CN108009273B - Image display method, image display device and computer-readable storage medium - Google Patents

Image display method, image display device and computer-readable storage medium Download PDF

Info

Publication number
CN108009273B
CN108009273B CN201711376442.6A CN201711376442A CN108009273B CN 108009273 B CN108009273 B CN 108009273B CN 201711376442 A CN201711376442 A CN 201711376442A CN 108009273 B CN108009273 B CN 108009273B
Authority
CN
China
Prior art keywords
image
images
ball
display
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711376442.6A
Other languages
Chinese (zh)
Other versions
CN108009273A (en
Inventor
龙飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiaomi Mobile Software Co Ltd
Original Assignee
Beijing Xiaomi Mobile Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Xiaomi Mobile Software Co Ltd filed Critical Beijing Xiaomi Mobile Software Co Ltd
Priority to CN201711376442.6A priority Critical patent/CN108009273B/en
Publication of CN108009273A publication Critical patent/CN108009273A/en
Application granted granted Critical
Publication of CN108009273B publication Critical patent/CN108009273B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/54—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
    • G06F16/168—Details of user interfaces specifically adapted to file systems, e.g. browsing and visualisation, 2d or 3d GUIs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/04815—Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The present disclosure relates to an image display method, an image display device and a computer readable storage medium, and relates to the technical field of information processing, wherein the method comprises the following steps: acquiring a plurality of images; the surface of the image ball includes a plurality of display positions, different ones of the plurality of images being displayed at different ones of the plurality of display positions. Because different images in the images can be displayed on the display positions of the image ball in a concentrated manner, when a user browses the images, the images can be conveniently browsed integrally through the image ball, and visual experience is more intuitive for the user, so that the user can more quickly find the interested images from the images. Moreover, when the user browses the images, the browsing of the plurality of images can be realized by operating the image ball, and compared with the prior art that the plurality of images are tiled and displayed in a plurality of display pages, the user browses the plurality of images by vertically rolling the display pages, so that the operation distance is shortened.

Description

Image display method, image display device and computer-readable storage medium
Technical Field
The present disclosure relates to the field of information processing technologies, and in particular, to an image display method and apparatus, and a computer-readable storage medium.
Background
Currently, terminals such as smart phones, tablet computers, and the like have an image display function by which the terminal can display a plurality of stored images. The stored images may be images in an album. In the related art, when the terminal displays the stored multiple images, the terminal may sequentially display the stored multiple images in the image display page in the form of thumbnails according to the order of the stored time.
Disclosure of Invention
In order to overcome the problem of poor display effect when thumbnails of images are displayed according to the sequence of stored time in the related art, the present disclosure provides an image display method, an image display apparatus, and a computer-readable storage medium.
According to a first aspect of embodiments of the present disclosure, there is provided an image display method, the method including:
acquiring a plurality of images;
displaying an image ball, a surface of the image ball including a plurality of display positions, different ones of the plurality of images being displayed on different ones of the plurality of display positions.
Optionally, the display image ball includes:
determining display positions of the images on the surface of the image ball, wherein the display positions are obtained based on similar image clustering analysis on the images, and the distance between the display positions of the images is in negative correlation with the similarity between the images;
displaying the image ball based on the plurality of images at display positions of a surface of the image ball.
Optionally, the determining the display positions of the plurality of images on the surface of the image ball includes:
acquiring a high-dimensional feature vector of each image in the plurality of images through a neural network model;
performing dimensionality reduction on the high-dimensional feature vector of each image in the plurality of images to obtain the position coordinates of each image in the plurality of images in a low-dimensional coordinate system;
and determining the display positions of the images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
Optionally, each of the plurality of images corresponds to a position coordinate in a low-dimensional coordinate system;
the determining the display positions of the plurality of images on the surface of the image ball comprises:
determining a number of positions of a plurality of display positions included in a surface of the image sphere;
when the number of the positions is smaller than the number of the images of the plurality of images, on the basis of the position coordinates of each image in the low-dimensional coordinate system, the images of the plurality of images, the number of which is the number of the positions, are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball, and the display positions of each image in the images, the number of which is the number of the positions, on the surface of the image ball are obtained.
Optionally, the one-to-one correspondence of the images with the number of positions in the plurality of images to the plurality of display positions included in the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system includes:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball in a one-to-one manner;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
Optionally, the display image ball includes:
determining at least one classification label corresponding to each image in the plurality of images;
and displaying the image ball based on at least one classification label corresponding to each image in the plurality of images.
Optionally, the displaying the image ball based on at least one classification label corresponding to each image in the plurality of images includes:
determining a plurality of target classification labels based on at least one classification label corresponding to each image in the plurality of images, wherein each target classification label in the plurality of target classification labels corresponds to at least one image;
and displaying a plurality of image balls based on the plurality of target classification labels, wherein images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
Optionally, the determining a plurality of target classification labels based on at least one classification label corresponding to each of the plurality of images includes:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as the plurality of target classification labels.
Optionally, after the displaying the image ball, the method further includes:
when a first preset operation for the image ball is detected, displaying an image which is not displayed on the image ball.
Optionally, after the displaying the image ball, the method further includes:
when a preset instruction for a target image ball is detected, updating the position number of a plurality of display positions included in the surface of the target image ball;
updating the image displayed on the surface of the target image sphere based on the updated number of positions.
Optionally, after the displaying the image ball, the method further includes:
when a sliding operation for a target image ball is detected, the target image ball is rotated based on the sliding operation.
Optionally, the rotating the target image ball based on the sliding operation includes:
detecting a sliding speed of the sliding operation;
determining a rotation speed based on the sliding speed, and rotating the target image ball based on the rotation speed; or, determining a rotation angle based on the sliding speed, and rotating the target image ball by the rotation angle.
Optionally, the rotating the target image ball based on the sliding operation includes:
detecting a sliding direction of the sliding operation;
rotating the target image ball in the sliding direction while the sliding operation is maintained;
when the sliding operation is detected to be finished, stopping rotating the target image ball.
Optionally, after the displaying the image ball, the method further includes:
displaying a target image in a first preset display area of a current page, wherein the first preset display area is an area outside an area for displaying the image ball; alternatively, the first and second electrodes may be,
displaying a target image in a preset floating window with preset transparency, wherein the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
setting the transparency of a target image to be a preset transparency, and performing suspension display on the set target image, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball;
wherein the target image is an image located at a center position of the image ball or an image selected by a user on the image ball.
Optionally, after the displaying the image ball, the method further includes:
acquiring the associated information of a target image;
and displaying the associated information in a second preset display area of the current page.
Optionally, each image in the plurality of images corresponds to at least one classification label, and the association information includes at least one classification label corresponding to the target image;
after the displaying the associated information in a second preset display area of the current page, the method further includes:
when the selection operation of any one classification label A in at least one classification label displayed in the second preset display area is detected, jumping to a secondary page;
and displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
According to a second aspect of the embodiments of the present disclosure, there is provided an image display apparatus, the apparatus including:
the acquisition module is used for acquiring a plurality of images;
the display device comprises a first display module and a second display module, wherein the first display module is used for displaying an image ball, the surface of the image ball comprises a plurality of display positions, and different images in the images are displayed on different display positions in the display positions.
Optionally, the first display module includes:
the first determining unit is used for determining the display positions of the images on the surface of the image ball, the display positions are obtained based on similar image clustering analysis on the images, and the distance between the display positions of the images and the similarity between the images are in negative correlation;
a first display unit configured to display the image ball at display positions of a surface of the image ball based on the plurality of images.
Optionally, the first determining unit includes:
the acquisition subunit is used for acquiring the high-dimensional characteristic vector of each image in the plurality of images through a neural network model;
the processing subunit is configured to perform dimensionality reduction processing on the high-dimensional feature vector of each of the multiple images to obtain a position coordinate of each of the multiple images in a low-dimensional coordinate system;
the first determining subunit is used for determining the display positions of the images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
Optionally, each of the plurality of images corresponds to a position coordinate in a low-dimensional coordinate system;
the first determination unit is configured to:
determining a number of positions of a plurality of display positions included in a surface of the image sphere;
when the number of the positions is smaller than the number of the images of the plurality of images, on the basis of the position coordinates of each image in the low-dimensional coordinate system, the images of the plurality of images, the number of which is the number of the positions, are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball, and the display positions of each image in the images, the number of which is the number of the positions, on the surface of the image ball are obtained.
Optionally, the first determining unit is configured to:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball in a one-to-one manner;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
Optionally, the first display module includes:
the second determining unit is used for determining at least one classification label corresponding to each image in the plurality of images;
and the second display unit is used for displaying the image ball based on at least one classification label corresponding to each image in the plurality of images.
Optionally, the second display unit includes:
a second determining subunit, configured to determine, based on at least one classification label corresponding to each of the plurality of images, a plurality of target classification labels, where each of the plurality of target classification labels corresponds to at least one image;
and the display subunit is used for displaying a plurality of image balls based on the plurality of target classification labels, wherein images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
Optionally, the second determining subunit is specifically configured to:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as the plurality of target classification labels.
Optionally, the apparatus further comprises:
and the second display module is used for displaying the image which is not displayed on the image ball when the first preset operation aiming at the image ball is detected.
Optionally, the apparatus further comprises:
the updating module is used for updating the position number of a plurality of display positions included in the surface of the target image ball when a preset instruction for the target image ball is detected;
the updating module is further used for updating the image displayed on the surface of the target image ball based on the updated position number.
Optionally, the apparatus further comprises:
and the rotating module is used for rotating the target image ball based on the sliding operation when the sliding operation aiming at the target image ball is detected.
Optionally, the rotation module comprises:
a first detection unit for detecting a sliding speed of the sliding operation;
a first rotation unit for determining a rotation speed based on the sliding speed and rotating the target image ball based on the rotation speed; or, the second determination unit is configured to determine a rotation angle based on the sliding speed, and rotate the target image ball by the rotation angle.
Optionally, the rotation module comprises:
a second detection unit for detecting a sliding direction of the sliding operation;
a second rotating unit configured to rotate the target image ball in the sliding direction in a process of the sliding operation holding;
a stopping unit configured to stop rotating the target image ball when the end of the sliding operation is detected.
Optionally, the apparatus further comprises:
the third display module is used for displaying the target image in a first preset display area of the current page, wherein the first preset display area is an area outside an area for displaying the image ball; alternatively, the first and second electrodes may be,
the third display module is used for displaying the target image in a preset floating window with preset transparency, and the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
the third display module is used for setting the transparency of the target image to be a preset transparency and displaying the set target image in a suspended manner, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball;
wherein the target image is an image located at a center position of the image ball or an image selected by a user on the image ball.
Optionally, the apparatus further comprises:
the acquisition module is used for acquiring the associated information of the target image;
and the fourth display module is used for displaying the associated information in a second preset display area of the current page.
Optionally, each image in the plurality of images corresponds to at least one classification label, and the association information includes at least one classification label corresponding to the target image;
the device further comprises:
the skipping module is used for skipping to a secondary page when the selection operation of any one of the at least one classification label A displayed in the second preset display area is detected;
and the fifth display module is used for displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
According to a third aspect of the embodiments of the present disclosure, there is provided an image display apparatus, the apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the steps of any one of the methods of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon instructions which, when executed by a processor, implement the steps of any one of the methods of the first aspect described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product which, when run on a computer, causes the computer to perform the steps of any one of the methods of the first aspect described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: a plurality of images is acquired, an image ball is displayed, a surface of the image ball includes a plurality of display positions, and different ones of the plurality of images are displayed at different ones of the plurality of display positions. Because different images in the images can be displayed on the display positions of the image ball in a concentrated manner, when a user browses the images, the images can be conveniently browsed integrally through the image ball, and visual experience is more intuitive for the user, so that the user can more quickly find the interested images from the images. Moreover, the plurality of images can be displayed on the surface of the image ball in a concentrated manner, so that when a user browses the images, the plurality of images can be browsed by operating the image ball.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a flowchart illustrating an image display method according to an exemplary embodiment.
Fig. 2A is a flowchart illustrating an image display method according to an exemplary embodiment.
Fig. 2B is a schematic diagram of projecting a preset number of images of multiple images onto a square canvas based on the position coordinates of each image according to an embodiment of the present disclosure.
Fig. 2C is a schematic diagram of an image display interface according to an embodiment of the disclosure.
Fig. 3 is a flow chart illustrating an image display method according to an exemplary embodiment.
Fig. 4A is a block diagram illustrating an image display apparatus according to an exemplary embodiment.
FIG. 4B is a block diagram illustrating a first display module according to an exemplary embodiment.
Fig. 4C is a block diagram illustrating another first display module according to an example embodiment.
Fig. 5 is a block diagram illustrating an image display apparatus according to an exemplary embodiment.
Detailed Description
To make the objects, technical solutions and advantages of the present disclosure more apparent, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.
Before explaining the embodiments of the present disclosure in detail, an application scenario related to the embodiments of the present disclosure will be described.
Currently, terminals such as smart phones, tablet computers, and the like are widely used in daily life, and a user can browse various images displayed on the terminals. The terminal can be provided with an album or gallery application, and the terminal can display a plurality of stored images through the album or gallery application. Alternatively, the terminal may display a web page through an installed browser and display a plurality of images in the currently displayed web page. The image display method provided by the embodiment of the disclosure can be applied to the above-mentioned scene to display a plurality of images stored in the terminal or a plurality of images in the currently displayed webpage.
It should be noted that, when a plurality of images are displayed in a currently displayed webpage, the server may perform the step of performing cluster analysis on the plurality of images and determining the display positions of the plurality of images on the surface of the image ball based on the result of the cluster analysis, or classifying each of the plurality of images to determine at least one classification tag corresponding to each image, and then, the server transmits the display positions of the plurality of images on the surface of the image ball or the at least one classification tag corresponding to each image in the plurality of images to the terminal, and the terminal may display the plurality of images in the currently displayed webpage through the image ball according to the display positions of the plurality of images on the surface of the image ball or the at least one classification tag corresponding to each image. Of course, the above-mentioned operations executed by the server may be performed by the terminal, that is, the terminal may perform the cluster analysis or classification of the plurality of images independently, and then display the plurality of images included in the currently displayed web page through the image ball. In the following embodiments, the image display method provided by the embodiments of the present disclosure will be described mainly with a terminal as an execution subject.
In addition, the above are only two exemplary application scenarios given by the embodiment of the present disclosure, and in practical applications, there may be other scenarios displaying multiple images.
Next, an image display method provided by an embodiment of the present disclosure will be described.
Fig. 1 is a flowchart illustrating an image display method according to an exemplary embodiment, which may be used in a terminal, as shown in fig. 1, including the steps of:
in step 101, a plurality of images are acquired.
In step 102, an image ball is displayed, a surface of the image ball including a plurality of display positions, different ones of the plurality of images being displayed at different ones of the plurality of display positions.
In the disclosed embodiment, the terminal may acquire a plurality of images, display an image ball, the surface of the image ball including a plurality of display positions, different images of the plurality of images being displayed on different display positions of the plurality of display positions. Because different images in the images can be displayed on the display positions of the image ball in a concentrated manner, when a user browses the images, the images can be conveniently browsed integrally through the image ball, and visual experience is more intuitive for the user, so that the user can more quickly find the interested images from the images. Moreover, the plurality of images can be displayed on the surface of the image ball in a concentrated manner, so that when a user browses the images, the plurality of images can be browsed by operating the image ball.
In the disclosed embodiment, after the image ball is displayed, the terminal may implement interaction with the user in a variety of alternative ways as follows.
Optionally, after the image ball is displayed, the method further includes:
when a first preset operation for the image ball is detected, an image which is not displayed on the image ball is displayed.
Optionally, after the image ball is displayed, the method further includes:
when a preset instruction for the target image ball is detected, the number of positions of a plurality of display positions included on the surface of the target image ball is updated, the preset instruction is triggered by a second preset operation or is a voice instruction, and the target image ball can be any image ball;
the image displayed on the surface of the target image ball is updated based on the updated number of positions.
Optionally, after the image ball is displayed, the method further includes:
when a sliding operation for a target image ball is detected, the target image ball is rotated based on the sliding operation, and the target image ball can be any image ball.
Optionally, rotating the target image ball based on a sliding operation includes:
detecting a sliding speed of the sliding operation;
determining a rotation speed based on the sliding speed, and rotating the target image ball based on the rotation speed; alternatively, the rotation angle is determined based on the sliding speed, and the target image ball is rotated by the rotation angle.
Optionally, rotating the target image ball based on a sliding operation includes:
detecting a sliding direction of the sliding operation;
rotating the target image ball in the sliding direction in the sliding operation holding process;
when the end of the sliding operation is detected, the rotation of the target image ball is stopped.
Optionally, after the image ball is displayed, the method further includes:
displaying the target image in a first preset display area of the current page, wherein the first preset display area is an area outside an area for displaying an image ball; alternatively, the first and second electrodes may be,
displaying a target image in a preset floating window with preset transparency, wherein the center of the preset floating window is superposed with the center of an image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
setting the transparency of the target image to be a preset transparency, and performing suspension display on the set target image, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball;
wherein the target image is an image located at the center position of the image ball or an image selected by the user on the image ball.
Optionally, after the image ball is displayed, the method further includes:
acquiring the associated information of a target image;
and displaying the associated information in a second preset display area of the current page.
Optionally, each image in the plurality of images corresponds to at least one classification label, and the associated information includes at least one classification label corresponding to the target image;
after the associated information is displayed in a second preset display area of the current page, the method further comprises the following steps:
when the selection operation of any one classification label A in at least one classification label displayed in a second preset display area is detected, jumping to a secondary page;
and displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
Optionally, an image ball is displayed comprising:
determining the display positions of the plurality of images on the surface of the image ball, wherein the display positions are obtained based on similar image clustering analysis of the plurality of images, and the distance between the display positions of the images is in negative correlation with the similarity between the images;
the image ball is displayed at the display position on the surface of the image ball based on the plurality of images.
Optionally, determining the display positions of the plurality of images on the surface of the image ball comprises:
acquiring a high-dimensional feature vector of each image in a plurality of images through a neural network model;
performing dimensionality reduction on the high-dimensional feature vector of each image in the plurality of images to obtain the position coordinates of each image in the plurality of images in a low-dimensional coordinate system;
and determining the display positions of the plurality of images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
Optionally, each of the plurality of images corresponds to a position coordinate in the low-dimensional coordinate system;
determining the display positions of the plurality of images on the surface of the image ball, comprising:
determining a number of positions of a plurality of display positions included in a surface of the image ball;
when the number of the positions is smaller than that of the images of the plurality of images, the images of which the number is the number of the positions in the plurality of images are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball on the basis of the position coordinates of each image in the low-dimensional coordinate system in the plurality of images, and the display positions of each image in the images of which the number is the number of the positions on the surface of the image ball are obtained.
Optionally, the one-to-one correspondence of the images with the number of positions in the plurality of images to the plurality of display positions included in the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system includes:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball one to one;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
Optionally, an image ball is displayed comprising:
determining at least one classification label corresponding to each image in the plurality of images;
and displaying the image ball based on at least one classification label corresponding to each image in the plurality of images.
Optionally, displaying the image ball based on at least one classification label corresponding to each of the plurality of images, includes:
determining a plurality of target classification labels based on at least one classification label corresponding to each image in the plurality of images, wherein each target classification label in the plurality of target classification labels corresponds to at least one image;
and displaying a plurality of image balls based on the plurality of target classification labels, wherein images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
Optionally, determining a plurality of target classification labels based on at least one classification label corresponding to each of the plurality of images includes:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
and determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as a plurality of target classification labels.
All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present disclosure, and the embodiments of the present disclosure are not described in detail again.
In the embodiment of the present disclosure, the terminal may display the image ball based on the result of the cluster analysis on the plurality of images, or may display the image ball based on the result of the classification on the plurality of images. In the embodiment of the present disclosure, the operation of performing cluster analysis on a plurality of images or classifying a plurality of images may be performed by a terminal or a server. The first method, i.e., the method for displaying the image ball based on the result of the multi-image cluster analysis, will be described with reference to fig. 2A-2C.
Fig. 2A is a flowchart illustrating an image display method according to an exemplary embodiment, which may be applied to a terminal, as shown in fig. 2A, and which may include the steps of:
in step 201, a plurality of images are acquired.
In the embodiment of the present disclosure, the plurality of images may be images stored in the terminal, or may be a plurality of images included in a webpage currently displayed by the terminal.
The terminal can acquire a plurality of images stored in the terminal when detecting that an installed gallery application or an application for displaying the stored images, such as an album application, is started. Alternatively, the terminal may acquire a plurality of images when it is detected that the acquired currently displayed web page includes the plurality of images.
Alternatively, for the stored multiple images, the terminal may acquire the multiple images at any time before displaying the multiple images, and analyze the multiple images through step 202.
In step 202, similar image clustering analysis is performed on the plurality of images to obtain a clustering analysis result.
After the plurality of images are acquired, the terminal can perform similar image clustering analysis on the plurality of images to obtain a clustering analysis result.
The terminal can obtain the high-dimensional feature vector of each image in the multiple images through the neural network model, and the obtained high-dimensional feature vector is determined as a cluster analysis result.
The terminal may use the image a as an input of the neural network model for any image a of the plurality of images. Generally, the neural network model includes convolutional layers and fully-connected layers, where the number of fully-connected layers may be generally three, and three fully-connected layers may serve as the last three layers of the neural network model. Through the convolution layer and the full connection layer included in the neural network model, feature extraction can be carried out on the image A. The terminal can obtain output values of all neurons of the fully connected layer of the penultimate layer of the neural network model, and concatenate the output values to form the high-dimensional feature vector of the image A. Wherein the high-dimensional feature vector may have a dimension between 512 and 4096 dimensions. In addition, in the embodiment of the present disclosure, the Neural Network model may be a CNN (Convolutional Neural Network) model, for example, the Neural Network model may be an ImageNet model, an AlexNet model, or the like.
It should be noted that, the above is only an exemplary cluster analysis method provided by the embodiment of the present disclosure, and optionally, in the embodiment of the present disclosure, the terminal may also extract a feature vector of each image, and perform cluster analysis on the multiple images through a K-means algorithm according to the feature of each image, so as to determine a position between the feature vector of each image and a cluster center in the multiple images, and determine the determined position between the feature vector of each image and the cluster center as a cluster analysis result.
In addition, the terminal may further cluster the plurality of images through other clustering algorithms to obtain a clustering analysis result, and the specific clustering algorithm is not limited in the embodiment of the present disclosure.
In step 203, based on the cluster analysis result, the display positions of the plurality of images on the surface of the image ball are determined.
In the embodiment of the disclosure, after the cluster analysis result is obtained, the terminal may determine the display positions of the multiple images on the surface of the image ball according to the cluster analysis result, wherein the cluster analysis result may represent the degree of similarity between the images, and therefore, the terminal may determine the display positions of the multiple images on the surface of the image ball according to the degree of similarity between the multiple images, where for any two images, the closer the display positions of the two images on the surface of the image ball are, the higher the degree of similarity between the two images is, that is, the distance between the display positions of the images is in negative correlation with the degree of similarity of the images.
Based on the above description, the clustering analysis result may be a high-dimensional feature vector of an image output by the neural network model, based on which, after the high-dimensional feature vector of each of the plurality of images is obtained, the terminal may perform dimension reduction processing on the high-dimensional feature vector of each of the plurality of images to obtain a position coordinate of each of the plurality of images in a low-dimensional coordinate system, and a distance between any two images in the plurality of images is used to indicate a similarity between the two images; after that, the terminal may determine the display positions of the plurality of images on the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system.
For any image A in the plurality of images, the terminal can perform dimensionality reduction processing on the high-dimensional feature vector of the image A through a principal component analysis method to obtain a low-dimensional feature vector, and the low-dimensional feature vector is used as the position coordinate of the image A in a low-dimensional coordinate system. The dimension of the low-dimensional feature vector may be two-dimensional or three-dimensional. For example, when the dimension of the low-dimensional feature vector is two-dimensional, it is assumed that the feature vector is [ x, y ], and in this case, x may be an abscissa of the image a in the two-dimensional coordinate system, and y may be an ordinate of the image a in the two-dimensional coordinate system. Similarly, when the dimension of the low-dimensional feature vector is three-dimensional, the feature vector can be used as the position coordinate of the image a in the three-dimensional coordinate system.
It should be noted that the low-dimensional coordinate system may be an arbitrary coordinate system in a low dimension, that is, assuming that the low-dimensional coordinate system is a two-dimensional coordinate system, the coordinate system may be a two-dimensional coordinate system established by taking an arbitrary point as an origin in two dimensions, but it should be noted that the position coordinates of each image determined by the above method are coordinates in the same low-dimensional coordinate system.
After the position coordinates of each of the plurality of images in the low-dimensional coordinate system are determined by the method, the terminal may determine the display positions of the plurality of images on the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system. Since the position coordinates are obtained by analyzing the high-dimensional feature vectors of the images by a principal component analysis method, the distance between any two images in the plurality of images can be used for indicating the similarity between the two images. That is, the closer the position coordinates of the two images are, the greater the similarity between the two images is.
Optionally, in this embodiment of the present disclosure, after acquiring the high-dimensional feature vector of each image through the neural network model, the terminal may further acquire and store a classification label of each image output by an output layer of the neural network model, where the output layer is usually the last fully connected layer, and each image may correspond to at least one classification label.
After the terminal determines the position coordinates of each of the plurality of images in the low-dimensional coordinate system, the terminal may determine the display position of each of the plurality of images on the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system.
The operation of the terminal determining the display positions of the multiple images on the surface of the image ball based on the position coordinates of each of the multiple images in the low-dimensional coordinate system may be: determining a number of positions of a plurality of display positions included in a surface of the image ball; when the number of the positions is smaller than that of the images of the plurality of images, the images of the plurality of images with the number of the positions are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball on the basis of the position coordinates of each image of the plurality of images in the low-dimensional coordinate system, and therefore the display positions of each image of the images with the number of the positions on the surface of the image ball are obtained.
In the embodiment of the present disclosure, the number of positions of the display position of the surface of the image ball may be fixed, that is, the number of images that can be displayed on the surface of the image ball is fixed. Alternatively, the number of positions of the display position of the surface of the image ball may also be determined in real time, that is, the terminal may determine the number of images displayed on the image ball in real time.
When the number of the positions is fixed, the terminal can acquire the number of the positions of the image ball, wherein the number of the positions can be a preset number of the positions, that is, the terminal can determine the display size of the image which is most suitable for the user to browse in advance according to the size of the image ball, so that the number of the images which can be displayed on the image ball is determined according to the display size of the image, that is, the number of the positions on the surface of the image ball, and thus, the images displayed on the surface of the image ball can be displayed in the size which is most suitable for the user to browse, and better visual experience can be brought to the user.
When the number of positions is determined in real time, the terminal may determine the number of positions of the display position of the surface of the image ball according to the image display size currently set by the user, or the terminal may determine the image display size according to a gesture operation of the user, thereby determining the number of positions of the display position of the surface of the image ball.
After determining the number of positions of the display positions of the surface of the image ball, the terminal may select a part of the image from the plurality of images to display based on the number of positions may be less than the number of images of the plurality of images, that is, the surface of the image ball may not be able to display the plurality of images at one time. In practical applications, the terminal may determine whether the number of the plurality of images is greater than the number of positions, and when the number of the plurality of images is greater than the number of positions, the terminal may select a reference image from the plurality of images based on the position coordinates of each image in the low-dimensional coordinate system, and determine the reference display position in the low-dimensional canvas as the display position of the reference image on the surface of the image ball. The dimension of the low-dimensional canvas is equal to that of the low-dimensional coordinate system, and a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball in a one-to-one mode. Thereafter, the terminal may select images of the number of remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determine the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
The terminal may select one reference image from the multiple images according to a distribution of the position coordinates of each of the multiple images in the low-dimensional coordinate system, where the reference image may be one image located at the center of a distribution range of the multiple images, may be one image with the smallest abscissa and/or ordinate in the multiple images, and may be one image with the largest abscissa and/or ordinate in the multiple images, that is, the reference image may be one image located at the leftmost end, the rightmost end, the uppermost edge, or the lowermost edge in the distribution range of the multiple images. Of course, the reference image may be any one of the plurality of images.
After selecting the reference image, the terminal may use the reference image as the first image in the low-dimensional canvas and project the reference image onto a reference display position of the low-dimensional canvas, where the reference display position is actually the display position of the reference image on the surface of the image ball. Then, the terminal may select images from the remaining plurality of images in order of decreasing distance between the position coordinate of each image in the remaining plurality of images and the position coordinate of the reference image, and sequentially project the selected images to the low-dimensional canvas where the reference image is located in order of decreasing distance between the selected images and the position coordinate of the reference image, thereby obtaining the low-dimensional canvas containing the images in the number of positions. Wherein each position in the low-dimensional canvas containing the images with the number of positions corresponds to a display position of the surface of the image ball, namely, the surface of the image ball is obtained by processing the low-dimensional canvas which is actually an expansion form of the surface of the image ball in a low-dimensional coordinate system.
Alternatively, when the number of the plurality of images is not greater than the number of the positions of the display positions of the surface of the image ball, the terminal may project the plurality of images one by one onto the plurality of display positions of the surface of the image ball based on the position coordinates of each of the plurality of images in the low-dimensional coordinate system. The terminal projects the multiple images one by one to the multiple display positions on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system in the multiple images, and the specific implementation manner may refer to the position coordinates of each image in the low-dimensional coordinate system, and corresponds each image to the multiple display positions included in the surface of the image ball one by one.
Alternatively, in the embodiment of the present disclosure, steps 202 and 203 may be performed by the server, in which case, after the server determines the display positions of the plurality of images on the surface of the image ball, the display positions of the plurality of images on the surface of the image ball may be transmitted to the terminal, and then the terminal may display the image ball based on the received display positions of the plurality of images on the surface of the image ball by the method in step 204.
In step 204, an image ball is displayed at the display position of the surface of the image ball based on the plurality of images.
After determining the display positions of the plurality of images on the surface of the image ball, the terminal may display each image on the corresponding display position of the surface of the image ball accordingly.
Based on the foregoing description, it can be known that the terminal can one-to-one correspond a plurality of images to the low-dimensional canvas, and based on this, after obtaining the low-dimensional canvas containing the images, the terminal can display the low-dimensional canvas as an image ball by adopting a perspective transformation method, that is, a 3D technique or a pseudo 3D technique, and accordingly, the images contained in the low-dimensional canvas are also displayed on different display positions on the surface of the image ball in a one-to-one correspondence manner.
Next, a specific implementation process of determining the display positions of the plurality of images on the surface of the image ball and displaying the image ball based on the determined display positions of the plurality of images on the surface of the image ball will be described by taking a two-dimensional coordinate system as an example, that is, the position coordinate of each image in the low-dimensional coordinate system is the position coordinate in the two-dimensional coordinate system.
Assuming that a cluster analysis result of 1000 images is obtained currently, that is, a high-dimensional feature vector of 1000 images is determined, the terminal may reduce the high-dimensional feature vector of each image into a two-dimensional vector, thereby obtaining a position coordinate of each image in a two-dimensional coordinate system. And the image sphere surface contains 900 display positions. In this case, the terminal needs to select 900 images from the 1000 images and display the 900 images on the 900 display positions of the image ball in a one-to-one correspondence.
As shown in fig. 2B, first, the terminal may select a reference image from the 1000 images, and assuming that the abscissa and the ordinate of the reference image are both smaller than those of the other 999 images, that is, the reference image is an image at the leftmost lower corner in the area where the 1000 images are distributed, the terminal may project the reference image a to the display position at the leftmost lower corner of the square canvas with 900 display positions, where the display position at the leftmost lower corner is actually the reference display position, that is, the display position of the reference image in the image ball. For convenience of explanation, in fig. 2B, one display position is identified by one small square. Thereafter, the terminal may determine three images B, C, D closest in distance from the position coordinates where the reference image a is located, and project images B, C, D onto three display positions adjacent to the reference image a, respectively, that is, as shown in fig. 2B, the images B, C, and D onto the display positions 1, 2, and 3 adjacent to the reference image a, respectively. Next, the terminal may continue to select five images closest to the reference image a from the remaining plurality of images and project the five images to five display positions adjacent to the display positions 1, 2, and 3, respectively, as indicated by the hatched portions in fig. 2B. And so on until 900 of the 1000 images are projected onto a square canvas with 900 display positions. Thereafter, the terminal may display a square canvas containing 900 images as one image ball through a 3D technology or a pseudo 3D technology.
Alternatively, after the image B, the image C, and the image D closest to the reference image a are projected onto the display positions 1, 2, and 3 adjacent to the reference image a, respectively, in the above-described projection process, the terminal may also project the remaining plurality of images in another manner. That is, the terminal may determine an image closest to the image B, the image C, and the image D, respectively, using the images as reference images, and display the determined images at corresponding adjacent positions. For example, as shown in fig. 2B, for image B, since there are two display positions adjacent to image B, the terminal may determine two images closest to image B among the remaining plurality of images and project the two images onto the two display positions adjacent to image B. For image C, since there are three display positions adjacent to image C, one of which is commonly adjacent to image B, the terminal can determine two images closest to image C among the remaining plurality of images and project the two images onto two image positions adjacent to image C but not adjacent to image B. Of course, the terminal may determine three images closest to the image C among the remaining plurality of images, determine distances between the images projected onto the display positions adjacent to both the images B and C and the image C, compare the four distances, display the three images closest to the image C at three positions adjacent to the image C if the distances between the images projected onto the display positions adjacent to both the images B and C are greater than the three distances closest to the image C, and otherwise, display two images among the remaining three images closest to the image C at the remaining two display positions adjacent to the image C while keeping the images projected onto the display positions adjacent to both the images B and C unchanged. For the image D, the processing method may refer to the processing methods of the images B and C described above. After the images at the display locations adjacent to images B, C and D have been determined, the projection of the remaining images may be processed as described above with reference to the method based on the most recently projected image onto the square canvas.
In practical applications, the terminal may also adopt other methods to correspond the images with the number of positions in the plurality of images to the plurality of display positions on the surface of the image ball one by one, which is not specifically limited by the embodiment of the present disclosure.
After displaying the image ball, the terminal may highlight the image at the center position of the image ball, wherein the terminal may realize the highlighting of the image at the center position of the image ball in several different ways.
The first mode is as follows: and displaying the target image in a first preset display area of the current page, wherein the first preset display area is an area outside the area for displaying the image ball.
Wherein the target image may be an image currently located at the center position of the image ball. The terminal may divide the current page into two display areas, where one display area is used for displaying the image ball, and the other display area, that is, the first preset display area, may be used for displaying the target image. It should be noted that, when the image located at the center position of the image ball is displayed in the first preset display area, the size of the image may be larger than the size of the image displayed on the surface of the image ball, so that the user can view the image more clearly. Wherein the image located at the center of the image ball may change with the rotation of the image ball.
Optionally, in this embodiment of the present disclosure, the target image may also be an image selected by the user on the image ball, in this case, the terminal may detect, in real time, a selection operation of the user on the image on the target image ball, and when the terminal detects the selection operation on a certain image on the target image ball, determine the image selected by the user as the target image, and display the target image in the first preset display area of the current page.
Further, after the terminal determines the image selected by the user as the target image, the image ball may be rotated according to the position of the target image displayed on the image ball, so that the target image is located at the center position of the rotated image ball, and at this time, the terminal may display the target image in the first preset display area of the current page.
The second mode is as follows: and displaying the target image in a preset floating window with preset transparency, wherein the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image.
In this implementation, the target image may be an image located at the center of the image ball, or may be any image selected by the user on the image ball.
When the target image is an image located at the center position of the image ball, after the image ball is displayed, the terminal may display a preset floating window on an upper layer of the image located at the center position of the image ball, where a size of the preset floating window may be larger than a size of the image located at the center position on the image ball, and then, the terminal may display the image located at the center position of the image ball in the preset floating window after being enlarged. Since the size of the preset floating window may be larger than the size of the image displayed on the surface of the image ball, in order to avoid blocking other images displayed on the surface of the lower image ball, the transparency of the preset floating window may be set to be the preset transparency.
When the target image is any one of the images on the image ball selected by the user, the terminal may detect the image selected by the user after displaying the image ball and determine the image selected by the user as the target image. And then, the terminal can acquire the target image and display the target image in a preset floating window of the image ball. Since the center of the preset floating window coincides with the center of the image ball, when the target image is not the image currently located at the center of the image ball, displaying the target image in the preset floating window may cause a blockage of the image located at the center of the image ball of the lower layer, and therefore, the terminal may set the transparency of both the preset floating window and the target image to the preset transparency.
Optionally, in this embodiment of the present disclosure, the preset floating window may move according to the determined display position of the target image on the image ball. That is, after the terminal determines the image selected by the user as the target image, the terminal may move the preset floating window to the display position of the target image, and the center of the preset floating window may coincide with the center of the display position where the target image is located. And then, the terminal can display the target image in the preset floating window so as to avoid the shielding of other images when the target image is displayed in the preset floating window.
The third mode is as follows: and setting the transparency of the target image to be a preset transparency, and performing suspension display on the set target image, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball.
In this implementation, the target image may also be an image located at the center position of the image ball or an image selected by the user.
When the target image is an image located at the center of the image ball, the terminal may set the transparency of the image located at the center of the image ball to a preset transparency, and perform floating display on the set target image, where the size of the image after floating display may be larger than the size of the images displayed at the rest positions of the image ball, so that a user may view the image more clearly.
It should be noted that, in this implementation, the method for displaying the image in a floating manner is different from the method for displaying the image in the second implementation in which the preset floating window is set, in which the terminal may obtain the image located at the center of the image ball, and display the image located at the center of the image ball and the displayed image ball on two different image layers by setting different image layers, and the terminal may set the transparency of the image to be the preset transparency and set the size of the image to be larger than the sizes of the images displayed at the rest positions of the image ball, so that the image displayed in a floating manner is more beneficial for the user to view, and meanwhile, large-area blocking of the images displayed at the rest positions in the image ball may be avoided.
Alternatively, when the target image is an image selected by the user, the terminal may determine, when a selection operation of the user for any one of the images on the target image ball is detected, the image as the target image, and thereafter, the terminal may set the transparency of the target image to a preset transparency and display the set target image in a floating manner on an upper layer of a display position of the target image on the image ball. Or, the terminal may rotate the image ball according to the display position of the target image on the image ball after determining the target image selected by the user, so that the image displayed at the center position of the rotated image ball is the target image, and then may set the target image to a preset transparency and display the set target image on the upper layer of the display position of the target image on the image ball in a floating manner.
Optionally, in this embodiment of the present disclosure, for the target image, the terminal may further obtain associated information of the target image, and display the obtained associated information in the second preset display area.
The associated information may be at least one classification tag corresponding to the image acquired through the neural network model in step 202, or the associated information may be other attribute information such as an original size of the image, a shooting date, and the like, or the associated information may also be a network address link related to the image, for example, the network address link may be a connection of a web page including the image or a web page link related to content of the image. Through the associated information, the user can clearly know other information related to the image, or the user can quickly link the displayed associated information to the webpage related to the image so as to acquire the other information related to the image, the user does not need to spend time to acquire the associated information through retrieval or other modes, the user operation is further simplified, and the time of the user is saved.
It should be noted that the second preset display area may be an area included in the first preset display area, may also be an area in the preset floating window, or may be an area other than the area for displaying the image ball.
Further, when the associated information includes at least one classification tag, after displaying the associated information, the terminal may further detect whether a selection operation for a target classification tag is received, where the target classification tag may be any one of the displayed at least one classification tag. When the selection operation aiming at the target classification label is detected, the terminal can jump to a secondary page, and the image of which the corresponding classification label in the plurality of images contains the target classification label is displayed in the secondary page. Therefore, for any displayed classification label, a user can quickly view all images under the classification label by selecting the classification label, and the user can find similar images more easily.
For example, fig. 2C is a schematic diagram of an image display interface shown in an embodiment of the disclosure. As shown in fig. 2C, the terminal may divide the display screen into an upper display area a and a lower display area B, where an image ball is displayed in the lower display area B, currently, an image 1 is located at a center position of the image ball, and if the classification label corresponding to the image 1 is a person, a sky, and a building, the terminal may display the image 1 in the upper display area a alone, where the display area a is a first preset display area, and display the classification label on one side of the image 1. When the terminal detects that the user selects one of the displayed classification labels, the terminal can jump to the secondary page to display all the images under the classification label.
It should be noted that when the terminal jumps to the secondary page to display all the images under the target classification label, the multiple images under the target classification label can be sequentially displayed in the secondary page according to a conventional image display mode. Alternatively, the terminal may use the target image displayed in the first preset display area as the first image in the secondary page, and sequentially display a plurality of images also having the target classification label according to the similarity with the target image according to the clustering result in step 202. Alternatively, the terminal may display the multiple images under the target classification label in the secondary page in the form of an image ball according to the foregoing method, which is not specifically limited in this disclosure.
After the image ball is displayed, the terminal may interact with the user through the method described in step 205.
In step 205, the interaction operation of the user for the image ball is detected, and interaction with the user is performed based on the detected interaction operation.
The terminal can realize different interactions by detecting different interaction operations.
The first mode is as follows: when a first preset operation for the image ball is detected, an image which is not displayed on the image ball in the plurality of images is displayed.
As is apparent from the foregoing description, when the number of positions of the display positions of the surface of the image ball is less than the number of images of the plurality of images, the terminal may select a part of the image from the plurality of images to display. Therefore, for the images which are not displayed on the image ball in the plurality of images, the terminal can display the rest images which are not displayed on the image ball in the plurality of images when detecting the first preset operation for the image ball.
Wherein the terminal can use the method introduced in the foregoing. And determining the position of each image on the image ball according to the position coordinates of each image in the rest images which are not displayed on the image ball under a low-dimensional coordinate system, and then displaying the rest images which are not displayed on the image ball according to the determined positions. In this way, for the remaining undisplayed images, when the user browses the images, the images can be browsed integrally through the image ball, so that a more intuitive visual experience is brought to the user. When a user wants to search the interested images from the rest of the undisplayed images, the images are easier to search, and the operation is more convenient.
The second mode is as follows: when a preset instruction for the image ball is detected, updating the number of positions of a plurality of display positions included on the surface of the image ball, wherein the preset instruction can be triggered by a second preset operation or is a voice instruction; the image displayed on the surface of the image ball is updated based on the updated number of positions.
In the embodiment of the present disclosure, the terminal may detect a preset instruction for the image ball, and when the preset instruction is detected, the terminal may update the number of positions of the display positions included in the surface of the image ball according to the preset instruction. The preset instruction may be triggered by a second preset operation, or the preset instruction may be a voice instruction, that is, the user may update the number of images displayed on the image ball by issuing the preset instruction or performing the preset operation. The terminal may then display the image ball according to the updated number of positions.
For example, when the user wants to make the size of the image displayed on the image ball larger and easier to view some, the user may perform a second preset operation, which may be a zoom-in operation in which two fingers slide in opposite directions at the same time. When the second preset operation is a zoom-in operation in which the two fingers simultaneously move in opposite directions, the terminal may reduce the number of positions of the display position of the surface of the image ball, that is, the terminal may display fewer images on the surface of the image ball, so that the size of the image displayed on the surface of the image ball is increased without changing the size of the image ball. Similarly, when the second preset operation is a two-finger pinch operation, the number of positions of the display positions of the surface of the image ball may be increased so that the surface of the image ball displays more images, and thus, the size of the image displayed on the surface of the image ball may be reduced without changing the size of the image ball.
In the embodiment of the disclosure, the terminal may update the number of the display positions on the surface of the image ball in real time through the detected second preset operation, and actually update the size of the image displayed on the surface of the image ball under the condition that the size of the image ball is not changed, that is, the user may adjust the size of the image displayed on the surface of the image ball by executing the second preset operation, so that more choices are provided for the user, the image display is more flexible, and the user requirements are better met.
Of course, the second preset operation may be replaced by a voice instruction, for example, the user may directly issue a voice instruction for zooming out or zooming in, and when the terminal receives the voice instruction, the number of positions of the display position on the surface of the image ball may be updated according to the voice instruction, and the displayed image may be updated based on the updated number of positions. Therefore, the user does not need to execute the second preset operation by using two hands, the two hands of the user are liberated, and greater convenience is brought to the user.
The third mode is as follows: when a sliding operation for the image ball is detected, the image ball is rotated based on the sliding operation.
After displaying a plurality of images on the surface of the image ball, the user can rotate the image ball by performing a sliding operation on the image ball, thereby browsing the images displayed on the image ball. Based on this, the terminal can determine whether a sliding operation for the image ball is detected in real time in the current page on which the image ball is displayed, and when the sliding operation for the image ball is detected, the image ball is rotated based on the sliding operation.
Wherein, the terminal can detect the sliding speed of the sliding operation; determining a rotation speed based on the sliding speed, and rotating the image ball based on the rotation speed; alternatively, the rotation angle is determined based on the sliding speed, and the image ball is rotated by the rotation angle.
In the embodiment of the present disclosure, the terminal may rotate the image ball according to the sliding speed of the sliding operation. In one possible implementation, the terminal may determine the corresponding rotational speed from the slip speed. The faster the slip speed, the faster the rotational speed. In another possible implementation manner, the terminal may determine the rotation angle according to the sliding speed, and the faster the sliding speed is, the larger the rotation angle is.
Alternatively, the terminal may detect a sliding direction of the sliding operation; rotating the image ball in the sliding direction during the holding of the sliding operation; when the end of the sliding operation is detected, the rotation of the image ball is stopped.
The terminal can determine the sliding direction of the sliding operation when the sliding operation is detected, and then the terminal can detect the position acted by the sliding operation in real time from the starting point of the sliding operation, when the acted position is detected currently, the sliding operation is determined to be still in the process of keeping, otherwise, the sliding operation is determined to be finished.
The terminal may rotate the image ball in accordance with the detected sliding direction during the holding of the sliding operation, and when the sliding operation is stopped, the rotation of the image ball is also stopped.
That is, in the embodiment of the present disclosure, when the user browses an image, the user can conveniently perform a sliding operation on the image ball, so that the image ball rotates, and thus, multiple images on the image ball are browsed, and compared with the case that the user browses multiple images by scrolling the display page up and down, the operation distance is shortened.
In the embodiment of the disclosure, the terminal may obtain a plurality of images, perform similar image clustering analysis on the plurality of images to obtain a clustering analysis result, and then display the plurality of images on the surface of the image ball according to the clustering analysis result. The terminal can determine the position coordinates of each image in the multiple images according to the cluster analysis result, wherein the closer the position coordinates are, the greater the similarity of the two images, so that when the multiple images are displayed on the surface of an image ball according to the cluster analysis result, the closer the images on the surface of the image ball are, the more similar the images are, that is, the user can judge the similarity degree between the images according to the positions of the multiple images on the image ball. When a user browses a plurality of images, similar pictures corresponding to each image can be conveniently and quickly found.
The foregoing embodiments mainly describe a first implementation manner of displaying a plurality of images in the form of an image ball, that is, a specific implementation manner of performing cluster analysis on the plurality of images, and determining display positions of the plurality of images on the surface of the image ball according to a result of the cluster analysis, so as to display the plurality of images on the surface of the image ball. Next, an image display method of classifying a plurality of images and then displaying the plurality of images on different image ball surfaces according to classification labels will be described, wherein the operation of classifying the plurality of images may be performed by a terminal or a server, and in the following embodiments, the terminal is taken as an example for explanation.
Fig. 3 is a flowchart illustrating an image display method according to an exemplary embodiment, which is applied to a terminal, as shown in fig. 3, and includes the steps of:
in step 301, a plurality of images are acquired.
The specific implementation manner of this step may refer to the specific implementation manner in step 201, and details of the embodiment of the present disclosure are not described herein again.
In step 302, at least one classification label corresponding to each of the plurality of images is determined.
After the plurality of images are acquired, the terminal can classify the plurality of images through the neural network model, so that at least one classification label corresponding to each image in the plurality of images is obtained.
For each of the plurality of images, the terminal may use the image as an input of the neural network model, and obtain at least one classification label of the image output by the neural network model output layer. The Neural Network model may be a CNN (Convolutional Neural Network) model, for example, the Neural Network model may be an ImageNet model, an AlexNet model, or the like.
It should be noted that, in the embodiment of the present disclosure, this step may also be executed by the server, and when this step is executed by the server, after obtaining at least one classification tag corresponding to each of the plurality of images, the server may send the at least one classification tag corresponding to each of the plurality of images to the terminal, and then the terminal may display the image ball through step 303 based on receiving the at least one classification tag corresponding to each of the plurality of images.
In step 303, an image ball is displayed based on at least one classification label corresponding to each of the plurality of images.
After acquiring the at least one classification label corresponding to each of the plurality of images, the terminal may determine a plurality of target classification labels based on the at least one classification label corresponding to each of the plurality of images, and display a plurality of image balls based on the plurality of target classification labels, where images corresponding to different target classification labels in the plurality of target classification labels may be displayed on surfaces of different image balls in the plurality of image balls.
As can be seen from the above description, each image may correspond to at least one classification label, and different images may correspond to the same classification label. Therefore, the terminal can combine all the classification labels corresponding to the multiple images into one label set, and perform de-duplication on the classification labels included in the label set, so as to obtain all the types of classification labels corresponding to the multiple images, and determine all the types of classification labels corresponding to the multiple images as the target classification labels.
Alternatively, considering that the number of all kinds of classification tags corresponding to a plurality of images may be large and the number of images corresponding to some classification tags may be very small, in this case, if a small number of images corresponding to the classification tags are displayed by one image ball, a waste of the display area of the current page may be caused. Based on this, the terminal can screen the classification labels, so as to obtain the target classification labels. The terminal can determine the number of images corresponding to each classification label, and determine a plurality of classification labels, of which the number of corresponding images is greater than a preset threshold value, as a plurality of target classification labels.
After the target classification tags are determined, the terminal may display a plurality of image balls according to the plurality of target classification tags, where an image corresponding to each target classification tag is displayed on a different image ball, that is, each target classification tag corresponds to one image ball. When the terminal displays the image corresponding to each target classification label on one image ball, the specific display method may refer to step 202 and step 203 in the foregoing embodiment.
It should be noted that, in the embodiment of the present disclosure, the at least one classification label corresponding to each image is obtained through a neural network model, and based on this, the terminal may further refer to the manner in step 202, and obtain the high-dimensional feature vector of each image while obtaining the at least one classification label of each image. Then, for any target classification label a, the terminal may determine, according to the correlation manner in step 202 and step 203, the position coordinates of each image corresponding to the target classification label a in the low-dimensional coordinate system, and project, according to the position coordinates, each image corresponding to the target classification label a onto the low-dimensional canvas, and then display the low-dimensional canvas in the form of an image ball through a 3D technique or a pseudo 3D technique. In this way, for the image ball corresponding to each target classification label, the images displayed on the image ball not only have the same classification label, but also the closer the image ball is, the greater the similarity between the images.
The terminal can display the images corresponding to the target classification tags on the surfaces of the image balls respectively in the above manner, that is, in the current page, a plurality of image balls can be displayed, and each image ball can correspond to one target classification tag. For each image ball in the plurality of image balls, the terminal may highlight a target image, which may be an image located at the center of the image ball or any image selected by the user to be located on the image ball. The implementation manner of highlighting the target image on each image ball by the terminal may refer to the related description of highlighting the target image in the image ball in the foregoing embodiment, which is not described in detail in this embodiment of the disclosure.
In addition, in the embodiment of the present disclosure, for the highlighted target image, the terminal may also acquire and display the related information of the target image.
Alternatively, as can be seen from the foregoing description, the number of images corresponding to some classification tags may be smaller than the preset threshold and cannot be used as a target classification tag, in this case, the terminal may simultaneously display the images corresponding to a plurality of classification tags on one image ball according to the number of positions of the display positions on the surface of the image ball. Wherein, the display positions of the images belonging to the same classification label can be adjacent to each other.
After displaying the image ball, the terminal may interact with the user through the method described in step 304 to achieve better display effect.
In step 304, the interaction operation of the user for the image ball is detected, and interaction with the user is performed based on the detected interaction operation.
Based on the foregoing description, the terminal may display a plurality of image balls in the current page, each image ball corresponding to one object classification tag. When a user wants to browse a plurality of images corresponding to a certain classification tag, the user can perform a selection operation on the image ball. The terminal may determine in real time whether a selection operation for a target image ball is detected, which may be any one of a plurality of image balls displayed in the current page. When the terminal detects the selection operation for the target image ball, the terminal can jump to the secondary page to display a plurality of images corresponding to the target classification label corresponding to the target image ball.
Further, if the number of the plurality of images corresponding to the target image tag is greater than the number of the images displayed on the target image ball, that is, the target image ball cannot display all the plurality of images corresponding to the target classification tag, in this case, when the terminal detects a selection operation, it may jump to a secondary page and display an image that cannot be displayed on the target image ball in the images corresponding to the target classification tag in the secondary page.
Optionally, in this embodiment of the disclosure, if the number of the plurality of images corresponding to the target image tag is greater than the number of images displayed on the target image ball, the terminal may further detect a first preset operation for the target image ball, and when the terminal detects the first preset operation for the target image ball, an image that is not displayed on the target image ball in the images corresponding to the target classification tag may be displayed on the target image ball.
Optionally, the terminal may also interact with the user through the second and third ways described in step 205 of the foregoing embodiments.
It should be noted that, in the embodiment of the present disclosure, the terminal may further combine the method for interacting with the user to display the image introduced in this step with the method for interacting with the user introduced in step 204 in the foregoing embodiment, so as to make the image display modes richer and more diverse.
In the embodiment of the disclosure, the terminal may obtain a plurality of images, classify the plurality of images through the neural network model to obtain at least one classification label corresponding to each of the plurality of images, and then display the plurality of images in the form of an image ball based on the at least one classification label corresponding to each of the plurality of images. Therefore, the terminal can display the plurality of image balls in the current page according to at least one classification label corresponding to each image in the plurality of images, each image ball corresponds to one classification label, and a user can browse the plurality of images according to the classification labels, so that the method is more convenient. Moreover, for a plurality of images corresponding to each classification label, the terminal can display the plurality of images on the image ball according to the clustering analysis result, that is, the images displayed on each image ball not only have the same classification label, but also the closer the images on the image ball are, the greater the similarity between the images is. Therefore, when browsing a plurality of images, the user can search and operate the plurality of images more easily.
Next, an image display device provided by an embodiment of the present disclosure will be described.
Fig. 4A is a block diagram illustrating an image display apparatus 400 according to an exemplary embodiment. Referring to fig. 4A, the apparatus includes an acquisition module 401 and a first display module 402.
An obtaining module 401, configured to obtain multiple images;
the first display module 402 is configured to display an image ball, a surface of the image ball includes a plurality of display positions, and different images of the plurality of images are displayed at different display positions of the plurality of display positions.
Alternatively, referring to fig. 4B, the first display module 402 includes:
the first determining unit 4021 is configured to determine display positions of the plurality of images on the surface of the image ball, where the display positions are obtained based on similar image cluster analysis performed on the plurality of images, and a distance between the display positions of the images is in negative correlation with a similarity between the images;
the first display unit 4022 is configured to display the image ball at display positions on the surface of the image ball based on the plurality of images.
Optionally, the first determining unit 4021 includes:
the acquisition subunit is used for acquiring a high-dimensional feature vector of each image in the plurality of images through the neural network model;
the processing subunit is used for performing dimensionality reduction processing on the high-dimensional feature vector of each image in the multiple images to obtain the position coordinates of each image in the low-dimensional coordinate system in the multiple images;
and the first determining subunit is used for determining the display positions of the multiple images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
Optionally, each of the plurality of images corresponds to a position coordinate in the low-dimensional coordinate system;
the first determination unit is configured to:
determining a number of positions of a plurality of display positions included in a surface of the image ball;
when the number of the positions is smaller than that of the images of the plurality of images, the images of which the number is the number of the positions in the plurality of images are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball on the basis of the position coordinates of each image in the low-dimensional coordinate system in the plurality of images, and the display positions of each image in the images of which the number is the number of the positions on the surface of the image ball are obtained.
Optionally, the first determining unit is configured to:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball one to one;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
Alternatively, referring to fig. 4C, the first display module 402 includes:
a second determining unit 4023, configured to determine at least one classification label corresponding to each of the plurality of images;
the second display unit 4024 is configured to display the image ball based on at least one classification label corresponding to each of the plurality of images.
Optionally, the second display unit comprises:
the second determining subunit is used for determining a plurality of target classification labels based on at least one classification label corresponding to each image in the plurality of images, and each target classification label in the plurality of target classification labels corresponds to at least one image;
and the display subunit is used for displaying the plurality of image balls based on the plurality of target classification labels, and the images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
Optionally, the second determining subunit is specifically configured to:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
and determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as a plurality of target classification labels.
Optionally, the apparatus 400 further comprises:
and the second display module is used for displaying the image which is not displayed on the image ball when the first preset operation aiming at the image ball is detected.
Optionally, the apparatus 400 further comprises:
the updating module is used for updating the position number of a plurality of display positions included in the surface of the target image ball when a preset instruction for the target image ball is detected;
the updating module is further used for updating the image displayed on the surface of the target image ball based on the updated position number.
Optionally, the apparatus 400 further comprises:
and the rotating module is used for rotating the target image ball based on the sliding operation when the sliding operation aiming at the target image ball is detected.
Optionally, the rotation module comprises:
a first detection unit for detecting a sliding speed of the sliding operation;
a first rotation unit for determining a rotation speed based on the sliding speed and rotating the target image ball based on the rotation speed; alternatively, the second determination unit is configured to determine a rotation angle based on the sliding speed and rotate the target image ball by the rotation angle.
Optionally, the rotation module comprises:
a second detection unit for detecting a sliding direction of the sliding operation;
a second rotating unit for rotating the target image ball in the sliding direction in the sliding operation holding process;
a stopping unit for stopping the rotation of the target image ball when the end of the sliding operation is detected.
Optionally, the apparatus 400 further comprises:
the third display module is used for displaying the target image in a first preset display area of the current page, wherein the first preset display area is an area outside an area for displaying the image ball; alternatively, the first and second electrodes may be,
the third display module is used for displaying the target image in a preset floating window with preset transparency, and the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
and the third display module is used for setting the transparency of the target image to be preset transparency and displaying the set target image in a suspended manner, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball.
Optionally, the apparatus 400 further comprises:
an obtaining module 401, configured to obtain associated information of a target image;
and the fourth display module is used for displaying the associated information in a second preset display area of the current page.
Optionally, each image in the plurality of images corresponds to at least one classification label, and the associated information includes at least one classification label corresponding to the target image;
the apparatus 400 further comprises:
the skipping module is used for skipping to a secondary page when the selection operation of any one of the at least one classification label A displayed in the second preset display area is detected;
and the fifth display module is used for displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In the embodiment of the disclosure, the plurality of images are acquired, and the plurality of images are displayed in the form of the image ball, so that when a user browses the images, the image ball can be conveniently slid to rotate, so that the plurality of images on the image ball are browsed, and compared with the case that the user browses the plurality of images by vertically scrolling the display page, the operation is easier.
Fig. 5 is a block diagram illustrating an apparatus 500 for image display according to an exemplary embodiment. For example, the apparatus 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 5, the apparatus 500 may include one or more of the following components: processing component 502, memory 504, power component 506, multimedia component 508, audio component 510, input/output (I/O) interface 512, sensor component 514, and communication component 516.
The processing component 502 generally controls overall operation of the device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 502 may include one or more processors 520 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interaction between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.
The memory 504 is configured to store various types of data to support operations at the apparatus 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 504 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 506 provides power to the various components of the device 500. The power components 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power supplies for the apparatus 500.
The multimedia component 508 includes a screen that provides an output interface between the device 500 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 500 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 510 is configured to output and/or input audio signals. For example, audio component 510 includes a Microphone (MIC) configured to receive external audio signals when apparatus 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 504 or transmitted via the communication component 516. In some embodiments, audio component 510 further includes a speaker for outputting audio signals.
The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the device 500. For example, the sensor assembly 514 may detect an open/closed state of the apparatus 500, the relative positioning of the components, such as a display and keypad of the apparatus 500, the sensor assembly 514 may also detect a change in the position of the apparatus 500 or a component of the apparatus 500, the presence or absence of user contact with the apparatus 500, orientation or acceleration/deceleration of the apparatus 500, and a change in the temperature of the apparatus 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 516 is configured to facilitate communication between the apparatus 500 and other devices in a wired or wireless manner. The apparatus 500 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the methods provided by the embodiments shown in fig. 1, 2A, 2B, 2C and 3 described above.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 504 comprising instructions, executable by the processor 520 of the apparatus 500 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer readable storage medium, wherein instructions, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the methods provided by the embodiments illustrated in fig. 1, 2A, 2B, 2C and 3 described above.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims (32)

1. An image display method, characterized in that the method comprises:
acquiring a plurality of images;
displaying an image ball, a surface of the image ball comprising a plurality of display positions, different ones of the plurality of images being displayed on different ones of the plurality of display positions;
displaying a target image in a first preset display area of a current page, wherein the first preset display area is an area outside an area for displaying the image ball; alternatively, the first and second electrodes may be,
displaying a target image in a preset floating window with preset transparency, wherein the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
setting the transparency of a target image to be a preset transparency, and performing suspension display on the set target image, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball;
wherein the target image is an image located at a center position of the image ball or an image selected by a user on the image ball.
2. The method of claim 1, wherein the displaying the image ball comprises:
determining display positions of the images on the surface of the image ball, wherein the display positions are obtained based on similar image clustering analysis on the images, and the distance between the display positions of the images is in negative correlation with the similarity between the images;
displaying the plurality of images on an image ball based on display positions of the plurality of images on a surface of the image ball.
3. The method of claim 2, wherein the determining the display positions of the plurality of images on the surface of the image ball comprises:
acquiring a high-dimensional feature vector of each image in the plurality of images through a neural network model;
performing dimensionality reduction on the high-dimensional feature vector of each image in the plurality of images to obtain the position coordinates of each image in the plurality of images in a low-dimensional coordinate system;
and determining the display positions of the images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
4. The method of claim 2, wherein each of the plurality of images corresponds to a location coordinate in a low-dimensional coordinate system;
the determining the display positions of the plurality of images on the surface of the image ball comprises:
determining a number of positions of a plurality of display positions included in a surface of the image sphere;
when the number of the positions is smaller than the number of the images of the plurality of images, on the basis of the position coordinates of each image in the low-dimensional coordinate system, the images of the plurality of images, the number of which is the number of the positions, are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball, and the display positions of each image in the images, the number of which is the number of the positions, on the surface of the image ball are obtained.
5. The method according to claim 4, wherein the one-to-one correspondence of the images with the number of positions in the plurality of images to the plurality of display positions included in the surface of the image ball based on the position coordinates of each of the plurality of images in a low-dimensional coordinate system comprises:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball in a one-to-one manner;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
6. The method of claim 1, wherein the displaying the image ball comprises:
determining at least one classification label corresponding to each of the plurality of images;
and displaying the image ball based on at least one classification label corresponding to each image in the plurality of images.
7. The method of claim 6, wherein displaying the image ball based on the at least one classification label corresponding to each image of the plurality of images comprises:
determining a plurality of target classification labels based on at least one classification label corresponding to each image in the plurality of images, wherein each target classification label in the plurality of target classification labels corresponds to at least one image;
and displaying a plurality of image balls based on the plurality of target classification labels, wherein images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
8. The method of claim 7, wherein determining a plurality of target classification tags based on at least one classification tag corresponding to each of the plurality of images comprises:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as the plurality of target classification labels.
9. The method of any of claims 1-8, further comprising, after displaying the image ball:
when a first preset operation for the image ball is detected, displaying an image which is not displayed on the image ball.
10. The method of any of claims 1-8, further comprising, after displaying the image ball:
when a preset instruction for a target image ball is detected, updating the position number of a plurality of display positions included in the surface of the target image ball;
updating the image displayed on the surface of the target image sphere based on the updated number of positions.
11. The method of any of claims 1-8, further comprising, after displaying the image ball:
when a sliding operation for a target image ball is detected, the target image ball is rotated based on the sliding operation.
12. The method of claim 11, wherein the rotating the target image ball based on the sliding operation comprises:
detecting a sliding speed of the sliding operation;
determining a rotation speed based on the sliding speed, and rotating the target image ball based on the rotation speed; or, determining a rotation angle based on the sliding speed, and rotating the target image ball by the rotation angle.
13. The method of claim 11, wherein the rotating the target image ball based on the sliding operation comprises:
detecting a sliding direction of the sliding operation;
rotating the target image ball in the sliding direction while the sliding operation is maintained;
when the sliding operation is detected to be finished, stopping rotating the target image ball.
14. The method of claim 1, wherein after displaying the image ball, further comprising:
acquiring the associated information of a target image;
and displaying the associated information in a second preset display area of the current page.
15. The method of claim 14, wherein each image of the plurality of images corresponds to at least one classification label, and the association information comprises at least one classification label corresponding to the target image;
after the displaying the associated information in a second preset display area of the current page, the method further includes:
when the selection operation of any one classification label A in at least one classification label displayed in the second preset display area is detected, jumping to a secondary page;
and displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
16. An image display apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring a plurality of images;
a first display module for displaying an image ball, a surface of the image ball including a plurality of display positions, different ones of the plurality of images being displayed at different ones of the plurality of display positions;
the third display module is used for displaying the target image in a first preset display area of the current page, wherein the first preset display area is an area outside an area for displaying the image ball; alternatively, the first and second electrodes may be,
the third display module is used for displaying the target image in a preset floating window with preset transparency, and the center of the preset floating window is superposed with the center of the image ball, or the center of the preset floating window is superposed with the center of the position of the target image; alternatively, the first and second electrodes may be,
the third display module is used for setting the transparency of the target image to be a preset transparency and displaying the set target image in a suspended manner, wherein the size of the target image is larger than the size of the image displayed at the rest positions of the image ball;
wherein the target image is an image located at a center position of the image ball or an image selected by a user on the image ball.
17. The apparatus of claim 16, wherein the first display module comprises:
the first determining unit is used for determining the display positions of the images on the surface of the image ball, the display positions are obtained based on similar image clustering analysis on the images, and the distance between the display positions of the images and the similarity between the images are in negative correlation;
a first display unit configured to display the image ball at display positions of a surface of the image ball based on the plurality of images.
18. The apparatus of claim 17, wherein the first determining unit comprises:
the acquisition subunit acquires a high-dimensional characteristic vector of each image in the plurality of images through a neural network model;
the processing subunit is configured to perform dimensionality reduction processing on the high-dimensional feature vector of each of the multiple images to obtain a position coordinate of each of the multiple images in a low-dimensional coordinate system;
the first determining subunit is used for determining the display positions of the images on the surface of the image ball based on the position coordinates of each image in the low-dimensional coordinate system.
19. The apparatus of claim 17, wherein each of the plurality of images corresponds to a location coordinate in a low-dimensional coordinate system;
the first determination unit is configured to:
determining a number of positions of a plurality of display positions included in a surface of the image sphere;
when the number of the positions is smaller than the number of the images of the plurality of images, on the basis of the position coordinates of each image in the low-dimensional coordinate system, the images of the plurality of images, the number of which is the number of the positions, are in one-to-one correspondence with a plurality of display positions included in the surface of the image ball, and the display positions of each image in the images, the number of which is the number of the positions, on the surface of the image ball are obtained.
20. The apparatus of claim 19, wherein the first determining unit is configured to:
selecting a reference image from the plurality of images, and determining a reference display position on a low-dimensional canvas as a display position of the reference image on the surface of the image ball, wherein a plurality of display positions included on the low-dimensional canvas correspond to a plurality of display positions on the surface of the image ball in a one-to-one manner;
selecting images of which the number is the number of the remaining display positions from the plurality of images based on the relative positional relationship between the position coordinates of the reference image and the position coordinates of the other images in the plurality of images, and determining the remaining display positions on the low-dimensional canvas as the display positions of the selected images on the surface of the image ball.
21. The apparatus of claim 16, wherein the first display module comprises:
the second determining unit is used for determining at least one classification label corresponding to each image in the plurality of images;
and the second display unit is used for displaying the image ball based on at least one classification label corresponding to each image in the plurality of images.
22. The apparatus of claim 21, wherein the second display unit comprises:
a second determining subunit, configured to determine, based on at least one classification label corresponding to each of the plurality of images, a plurality of target classification labels, where each of the plurality of target classification labels corresponds to at least one image;
and the display subunit is used for displaying a plurality of image balls based on the plurality of target classification labels, wherein images corresponding to different target classification labels in the plurality of target classification labels are displayed on the surfaces of different image balls in the plurality of image balls.
23. The apparatus according to claim 22, wherein the second determining subunit is specifically configured to:
determining the number of images corresponding to each classification label based on at least one classification label corresponding to each image in the plurality of images;
determining a plurality of classification labels of which the number of the corresponding images is larger than a preset threshold value as the plurality of target classification labels.
24. The apparatus of any of claims 16-23, further comprising:
and the second display module is used for displaying the image which is not displayed on the image ball when the first preset operation aiming at the image ball is detected.
25. The apparatus of any of claims 16-23, further comprising:
the updating module is used for updating the position number of a plurality of display positions included in the surface of the target image ball when a preset instruction for the target image ball is detected;
the updating module is further used for updating the image displayed on the surface of the target image ball based on the updated position number.
26. The apparatus of any of claims 16-23, further comprising:
and the rotating module is used for rotating the target image ball based on the sliding operation when the sliding operation aiming at the target image ball is detected.
27. The apparatus of claim 26, wherein the rotation module comprises:
a first detection unit for detecting a sliding speed of the sliding operation;
a first rotation unit for determining a rotation speed based on the sliding speed and rotating the target image ball based on the rotation speed; or, determining a rotation angle based on the sliding speed, and rotating the target image ball by the rotation angle.
28. The apparatus of claim 26, wherein the rotation module comprises:
a second detection unit for detecting a sliding direction of the sliding operation;
a second rotating unit configured to rotate the target image ball in the sliding direction in a process of the sliding operation holding;
a stopping unit configured to stop rotating the target image ball when the end of the sliding operation is detected.
29. The apparatus of claim 16, further comprising:
the acquisition module is used for acquiring the associated information of the target image;
and the fourth display module is used for displaying the associated information in a second preset display area of the current page.
30. The apparatus of claim 29, wherein each image of the plurality of images corresponds to at least one classification label, and the association information comprises at least one classification label corresponding to the target image;
the device further comprises:
the skipping module is used for skipping to a secondary page when the selection operation of any one of the at least one classification label A displayed in the second preset display area is detected;
and the fifth display module is used for displaying the image containing the classification label A in at least one corresponding classification label in the plurality of images in the secondary page.
31. An image display apparatus, characterized in that the apparatus comprises:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to the steps of the method of any one of claims 1-15.
32. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of the method of any of claims 1-15.
CN201711376442.6A 2017-12-19 2017-12-19 Image display method, image display device and computer-readable storage medium Active CN108009273B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711376442.6A CN108009273B (en) 2017-12-19 2017-12-19 Image display method, image display device and computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711376442.6A CN108009273B (en) 2017-12-19 2017-12-19 Image display method, image display device and computer-readable storage medium

Publications (2)

Publication Number Publication Date
CN108009273A CN108009273A (en) 2018-05-08
CN108009273B true CN108009273B (en) 2021-12-14

Family

ID=62060032

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711376442.6A Active CN108009273B (en) 2017-12-19 2017-12-19 Image display method, image display device and computer-readable storage medium

Country Status (1)

Country Link
CN (1) CN108009273B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109829069B (en) * 2018-12-28 2021-03-12 广州华多网络科技有限公司 Image auditing processing method and device, electronic equipment and storage medium
CN109977247B (en) * 2019-03-27 2022-03-25 联想(北京)有限公司 Image processing method and image processing apparatus
CN111158554B (en) * 2019-12-31 2021-07-16 联想(北京)有限公司 Image display method, electronic equipment and image display system

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101017570A (en) * 2006-02-06 2007-08-15 奥林巴斯映像株式会社 Image combining apparatus and image combining method
CN101510978A (en) * 2008-02-13 2009-08-19 索尼株式会社 Image display apparatus, image display method, program, and record medium
CN101902578A (en) * 2009-05-26 2010-12-01 三洋电机株式会社 Image-reproducing means and filming apparatus
CN103460129A (en) * 2012-01-03 2013-12-18 孔亮 Three dimensional display system
CN104978146A (en) * 2015-06-30 2015-10-14 广东欧珀移动通信有限公司 Image operation method and mobile terminal
CN105163158A (en) * 2015-08-05 2015-12-16 北京奇艺世纪科技有限公司 Image processing method and device
US9258566B1 (en) * 2014-07-17 2016-02-09 Yahoo! Inc. System and method of spherical image compression
CN105741233A (en) * 2016-01-27 2016-07-06 桂林长海发展有限责任公司 Spherical mosaic method and system of video image
CN105809701A (en) * 2016-03-25 2016-07-27 成都易瞳科技有限公司 Panorama video posture calibrating method
CN107230180A (en) * 2016-10-10 2017-10-03 华为技术有限公司 A kind of mapping method of panoramic picture, device and equipment
CN107438813A (en) * 2015-05-27 2017-12-05 谷歌公司 Including the leader's method, apparatus investigated for virtual reality and the system for participating in method, apparatus

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101017570A (en) * 2006-02-06 2007-08-15 奥林巴斯映像株式会社 Image combining apparatus and image combining method
CN101510978A (en) * 2008-02-13 2009-08-19 索尼株式会社 Image display apparatus, image display method, program, and record medium
CN101902578A (en) * 2009-05-26 2010-12-01 三洋电机株式会社 Image-reproducing means and filming apparatus
CN103460129A (en) * 2012-01-03 2013-12-18 孔亮 Three dimensional display system
US9258566B1 (en) * 2014-07-17 2016-02-09 Yahoo! Inc. System and method of spherical image compression
CN107438813A (en) * 2015-05-27 2017-12-05 谷歌公司 Including the leader's method, apparatus investigated for virtual reality and the system for participating in method, apparatus
CN104978146A (en) * 2015-06-30 2015-10-14 广东欧珀移动通信有限公司 Image operation method and mobile terminal
CN105163158A (en) * 2015-08-05 2015-12-16 北京奇艺世纪科技有限公司 Image processing method and device
CN105741233A (en) * 2016-01-27 2016-07-06 桂林长海发展有限责任公司 Spherical mosaic method and system of video image
CN105809701A (en) * 2016-03-25 2016-07-27 成都易瞳科技有限公司 Panorama video posture calibrating method
CN107230180A (en) * 2016-10-10 2017-10-03 华为技术有限公司 A kind of mapping method of panoramic picture, device and equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"基于纹理渲染与纹理映射的实时球幕图像生成方法";柳喆俊;《艺术与设计(理论)》;20140131(第Z1期);第78-80页 *
"平面屏式真三维立体显示的图像数据生成方法";段现银 等;《山东大学学报(工学版)》;20110430;第41卷(第2期);第66-70页 *

Also Published As

Publication number Publication date
CN108009273A (en) 2018-05-08

Similar Documents

Publication Publication Date Title
KR102148002B1 (en) Automatic recognition and capture of an object
EP2690879B1 (en) Mobile terminal and method for controlling of the same
KR101993241B1 (en) Method and system for tagging and searching additional information about image, apparatus and computer readable recording medium thereof
WO2019120068A1 (en) Thumbnail display control method and mobile terminal
US20150024728A1 (en) Mobile terminal and controlling method thereof
KR101917690B1 (en) Mobile terminal and control method for the mobile terminal
US20120038668A1 (en) Method for display information and mobile terminal using the same
US20170083741A1 (en) Method and device for generating instruction
US20120007890A1 (en) Method for photo editing and mobile terminal using this method
KR101871718B1 (en) Mobile terminal and method for controlling the same
US20170322689A1 (en) Method and device for multi-task management, and computer-readable medium
EP3128411B1 (en) Interface display method, terminal, computer program and recording medium
KR20150059466A (en) Method and apparatus for recognizing object of image in electronic device
US20140192081A1 (en) Method and apparatus for laying out image using image recognition
US9525828B2 (en) Group recording method, machine-readable storage medium, and electronic device
KR20160086090A (en) User terminal for displaying image and image display method thereof
US20160196057A1 (en) Display device and method of displaying screen on said display device
EP3260998A1 (en) Method and device for setting profile picture
US20150063785A1 (en) Method of overlappingly displaying visual object on video, storage medium, and electronic device
CN112954210A (en) Photographing method and device, electronic equipment and medium
CN108009273B (en) Image display method, image display device and computer-readable storage medium
CN106055707A (en) Bullet screen display method and device
WO2016065814A1 (en) Information selection method and device
CN110851062A (en) Drawing method and electronic equipment
EP2990905B1 (en) Method and device for displaying image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant