Photo album generation method, system and device, medium and product

Abstract

The invention discloses a photo album generation method, system and device, a medium and a product, and relates to the technical field of electronic photo album management.The photo album classification preference of a user is obtained; and according to the photo album classification preference, classifying pictures to generate a photo album. By adopting the embodiment of the invention, the photo album management burden of the user can be simplified, the user does not need to memorize the picture storage time or position, but can directly query based on the logic of photo album classification preference, and the automatic photo album generation can realize efficient photo album management.

Description

Technical Field

[0001] This invention relates to the field of electronic photo album management technology, and in particular to a photo album generation method, system, device, medium and product. Background Technology

[0002] In the digital age, the number of photos taken by people using electronic devices has increased dramatically. Existing photo album management systems mostly arrange photos simply in chronological order, causing users to spend a lot of time and effort searching for and reviewing specific content. Summary of the Invention

[0003] The present invention aims to provide a method, system, device, medium and product for generating photo albums, which can classify pictures according to users' specific preferences to achieve efficient photo album management.

[0004] In a first aspect, embodiments of the present invention provide a photo album generation method, including: Obtain the user's photo album category preferences; Based on the album category preferences, the images are categorized and albums are generated.

[0005] As an improvement to the above scheme, the album classification preferences include theme classification, time period classification, location classification, and people classification.

[0006] As an improvement to the above solution, when the album categorization preference is theme-based, the step of categorizing the user's pictures and generating an album based on the album categorization preference includes: Convert all the images into bitmap images; Calculate the color space of the bitmap image; Select a subject reference image from all bitmap images, and calculate the subject similarity between the subject reference image and other bitmap images according to the color space. If the theme similarity is greater than a preset similarity threshold, the corresponding images will be grouped into the same album to generate a theme album.

[0007] As an improvement to the above solution, obtaining the user's album category preferences includes: Collect global album configuration data set by the user; Based on the global album configuration data, the user's album category preferences are obtained.

[0008] As an improvement to the above scheme, the calculation of the color space of the bitmap image includes: The bitmap image is divided into several local images; Obtain the hue value, saturation value, and brightness value of each pixel in each local image, and calculate the average hue value, average saturation value, and average brightness value of the local image; Based on the average hue value, average saturation value, and average brightness value, a hue sequence, a saturation sequence, and a brightness sequence are formed for the bitmap image, thus constructing a color space.

[0009] As an improvement to the above scheme, the step of selecting a subject reference image from all bitmap images and calculating the subject similarity between the subject reference image and other bitmap images according to the color space includes: Select the subject reference image by iterating through all bitmap images; Based on the color space, obtain the first hue sequence, first saturation sequence, and first brightness sequence of the subject reference image, and obtain the second hue sequence, second saturation sequence, and second brightness sequence of other images; Using the Pearson correlation coefficient, the correlation coefficients between the first hue sequence and the second hue sequence, the first saturation sequence and the second saturation sequence, and the first lightness sequence and the second lightness sequence were calculated respectively, resulting in hue correlation index, saturation correlation index, and lightness correlation index; Based on preset weight values, the hue correlation index, saturation correlation index, and brightness correlation index are weighted and fused to obtain the theme similarity between the color space of the theme reference image and the color space of other bitmap images.

[0010] As an improvement to the above solution, when the album classification preference is time period classification, the step of classifying the images according to the album classification preference and generating an album includes: Obtain the timestamps of all images, and sort the images in chronological order according to the timestamps to obtain the image sequence; Calculate the time difference between the timestamps of adjacent images in the image sequence; If the time difference is not greater than a preset time threshold, the adjacent images are grouped into the same album to generate a time-segment album.

[0011] As an improvement to the above solution, when the album categorization preference is location-based, the step of categorizing the user's pictures and generating an album based on the album categorization preference includes: Get the coordinates of all images; Iterate through all the images to select a location reference image, and calculate the distance difference between the coordinates of the location reference image and the coordinates of other images; If the distance difference is not greater than a preset distance threshold, the corresponding images are grouped into the same album to generate a location album.

[0012] As an improvement to the above solution, when the album classification preference is people, the step of classifying the user's pictures according to the album classification preference and generating an album includes: Using facial recognition algorithms, identify people in all images; The images are categorized by the individuals mentioned, and a photo album of each individual is generated.

[0013] As an improvement to the above solution, after classifying the user's pictures according to the album classification preferences and generating albums, the album generation method further includes: Based on the album category preferences and image content corresponding to the generated album, generate album names and album covers.

[0014] Secondly, embodiments of the present invention provide a photo album generation system, including: The preference acquisition module is used to acquire the user's photo album category preferences; The image classification module is used to classify images according to the album classification preferences and generate albums.

[0015] Thirdly, embodiments of the present invention provide a photo album generation device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the photo album generation method as described above.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the album generation method as described above.

[0017] Fifthly, embodiments of the present invention provide a computer program product, the computer program product including a computer program or computer instructions, which, when executed by a processor, performs the album generation method as described above.

[0018] Compared with existing technologies, the album generation method, system, device, medium, and product disclosed in this invention obtain the user's album classification preferences; and classifies the pictures according to the album classification preferences to generate albums. Using the embodiments of this invention simplifies the user's album management burden. Users do not need to remember the time or location of image storage, but can directly query based on the logic of album classification preferences. This automated album generation enables efficient album management. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of a photo album generation method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a photo album generation system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a photo album generation device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] In the description and claims, it should be understood that the terms "first," "second," etc., used in the description and claims are only for the purpose of distinguishing the description of the same technical features, and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated, nor necessarily the order of description or chronological order. The terms are interchangeable where appropriate. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In traditional image storage applications, images are typically arranged and displayed in chronological order, and users can only view them sequentially by swiping or flipping through pages. Existing album management often relies on users manually adding tags or creating albums by selecting images themselves, and cannot automatically categorize and organize images according to specific user preferences. This results in users spending a lot of time and effort searching for and reviewing specific content.

[0023] Based on the above considerations, this invention provides a method for generating a photo album. Please refer to [link / reference]. Figure 1 In this embodiment, the album generation method is specifically executed through steps S1 to S2: S1. Obtain the user's photo album category preferences; S2. Based on the album classification preferences, classify the images and generate albums.

[0024] It should be noted that the album categorization preference refers to the user's personalized tendencies, reflecting the user's own usage habits and image management needs, and is the core basis for subsequent image categorization.

[0025] Preferably, image classification is performed by generating classification tags for each image and then classifying it based on those tags. There is no limit to the number of classification tags for the same image; that is, the same image can be classified into multiple albums simultaneously.

[0026] It is understandable that the images in the album can be the original images, copies of the original images, or pointers pointing to the original images. The format of the images in the generated album does not affect the beneficial effects of this invention.

[0027] The embodiments of the present invention can be applied to any application with image management functions. For example, the embodiments of the present invention can be applied to photo album applications, social media platforms, photography studio applications, and e-commerce platforms.

[0028] In some preferred image storage applications, the access attribute of images is set to accessible by default; while in other preferred image editing applications, the access attribute of images is set to inaccessible by default. In this embodiment of the invention, the images to be categorized are those that are accessible as defined by the user.

[0029] The above solution simplifies the burden of album management for users. Users do not need to remember the time or location of image storage, but can directly query based on album category preferences. This automated album generation enables efficient album management.

[0030] As a preferred implementation, step S1, obtaining the user's photo album category preferences, includes: Collect global album configuration data set by the user; Based on the global album configuration data, the user's album category preferences are obtained.

[0031] It should be noted that the global album configuration data includes the album category preferences set by the user.

[0032] As a preferred implementation, the album categorization preferences include theme categorization, time period categorization, location categorization, and people categorization.

[0033] Theme classification refers to classifying images according to content, time period classification refers to classifying images according to time, location classification refers to classifying images according to geographical location, and people classification refers to classifying images according to people.

[0034] In this embodiment of the invention, the album category preferences set in the user's global album configuration data are at least one of time period category, location category, people category, and theme category.

[0035] In some other preferred embodiments, the user's album category preferences are obtained based on the user's existing albums. Specifically, step S1, obtaining the user's album category preferences, includes: Retrieve the user's generated photo albums; Based on the classification rules of the images in the generated albums and the names of the generated albums, the user's album classification preferences are obtained.

[0036] For example, when the name of the generated album includes a time period, the user's album category preference is considered to be time period category; when the name of the generated album includes a location, the user's album category preference is considered to be location category; when the name of the generated album includes a person's name, or when all the pictures in the album are of the same person, the user's album category preference is considered to be person category; when the name of the generated album includes an event, the user's album category preference is considered to be theme category.

[0037] In the above solution, album categorization preferences are obtained through user settings or usage habits. Multiple album categorization preferences can accurately meet the diverse needs of different users and achieve highly personalized album categorization.

[0038] It should be noted that different album classification preferences correspond to different image classification algorithms in order to achieve accurate image classification.

[0039] As a preferred implementation, when the album categorization preference is theme-based, step S2, categorizing the images according to the album categorization preference and generating an album, is executed through steps S21-S24: S21. Convert all the images into bitmap images; S22. Calculate the color space of the bitmap image; S23. Select a subject reference image from all bitmap images, and calculate the subject similarity between the subject reference image and other bitmap images according to the color space. S24. If the theme similarity is greater than the preset similarity threshold, the corresponding images are grouped into the same album to generate a theme album.

[0040] Bitmap images are images composed of an array of pixels. Considering that images from different sources may be in different formats, step S21 of this embodiment converts the image into a bitmap image, so that the images are all presented in the form of a pixel array. Furthermore, each pixel of the bitmap image contains clear color information, which can ensure that subsequent color space calculations are uniformly based on pixel-level data.

[0041] It is worth noting that existing solutions for classifying images by theme often rely on users manually adding tags or notes, and there is no effective method for automatically analyzing and classifying the characteristics of photos such as color and content.

[0042] In this embodiment of the invention, theme aggregation is achieved through the similarity of color spaces, and the generated theme album can accurately correspond to the visual theme perceived by the user, making it easy to trace back the images according to visual style.

[0043] Further, preferably, step S22, calculating the color space of the bitmap image, includes: The bitmap image is divided into several local images; Obtain the hue value, saturation value, and brightness value of each pixel in each local image, and calculate the average hue value, average saturation value, and average brightness value of the local image; Based on the average hue value, average saturation value, and average brightness value, a hue sequence, a saturation sequence, and a brightness sequence are formed for the bitmap image, thus constructing a color space.

[0044] Generally speaking, images on the same theme not only have similar overall colors, but also often share common spatial distributions of local colors. Dividing the image into local parts can preserve this relationship between spatial location and color, avoiding the loss of spatial information caused by directly calculating the average color of the whole image.

[0045] In some preferred embodiments, the bitmap image is divided according to a 3x3 grid; in other preferred embodiments, the bitmap image is divided proportionally from top to bottom; and in still other preferred embodiments, the bitmap image is divided proportionally from left to right.

[0046] It should be noted that, in the embodiments of the present invention, the number of local images obtained by dividing each bit image is consistent.

[0047] It should also be noted that the color information contained in pixels in bitmap images is generally RGB. In this embodiment of the invention, it is further converted into the HSV color space, and different themes are distinguished by the combination of hue, saturation and brightness.

[0048] In this embodiment of the invention, the order of the hue sequence, saturation sequence, and brightness sequence is sorted according to the spatial position of the local image, and the sequence can reflect the spatial distribution pattern of each color attribute value in the color space.

[0049] In the above scheme, the spatial information of the bitmap image is preserved by local segmentation, and the average color value of the local image is further calculated to condense local features and reduce the amount of computation. Finally, the data in the local image are integrated into a structured feature sequence according to spatial order to ensure the comparability of subsequent similarity calculations.

[0050] Furthermore, preferably, step S23, selecting a subject reference image from all bitmap images and calculating the subject similarity between the subject reference image and other bitmap images according to the color space, includes: Select the subject reference image by iterating through all bitmap images; Based on the color space, obtain the first hue sequence, first saturation sequence, and first brightness sequence of the subject reference image, and obtain the second hue sequence, second saturation sequence, and second brightness sequence of other images; Using the Pearson correlation coefficient, the correlation coefficients between the first hue sequence and the second hue sequence, the first saturation sequence and the second saturation sequence, and the first lightness sequence and the second lightness sequence were calculated respectively, resulting in hue correlation index, saturation correlation index, and lightness correlation index; Based on preset weight values, the hue correlation index, saturation correlation index, and brightness correlation index are weighted and fused to obtain the theme similarity between the color space of the theme reference image and the color space of other bitmap images.

[0051] The Pearson correlation coefficient is a statistical value that measures the degree of linear correlation between two sequences. The closer the correlation coefficient is to 1, the more consistent the trends of the two sequences are. The closer the correlation coefficient is to -1, the more opposite the trends of the two sequences are. If it is close to 0, they are unrelated.

[0052] By using the Pearson correlation coefficient, we can not only capture the similarity of color values ​​between two images, but also capture the trend of color changes in space, avoiding local numerical differences from masking the overall similarity of the theme and improving the fault tolerance of classification.

[0053] It should be noted that different themes have different dependencies on the color dimension. By setting preset weight values, information from the three dimensions can be weighted and integrated based on the theme, avoiding the one-sidedness of judging from a single dimension. Preferably, there are several preset scene themes, and the preset weight values ​​corresponding to different scene themes are different. When generating a theme album, it is first determined which scene theme the image content belongs to, and then the corresponding preset weight value is selected for classification.

[0054] In a preferred embodiment, each bit image is first divided into an equal number of local images, and then the local images are converted from the RGB color space to the HSV color space to obtain the hue value, saturation value and brightness value of each pixel in the local image.

[0055] Next, calculate the average hue value of all pixels in each local image, denoted as HP; calculate the average saturation value of all pixels in each local image, denoted as SP; calculate the average lightness value of all pixels in each local image, denoted as VP. The color space Pi of bitmap image i is represented as... , , where f is the total number of local images in the bitmap image, and g represents the g-th local image.

[0056] Next, iterate through the selected subject reference images, and use the Pearson correlation coefficient to calculate the correlation coefficient QH between the subject reference image and other images in terms of hue, QS between the subject reference image and other images in terms of saturation, and QV between the subject reference image and other images in terms of brightness.

[0057] Then through Calculate the subject similarity between the baseline image and other images, where... , and These are preset weight values ​​for hue, saturation, and brightness, respectively. Finally, the topic similarity Q is compared with a preset similarity threshold. If a comparison is made, If so, the corresponding image will be grouped into the same theme album as the theme's base image.

[0058] As a preferred implementation, when the album categorization preference is time period categorization, step S2, categorizing the images according to the album categorization preference and generating an album, includes: Obtain the timestamps of all images, and sort the images in chronological order according to the timestamps to obtain the image sequence; Calculate the time difference between the timestamps of adjacent images in the image sequence; If the time difference is not greater than a preset time threshold, the adjacent images are grouped into the same album to generate a time-segment album.

[0059] It should be noted that some images currently contain shooting time information or storage information, which generally includes a timestamp to indicate when the image was generated or stored locally, serving as the basic data for measuring the chronological order of images.

[0060] Preferably, the preset time threshold is an adjustable dynamic threshold. For example, the preset time threshold is automatically adjusted according to time period differences; for holiday periods, the preset time threshold is 2 hours; for weekday periods, the preset time threshold is 30 minutes. Of course, the preset time threshold can also be controlled by the user.

[0061] In some preferred embodiments, all images are sorted according to timestamps, and the time difference between adjacent images is calculated. The time difference sequence of all images is then marked as... The total number of images is n+1.

[0062] Next With preset time threshold Comparison, Then, following the timeline, obtain continuous... The corresponding image.

[0063] Further obtain the minimum corresponding value of i The first shooting time point, and obtain the maximum value of i corresponding to The second shooting time point, based on the first shooting time point and the first shooting time point, constructs a time-segment album. Continuous The corresponding images are assigned to the album for that time period.

[0064] For example, if the preset time threshold is 30 minutes, the timestamp of image 1 is 10:00, the timestamp of image 2 is 10:15, and the time difference between the two is 15 minutes, then they will be classified into the same time period album.

[0065] In the above scheme, the time difference between adjacent timestamps is used as the classification basis. As long as adjacent images meet the preset time threshold condition, the corresponding images are considered to have a continuous relationship. There is no excessive restriction on the total duration spanned by the images contained in the entire album. This embodiment of the invention can aggregate both short-duration and long-duration activities, adapting to diverse user scenarios.

[0066] As a preferred implementation, when the album classification preference is location-based, step S2, classifying the images according to the album classification preference and generating an album, includes: Get the coordinates of all images; Iterate through all the images to select a location reference image, and calculate the distance difference between the coordinates of the location reference image and the coordinates of other images; If the distance difference is not greater than a preset distance threshold, the corresponding images are grouped into the same album to generate a location album.

[0067] In this embodiment of the invention, the coordinates of the images are in the form of latitude and longitude. Latitude and longitude are globally unified geographic positioning standards, which ensure that the geographical location of all images can be measured in the same dimension.

[0068] It should be noted that when iterating through and selecting location reference images, the selection is performed iteratively from the remaining unclassified images to ensure coverage of all geographical locations involved in the images. If only one reference image is selected, it would be impossible to distinguish images from different locations. In this embodiment of the invention, a location reference image is selected each time, and images spatially close to it are processed. New location reference images are then selected for the remaining unclassified images, until all images are classified, ensuring that a corresponding album can be generated for each location.

[0069] In some preferred embodiments, the coordinates of the image are represented as follows: , Where m is the total number of images, m = n + 1; Indicates longitude. Indicates latitude.

[0070] Next, select the location reference image t, whose coordinates are... And build a location album based on the location's baseline image.

[0071] pass Calculate the distance difference between other images and the location reference image. .Will and preset distance threshold If a comparison is made, Then the image will be added to the location album of the current location reference image.

[0072] Once all images have been matched with the current location reference image, a new location reference image is selected from the unclassified images, and the matching process is repeated until all images with coordinate attributes have been classified.

[0073] For example, based on the coordinates of image 1, with a preset distance threshold of 5 kilometers, if the coordinates of image 2 are less than 5 kilometers away from image 1, they will be grouped into the same location album.

[0074] In the above solution, by selecting a location reference image and quantifying the distance difference between objective coordinates, the generated location album can accurately correspond to each geographical region, making it convenient for users to trace back images by location, thus improving the scene reproduction and usage efficiency of the album.

[0075] As a preferred implementation, when the album classification preference is people, step S2, classifying the pictures according to the album classification preference and generating an album, includes: Using facial recognition algorithms, identify people in all images; The images are categorized by the individuals mentioned, and a photo album of each individual is generated.

[0076] In this embodiment of the invention, a facial recognition algorithm is first used to identify people in the images, and then images containing people are further filtered from all images. Next, a people album is created for each person, and the images are categorized, with images of the same person grouped into the same album.

[0077] Preferably, when the same multiple people appear in multiple pictures at the same time, a group album of the multiple people is generated.

[0078] In a preferred embodiment, the album generation method further includes step S3, which is performed after step S2: S3. Generate album name and album cover based on the album category preferences and image content corresponding to the generated album.

[0079] In some preferred embodiments, albums with the same album category preferences are integrated into an album set, and the album set is pushed to the user in a unified manner.

[0080] The above solution also sets unique names and covers for each album, allowing users to intuitively understand the core content and features of each album and roughly determine whether it meets their needs without opening the album.

[0081] The album generation method provided by this invention simplifies the album management burden for users. Users do not need to remember the time or location of image storage, but can directly query based on album category preferences. This automated album generation enables efficient album management.

[0082] This invention provides a photo album generation system. Please refer to [link / reference]. Figure 2 The album generation system includes a preference acquisition module 11 and an image classification module 12, wherein: Preference acquisition module 11 is used to acquire the user's album category preferences; Image classification module 12 is used to classify images according to the album classification preferences and generate albums.

[0083] In a preferred embodiment, the preference acquisition module 11 is specifically used for: Collect global album configuration data set by the user; Based on the global album configuration data, the user's album category preferences are obtained.

[0084] As a preferred implementation, the album categorization preferences include theme categorization, time period categorization, location categorization, and people categorization.

[0085] In a preferred embodiment, when the album categorization preference is theme-based, the image categorization module 12 includes: Bitmap conversion unit, used to convert all the images into bitmap images; A color space calculation unit is used to calculate the color space of the bitmap image; The similarity calculation unit is used to traverse and select a subject reference image from all bitmap images, and calculate the subject similarity between the subject reference image and other bitmap images according to the color space. The theme album generation unit is used to divide the corresponding images into the same album and generate a theme album if the theme similarity is greater than a preset similarity threshold.

[0086] In a preferred embodiment, the color space calculation unit is specifically used for: The bitmap image is divided into several local images; Obtain the hue value, saturation value, and brightness value of each pixel in each local image, and calculate the average hue value, average saturation value, and average brightness value of the local image; Based on the average hue value, average saturation value, and average brightness value, a hue sequence, a saturation sequence, and a brightness sequence are formed for the bitmap image, thus constructing a color space.

[0087] Furthermore, as a preferred embodiment, the similarity calculation unit is specifically used for: Select the subject reference image by iterating through all bitmap images; Based on the color space, obtain the first hue sequence, first saturation sequence, and first brightness sequence of the subject reference image, and obtain the second hue sequence, second saturation sequence, and second brightness sequence of other images; Using the Pearson correlation coefficient, the correlation coefficients between the first hue sequence and the second hue sequence, the first saturation sequence and the second saturation sequence, and the first lightness sequence and the second lightness sequence were calculated respectively, resulting in hue correlation index, saturation correlation index, and lightness correlation index; Based on preset weight values, the hue correlation index, saturation correlation index, and brightness correlation index are weighted and fused to obtain the theme similarity between the color space of the theme reference image and the color space of other bitmap images.

[0088] In a preferred embodiment, when the album categorization preference is time period categorization, the image categorization module 12 is used to: Obtain the timestamps of all images, and sort the images in chronological order according to the timestamps to obtain the image sequence; Calculate the time difference between the timestamps of adjacent images in the image sequence; If the time difference is not greater than a preset time threshold, the adjacent images are grouped into the same album to generate a time-segment album.

[0089] In a preferred embodiment, when the album categorization preference is location-based, the image categorization module 12 is used to: Get the coordinates of all images; Iterate through all the images to select a location reference image, and calculate the distance difference between the coordinates of the location reference image and the coordinates of other images; If the distance difference is not greater than a preset distance threshold, the corresponding images are grouped into the same album to generate a location album.

[0090] In a preferred embodiment, when the album categorization preference is people, the image categorization module 12 is used to: Using facial recognition algorithms, identify people in all images; The images are categorized by the individuals mentioned, and a photo album of each individual is generated.

[0091] As a preferred embodiment, after classifying the user's pictures according to the album classification preferences and generating albums, the album generation system further includes a name and cover generation module, used for: Based on the album category preferences and image content corresponding to the generated album, generate album names and album covers.

[0092] The album generation system provided by this invention simplifies the album management burden for users. Users do not need to remember the time or location of image storage, but can directly query based on album category preferences. This automated album generation enables efficient album management.

[0093] Please see Figure 3 , Figure 3 This is a structural block diagram of a photo album generation device provided in an embodiment of the present invention. The photo album generation device includes a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program, it implements the steps in the above-described embodiments of the various photo album generation methods, such as steps S1 to S2.

[0094] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the photo album generation device.

[0095] The album generation device may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will understand that the schematic diagram is merely an example of an album generation device and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the album generation device may also include input / output devices, network access devices, buses, etc.

[0096] The processor 31 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 31 is the control center of the album generation device, connecting all parts of the album generation device via various interfaces and lines.

[0097] The memory 32 can be used to store the computer program and / or modules. The processor 31 implements various functions of the photo album generation device by running or executing the computer program and / or modules stored in the memory 32 and calling the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0098] If the modules / units integrated into the album generation device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 31, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0099] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a photo album, characterized in that, include: Obtain the user's photo album category preferences; Based on the album category preferences, the images are categorized and albums are generated.

2. The album generation method as described in claim 1, characterized in that, The process of obtaining the user's photo album category preferences includes: Collect global album configuration data set by the user; Based on the global album configuration data, the user's album category preferences are obtained.

3. A photo album generation method as described in claim 1 or 2, characterized in that, The album categorization preferences include theme categorization, time period categorization, location categorization, and people categorization.

4. The album generation method as described in claim 1, characterized in that, When the album categorization preference is theme-based, the step of categorizing the user's pictures and generating an album based on the album categorization preference includes: Convert all the images into bitmap images; Calculate the color space of the bitmap image; Select a subject reference image from all bitmap images, and calculate the subject similarity between the subject reference image and other bitmap images according to the color space. If the theme similarity is greater than a preset similarity threshold, the corresponding images will be grouped into the same album to generate a theme album.

5. The album generation method as described in claim 4, characterized in that, The calculation of the color space of the bitmap image includes: The bitmap image is divided into several local images; Obtain the hue value, saturation value, and brightness value of each pixel in each local image, and calculate the average hue value, average saturation value, and average brightness value of the local image; Based on the average hue value, average saturation value, and average brightness value, a hue sequence, a saturation sequence, and a brightness sequence are formed for the bitmap image, thus constructing a color space.

6. The album generation method as described in claim 5, characterized in that, The step of selecting a subject reference image from all bitmap images and calculating the subject similarity between the subject reference image and other bitmap images based on the color space includes: Select the subject reference image by iterating through all bitmap images; Based on the color space, obtain the first hue sequence, first saturation sequence, and first brightness sequence of the subject reference image, and obtain the second hue sequence, second saturation sequence, and second brightness sequence of other images; Using the Pearson correlation coefficient, the correlation coefficients between the first hue sequence and the second hue sequence, the first saturation sequence and the second saturation sequence, and the first lightness sequence and the second lightness sequence were calculated respectively, resulting in hue correlation index, saturation correlation index, and lightness correlation index; Based on preset weight values, the hue correlation index, saturation correlation index, and brightness correlation index are weighted and fused to obtain the theme similarity between the color space of the theme reference image and the color space of other bitmap images.

7. The album generation method as described in claim 1, characterized in that, When the album categorization preference is time-based, the step of categorizing the images and generating an album based on the album categorization preference includes: Obtain the timestamps of all images, and sort the images in chronological order according to the timestamps to obtain the image sequence; Calculate the time difference between the timestamps of adjacent images in the image sequence; If the time difference is not greater than a preset time threshold, the adjacent images are grouped into the same album to generate a time-segment album.

8. The album generation method as described in claim 1, characterized in that, When the album category preference is location-based, the step of categorizing the user's pictures and generating an album based on the album category preference includes: Get the coordinates of all images; Iterate through all the images to select a location reference image, and calculate the distance difference between the coordinates of the location reference image and the coordinates of other images; If the distance difference is not greater than a preset distance threshold, the corresponding images are grouped into the same album to generate a location album.

9. The album generation method as described in claim 1, characterized in that, When the album category preference is "people," the step of categorizing the user's pictures and generating an album based on the album category preference includes: Using facial recognition algorithms, identify people in all images; The images are categorized by the individuals mentioned, and a photo album of each individual is generated.

10. The album generation method as described in claim 1, characterized in that, After classifying the user's pictures according to the album classification preferences and generating albums, the album generation method further includes: Based on the album category preferences and image content corresponding to the generated album, generate album names and album covers.

11. A photo album generation system, characterized in that, include: The preference acquisition module is used to acquire the user's photo album category preferences; The image classification module is used to classify images according to the album classification preferences and generate albums.

12. A photo album generation device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the album generation method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the album generation method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, perform the album generation method as described in any one of claims 1 to 10.

Images