of a plurality of element images in a target image;

and performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

Another aspect provides an image composition analyzing apparatus, the apparatus comprising:

the image layer information acquisition module is used for acquiring image layer information of a target image, wherein the image layer information represents the target image and basic attribute information of a plurality of element images in the target image;

a layout structure information determination module for determining layout structure information of a plurality of element images in a target image;

and the composition analysis module is used for performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

Another aspect provides an image composition analysis apparatus comprising a processor and a memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions that is loaded and executed by the processor to implement an image composition analysis method as described above.

Another aspect provides a computer readable storage medium having stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded and executed by a processor to implement an image composition analysis method as described above.

The image composition analysis method and device provided by the application have the following technical effects:

the method comprises the steps of obtaining layer information of a target image and layout structure information of a plurality of element images in the target image; the composition analysis is carried out on the target image based on the layer information and/or the layout structure information, so that composition analysis data which effectively reflects the layout structure condition of the target image can be obtained, the rapid and accurate image composition analysis is realized, the cost of the composition analysis is greatly reduced, and the accuracy and the processing efficiency of subsequent image screening are improved.

Drawings

In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic flowchart of an image composition analysis method provided in an embodiment of the present application;

fig. 2 is a partial schematic view of a target image and layer information thereof according to an embodiment of the present disclosure;

FIG. 3 is a schematic flowchart illustrating a process of determining layout structure information of a plurality of elemental images in a target image according to an embodiment of the present application;

FIG. 4 is a schematic diagram illustrating contour information of a plurality of elemental images in a target image according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a center of gravity of an elemental image provided in an embodiment of the present application;

fig. 6 is a schematic flow chart of composition analysis data for obtaining the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information according to the embodiment of the present application;

FIG. 7 is a diagram illustrating alignment information of a plurality of elemental images in a target image in a target coordinate system according to the present application;

FIG. 8 is a diagram illustrating tilt deviation information between two elemental images according to an embodiment of the present disclosure;

fig. 9 is another schematic flow chart of composition analysis data for obtaining the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information according to the embodiment of the present application;

FIG. 10 is a diagram illustrating a fitting of contour information of a spiral line and an element image provided by an embodiment of the present application;

FIG. 11 is a schematic flow chart diagram illustrating another image composition analysis method provided in an embodiment of the present application;

FIG. 12 is a schematic flowchart of an image screening process based on composition analysis data according to an embodiment of the present application

FIG. 13 is a schematic structural diagram of an image composition analysis apparatus according to an embodiment of the present disclosure;

fig. 14 is a schematic structural diagram of a client according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The image composition analysis method provided by the embodiment of the application can be applied to any electronic equipment, such as terminal equipment of smart phones, desktop computers, tablet computers, notebook computers, digital assistants, Augmented Reality (AR)/Virtual Reality (VR) equipment, intelligent wearable equipment and the like, and also can be used for servers which run independently, distributed servers and server clusters formed by a plurality of servers.

An image composition analysis method of the present application is described below, and fig. 1 is a schematic flow chart of an image composition analysis method provided in an embodiment of the present application, and the present specification provides the method operation steps as described in the embodiment or the flow chart, but may include more or less operation steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 1, the method may include:

s101: and acquiring layer information of the target image.

In the embodiment of the present specification, the target image may include any image that needs composition analysis.

The layer information may represent basic attribute information of the target image and a plurality of element images in the target image; specifically, the element images in the target image may include text, graphics, pictures, tables, and other information distributed in the respective layers of the respective target images in the form of images.

In the embodiment of the present specification, in practical application, the source file of the target image: for example, a source file of a picture designed by using design software such as Photoshop or Sketch includes information such as an element image of each layer and a position and a size thereof. The information such as the size and position of the image can be used as the basic attribute information of the image. Specifically, the layer information may include size information of the target image and vertex position information of a plurality of elemental images (the vertex position information herein is a position of a vertex of an elemental image in the target image). In a specific embodiment, as shown in fig. 2, fig. 2 is a partial schematic view of a target image and layer information thereof according to an embodiment of the present disclosure.

S103: layout structure information of a plurality of elemental images in a target image is determined.

In this embodiment of the present specification, the layout structure information of the element image may include related information reflecting the layout structure of the element image itself, and specifically, the layout structure information may include at least one of: contour information, center of gravity and tilt angle.

In a specific embodiment, as shown in fig. 3, determining layout structure information of a plurality of elemental images in the target image may include:

s1031: carrying out binarization processing on the target image to obtain a binary image;

s1033: determining vertex positions of a plurality of polygons in the binary image;

s1035: determining contour information for the plurality of elemental images based on vertex positions of the plurality of polygons;

s1037: calculating respective moments of contour information of the plurality of elemental images;

s1039: determining the gravity center of each element image according to each moment of the contour information of each element image;

s10311: determining the inclination angle of each side of the polygon according to the vertex position of the polygon corresponding to each element image;

s10313: determining the inclination angle of the corresponding element image according to the inclination angle of each edge of the polygon;

s10315: at least one of contour information, a center of gravity, and an inclination angle of the element image is taken as the layout structure information.

In practical applications, the specific step of determining the layout structure information of the plurality of elemental images in the target image may include, but is not limited to, invoking an OpenCV Library (open source Computer Vision Library) in combination with a code such as python (a Computer programming language) to obtain the information of the contour information, the gravity center, and the tilt angle.

Specifically, after the binary image, the binary image may be preprocessed, specifically, the preprocessing may include edge removal, denoising, and the like, and the contour information of the element image is detected after the binary image is preprocessed, so that the accuracy of the detected contour information may be improved. In a specific embodiment, assuming that the target image is the image shown in fig. 2, after performing contour detection, contour information of a plurality of element images in the target image shown in fig. 4 can be obtained.

In a specific embodiment, as shown in fig. 5, taking the element image (triangle) at the bottom right corner in the target image as an example, 500 in fig. 5 is the contour information of the element image of the triangle, and 510 is located at the center of gravity of the element image of the triangle. In the embodiment of the present specification, the barycenter of the element image is the barycenter position corresponding to the contour information of the element image.

Specifically, when the inclination angle of each side of the polygon is determined according to the vertex position of the polygon corresponding to each element image, the minimum circumscribed rectangle of each element image may be determined according to the vertex, then, the inclination angle of each side in the minimum external matrix is calculated, and then, the inclination angle of each side of the minimum circumscribed rectangle corresponding to the element image may be averaged to obtain the inclination angle of the element image.

S105: and performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

In the embodiment of the present specification, by acquiring image information of a target image and layout structure information of a plurality of element images in the target image, composition analysis is performed on the target image based on layer information and/or layout structure information, and then composition analysis data that effectively reflects a layout structure condition of the target image can be obtained. Specifically, in this embodiment of the present specification, the composition analysis data of the target image may be a measure of the quality of the layout structure of the target image, and in this embodiment of the present specification, the measure of the quality of the layout structure of the target image may be embodied in various aspects.

In a specific embodiment, when the layer information includes size information of the target image and vertex position information of the plurality of element images, the layout structure information includes contour information; as shown in fig. 6, performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image may include:

s601: and constructing a target coordinate system according to the size information of the target image.

S603: and determining the coordinate positions of the element images in the target coordinate system according to the vertex position information and the contour information of the element images.

S605: determining alignment information in the target coordinate system in the plurality of elemental images from the coordinate positions.

S607: composition analysis data of the target image on image alignment is analyzed based on the alignment information.

In practical applications, the target coordinate system may include, but is not limited to, a planar rectangular coordinate system, a polar coordinate system; in a specific embodiment, taking a plane rectangular coordinate system as an example, according to the size information of the target image, taking the upper left corner as the origin (0, 0) of the coordinate system; the upper right corner is a (0, W) point, where W represents the width of the target image; the lower left corner is a point (H, 0), where H represents the height of the target image.

In the embodiments of the present specification, the alignment information may include, but is not limited to, information characterizing alignment between element images in the target image, such as edge alignment, center line alignment, and the like. Specifically, the edge alignment may be the alignment of the element images located at the edge of the target coordinate system (i.e. the element images located at one side of the target coordinate system and having a distance smaller than a preset threshold); the centerline alignment may include, but is not limited to, a centerline alignment condition of the elemental images located in the middle of the target coordinate system (i.e., the elemental images located at the four sides of the target coordinate system each having a distance greater than or equal to a preset threshold).

In this embodiment of the present description, composition analysis data of a target image in image alignment may represent alignment degrees between element images in the target image, and specifically, the better the alignment degree between the element images in the target image is, the larger the composition analysis data of the target image in image alignment is, the better (better) the layout structure of the target image is correspondingly; conversely, the worse the alignment degree between the element images in the target image, the smaller the composition analysis data of the target image on the image alignment, and correspondingly, the worse (inferior) the layout structure of the target image.

In a specific embodiment, taking edge alignment as an example, as shown in fig. 7, fig. 7 is a schematic diagram of alignment information of a plurality of element images in a target image in a target coordinate system provided by the present application. Specifically, as can be seen from fig. 7, the upper edge of the target coordinate system corresponds to two element images, and accordingly, the distance a between the two element images and the upper edge of the target coordinate system can be taken as the upper alignment distance; the lower edge of the target coordinate system corresponds to two element images, and correspondingly, the distance B between the two element images and the lower edge of the target coordinate system can be used as a lower alignment distance; the right edge of the target coordinate system corresponds to two element images, and correspondingly, the distance C between the two element images and the right edge of the target coordinate system can be used as a right alignment distance; the left edge of the target coordinate system has no elemental image; accordingly, the alignment information of the plurality of elemental images of the target image may include an upper alignment distance, a lower alignment distance, and a right alignment distance.

Further, as can be seen from fig. 7, the upper alignment distance a > the lower alignment distance B > the right alignment distance C; accordingly, when analyzing the composition analysis data of the target image in the image alignment based on the alignment information, the alignment information may be substituted into a function in which the alignment information is proportional to the composition analysis data to obtain the composition analysis data, and in a specific embodiment, it is assumed that the function may be a function in which a mean value of alignment distances of respective sides (the upper alignment distance in fig. 7 includes an alignment distance, a lower alignment distance, and a right alignment distance) is used as the composition analysis data, or a function in which a variance of the alignment distances of the respective sides is used as the composition analysis data, and the like.

In the embodiment of the present specification, alignment information representing an alignment condition between element images in a target image can be determined by size information of the target image in layer information, vertex position information of a plurality of element images, and contour information in layout structure information; based on the analysis of the alignment information, composition analysis data representing the alignment degree between the element images in the target image can be determined, so that the alignment condition of the element images of the target image can be measured quickly and accurately, the cost of composition analysis is greatly reduced, the processing efficiency of image composition analysis is improved, and the accuracy and the processing efficiency of subsequent image screening can be improved.

In another specific embodiment, when the layout structure information includes a tilt angle; the performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image may include:

1) determining inclination deviation information between every two element images according to the inclination angles of the element images;

2) and analyzing composition analysis data of the target image in the visual trend based on the inclination deviation information between every two element images.

In this embodiment, the tilt deviation information between two element images may be a difference between tilt angles of the element images. The composition analysis data of the target image in the visual trend can represent the consistency degree of the visual trend among the element images in the target image. Specifically, the larger the difference value corresponding to the tilt deviation information is, the worse the consistency degree of the visual trend among the element images in the target image is, and correspondingly, the worse (inferior) the layout structure of the target image is; on the contrary, the smaller the difference corresponding to the tilt deviation information is, the better the consistency of the visual trend among the element images in the target image is, and correspondingly, the better (better) the layout structure of the target image is.

In a specific embodiment, as shown in fig. 8, fig. 8 is a schematic diagram of tilt deviation information between two elemental images provided by the embodiment of the present application; specifically, the tilt angles of the three element images in the target image corresponding to a in fig. 8 (the tilt angle may be a tilt angle of a direction corresponding to the longest edge of the element image relative to a specified direction, and the specified direction may be set in combination with practical applications, for example, a direction from the horizontal to the right in the figure) are all 135 degrees, and correspondingly, the tilt deviation information between every two element images is 0 degree. In the target image corresponding to b in fig. 8, there are two element images "triangle" and "rectangle", where the inclination angle of the element image "triangle" is 135 degrees, the inclination angle of the element image "rectangle" is 135 degrees and 0 degree, and accordingly, the inclination deviation information between the element image "triangle" and "rectangle" is 0 degree.

In this embodiment, when composition analysis data of the target image in the visual direction is analyzed based on the tilt deviation information between each two element images, the tilt deviation information may be substituted into a function of the tilt deviation information and the composition analysis data to obtain the composition analysis data, and in a specific embodiment, the function may be a function in which a mean value of the tilt deviation information between each two element images is used as the composition analysis data, or a function in which a variance of the tilt deviation information is used as the composition analysis data.

In the embodiment of the description, composition analysis data representing the consistency degree of visual trends among the element images in the target image can be determined through the inclination angles of the element images in the target image, so that the visual trend conditions of the element images of the target image can be measured quickly and accurately, the cost of composition analysis is greatly reduced, the processing efficiency of image composition analysis is improved, and the accuracy and the processing efficiency of subsequent image screening can also be improved.

In other embodiments, the layer information includes size information of the target image and vertex position information of the plurality of elemental images; the layout structure information includes contour information; as shown in fig. 9, the performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image includes:

s901: and constructing a target coordinate system according to the size information of the target image.

S903: and drawing the contour information of the element images in the target coordinate system according to the vertex position information and the contour information of the element images.

S905: and drawing a spiral line corresponding to the golden section in the target coordinate system.

S907: analyzing first composition analysis data of the target image on an element structure based on a degree of fitting of the spiral line and the contour information of the plurality of element images in the target coordinate system.

Specifically, the construction of the target coordinate system may refer to the above related steps, which are not described herein again. In a specific embodiment, as shown in fig. 10, fig. 10 is a schematic diagram of a fitting situation of contour information of a spiral line and an element image provided by an embodiment of the present application. Specifically, as can be seen from the figure, the target image includes three element images, which are respectively a triangle in the lower right corner, a rectangle in the upper left corner and a rectangle on the right side in fig. 10; the fitting degree of the contour information of the triangle at the lower right corner and the spiral line is higher than that of the rectangle at the upper left corner and the rectangle at the right side.

In this embodiment of the present specification, the higher the fitting degree of the spiral line and the contour information of the plurality of elemental images is, the larger the first composition analysis data of the target image on the elemental structure is, and accordingly, the better (better) the layout structure of the target image is; conversely, the lower the fitting degree of the spiral line and the contour information of the plurality of element images is, the smaller the first composition analysis data of the target image on the element structure is, and accordingly, the worse (inferior) the layout structure of the target image is.

In the embodiment of the present specification, the fitting degree of the contour information and the spiral line of each element image in the target image may be quantized, so as to obtain a quantized fitting degree; the fit may then be substituted into a function of the first composition analysis data in combination with the fit to obtain the first composition analysis data. In a specific embodiment, it is assumed that the function may be a function in which the average of the degrees of fitting corresponding to each elemental image is used as the first composition analysis data, a function in which the variance of the degrees of fitting corresponding to each elemental image is used as the first composition analysis data, or the like.

In the embodiment of the specification, a target coordinate system is constructed through size information of a target image in layer information, then, by combining vertex position information of a plurality of element images in the layer information and contour information in layout structure information, contour information of the plurality of element images is drawn in the target coordinate system, a spiral line corresponding to golden section is drawn in the target coordinate system, and first composition analysis data of the target image on an element structure can be analyzed through the fitting degree of the spiral line and the contour information of the plurality of element images; based on the first composition analysis data, the element structure condition of the target image can be measured quickly and accurately, the composition analysis cost is greatly reduced, the processing efficiency of the image composition analysis is improved, and the accuracy and the processing efficiency of subsequent image screening can be improved.

In another specific embodiment, when the layout structure information includes a center of gravity; when the layer information includes size information of the plurality of element images; the performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image may include:

1) determining an image proportion divided by the gravity center of each element image according to the size information of the plurality of element images and the gravity center of each element image;

2) second composition analysis data of the target image on an element structure is analyzed based on image scales of the plurality of element images.

In a specific embodiment, when analyzing the composition of the second composition analysis data of the target image on the element structure based on the image proportions of the plurality of element images, a golden section ratio may be combined, and specifically, the smaller the difference between the image proportion divided by the gravity centers of the element images and the golden section ratio, the larger the second composition analysis data of the target image on the element structure, and accordingly, the better (better) the layout structure of the target image; conversely, the larger the difference between the image proportion divided by the gravity center of the element image and the golden section proportion is, the smaller the second composition analysis data of the target image on the element structure is, and correspondingly, the worse (inferior) the layout structure of the target image is.

In the embodiment of the present specification, second composition analysis data of the target image on the element structure may be determined by the center of gravity in the layout structure information and size information of a plurality of element images in the layer information; based on the second composition analysis data, the element structure condition of the target image can be measured quickly and accurately, the composition analysis cost is greatly reduced, the processing efficiency of the image composition analysis is improved, and the accuracy and the processing efficiency of subsequent image screening can be improved.

In another specific embodiment, the layer information may further include: a hierarchical relationship between the plurality of elemental images; the performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image may include:

and analyzing composition analysis data of the target image on the image coverage according to the hierarchical relation among the plurality of element images.

In practical applications, the target image is composed of a plurality of element images which are stacked one on another in a front-back order. Correspondingly, each element image is located in one layer, and the hierarchical relationship between the element images is whether the layers between the element images are overlapped. In a specific embodiment, in this specification embodiment, the composition analysis data of the target image on the image overlay may be determined based on the number of the element image groups (i.e., two element images) where the layer overlap exists; specifically, the larger the number of the element image groups, the smaller the composition analysis data, and correspondingly, the worse (inferior) the layout structure of the target image; conversely, the smaller the number of element image groups, the larger the composition analysis data, and correspondingly, the better (better) the layout structure of the target image.

In the embodiment of the specification, composition analysis data of a target image on image coverage can be analyzed through the hierarchical relationship among a plurality of element images; based on the composition analysis data, the image coverage condition of the target image can be measured quickly and accurately, the composition analysis cost is greatly reduced, the processing efficiency of the image composition analysis is improved, and the accuracy and the processing efficiency of subsequent image screening can be improved.

In another specific embodiment, when the composition analysis data includes a plurality of types of composition analysis data, as shown in fig. 11, the method further includes:

s107: the normalization processing is performed for a plurality of types of composition analysis data.

S109: determining a composition weight of the plurality of types of composition analysis data.

S111: and carrying out weighted average processing on the basis of the normalized composition analysis data and the composition weight to obtain target composition analysis data of the target image.

In this embodiment of the present specification, the composition weight may characterize a degree of influence of each type of composition analysis data on the layout structure of the target image. Specifically, the composition weight may be preset in combination with the degree of influence of each type of composition analysis data on the layout structure of the target image in the actual application.

Further, it should be noted that when the composition analysis data includes a plurality of types of composition analysis data, it is not limited to the above-mentioned weighted average method to obtain the target composition analysis data of the target image. Various types of composition analysis data may also be converted into target composition analysis data of a target image using geometric averaging, harmonic averaging, or the like.

In another specific embodiment, as shown in fig. 12, the method further comprises:

s113: and carrying out image screening processing on the target image based on the composition analysis data or the target composition analysis data.

In practical application, when images needing to be displayed and released are screened by some platforms according to the composition quality condition of the images, the target images can be directly screened based on the composition analysis data or the target composition analysis data, and the accuracy and the processing efficiency of image screening are effectively improved.

In a specific embodiment, an image whose composition analysis data or target composition analysis data is greater than or equal to a preset value may be taken as a demonstrable and distributable image, and conversely, an image whose composition analysis data or target composition analysis data is less than the preset value may be deleted.

In another specific embodiment, images sorted to the top N (N is a positive integer) may be used as displayable published images, and conversely, images sorted to the back N (N is a positive integer) may be deleted according to the numerical size of the composition analysis data or the target composition analysis data.

Furthermore, it should be noted that, considering that the tolerance term is combined in the process of determining the composition analysis data, specifically, for example, in the process of determining the composition analysis data by the above-mentioned contour information and spiral line fitting, by setting the tolerance term, the point close to the spiral line but not completely falling on the spiral line can be regarded as being fitted with the spiral line.

As can be seen from the technical solutions provided by the embodiments of the present specification, in the embodiments of the present specification, layer information of a target image and layout structure information of a plurality of element images in the target image are obtained; composition analysis is carried out on the target image based on the layer information and/or the layout structure information, composition analysis data which effectively reflects the layout structure condition of the target image can be obtained, and measurement of the quality of the layout structure of the target image from multiple aspects is achieved through the composition analysis data of the target image. The technical scheme provided by the application can be used for rapidly and accurately carrying out image composition analysis, solving the problems of high cost, low processing efficiency and the like caused by manual processing, greatly reducing the cost of composition analysis, improving the processing efficiency of image composition analysis, and simultaneously improving the accuracy and the processing efficiency of subsequent image screening.

In other embodiments, the present application may further perform image composition analysis processing in combination with machine learning, specifically, may combine a composition analysis model capable of analyzing image composition; specifically, the patternable analysis model may be obtained by training in the following manner:

acquiring a large number of images with different layout structures (different compositions), and taking the images as training data;

setting composition analysis data for the images of the different layout structures;

inputting training data into a machine learning model to perform learning training of composition weight, wherein parameters of the machine learning model can be adjusted in the learning training process, so that the output of the machine learning model is matched with composition analysis data corresponding to the training data;

taking the machine learning model when the output is matched with the composition analysis data corresponding to the training data as a composition analysis model;

further, by inputting an arbitrary image to the composition analysis model, composition analysis data of the image can be obtained.

An embodiment of the present application further provides an image composition analysis apparatus, as shown in fig. 13, the apparatus includes:

the layer information obtaining module 1310 may be configured to obtain layer information of a target image, where the layer information represents the target image and basic attribute information of multiple element images in the target image;

a layout structure information determination module 1320, operable to determine layout structure information of a plurality of elemental images in the target image;

the composition analysis module 1330 may be configured to perform composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

In some embodiments, the layer information includes size information of the target image and vertex position information of the plurality of elemental images, and the layout structure information includes contour information;

the composition analysis module 1330 includes:

the first target coordinate system construction unit is used for constructing a target coordinate system according to the size information of the target image;

a coordinate position determination unit configured to determine coordinate positions of the plurality of elemental images in the target coordinate system based on vertex position information and the contour information of the plurality of elemental images;

an alignment information determining unit configured to determine alignment information in the target coordinate system in the plurality of elemental images according to the coordinate positions;

a first composition analysis data determination unit for analyzing composition analysis data of the target image on image alignment based on the alignment information.

In some embodiments, the layout structure information includes a tilt angle;

the composition analysis module 1330 includes:

the inclination deviation information determining unit is used for determining inclination deviation information between every two element images according to the inclination angles of the element images;

and the second composition analysis data determining unit is used for analyzing composition analysis data of the target image in the visual trend based on the inclination deviation information between every two element images.

The layer information comprises size information of the target image and vertex position information of the element images; the layout structure information includes contour information;

the composition analysis module 1330 includes:

the second target coordinate system construction unit is used for constructing a target coordinate system according to the size information of the target image;

a contour information rendering unit configured to render contour information of the plurality of element images in the target coordinate system based on vertex position information of the plurality of element images and the contour information;

the spiral line drawing unit is used for drawing a spiral line corresponding to the golden section in the target coordinate system;

a third composition analysis data determination unit configured to analyze first composition analysis data of the target image on an elemental structure based on a degree of fitting of the spiral line in the target coordinate system and the contour information of the plurality of elemental images.

In some embodiments, the layout structure information includes: a center of gravity; the layer information includes size information of the plurality of elemental images;

the composition analysis module 1330 includes:

an image scale determining unit configured to determine an image scale into which a center of gravity of each of the elemental images is divided, based on the size information of the plurality of elemental images and the center of gravity of each of the elemental images;

a fourth composition analysis data determination unit for analyzing second composition analysis data of the target image on an element structure based on an image scale of the plurality of element images.

In some embodiments, the layout structure information determination module comprises:

a binarization processing unit, configured to perform binarization processing on the target image to obtain a binary image;

a vertex position determination unit configured to determine vertex positions of a plurality of polygons in the binary image;

a contour information determination unit configured to determine contour information of the plurality of elemental images based on vertex positions of the plurality of polygons;

an order moment calculation unit for calculating order moments of the contour information of the plurality of element images;

a center of gravity determining unit configured to determine a center of gravity of each element image from respective moments of contour information of the each element image;

the first inclination angle determining unit is used for determining the inclination angle of each side of the polygon according to the vertex position of the polygon corresponding to each element image;

the second inclination angle determining unit is used for determining the inclination angle of the corresponding element image according to the inclination angle of each side of the polygon;

a layout structure information determination unit configured to take at least one of contour information, a center of gravity, and an inclination angle of the element image as the layout structure information.

In some embodiments, the layer information further includes: a hierarchical relationship between the plurality of elemental images;

the composition analysis module 1330 includes:

and the fifth composition analysis data determining unit is used for analyzing composition analysis data of the target image on image coverage according to the hierarchical relation among the plurality of element images.

In some embodiments, when the composition analysis data includes a plurality of types of composition analysis data, the apparatus further includes:

the normalization processing module is used for performing normalization processing on the various types of composition analysis data;

the composition weight determining module is used for determining the composition weight of the composition analysis data of the plurality of types, and the composition weight represents the influence degree of each type of composition analysis data on the layout structure of the target image;

and the weighted average processing module is used for carrying out weighted average processing on the basis of the normalized composition analysis data and the composition weight to obtain target composition analysis data of the target image.

In some embodiments, the apparatus further comprises:

and the image screening processing module is used for carrying out image screening processing on the target image based on the composition analysis data or the target composition analysis data.

The device and method embodiments in the device embodiment are based on the same application concept.

An embodiment of the present application provides an image composition analysis apparatus, which includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or a set of instructions, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the image composition analysis method provided in the above method embodiment.

The memory may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.

The method provided by the embodiment of the invention can be executed in a client (a mobile terminal, a computer terminal), a server or a similar operation device. Taking the operation on the client as an example, fig. 14 is a schematic structural diagram of a client according to an embodiment of the present invention, and as shown in fig. 14, the client may be used to implement the information interaction method provided in the foregoing embodiment. Specifically, the method comprises the following steps:

the client may include RF (Radio Frequency) circuitry 1410, memory 1420 including one or more computer-readable storage media, input unit 1430, display unit 1440, sensors 1450, audio circuitry 1460, WiFi (wireless fidelity) module 1470, processor 1480 including one or more processing cores, and power supply 1490. Those skilled in the art will appreciate that the client architecture shown in fig. 14 does not constitute a limitation on the client, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. Wherein:

the RF circuit 1414 may be used for receiving and transmitting signals during a message transmission or call, and in particular, for receiving downlink information from a base station and processing the received downlink information by the one or more processors 1480; in addition, data relating to uplink is transmitted to the base station. In general, the RF circuitry 1414 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, and the like. In addition, the RF circuit 1414 may communicate with networks and other clients via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System for mobile communications), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), and the like.

The memory 1420 may be used to store software programs and modules, and the processor 1480 executes various functional applications and data processing by operating the software programs and modules stored in the memory 1420. The memory 1420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to the use of the client, and the like. Further, memory 1420 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1420 may also include a memory controller to provide the processor 1480 and the input unit 1430 access to the memory 1420.

The input unit 1430 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, input unit 1430 may include a touch-sensitive surface 1431 as well as other input devices 1432. Touch-sensitive surface 1431, also referred to as a touch display screen or touch pad, may collect touch operations by a user on or near the touch-sensitive surface 1431 (e.g., operations by a user on or near the touch-sensitive surface 1431 using a finger, a stylus, or any other suitable object or attachment), and drive the corresponding connection device according to a predefined program. Optionally, touch-sensitive surface 1431 may include both touch detection means and touch controller portions. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device and converts it to touch point coordinates, which are provided to the processor 1480 and can receive and execute commands from the processor 1480. Additionally, the touch-sensitive surface 1431 may be implemented using various types of resistive, capacitive, infrared, and surface acoustic waves, among others. In addition to touch-sensitive surface 1431, input unit 1430 may also include other input devices 1432. In particular, other input devices 1432 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 1440 may be used to display information input by or provided to the user as well as various graphical user interfaces of the client, which may be made up of graphics, text, icons, video, and any combination thereof. The display unit 1440 may include a display panel 1441, and optionally, the display panel 1441 may be configured in the form of an LCD (Liquid crystal display), an OLED (Organic Light-Emitting Diode), or the like. Further, touch-sensitive surface 1431 can overlie display panel 1441, and when touch operations are detected on or near touch-sensitive surface 1431, they are passed to processor 1480 for determining the type of touch event, and processor 1480 then provides a corresponding visual output on display panel 1441 in accordance with the type of touch event. Where the touch-sensitive surface 1431 and the display 1441 may implement input and output functions as two separate components, in some embodiments the touch-sensitive surface 1431 may be integrated with the display 1441 to implement input and output functions.

The client may also include at least one sensor 1450, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 1441 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 1441 and/or the backlight when the client moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when the device is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration) for identifying client gestures, and related functions (such as pedometer and tapping) for vibration identification; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which may be further configured at the client, detailed description is omitted here.

Audio circuitry 1460, speaker 1461, microphone 1462 may provide an audio interface between a user and the client. The audio circuit 1460 can transmit the received electrical signal converted from the audio data to the loudspeaker 1461, and the electrical signal is converted into a sound signal by the loudspeaker 1461 and output; on the other hand, the microphone 1462 converts collected sound signals into electrical signals, which are received by the audio circuit 1460 and converted into audio data, which are then processed by the audio data output processor 1480, and then passed through the RF circuit 1410 for transmission to, for example, another client, or for output to the memory 1420 for further processing. The audio circuit 1460 may also include an earbud jack to provide communication of peripheral headphones with the client.

WiFi belongs to short-distance wireless transmission technology, the client can help a user to send and receive e-mails, browse webpages, access streaming media and the like through a WiFi module 1470, and wireless broadband internet access is provided for the user. Although fig. 14 shows the WiFi module 1470, it is understood that it does not belong to the essential constitution of the client and can be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 1480 is a control center of the client, connects various parts of the entire client by various interfaces and lines, and performs various functions of the client and processes data by running or executing software programs and/or modules stored in the memory 1420 and calling data stored in the memory 1420, thereby performing overall monitoring of the client. Optionally, the processor 1480 may include one or more processing cores; preferably, the processor 1480 may integrate an application processor, which handles primarily operating systems, user interfaces, and applications, among others, with a modem processor, which handles primarily wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 1480.

The client also includes a power supply 1490 (e.g., a battery) that powers the various components, and preferably, the power supply may be logically coupled to the processor 1480 via a power management system to manage charging, discharging, and power consumption management functions via the power management system. The power supply 1490 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and the like.

Although not shown, the client may further include a camera, a bluetooth module, and the like, which are not described herein again. Specifically, in this embodiment, the display unit of the client is a touch screen display, the client further includes a memory and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors according to the instructions of the method embodiments of the present invention.

Embodiments of the present application also provide a storage medium that can be disposed in a device to store at least one instruction, at least one program, a set of codes, or a set of instructions related to implementing an image composition analysis method in the method embodiments, where the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the image composition analysis method provided by the above-mentioned method embodiments.

Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

As can be seen from the embodiments of the image composition analysis method, the apparatus, the server or the storage medium provided in the present application, the layer information of the target image and the layout structure information of the plurality of element images in the target image are obtained; composition analysis is carried out on the target image based on the layer information and/or the layout structure information, composition analysis data which effectively reflects the layout structure condition of the target image can be obtained, and measurement of the quality of the layout structure of the target image from multiple aspects is achieved through the composition analysis data of the target image. The technical scheme provided by the application can be used for rapidly and accurately carrying out image composition analysis, solving the problems of high cost, low processing efficiency and the like caused by manual processing, greatly reducing the cost of composition analysis, improving the processing efficiency of image composition analysis, and simultaneously improving the accuracy and the processing efficiency of subsequent image screening.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and server embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware to implement the above embodiments, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.

The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (10)

1. An image composition analysis method, characterized in that the method comprises:

acquiring layer information of a target image, wherein the layer information represents the target image and basic attribute information of a plurality of element images in the target image;

determining layout structure information of a plurality of element images in a target image;

and performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

2. The method according to claim 1, wherein the layer information includes size information of the target image and vertex position information of the plurality of elemental images, and the layout structure information includes contour information;

the obtaining composition analysis data of the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information includes:

constructing a target coordinate system according to the size information of the target image;

determining coordinate positions of the plurality of element images in the target coordinate system according to the vertex position information and the contour information of the plurality of element images;

determining alignment information in the target coordinate system in the plurality of elemental images from the coordinate positions;

composition analysis data of the target image on image alignment is analyzed based on the alignment information.

3. The method of claim 1, wherein the layout structure information includes a tilt angle;

the obtaining composition analysis data of the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information includes:

determining inclination deviation information between every two element images according to the inclination angles of the element images;

and analyzing composition analysis data of the target image in the visual trend based on the inclination deviation information between every two element images.

4. The method according to claim 1, wherein the layer information includes size information of the target image and vertex position information of the plurality of elemental images; the layout structure information includes contour information;

the obtaining composition analysis data of the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information includes:

constructing a target coordinate system according to the size information of the target image;

drawing the contour information of the element images in the target coordinate system according to the vertex position information and the contour information of the element images;

drawing a spiral line corresponding to the golden section in the target coordinate system;

analyzing first composition analysis data of the target image on an element structure based on a degree of fitting of the spiral line and the contour information of the plurality of element images in the target coordinate system.

5. The method of claim 1, wherein the layout structure information comprises: a center of gravity; the layer information includes size information of the plurality of elemental images;

the obtaining composition analysis data of the target image by performing composition analysis on the target image based on the layer information and/or the layout structure information includes:

determining an image proportion divided by the gravity center of each element image according to the size information of the plurality of element images and the gravity center of each element image;

second composition analysis data of the target image on an element structure is analyzed based on image scales of the plurality of element images.

6. The method according to claim 1, wherein the layer information further includes: a hierarchical relationship between the plurality of elemental images;

the method further comprises the following steps:

and analyzing composition analysis data of the target image on the image coverage according to the hierarchical relation among the plurality of element images.

7. The method of claim 1, wherein determining layout structure information for a plurality of elemental images in a target image comprises:

carrying out binarization processing on the target image to obtain a binary image;

determining vertex positions of a plurality of polygons in the binary image;

determining contour information for the plurality of elemental images based on vertex positions of the plurality of polygons;

calculating respective moments of contour information of the plurality of elemental images;

determining the gravity center of each element image according to each moment of the contour information of each element image;

determining the inclination angle of each side of the polygon according to the vertex position of the polygon corresponding to each element image;

determining the inclination angle of the corresponding element image according to the inclination angle of each edge of the polygon;

at least one of contour information, a center of gravity, and an inclination angle of the element image is taken as the layout structure information.

8. The method according to claim 1, wherein when the composition analysis data includes a plurality of types of composition analysis data, the method further comprises:

carrying out normalization processing on the various types of composition analysis data;

determining composition weights of the composition analysis data of the multiple types, wherein the composition weights represent the influence degree of each type of composition analysis data on the layout structure of the target image;

and carrying out weighted average processing on the basis of the normalized composition analysis data and the composition weight to obtain target composition analysis data of the target image.

9. The method of claim 8, further comprising:

and carrying out image screening processing on the target image based on the composition analysis data or the target composition analysis data.

10. An image composition analysis apparatus, comprising:

the image layer information acquisition module is used for acquiring image layer information of a target image, wherein the image layer information represents the target image and basic attribute information of a plurality of element images in the target image;

a layout structure information determination module for determining layout structure information of a plurality of element images in a target image;

and the composition analysis module is used for performing composition analysis on the target image based on the layer information and/or the layout structure information to obtain composition analysis data of the target image.

Images