Image aesthetic determination method and device, equipment and storage medium

Abstract

The invention provides an image aesthetics determination method and device, equipment and a storage medium. The method comprises the steps of obtaining eye movement data obtained when at least one user watches a to-be-detected image; the eye movement data comprises the number of first fixation points, the duration of each first fixation point and the position information of each first fixation point on the to-be-detected image; based on the number of the first fixation points and the duration of each first fixation point, determining an aesthetic parameter of the to-be-detected image; based on the number of the first fixation points and the position information of each first fixation point, determining style parameters of the to-be-detected image; the style parameter is used for representing the correlation degree of the to-be-detected image and the standard image; and determining aesthetic parameters of the to-be-detected image based on the aesthetic parameters of the to-be-detected image and the style parameters of the to-be-detected image.

Description

Technical Field

[0001] The present application relates to the field of human-computer interaction for intelligent driving, and in particular to a method, device, equipment and storage medium for determining image aesthetics. Background Art

[0002] With the continuous improvement of the level of automobile intelligence, the human-computer interaction mode in the car is multi-screen and multi-mode, and the beauty of the interface has a direct impact on the user experience and willingness to buy. Therefore, after designers design a variety of alternative design schemes based on market demand and their own understanding of the product, especially the appearance design scheme with a strong personal style of the designer, how to quickly and accurately select the design scheme that truly meets the expectations of consumers is a pain point. At present, most automobile manufacturers mainly rely on professional evaluation, user survey testing and other methods to confirm whether the interface is beautiful or not, but most of the above methods rely on the subjective evaluation of individuals or groups. There are also problems such as semantic ambiguity of user feedback, differences in expression ability, and the "halo effect" of the questionnaire during user surveys. Summary of the invention

[0003] The present application mainly provides a method, device, equipment and storage medium for determining image aesthetics, which can overcome the problem of poor accuracy in determining image aesthetics caused by reliance on subjective evaluation of individuals or groups in related technologies.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The present application embodiment provides a method for determining image aesthetics, including:

[0006] Acquire eye movement data obtained by at least one user viewing the image to be tested; the eye movement data includes the number of first fixation points, the duration of each of the first fixation points, and the position information of each of the first fixation points on the image to be tested;

[0007] Determining the aesthetic parameter of the image to be measured based on the number of the first gaze points and the duration of each of the first gaze points;

[0008] Determining a style parameter of the image to be tested based on the number of the first gaze points and the position information of each of the first gaze points; the style parameter is used to characterize the degree of correlation between the image to be tested and a standard image;

[0009] The aesthetic parameters of the image to be tested are determined based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

[0010] The embodiment of the present application can establish a measurement system for determining image aesthetics based on the eye movement data of at least one user. The system can not only determine the aesthetic parameters of the image to be tested based on the eye movement data, but also determine the degree of correlation between the image to be tested and the standard image based on the eye movement data, and then determine the aesthetic parameters of the image to be tested based on the aesthetic parameters and style parameters of the image to be tested. In this way, the quantification of the aesthetic parameters of the image to be tested is achieved through the eye movement data, which solves the problem of poor accuracy in determining the beauty of the image caused by the related technology relying on the subjective evaluation of individuals or groups, thereby improving the accuracy of determining the aesthetic parameters of the image to be tested.

[0011] Furthermore, since the number of fixation points and the duration of fixation points obtained by the user when viewing the image to be tested can reflect whether the user is interested in the image to be tested, the more interested the user is in the image to be tested, the higher the aesthetic parameters of the image to be tested are. Therefore, the embodiment of the present application can accurately determine the aesthetic parameters of the image to be tested based on the number of first fixation points and the duration of each first fixation point. At the same time, the number of fixation points and the positions of fixation points can reflect the degree of correlation between the image to be tested and the standard image. For example, when the number of fixation points and the positions of fixation points obtained by the user when viewing the image to be tested are similar to the number of fixation points and the positions of fixation points obtained by the user when viewing the standard image, it can be said that the image to be tested is an image with a high degree of correlation with the standard image. Therefore, the embodiment of the present application can accurately determine the style parameters of the image to be tested based on the number of first fixation points and the position of each first fixation point.

[0012] In some embodiments, determining the aesthetic parameters of the image to be tested based on the number of the first fixation points and the duration of each of the first fixation points includes: determining the contrast parameters of the image to be tested based on the number of the first fixation points and the duration of each of the first fixation points; the contrast parameters are used to characterize the visual differences between individual elements in the image to be tested; and determining the aesthetic parameters of the image to be tested based on the contrast parameters of the image to be tested and the duration of each of the first fixation points.

[0013] Since the number of first fixation points and the duration of each first fixation point can reflect the visual difference between individual elements in the image to be tested, for example, when the number of first fixation points is small and the duration of each first fixation point is relatively even, it means that the visual difference between individual elements in the image to be tested is small, and the visual difference between individual elements in the image to be tested can reflect the aesthetics of the image to be tested. Therefore, the embodiment of the present application can accurately determine the contrast parameter of the image to be tested for characterizing the visual difference between individual elements in the image to be tested through the number of first fixation points and the duration of each first fixation point, and then determine the aesthetic parameters of the image to be tested based on the contrast parameter and the duration of each first fixation point, thereby improving the accuracy of determining the aesthetic parameters of the image to be tested.

[0014] In some embodiments, determining the contrast parameter of the image to be tested based on the number of the first fixation points and the duration of each of the first fixation points includes: determining the purity parameter of the image to be tested based on the number of the first fixation points; determining the density parameter of the image to be tested based on the duration of each of the first fixation points; determining the contrast parameter of the image to be tested based on the purity parameter of the image to be tested and the density parameter of the image to be tested.

[0015] Since the number of first gaze points can reflect the purity parameter of the image to be tested, the larger the number of first gaze points, the higher the complexity of the image to be tested, that is, the smaller the purity parameter. Therefore, the embodiment of the present application can accurately determine the purity parameter of the image to be tested based on the number of first gaze points, and then determine the complexity of the image to be tested through the purity parameter. The duration of each first gaze point can also determine the degree of fluctuation of the duration of the first gaze point, so based on the duration of each first gaze point, the weight parameter of the image to be tested can also be determined, and then the degree of visual inertia generated by the image to be tested in the overall vision can be determined through the weight parameter. Therefore, the contrast parameter of the image to be tested can be accurately determined through the purity parameter and the weight parameter.

[0016] In some embodiments, determining the aesthetic parameters of the image to be tested based on the contrast parameters of the image to be tested and the duration of each first gaze point includes: determining the average gaze duration based on the duration of each first gaze point; determining the aesthetic parameters of the image to be tested based on the ratio of the contrast parameters of the image to be tested to the average gaze duration.

[0017] The aesthetic parameters in the embodiment of the present application are not only related to the contrast parameter, but also to the average gaze duration. This is because the average gaze duration can reflect the user's aesthetic taste. Too short indicates that it is unattractive, and too long may indicate that the user is confused about it. Therefore, the embodiment of the present application can accurately determine the aesthetic parameters of the image to be tested based on the ratio of the contrast parameter of the image to be tested to the average gaze duration of at least one user. .

[0018] In some embodiments, the style parameters of the image to be tested are determined based on the number of the first gaze points and the position information of each of the first gaze points, including: determining at least one first area of ​​the user's attention on the image to be tested based on the position information of each of the first gaze points; determining at least one second area of ​​the user's attention on the standard image based on the position information of each second gaze point on the standard image; the second gaze point is a gaze point obtained by at least one of the users when viewing the standard image; and determining the style parameters of the image to be tested based on the first area, the second area, the position information of each of the first gaze points, the number of the first gaze points, and the number of the second gaze points.

[0019] Since the correlation degree between the image to be tested and the standard image (i.e., style parameters) can be determined by the areas that the user pays attention to on the image to be tested and the areas that the user pays attention to on the standard image, for example, when there are more gaze points in the overlapping area of ​​the areas that the user pays attention to on the two, it can be determined that the correlation degree between the image to be tested and the standard image is high. Therefore, the embodiment of the present application can accurately determine the style parameters used to characterize the correlation degree between the image to be tested and the standard image based on the first area that characterizes the attention of at least one user on the image to be tested, the second area that characterizes the attention of at least one user on the standard image, and the number of gaze points of the user viewing the image to be tested and the standard image respectively.

[0020] In some embodiments, the style parameters include suitability parameters; determining the style parameters of the image to be tested based on the first area, the second area, the position information of each of the first fixation points, the number of the first fixation points and the number of the second fixation points includes: determining the overlapping area between the first area and the second area; determining the number of third fixation points located in the overlapping area based on the position information of each of the first fixation points; and determining the ratio of the number of the third fixation points to the sum of the number of the first fixation points and the number of the second fixation points as the suitability parameter.

[0021] Since the gaze points that appear in the overlapping area between the first area that represents the user's attention on the image to be tested and the second area that represents the user's attention on the standard image can reflect whether the user pays attention to the overlapping area, when there are more gaze points in the overlapping area, it means that the focus of the user on the image to be tested and the standard image is consistent, that is, the style of the image to be tested and the standard image is similar. Therefore, the embodiment of the present application can accurately determine the suitability parameter that represents the similarity of the style of the image to be tested and the standard image based on the number of the third gaze points, the number of the first gaze points, and the number of the second gaze points in the overlapping area.

[0022] In some embodiments, the style parameters also include novelty parameters; determining the style parameters of the image to be tested based on the first area, the second area, the position information of each of the first fixation points, the number of the first fixation points and the number of the second fixation points includes: determining the non-overlapping area between the first area and the second area; determining the number of fourth fixation points located in the non-overlapping area based on the position information of each of the first fixation points; and determining the ratio of the number of the fourth fixation points to the sum of the number of the first fixation points and the number of the second fixation points as the novelty parameter.

[0023] Since the gaze points that appear in the non-overlapping area representing the first area that the user pays attention to on the image to be tested and the second area that the user pays attention to on the standard image can reflect whether the user pays attention to the non-overlapping area, when there are more gaze points in the non-overlapping area, it means that the focus of the user on the image to be tested and the standard image is different, that is, the style of the image to be tested and the standard image are not similar. Therefore, based on the number of fourth gaze points, the number of first gaze points, and the number of second gaze points in the overlapping area, the embodiment of the present application can accurately determine the novelty parameter that represents the difference in style between the image to be tested and the standard image.

[0024] In some embodiments, the style parameters include a suitability parameter and a novelty parameter; determining the aesthetic parameters of the image to be tested based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested includes: determining that the product of the aesthetic parameters of the image to be tested and the novelty parameters of the image to be tested is the first value of the image to be tested; determining that the product of the aesthetic parameters of the image to be tested, the novelty parameters of the image to be tested, and the suitability parameters of the image to be tested is the second value of the image to be tested; determining the aesthetic parameters of the image to be tested based on the difference between the product of the first numerical power of the natural constant and the suitability parameter and the second numerical power of the natural constant.

[0025] Since images with a high aesthetic level generally have individual elements similar to images with a high aesthetic level (i.e., standard images) recognized in the art, but if only individual elements similar to standard images exist, aesthetic fatigue will occur, so a certain degree of novelty is required. Therefore, the embodiment of the present application can accurately determine the aesthetic level (i.e., aesthetic parameters) of the image to be tested based on the suitability parameter, novelty parameter, and aesthetic parameter of the image to be tested.

[0026] The present application embodiment provides a device for determining image aesthetics, the device comprising:

[0027] an acquisition unit, configured to acquire eye movement data obtained by at least one user viewing the image to be tested; the eye movement data comprising the number of first fixation points, the duration of each of the first fixation points, and the position information of each of the first fixation points on the image to be tested;

[0028] A first determining unit, configured to determine the aesthetic parameter of the image to be measured based on the number of the first fixation points and the duration of each of the first fixation points;

[0029] a second determining unit, configured to determine a style parameter of the image to be tested based on the number of the first fixation points and the position information of each of the first fixation points; the style parameter is used to characterize the degree of correlation between the image to be tested and a standard image;

[0030] The third determining unit is used to determine the aesthetic parameters of the image to be tested based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

[0031] An embodiment of the present application provides an image aesthetics determination device, comprising: a memory for storing executable instructions; and a processor for implementing the image aesthetics determination method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0032] An embodiment of the present application provides a storage medium having executable instructions stored thereon. When the executable instructions are executed by a processor, the image aesthetics determination method provided in the embodiment of the present application is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application;

[0034] Figure 2 is a flow chart of a method for determining image aesthetics provided in an embodiment of the present application;

[0035] Figure 3a A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application;

[0036] Figure 3b A schematic diagram of a first area and a second area provided in an embodiment of the present application;

[0037] Figure 4 A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application;

[0038] Figure 5 A scene framework diagram of the image aesthetics determination method provided in an embodiment of the present application;

[0039] Figure 6A schematic diagram of the structure of the image aesthetics determination device provided in an embodiment of the present application;

[0040] Figure 7 A schematic diagram of the composition structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The technical solution of the present application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] In order to enable those skilled in the art to better understand the embodiments of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0043] The terms "first", "second", and "third" in the specification embodiments and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or precedence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, including a series of steps or units. The method, system, product or device is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] In order to solve the problem of poor accuracy in determining image aesthetics due to reliance on subjective evaluation of individuals or groups in related technologies, an embodiment of the present application provides a method for determining image aesthetics, which can be applied to a computer device, which includes but is not limited to a fixed device and / or a mobile device, for example, the fixed device includes but is not limited to: a personal computer (PC), or a server, etc., and the server can be a cloud server or an ordinary server. The mobile device includes but is not limited to: one or more of a mobile phone, a tablet computer or a wearable device.

[0045] Figure 1 A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application, such as Figure 1 As shown, the process may include:

[0046] In S101, eye movement data obtained when at least one user views an image to be tested is obtained.

[0047] In the embodiment of the present application, when at least one user views the image to be tested, the eye movement data of at least one user can be collected in real time by the eye movement collection device, and then the eye movement data is obtained from the eye movement collection device. In other embodiments, the eye movement data can also be collected in advance by the eye movement collection device and then stored in a storage device, and then obtained from the storage device.

[0048] Here, the image to be tested may be a two-dimensional image or a three-dimensional image. In some embodiments, the image to be tested may be a display interface diagram of a vehicle. Exemplarily, the display interface diagram may be a static user interface (UI) diagram, a low-fidelity prototype diagram, a high-fidelity prototype, and the like.

[0049] Here, the eye movement data includes the number of first fixation points, the duration of each first fixation point, and the position information of each first fixation point on the image to be tested. The number of first fixation points includes the number of fixation points of all users when viewing the image to be tested. For example, when at least one user includes user 1 and user 2, the number of fixation points of user 1 viewing the image to be tested is A, and the number of fixation points of user 2 viewing the image to be tested is B, then the number of first fixation points is A+B; the duration of each first fixation point can represent the length of time the user stays at each fixation point. For example, the duration of fixation point 1 is 2s, which means that the user stays at fixation point 1 for 2s; the position information of each first fixation point on the image to be tested can be the coordinate information of each fixation point on the image to be tested, and the coordinate information can be rectangular coordinate information or polar coordinate information.

[0050] In S102, based on the number of first gaze points and the duration of the first gaze points, the aesthetic parameters of the image to be measured are determined.

[0051] Here, the aesthetic parameter is used to characterize the visual balance degree of the user when viewing the image to be tested. The higher the aesthetic parameter, the higher the visual balance degree of the user when viewing the image to be tested, that is, the higher the pleasure degree brought to the user by the image to be tested.

[0052] In some embodiments, the corresponding aesthetic parameter may be determined based on a mapping relationship between the number of first gaze points, the duration of each first gaze point, and the aesthetic parameter.

[0053] In an embodiment of the present application, a contrast parameter may be determined based on the number of first gaze points and the duration of each first gaze point, and then an aesthetic parameter of the image to be measured may be determined based on the contrast parameter and the duration of each first gaze point.

[0054] In S103, based on the number of first gaze points and the position information of each first gaze point, the style parameter of the image to be tested is determined.

[0055] Here, the style parameter is used to characterize the degree of correlation between the image to be tested and the standard image. In some embodiments, the style parameter of the image to be tested can be reflected by the degree of similarity between the image to be tested and the standard image and the degree of difference between the image to be tested and the standard image. The standard image can be an image with a high degree of aesthetics recognized in the art.

[0056] In some embodiments, the overlapping area and the non-overlapping area of ​​the image to be tested and the standard image can be determined based on the gaze point coordinate information of the image to be tested, and then the style parameters of the image to be tested are determined based on the two determined areas and the number of first gaze points.

[0057] In S104 , the aesthetic parameters of the image to be tested are determined based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

[0058] Here, the aesthetic parameter is used to characterize the aesthetics of the image to be tested.

[0059] In some embodiments, the weight coefficients of the aesthetic parameters and the weight coefficients of the style parameters may be determined first, and then based on the weight coefficients of the aesthetic parameters and the weight coefficients of the style parameters, the aesthetic parameters and the style parameters may be weightedly summed to obtain the aesthetic parameters of the image to be tested.

[0060] In some embodiments, in order to facilitate comparison of aesthetic parameters of different images to be tested, after the aesthetic parameters of the images to be tested are obtained, the aesthetic parameters of the images to be tested may be normalized.

[0061] The embodiment of the present application can establish a measurement system for determining image aesthetics based on the eye movement data of at least one user. The system can not only determine the aesthetic parameters of the image to be tested based on the eye movement data, but also determine the degree of correlation between the image to be tested and the standard image based on the eye movement data, and then determine the aesthetic parameters of the image to be tested based on the aesthetic parameters and style parameters of the image to be tested. In this way, the quantification of the aesthetic parameters of the image to be tested is achieved through the eye movement data, which solves the problem of poor accuracy in determining the beauty of the image caused by the related technology relying on the subjective evaluation of individuals or groups, thereby improving the accuracy of determining the aesthetic parameters of the image to be tested.

[0062] Figure 2 is a flow chart of the method for determining image aesthetics provided in the embodiment of the present application, based on Figure 1 , Figure 1 S102 in the example may include S201 to S202, which will be combined with Figure 2 The steps shown are explained.

[0063] In S201, a contrast parameter of the image to be measured is determined based on the number of first gaze points and the duration of each first gaze point.

[0064] In an embodiment of the present application, after obtaining the number of first gaze points corresponding to at least one user and the duration of each first gaze point, the contrast parameter of the image to be measured can be determined based on the number of first gaze points and the duration of each first gaze point.

[0065] Here, the contrast parameter is used to characterize the visual difference between different individual elements in the image to be tested. When the contrast parameter of the image to be tested is smaller, it means that the visual difference between different elements in the image to be tested is smaller.

[0066] In some embodiments, S201 may be implemented by the following steps:

[0067] In S211 , the purity parameter of the image to be tested is determined based on the number of the first gaze points.

[0068] In the embodiment of the present application, the reciprocal of the number of first fixation points may be determined as the purity parameter of the image to be tested.

[0069] Here, the purity parameter is used to characterize the complexity of the image to be tested. When the purity parameter is smaller, it means that the image to be tested contains fewer individual elements, and thus the complexity of the image to be tested is also smaller. The number of first fixation points can reflect the number of individual elements of the image to be tested. Since the user can see every individual element in the image to be tested with a high probability when viewing the image to be tested, the more individual elements there are in the image to be tested, the higher the number of first fixation points will be. Therefore, the reciprocal of the number of first fixation points can be used as the purity of the image to be tested.

[0070] In some embodiments, the purity parameter of the image to be tested can be realized by formula (1):

[0071]

[0072] Among them, Pur (Pureness) is purity, N F is the number of first fixation points.

[0073] In some embodiments, the purity parameter of the image to be tested can also be realized by formula (2):

[0074]

[0075] Wherein, Q is the number of main elements in the image to be tested. Exemplarily, when the image to be tested contains different vehicles, each vehicle is a main element, and each main element may contain multiple individual elements.

[0076] In S212, based on the duration of each first gaze point, a weight parameter of the image to be measured is determined.

[0077] Here, the weight parameter of the image to be tested is used to characterize the degree to which the visual inertia generated by the image to be tested accounts for the overall vision. In a unit of time, since visual inertia has similarity, the eye will be attracted to the element with the best weight. Therefore, the greater the variance of the duration of each fixation point, the lower its weight. Therefore, the weight parameter can be realized by formula (3):

[0078]

[0079] Among them, Pro (Proportion) is the specific gravity parameter, σ F is the variance of the duration of each first fixation point.

[0080] In S213, the contrast parameter of the image to be measured is determined based on the purity parameter and the specific gravity parameter.

[0081] In the embodiment of the present application, the contrast parameter of the image to be measured can be determined based on the purity parameter and the specific gravity parameter.

[0082] In the embodiment of the present application, since the purity parameter and the specific gravity parameter are inversely proportional to the contrast parameter, when the purity parameter and the specific gravity parameter increase, the contrast parameter will decrease accordingly. Therefore, the contrast parameter can be realized by formula (4):

[0083]

[0084] Among them, Con (Contrast) is the contrast parameter.

[0085] The embodiment of the present application can determine the purity parameter of the image to be tested based on the number of first fixation points, and the complexity of the image to be tested can be determined through the purity parameter. Then, based on the duration of each first fixation point, the weight parameter of the image to be tested is determined, and the degree of visual inertia generated by the image to be tested in the overall vision can be determined through the weight parameter. Furthermore, the contrast parameter of the image to be tested can be accurately determined through the purity parameter and the weight parameter.

[0086] In S202, the aesthetic parameters of the image to be measured are determined based on the contrast parameter and the duration of each first fixation point.

[0087] In the embodiment of the present application, the average fixation duration can be determined based on the duration of each first fixation point, and then the aesthetic parameter of the image to be measured can be determined based on the contrast parameter and the average fixation duration.

[0088] In some embodiments, S202 is implemented by the following steps:

[0089] In S221 , an average gaze duration is determined based on the duration of each first gaze point.

[0090] In the embodiment of the present application, the duration of each first gaze point carries a user identifier of the corresponding user, and the user identifier can indicate the identity of the user. The duration of each first gaze point can be classified based on the user identifier carried by the duration of each first gaze point to obtain at least one gaze point duration cluster classified according to different users; the duration of the first gaze point in each gaze point duration cluster is summed to obtain the total gaze duration of each user; the total gaze durations corresponding to at least one user are averaged to obtain the average gaze duration.

[0091] In S222, the aesthetic parameter of the image to be tested is determined based on the ratio of the contrast parameter of the image to be tested to the average gaze duration.

[0092] In the embodiment of the present application, the ratio of the contrast parameter of the image to be tested to the average fixation duration of at least one user is first determined, and then the aesthetic parameter of the image to be tested is determined based on the magnitude relationship between the ratio and a preset ratio, wherein the preset ratio may be 0.5.

[0093] In the embodiment of the present application, the aesthetic parameter of the image to be measured can be realized by formula (5):

[0094]

[0095] Among them, B is the aesthetic parameter, C is the contrast parameter, and T is the average fixation time.

[0096] It can be seen from formula (5) that the aesthetic parameter is not only related to the contrast parameter, but also to the average gaze duration of at least one user. This is because the average gaze duration can reflect the user's aesthetic taste. Too short indicates that it is unattractive, and too long may indicate that the user is confused about it. Therefore, the embodiment of the present application can first calculate the ratio of the contrast parameter of the image to be tested to the average gaze duration of at least one user, and then obtain the corresponding aesthetic parameter of the image to be tested based on the ratio and the piecewise function.

[0097] The embodiment of the present application can determine the aesthetic parameters of the image to be tested based on the ratio of the contrast parameter to the average gaze duration of at least one user, thereby achieving quantification of the aesthetic parameters of the image to be tested and improving the accuracy of determining the aesthetic parameters.

[0098] Figure 3a A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application is based on Figure 1 , Figure 1 S103 in the above example may include S301 to S303, which will be combined with Figure 3a The steps shown are explained.

[0099] In S301, based on the position information of each first gaze point, a first area focused on by at least one user on the image to be tested is determined.

[0100] In the embodiment of the present application, after the position information of each first gaze point is obtained, at least one first area of ​​interest to the user on the image to be tested can be fitted based on the position information of each first gaze point.

[0101] In the embodiment of the present application, the first area may be an elliptical area. When the position information of each first gaze point is rectangular coordinate information, the average value of the horizontal coordinate of each first gaze point may be determined as the horizontal coordinate of the center point of the elliptical area, and the average value of the vertical coordinate of each first gaze point may be determined as the vertical coordinate of the center point of the elliptical area; the standard deviation of the horizontal coordinate of each first gaze point and the standard deviation of the vertical coordinate of each first gaze point may be determined as the long radius and the short radius of the elliptical area. In this way, at least one first area of ​​interest to a user on the image to be tested may be fitted based on the position information of each first gaze point.

[0102] In S302, based on the position information of each second gaze point on the standard image, a second area focused on by at least one user on the standard image is determined.

[0103] In the embodiment of the present application, after the position information of each second gaze point is obtained, a second area that the user pays attention to on the standard image can be fitted based on the position information of each second gaze point.

[0104] Here, the second gaze point is a gaze point obtained by at least one user viewing the standard image. When at least one user views the standard image, the eye movement collection device can collect the position information of each second gaze point of at least one user in real time, and then obtain the position information of each second gaze point from the eye movement collection device.

[0105] In the embodiment of the present application, the second area may be an elliptical area. When the position information of each second gaze point is rectangular coordinate information, the average value of the horizontal coordinate of each second gaze point may be determined as the horizontal coordinate of the center point of the elliptical area, and the average value of the vertical coordinate of each second gaze point may be determined as the vertical coordinate of the center point of the elliptical area; the standard deviation of the horizontal coordinate of each second gaze point and the standard deviation of the vertical coordinate of each second gaze point may be determined as the long radius and the short radius of the elliptical area. In this way, at least one second area of ​​interest to the user on the image to be tested may be fitted based on the position information of each second gaze point.

[0106] In S303, based on the first area, the second area, the position information of each first gaze point, the number of first gaze points, and the number of second gaze points, the style parameter of the image to be tested is determined.

[0107] In the embodiment of the present application, the style parameter of the image to be tested may be determined based on the overlap between the first area and the second area, the position information of each first gaze point, the number of first gaze points, and the number of second gaze points.

[0108] In some embodiments, when the style parameters include suitability parameters, S303 may be implemented by the following steps:

[0109] In S331 , an overlapping area between the first area and the second area is determined.

[0110] In the embodiment of the present application, after the first area and the second area are fitted, an overlapping area between the first area and the second area may be determined.

[0111] Figure 3b Schematic diagram of the first area and the second area provided in the embodiment of the present application. Figure 3b As shown, region A is the second region that at least one user pays attention to on the standard image, region N is the first region that at least one user pays attention to on the image to be tested, and region C is the overlapping region between the first region and the second region.

[0112] In S332, based on the position information of each first gaze point, the number of third gaze points located in the overlapping area is determined.

[0113] In an embodiment of the present application, based on the position information of each first gaze point, each first gaze point can be marked in the rectangular coordinate system where the overlapping area between the first area and the second area is located, and then the number of third gaze points located in the overlapping area can be determined.

[0114] In S333, the ratio of the number of the third gaze points to the sum of the number of the first gaze points and the number of the second gaze points is determined as a suitability parameter.

[0115] In an embodiment of the present application, the number of first gaze points and the number of second gaze points may be summed to obtain the total number of gaze points, and then the ratio of the number of third gaze points to the total number of gaze points may be determined as a suitability parameter.

[0116] Here, the suitability parameter is used to characterize the similarity between the image to be tested and the standard image. Since the areas of interest to the user for images of related styles are similar, when the overlapping area between the area of ​​interest to the image to be tested and the area of ​​interest to the standard image is large, it means that the similarity between the image to be tested and the standard image is large, that is, the suitability parameter of the image to be tested is high.

[0117] In some embodiments, the fitness parameter can be implemented by formula (6):

[0118]

[0119] Among them, A is the suitability parameter, N A is the number of third fixation points, N T is the sum of the number of the first fixation points and the number of the second fixation points.

[0120] The embodiment of the present application can determine the overlapping area between the two based on the first area that represents the user's attention on the image to be tested and the second area that represents the user's attention on the standard image, and then based on the number of third gaze points, the number of first gaze points and the number of second gaze points in the overlapping area, it is possible to accurately determine the suitability parameter that represents the similarity in style between the image to be tested and the standard image.

[0121] In some embodiments, when the style parameter includes a novelty parameter, S303 may also be implemented by the following steps:

[0122] In S334 , a non-overlapping area between the first area and the second area is determined.

[0123] In the embodiment of the present application, after the first area and the second area are fitted, a non-overlapping area between the first area and the second area may be determined.

[0124] like Figure 3b As shown, region B is a non-overlapping region between the first region and the second region.

[0125] In S335, based on the position information of each first gaze point, the number of fourth gaze points located in the non-overlapping area is determined;

[0126] In an embodiment of the present application, based on the position information of each first gaze point, each first gaze point can be marked in the rectangular coordinate system where the non-overlapping area between the first area and the second area is located, and then the number of fourth gaze points located in the non-overlapping area can be determined.

[0127] In S336, the ratio of the number of fourth gaze points to the sum of the number of first gaze points and the number of second gaze points is determined as a novelty parameter.

[0128] In an embodiment of the present application, the number of first gaze points and the number of second gaze points may be summed to obtain the total number of gaze points, and then the ratio of the number of fourth gaze points to the total number of gaze points may be determined as the novelty parameter.

[0129] Here, the novelty parameter is used to characterize the degree of difference between the image to be tested and the standard image. Since the areas of interest to the user for images of related styles are similar, when the non-overlapping area between the area of ​​interest to the image to be tested and the area of ​​interest to the standard image is large, it means that the image to be tested is more different from the standard image, that is, the novelty parameter of the image to be tested is higher.

[0130] In some embodiments, the novelty parameter may be implemented by formula (7):

[0131]

[0132] Among them, N is the novelty parameter, N B is the number of the fourth fixation points, N T is the sum of the number of the first fixation points and the number of the second fixation points.

[0133] The embodiment of the present application can determine the non-overlapping area of ​​the two based on the first area that represents the user's attention on the image to be tested and the second area that represents the user's attention on the standard image, and then based on the number of fourth gaze points, the number of first gaze points and the number of second gaze points in the overlapping area, it is possible to accurately determine the novelty parameter that represents the difference in style between the image to be tested and the standard image.

[0134] In some embodiments, when the style parameters of the image to be tested only reflect the degree of similarity between the image to be tested and the standard image, the style parameters of the image to be tested may only include suitability parameters; when the style parameters of the image to be tested only reflect the degree of difference between the image to be tested and the standard image, the style parameters of the image to be tested may only include novelty parameters; when the style parameters of the image to be tested reflect both the degree of similarity and the degree of difference between the image to be tested and the standard image, the style parameters of the image to be tested may include novelty parameters and suitability parameters.

[0135] The embodiment of the present application fits a first area representing the focus of at least one user on the image to be tested based on the position information of each first fixation point, and fits a second area representing the focus of at least one user on the standard image based on the position information of the second fixation point on the standard image obtained by at least one user viewing the standard image. Finally, the style parameters of the image to be tested are determined based on the first area, the second area, the position information of each first fixation point, the number of first fixation points, and the number of second fixation points. In this way, the embodiment of the present application can accurately determine the style parameters used to characterize the degree of correlation between the image to be tested and the standard image based on the fitted first area, the second area, and the number of fixation points of the user viewing the image to be tested and the standard image respectively.

[0136] Figure 4 A schematic diagram of a flow chart of a method for determining image aesthetics provided in an embodiment of the present application is based on Figure 1 , when the style parameters include novelty parameters and suitability parameters, Figure 1 S104 in the above example may include S401 to S403, which will be combined with Figure 4 The steps shown are explained.

[0137] In S401, a product of an aesthetic parameter of the image to be tested and a novelty parameter of the image to be tested is determined as a first value of the image to be tested.

[0138] In S402, the product of the aesthetic parameter of the image to be tested, the novelty parameter of the image to be tested, and the suitability parameter of the image to be tested is determined as a second value of the image to be tested.

[0139] In S403, the aesthetic parameter of the image to be tested is determined based on the difference between the product of the first numerical power of the natural constant and the suitability parameter and the second numerical power of the natural constant.

[0140] In the embodiment of the present application, the aesthetic parameters of the image to be tested are determined based on the novelty parameter, the aesthetic parameter and the suitability parameter. This is because an image with a high aesthetic level generally has elements similar to an image with a high aesthetic level (i.e., a standard image) recognized in the art, but if only elements similar to the standard image exist, it will also cause aesthetic fatigue, so a certain degree of novelty is required.

[0141] In the embodiment of the present application, the aesthetic parameter of the image to be measured can be realized by formula (8):

[0142] Aes=Ae M ﹣e N +1 formula (8);

[0143] Wherein, Aes is an aesthetic parameter, e is a natural constant, M is a first value, and N is a second value;

[0144] In the embodiment of the present application, the novelty parameter, aesthetic parameter and suitability parameter of the image to be tested can be unified to between 0 and 1 through formula (8). The higher the aesthetic parameter, the greater the aesthetic degree of the corresponding image to be tested. In this way, the embodiment of the present application can realize the quantification of the aesthetic parameters, and the calculated aesthetic parameters include the novelty parameter, the aesthetic parameter and the suitability parameter, thereby improving the accuracy of determining the aesthetic degree of the image.

[0145] In some embodiments, when the style parameters include a novelty parameter or a suitability parameter, a weight coefficient of the novelty parameter or the suitability parameter can be determined, and a weight coefficient of the aesthetic parameter can be determined, and then based on the weight coefficient of the aesthetic parameter and the weight coefficient of the novelty parameter or the suitability parameter, the novelty parameter or the suitability parameter and the style parameter are weighted and summed to obtain the aesthetic parameters of the image to be tested. In some embodiments, the aesthetic parameters of the image to be tested after the weighted summation can also be normalized to facilitate comparison of the aesthetic parameters of different images to be tested.

[0146] Figure 5 A scene framework diagram of the image aesthetics determination method provided in the embodiment of the present application, such as Figure 5 As shown, the scene framework of the image aesthetics determination method includes a vehicle display area 501, a test display interface 502, a user 503, an eye movement collection device 504, and a data processing device 505. In some embodiments, the scene framework of the image aesthetics determination method can be set in a car driving environment, which includes but is not limited to a car that can be actually driven, a simulated test bench, a simulated cockpit, a static test car, and other environments that can actually or simulate the use and driving of a car.

[0147] The vehicle display area 501 is used to play the test image and the test display interface 502 (equivalent to the image to be tested in the above embodiment). The eye movement collection device 504 is used to collect the initial eye movement data of the user 503 when watching the test image or the test display interface 502, and send the collected initial eye movement data to the data processing device 505. The data processing device 505 is used to process the initial eye movement data to obtain the number of fixation points (equivalent to the number of first fixation points in the above embodiment), the duration of the fixation points (equivalent to the duration of each first fixation point in the above embodiment) and the fixation point coordinates (equivalent to the position information of each first fixation point in the above embodiment).

[0148] In the embodiment of the present application, based on the scene framework diagram of the image aesthetics determination method, the image aesthetics determination method provided in the embodiment of the present application can also be implemented by the following steps:

[0149] Step 1: Invite a representative user 503 to a car driving environment, including but not limited to a car that can be actually driven, a simulation test bench, a simulation cockpit, a static test car, and other environments that can actually or simulate car use and driving. According to daily driving requirements, the user 503 sits in the car seat and fastens the seat belt.

[0150] Step 2 is for the user 503 to wear the eye movement collection device 504, connect the eye movement collection device 504 to the data processing device 505, play the test picture in the vehicle display area 501, and confirm that the data processing device 505 can receive the data transmitted by the eye movement collection device 504. Then inform the user 503 to prepare to start the test.

[0151] Step 3, playing soothing pictures in the vehicle display area 501, including but not limited to entertainment videos, navigation maps, vehicle settings and other types of pictures often used during driving, to adjust the user's current emotional fluctuations and simulate real usage scenarios. After the eye movement data is stable, playing the test display interface 502 in the vehicle display area 501, including but not limited to static UI pictures, low-fidelity prototype pictures, high-fidelity prototypes, etc., the user can watch, touch, click, operate and other actions according to different test display interfaces during observation. The eye movement collection device 504 collects the user's eye movement data in the above actions in real time and transmits it to the data processing device 505. The data processing device 505 stores and records the data transmitted by the eye movement collection device 504, and processes it to obtain specific eye movement indicators such as the number of fixation points (equivalent to the number of first fixation points in the above embodiment), the duration of fixation points (equivalent to the duration of each first fixation point in the above embodiment) and the fixation point coordinates (equivalent to the position information of each first fixation point in the above embodiment).

[0152] Step 4: For each user ID's eye movement index data, based on the conversion relationship between eye movement index and aesthetic evaluation index, obtain the multi-level aesthetic evaluation indexes such as the proportion, purity, suitability and novelty of a solution for all users. The specific calculation formula is as follows:

[0153] (1) Purity pur. Purity indicates the number of elements. Fewer elements mean higher purity. The number of fixations in eye tracking data reflects the number of elements. Since the subjects have a high probability of seeing each element, the more elements there are, the higher the number of fixations. Purity pur can be achieved using formula (9):

[0154]

[0155] Among them, N F Indicates the number of fixation points.

[0156] (2) Proportion pro: In a unit of time, due to the similarity of visual inertia, the eyes will be attracted by the element with the best proportion. Therefore, the greater the variance of the duration of each fixation point, the lower its proportion. The proportion can be achieved by formula (10):

[0157]

[0158] Among them, σF It represents the variance of the duration of each fixation point (the larger the variance, the more the data deviates from the average value of the data, which means that the data is erratic).

[0159] (3) Contrast C. Contrast is inversely proportional to purity and specific gravity. When the two increase, they will have a significant impact on the contrast. The contrast can be achieved by formula (11):

[0160]

[0161] (4) Aesthetic value B. In addition to describing the elements, the total fixation time also reflects the user's aesthetic taste. Too short indicates that it is unattractive, and too long may indicate that the user is confused about it. When calculating, when there are two or more main elements in the image, it should be divided by the corresponding number of elements. When the contrast is half of the average total fixation time (the average value of all users for a single solution), the aesthetic value is the highest, that is, C / T = 0.5. When C / T < 0.5 or C / T > 0.5, the aesthetic value decreases in a quadratic function relationship with C / T. The aesthetic value can be achieved using formula (12):

[0162]

[0163] (5), suitability A and novelty N. Suitability and novelty are related to time and function, and a reference template is required for calculation. The suitability template (equivalent to the standard image in the above embodiment) can be derived from a well-known and excellent product in a certain category of products, while the novelty area should indicate the non-common elements of known products. The suitability template shows the concentrated area of ​​the distribution of gaze points in the best product, and the novelty area is the area where the gaze points are more concentrated in each product design scheme. These areas can be fitted into elliptical areas, the center of which is the average value of all gaze point coordinates, and the radius is the standard deviation of the X and Y coordinates. Based on these elliptical areas, the distribution law of gaze points can be obtained: the gaze points are concentrated in areas with greater visual stimulation. The elliptical area can be implemented by formula (13) and formula (14):

[0164]

[0165]

[0166] Where C is the center of the ellipse, is the average value of the horizontal coordinates of all fixation points, is the average value of the ordinates of all fixation points, R x With R y is the radius of the ellipse, σ x is the standard deviation of the horizontal coordinates of all fixation points, σ y is the standard deviation of the ordinates of all fixation points.

[0167] In some embodiments, suitability and novelty can be implemented according to formula (15) and formula (16), respectively:

[0168]

[0169]

[0170] Among them, A is the suitability, N A To represent the number of fixations in the overlapped part of area N and area A, area N represents the coordinate area of ​​all solutions, area A represents the coordinate area of ​​the existing design solution, and area N T is the total number of fixations; N is the novelty, N N represents the number of fixations in the non-overlapping portion of area N and area A.

[0171] Step 5, the data processing device 505 calculates the higher level aesthetic evaluation index such as contrast and aesthetic value from the basic index according to the established multi-level evaluation mathematical model, and finally calculates the quantitative aesthetic value of each scheme. The aesthetic value is realized according to formula (17):

[0172] Aes=Ae NB ﹣e NBA +1 formula (17);

[0173] Among them, Aes is the aesthetic value, B is the beauty value, N is the novelty, and A is the suitability.

[0174] The final calculated aesthetic value Aes is between 0 and 1.

[0175] In step 6, the data processing device 505 sorts the final calculated values ​​from high to low as a quantitative index standard for measuring the aesthetics of a single interface. After the designer exports it from the device, it is used as a quantitative reference for horizontal comparison, and the best design solution is selected based on other factors such as cost and design style.

[0176] The present application embodiment provides a device for determining image aesthetics. Figure 6 A schematic diagram of the structure of an image aesthetics determination device 600 provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the device includes: an acquisition unit 601, a first determination unit 602, a second determination unit 603 and a third determination unit 604, wherein:

[0177] An acquisition unit 601 is used to acquire eye movement data obtained by at least one user viewing an image to be tested; the eye movement data includes the number of first fixation points, the duration of each first fixation point, and the position information of each first fixation point on the image to be tested;

[0178] A first determining unit 602 is used to determine the aesthetic parameter of the image to be measured based on the number of the first fixation points and the duration of each of the first fixation points;

[0179] A second determining unit 603 is used to determine a style parameter of the image to be tested based on the number of the first fixation points and the position information of each of the first fixation points; the style parameter is used to characterize the degree of correlation between the image to be tested and a standard image;

[0180] The third determining unit 604 is configured to determine the aesthetic parameters of the image to be tested based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

[0181] In some embodiments, the first determination unit 602 is further used to determine the contrast parameters of the image to be tested based on the number of the first fixation points and the duration of each of the first fixation points; and to determine the aesthetic parameters of the image to be tested based on the contrast parameters of the image to be tested and the duration of each of the first fixation points.

[0182] In some embodiments, the first determination unit 602 is further used to determine the purity parameter of the image to be tested based on the number of the first fixation points; determine the density parameter of the image to be tested based on the duration of each of the first fixation points; and determine the contrast parameter of the image to be tested based on the purity parameter of the image to be tested and the density parameter of the image to be tested.

[0183] In some embodiments, the first determination unit 602 is further used to determine an average gaze duration based on the duration of each of the first gaze points; and determine an aesthetic parameter of the image to be measured based on a ratio of a contrast parameter of the image to be measured to the average gaze duration.

[0184] In some embodiments, the second determination unit 603 is further used to determine, based on the position information of each of the first gaze points, a first area on which the user is paying attention on the image to be tested; based on the position information of each of the second gaze points on the standard image, to determine a second area on which the user is paying attention on the standard image; the second gaze point is a gaze point obtained by at least one of the users when viewing the standard image; and based on the first area, the second area, the position information of each of the first gaze points, the number of the first gaze points and the number of the second gaze points, to determine the style parameters of the image to be tested.

[0185] In some embodiments, the style parameters include suitability parameters; the second determination unit 603 is also used to determine the overlapping area between the first area and the second area; based on the position information of each of the first gaze points, determine the number of third gaze points located in the overlapping area; and determine the ratio of the number of the third gaze points to the sum of the number of the first gaze points and the number of the second gaze points as the suitability parameter.

[0186] In some embodiments, the style parameters also include novelty parameters; the second determination unit 603 is also used to determine the non-overlapping area between the first area and the second area; based on the position information of each of the first gaze points, determine the number of fourth gaze points located in the non-overlapping area; and determine the ratio of the number of the fourth gaze points to the sum of the number of the first gaze points and the number of the second gaze points as the novelty parameter.

[0187] In some embodiments, the third determination unit 604 is further used to determine the product of the aesthetic parameters of the image to be tested and the novelty parameters of the image to be tested as the first value of the image to be tested; determine the product of the aesthetic parameters of the image to be tested, the novelty parameters of the image to be tested, and the suitability parameters of the image to be tested as the second value of the image to be tested; and determine the aesthetic parameters of the image to be tested based on the difference between the product of the first numerical power of the natural constant and the suitability parameter and the second numerical power of the natural constant.

[0188] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided in the embodiment of the present application can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0189] It should be noted that in the embodiments of the present application, if the above-mentioned image aesthetics determination method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiments of the present application are not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.

[0190] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.

[0191] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code is run in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method.

[0192] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0193] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.

[0194] The present application embodiment provides a computer device, Figure 7 FIG. 7 is a schematic diagram of the structure of a computer device 700 provided in an embodiment of the present application. The computer device may be the image aesthetics determination device in the above embodiment. Figure 7 As shown, the device includes: a processor 701, a communication interface 702 and a memory 703, wherein:

[0195] The processor 701 generally controls the overall operation of the computer device 700, and the overall operation may be to implement the image aesthetics determination method provided in the embodiment of the present application, for example, Figures 1 to 4 The method shown.

[0196] The communication interface 702 enables the computer device to communicate with other terminals or servers through a network.

[0197] The memory 703 is configured to store instructions and applications executable by the processor 701, and can also cache data to be processed or processed by the processor 701 and each module in the computer device 700 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission can be performed between the processor 701, the communication interface 702, and the memory 703 through the bus 704.

[0198] The embodiment of the present application provides a computer program product or a computer program, which includes computer instructions stored in a readable storage medium. A processor of a computer device reads the computer instructions from the readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned image aesthetics determination method of the embodiment of the present application.

[0199] The embodiment of the present application provides a readable storage medium storing executable instructions, wherein the executable instructions are stored. When the executable instructions are executed by a processor, the processor will execute the method for determining based on image aesthetics provided by the embodiment of the present application, for example, Figures 1 to 4 The method shown.

[0200] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0201] The processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that the electronic device that implements the functions of the processor may also be other, and the embodiments of the present application are not specifically limited.

[0202] The above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM) and the like; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0203] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.

[0204] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0205] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0206] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0207] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0208] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0209] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0210] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for determining image aesthetics, characterized in that: include: Acquire eye movement data obtained by at least one user viewing the image to be tested; the eye movement data includes the number of first fixation points, the duration of each of the first fixation points, and the position information of each of the first fixation points on the image to be tested; Determining the aesthetic parameter of the image to be measured based on the number of the first gaze points and the duration of each of the first gaze points; Determining the style parameter of the image to be tested based on the number of the first gaze points and the position information of each of the first gaze points; The style parameter is used to characterize the degree of correlation between the image to be tested and the standard image; The aesthetic parameters of the image to be tested are determined based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

2. The method according to claim 1, characterized in that The step of determining the aesthetic parameter of the image to be measured based on the number of the first gaze points and the duration of each of the first gaze points includes: Determining a contrast parameter of the image to be tested based on the number of the first fixation points and the duration of each of the first fixation points; the contrast parameter is used to characterize the visual difference between individual elements in the image to be tested; Based on the contrast parameter of the image to be tested and the duration of each first fixation point, an aesthetic parameter of the image to be tested is determined.

3. The method according to claim 2, characterized in that The determining the contrast parameter of the image to be measured based on the number of the first fixation points and the duration of each of the first fixation points includes: Determining a purity parameter of the image to be tested based on the number of the first fixation points; Determining a weight parameter of the image to be measured based on the duration of each of the first gaze points; Based on the purity parameter of the image to be tested and the specific gravity parameter of the image to be tested, a contrast parameter of the image to be tested is determined.

4. The method according to claim 2, characterized in that: The step of determining the aesthetic parameter of the image to be tested based on the contrast parameter of the image to be tested and the duration of each first fixation point includes: Determine an average fixation duration based on the duration of each of the first fixation points; Based on the ratio of the contrast parameter of the image to be tested to the average gaze duration, the aesthetic parameter of the image to be tested is determined.

5. The method according to any one of claims 1 to 4, characterized in that: The determining the style parameter of the image to be tested based on the number of the first gaze points and the position information of each of the first gaze points includes: Based on the position information of each of the first gaze points, determining at least one first area of ​​the user's attention on the image to be tested; Based on the position information of each second fixation point on the standard image, determine the second area that at least one user pays attention to on the standard image; the second fixation point is a fixation point obtained by at least one user when viewing the standard image; based on the first area, the second area, the position information of each of the first fixation points, the number of the first fixation points and the number of the second fixation points, determine the style parameters of the image to be tested.

6. The method according to claim 5, characterized in that The style parameter includes a suitability parameter; and determining the style parameter of the image to be tested based on the first area, the second area, the position information of each of the first gaze points, the number of the first gaze points, and the number of the second gaze points includes: determining an overlapping area between the first area and the second area; Determine the number of third gaze points located in the overlapping area based on the position information of each of the first gaze points; The ratio of the number of the third fixation points to the sum of the number of the first fixation points and the number of the second fixation points is determined as a suitability parameter.

7. The method according to claim 5, characterized in that The style parameter also includes a novelty parameter; determining the style parameter of the image to be tested based on the first area, the second area, the position information of each of the first gaze points, the number of the first gaze points, and the number of the second gaze points includes: determining a non-overlapping area between the first area and the second area; Determine the number of fourth gaze points located in the non-overlapping area based on the position information of each of the first gaze points; The ratio of the number of the fourth fixation points to the sum of the number of the first fixation points and the number of the second fixation points is determined as a novelty parameter.

8. The method according to any one of claims 1 to 4, characterized in that: The style parameters include a suitability parameter and a novelty parameter; the step of determining the aesthetic parameters of the image to be tested based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested includes: Determine a product of the aesthetic parameter of the image to be tested and the novelty parameter of the image to be tested as a first value of the image to be tested; Determine the product of the aesthetic parameter of the image to be tested, the novelty parameter of the image to be tested, and the suitability parameter of the image to be tested as a second value of the image to be tested; The aesthetic parameter of the image to be measured is determined based on the difference between the product of the first numerical power of the natural constant and the suitability parameter and the second numerical power of the natural constant.

9. An image aesthetics determination device, characterized in that: include: an acquisition unit, configured to acquire eye movement data obtained by at least one user viewing the image to be tested; the eye movement data comprising the number of first fixation points, the duration of each of the first fixation points, and the position information of each of the first fixation points on the image to be tested; A first determining unit, configured to determine the aesthetic parameter of the image to be measured based on the number of the first fixation points and the duration of each of the first fixation points; a second determining unit, configured to determine a style parameter of the image to be tested based on the number of the first gaze points and position information of each of the first gaze points; The style parameter is used to characterize the degree of correlation between the image to be tested and the standard image; The third determining unit is used to determine the aesthetic parameters of the image to be tested based on the aesthetic parameters of the image to be tested and the style parameters of the image to be tested.

10. An image aesthetics determination device, characterized in that include: A memory for storing executable instructions; A processor, configured to implement the method according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images