Recommended methods, devices, electronic equipment, chips, and storage media

Abstract

This application proposes a recommendation method, apparatus, electronic device, chip, and storage medium, relating to the field of image processing. The method includes: acquiring a captured image in response to a shooting operation; the image including a background image; displaying a recommendation window in the image based on the composition information of the background image; and the recommendation window indicating a recommended photographic area for the subject within the image. Thus, by analyzing the composition information of the background image and providing a recommendation window matching that information, the recommended photographic area for the subject within the captured image is intuitively indicated, making the composition process more intuitive and convenient. Even users without photography experience can easily capture high-quality images using this function, greatly enhancing the user's shooting experience. Simultaneously, this method has broad applicability, lowers the technical threshold for photography, and improves the overall quality and aesthetics of the captured images.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and more particularly to a recommended method, apparatus, electronic device, chip, and storage medium. Background Technology

[0002] Against the backdrop of rapid digital and intelligent development, photography and related technologies have undergone tremendous changes. With the widespread use of smartphones, digital cameras, and other electronic devices, photography has become an indispensable part of people's daily lives. Whether capturing beautiful moments in life or expressing personal creativity through visual content, users yearn to easily take professional-grade photos. To address this, composition recommendation technology has emerged. It intelligently analyzes the shooting scene and provides aesthetically optimized composition suggestions to help users easily achieve high-quality photographic results. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art.

[0004] To this end, this application proposes a recommendation method, apparatus, electronic device, chip, and storage medium to intuitively indicate the recommended shooting area of ​​the subject in the shooting frame, making the composition process more intuitive and convenient. Even users without photography experience can easily shoot high-quality images with the help of this function, greatly enhancing the user's shooting experience.

[0005] One embodiment of this application proposes a recommended method, including:

[0006] In response to a shooting operation, the captured image is obtained; wherein the image includes a background image;

[0007] Based on the composition information of the background image, a recommendation window is displayed in the image; wherein the recommendation window is used to indicate the recommended photography area of ​​the subject in the image.

[0008] Another embodiment of this application proposes a recommended apparatus, comprising:

[0009] The acquisition module is used to acquire the captured image in response to the shooting operation; wherein the image includes a background image;

[0010] The display module is used to display a recommendation window in the image based on the composition information of the background image; wherein the recommendation window is used to indicate the recommended photography area of ​​the subject in the image.

[0011] Another embodiment of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the recommended method as described in the foregoing aspect.

[0012] Another aspect of this application provides a chip including an interface circuit and a processing circuit coupled to each other, the interface circuit being used to input or output signals, and the processing circuit being configured to perform the recommended method as described in the foregoing aspect.

[0013] In another aspect of this application, a non-transitory computer-readable storage medium is provided, having stored thereon computer program instructions that, when executed by a processor, implement the recommended method as described in the foregoing aspect.

[0014] Another aspect of this application provides a computer program product having a computer program stored thereon, which, when executed by a processor, implements the recommended method as described in the foregoing aspect.

[0015] The proposed method, apparatus, electronic device, chip, and storage medium analyze the composition information of a background image and provide a recommendation window that matches this information. This intuitively indicates the recommended photographic area for the subject within the captured image, making the composition process more intuitive and convenient. Even users without photography experience can easily capture high-quality images using this function, greatly enhancing the user's shooting experience. Furthermore, this method has broad applicability, not only meeting the needs of professional photographers for efficient composition but also helping ordinary users get started quickly, lowering the technical barrier to photography, reducing the time and difficulty of manual adjustments, and effectively improving the overall quality and aesthetics of the captured images.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 A flowchart illustrating the first recommended method provided in the embodiments of this application;

[0019] Figure 2 A flowchart illustrating the second recommended method provided in the embodiments of this application;

[0020] Figure 3 A flowchart illustrating the third recommended method provided in the embodiments of this application;

[0021] Figure 4 A flowchart illustrating the fourth recommended method provided in the embodiments of this application;

[0022] Figure 5 This is a schematic diagram illustrating the implementation principle of any embodiment of this application;

[0023] Figure 6 This is a schematic diagram of the structure of a recommended device provided in an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of the structure of a chip proposed in an embodiment of this application. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0027] To facilitate understanding, the terminology used in this application will be introduced first.

[0028] 1. Composition Recommendation Technology

[0029] Composition recommendation technology is a technique that uses advanced technologies such as computer vision, artificial intelligence, and machine learning to help users optimize the layout of their shots. It provides aesthetically optimized composition suggestions through intelligent analysis of the shooting scene.

[0030] Among them, composition recommendation technology mainly includes the following:

[0031] (1) Deep learning methods: In the field of graph composition recommendation, deep learning models such as ViewProposal Networks (VPNs) have been widely used. These models can be trained using massive amounts of image data, quickly generate and score candidate graph compositions, and demonstrate excellent real-time performance.

[0032] (2) Multi-network fusion method: Some cutting-edge studies have attempted to combine salient object detection networks with aesthetic evaluation networks to optimize the composition recommendation process. First, the salient object detection network identifies key regions (or salient object regions) in the image and preliminarily determines the location of the cropping box. Then, a series of candidate cropping boxes are generated around the cropping box using various sizes and scales. Finally, the aesthetic evaluation network performs aesthetic scoring on these candidate cropping boxes and selects the option with the highest score as the final output ideal cropping box; whereby the ideal cropping box is used to indicate the best composition scheme in the image. This method not only significantly improves the efficiency of obtaining the ideal cropping box but also enhances the overall composition quality.

[0033] (3) Reinforcement Learning Method: Reinforcement learning can be introduced into the field of image composition recommendation to search for the best cropping box more efficiently. Compared with traditional methods, reinforcement learning can reduce the number of candidate cropping boxes while shortening the running time, thereby more accurately locating the best cropping box. This strategy not only improves the accuracy of image composition recommendation but also significantly improves processing speed, providing users with a smoother service experience.

[0034] 2. User Preferences

[0035] Composition is a highly subjective task, with different users having their own unique aesthetic standards and composition preferences. For example, related experiments have shown that even when faced with the same image, different users may choose vastly different preferred composition methods. Therefore, how to incorporate users' personalized preferences into composition recommendation algorithms has become an important research direction in this field.

[0036] In related technologies, models learn and adapt to user preferences through retraining and fine-tuning. However, this approach faces challenges such as insufficient data, leading to difficulties in practical applications. To address these issues, some cutting-edge research has proposed a new solution: introducing a dedicated module to generate a rating mechanism tailored to user preferences. This rating mechanism allows the system to dynamically adjust the graph recommendation results based on the user's individual preferences, thereby more accurately meeting the user's personalized needs.

[0037] 3. Application areas of composition recommendation technology

[0038] The application areas of composition recommendation technology mainly include the following:

[0039] In the field of photography, composition recommendation technology has evolved from initial post-processing composition adjustments to real-time composition recommendations before shooting. This advancement not only helps non-professional users better master photographic composition techniques but also significantly improves shooting results. Through an intuitive user interface (UI) and diverse functions, composition recommendation technology seamlessly integrates into photographic practice, providing users with convenient and efficient composition assistance. Whether capturing wonderful moments in life or creating artistic works, users can easily achieve professional-level composition effects with the help of this technology.

[0040] In the fields of graphic and UI design, composition recommendation technology has also demonstrated its enormous application potential. It helps designers more efficiently arrange layouts and elements, thereby enhancing the overall aesthetics and information delivery of their designs. For example, the system can recommend the best composition and element combinations based on different design themes and user needs. This intelligent design assistance tool not only accelerates the design process but also ensures that the final product accurately meets the aesthetic preferences and functional requirements of the target audience.

[0041] In the field of photography, related technologies primarily employ the following approach to recommend optimal shooting locations (or best positions) to users: By utilizing the relative positional relationships between people and scenery in sample images, positive rules are learned to analyze where a person should stand in the shooting scene; based on empirical composition rules, negative rules are defined to determine areas in the shooting scene unsuitable for people to stand in; based on the scores of the positive and negative rules, a total position score for each person is obtained, and the optimal position for the shooting scene is searched accordingly; finally, a human-shaped icon is marked on the captured image to indicate the best position for the portrait and recommended to the user.

[0042] However, this approach requires the construction of a dedicated training dataset and the supplementation of many empirical graph construction examples, resulting in low efficiency and unstable performance.

[0043] Therefore, in view of at least one of the problems existing in the above-mentioned related technologies, this application proposes a recommended method, apparatus, electronic device, chip and storage medium.

[0044] The recommended methods, apparatus, electronic devices, chips, and storage media of this application are described below with reference to the accompanying drawings. Before specifically describing the embodiments of this application, commonly used technical terms are first introduced for ease of understanding:

[0045] 1. Rule of thirds: Divide the image into three equal parts horizontally and vertically to form a nine-square grid, and place the subject at the intersection of the four dividing lines or on the dividing lines.

[0046] The characteristics of the rule of thirds composition are: 1) Balance and dynamism: avoids the rigidity of centering the subject and increases the dynamism of the picture; 2) Visual guidance: conforms to human visual habits and naturally attracts the viewer's attention; 3) Flexibility: applicable to a variety of shooting scenarios, such as landscapes, portraits, architecture, etc.

[0047] Example: When shooting landscapes, place the horizon at the top or bottom third of the frame, rather than in the center.

[0048] 2. Rule of thirds composition: Similar to the rule of thirds, the image is divided into nine sections using a grid, with the subject placed at the intersections or along the lines.

[0049] The characteristics of the grid composition method are: 1) It emphasizes the offset of the subject, enhancing the dynamism and sense of layering of the image; 2) It is suitable for scenes such as portraits, animals, and architecture where the subject needs to be highlighted but should not be static.

[0050] Example: When shooting landscapes, such as vast grasslands, magnificent mountains, and tranquil lakes, the rule of thirds and grid composition are commonly used. Elements such as the horizon can be placed at the intersections of the rule of thirds lines or grid lines to make the picture more layered and balanced, allowing the viewer's eye to flow naturally in the picture and better appreciate the overall picture and details of the landscape.

[0051] 3. Symmetrical composition method: Place the subject in the center of the frame to create a symmetrical or stable visual effect.

[0052] The characteristics of symmetrical composition are: 1) Emphasis on the subject: directly highlighting the core elements of the image; 2) Stability: suitable for scenes that need to express solemnity and grandeur.

[0053] Example: Shoot symmetrical buildings (such as churches or palaces) or scenes where a central point needs to be emphasized (such as product advertisements). Alternatively, when shooting people, symmetrical composition can highlight the subject, placing the person in the center of the frame to clearly show their expression and posture.

[0054] 4. Diagonal composition method: Arrange the main subject or main lines along the diagonal of the frame to create a dynamic visual effect.

[0055] Characteristics of diagonal composition: 1) Dynamism and tension: The diagonal direction is guiding and enhances the vitality of the picture; 2) Sense of extension: It stretches the space of the picture and creates a deep or broad visual effect; 3) Application scenarios: Roads, bridges, rivers, dynamic figures, etc.

[0056] Example: When shooting winding roads or sloping buildings, you can use diagonal lines to guide the viewer's eye. Alternatively, when shooting people and wanting to create a lively and dynamic atmosphere, you can use diagonal composition, aligning the person's body or gaze with the diagonal line to increase the tension and sense of depth in the image.

[0057] 5. Leading Line Composition: Use lines in the picture (such as roads, rivers, railings, etc.) to guide the viewer's eye to the subject.

[0058] The characteristics of leading lines composition: 1) Visual guidance: naturally leading the viewer's attention to the focal point of the picture; 2) Enhancing depth: increasing the sense of depth of the picture through the extension of lines; 3) Diversity: the lines can be straight lines, curves, converging lines, etc.

[0059] Example: When shooting city streets, use the road as a leading line to guide the viewer's eye to distant buildings. Alternatively, when shooting sporting events, dance performances, or other dynamic scenes, you can use leading lines in your composition, utilizing the lines of a track or stage to guide the viewer's eye to the moving subject, making the image more dynamic and coherent, and better capturing the moment of motion and the athlete's brilliant performance.

[0060] Figure 1 This is a flowchart illustrating the first recommended method provided in the embodiments of this application.

[0061] It should be noted that the recommendation method in this application embodiment can be applied to a recommendation device. In some possible embodiments, the recommendation device can be configured in an electronic device or chip so that the electronic device or chip can perform the recommendation function. Additionally, in some possible embodiments, the recommendation device can also be software in an electronic device.

[0062] In any embodiment of this application, the chip can be integrated into an electronic device. The chip includes a Central Processing Unit (CPU), an Image Signal Processing (ISP), an Application-Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a System-on-A-Chip (SOC), a Reduced Instruction Set Computer (RISC), etc., which will not be listed here.

[0063] The electronic devices mentioned include, but are not limited to, terminals and imaging devices (such as digital cameras). A terminal is a user-side entity used to receive or transmit signals, such as a mobile phone. Terminals can also be called terminal equipment (UE), user equipment (UE), mobile station (MS), mobile terminal (MT), etc. Terminals can be communication-enabled vehicles, smart cars, mobile phones, wearable devices, tablets, computers with wireless transceiver capabilities, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc. The embodiments of this application do not limit the specific technology or device form used in the terminal.

[0064] like Figure 1 As shown, the recommended method may include the following steps S101 to S102:

[0065] Step S101: In response to the shooting operation, the captured image is obtained; wherein the image includes a background image.

[0066] The shooting operation includes preview, photo taking, and video recording.

[0067] The images referred to are those captured or photographed by the camera, including but not limited to: photo previews and video recordings. The cameras referred to include, but are not limited to, front-facing cameras and rear-facing cameras.

[0068] The image includes a background image, which refers to the portion of the frame captured by the camera during shooting, excluding the main subject or foreground subject. Simply put, the background image is the part of the frame located behind the main subject, providing environmental information for the entire shooting scene.

[0069] The subjects of the photographs include, but are not limited to, people, animals, and scenery.

[0070] Background images can contain a variety of visual elements, such as buildings, landscapes, and natural or man-made objects like the sky. These visual elements together constitute the environment or context in which the subject is situated. Background images not only provide visual richness and depth but also help tell a story about the subject or create a specific mood and atmosphere.

[0071] In this embodiment of the application, when a user-triggered operation is detected, the image captured by the camera can be obtained. The image includes a background image.

[0072] For example, object detection algorithms or object recognition algorithms can be used to identify various object images in the scene. Each object image belongs to a candidate object, and the distance between the candidate object and the camera is obtained. Based on the distance of each candidate object, background objects (or background objects) are detected from the candidate objects, and the object image corresponding to the background object can be used as the background image. The distance of the background object is greater than the object distance parameter associated with the camera.

[0073] It should be noted that this application does not limit the method of obtaining the distance between the candidate object and the camera. For example, the distance between the candidate object and the camera can be calculated based on phase difference technology, or it can be detected based on structured light sensors, time-of-flight (ToF) sensors, LiDAR (Light Detection and Range) sensors, etc. The embodiments of this application do not limit this.

[0074] Step S102: Based on the composition information of the background image, display a recommendation window in the image; wherein, the recommendation window is used to indicate the recommended photography area of ​​the subject in the image.

[0075] The composition information is used to indicate the composition of the background image. The composition includes symmetrical composition (centered composition) and asymmetrical composition. Asymmetrical composition includes, but is not limited to: rule of thirds, grid composition, diagonal composition, and leading line composition.

[0076] In this embodiment of the application, the composition information of the background image can be identified, and a recommendation window matching the composition information can be displayed on the screen. The recommendation window is used to indicate the recommended photography area of ​​the subject in the whole screen. For example, the recommended photography area may include the ideal photography area and the best photography area.

[0077] The recommended method in this application analyzes the composition information of the background image and provides a recommendation window that matches the composition information to intuitively indicate the recommended shooting area of ​​the subject in the captured image. This makes the composition process more intuitive and convenient, allowing even users without photography experience to easily capture high-quality images, greatly enhancing the user's shooting experience. Furthermore, this method has broad applicability, not only meeting the needs of professional photographers for efficient composition but also helping ordinary users get started quickly, lowering the technical threshold of photography, reducing the time and difficulty of manual adjustments, and effectively improving the overall quality and aesthetics of the captured image.

[0078] This application provides another recommended method. Figure 2 This is a flowchart illustrating the second recommended method provided in the embodiments of this application.

[0079] It should be noted that the recommended method can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiments of this application, or it can be executed together with any technical solution in the related technology. The embodiments of this application do not limit this.

[0080] like Figure 2 As shown, the recommended method may include the following steps S201 to S203:

[0081] Step S201: In response to the shooting operation, the captured image is obtained; wherein the image includes a background image.

[0082] It should be noted that the explanation of step S201 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0083] Step S202: Based on the composition information of the background image, determine a recommended shooting point in the image that matches the composition information.

[0084] The composition information is used to indicate the composition of the background image. The composition includes symmetrical composition (centered composition) and asymmetrical composition. Asymmetrical composition includes, but is not limited to: rule of thirds, grid composition, diagonal composition, and leading line composition.

[0085] The recommended shooting point indicates the recommended shooting position of the subject in the frame. For example, the recommended shooting position can include the best shooting position (or ideal shooting position). Taking a person as an example, the recommended shooting point can also be called the recommended standing position, the best standing position, or the ideal standing position.

[0086] In this embodiment of the application, the composition information of the background image can be identified, and a recommended shooting point matching the composition information can be determined from the captured image based on the composition information.

[0087] In any embodiment of this application, when the composition information indicates that the background image is composed in a symmetrical manner, a recommended shooting point matching the symmetrical composition can be determined from the captured image based on the symmetrical composition strategy.

[0088] As an example, you can determine recommended shooting points that match symmetrical composition based on the center point of the frame. For instance, the center point of the frame can be used as a recommended shooting point to match symmetrical composition.

[0089] Understandably, symmetrical composition is a very stable and attractive composition method. Using the center point of the image as the recommended shooting point can place the subject in the center of the image. This not only highlights the subject and reduces unnecessary distracting elements, allowing the viewer's attention to focus more on the subject, but also strengthens the sense of balance and stability (i.e., enhances visual balance), making the whole picture look more harmonious and improving the aesthetic effect.

[0090] In any embodiment of this application, when the composition information indicates that the background image is composed in an asymmetrical manner, a recommended shooting point matching the asymmetrical composition can be determined from the captured image based on the asymmetrical composition strategy.

[0091] In summary, it is possible to calculate and recommend shooting points based on the composition information of the background image, thereby improving the rationality and reliability of the calculation results.

[0092] Step S203: Based on the recommended shooting points, display a recommendation window in the image; wherein, the recommendation window is used to indicate the recommended shooting area of ​​the subject in the image.

[0093] In this embodiment, a recommendation window can be displayed on the screen based on recommended shooting points. For example, the recommended shooting point can be used as the center point of the recommendation window, referred to as the window center in this application.

[0094] As an example, the recommended shooting point can be used as the center of the recommended window, and the size of the recommended window can be determined according to the set ratio and the size of the image. Thus, the recommended window can be displayed in the image based on the center and size of the recommended window.

[0095] The set ratio is a preset ratio, for example, 0.01. Exemplarily, the set ratio can be a ratio actively set by the user based on personalized needs, or it can be a default ratio built into the electronic device (such as a factory preset value or a smart recommended value). This application embodiment does not limit this.

[0096] For example, the width of the marked image is w, the height is h, the ratio is r, the recommended shooting point position in the image is (x*, y*), and the recommended window position can be: (x*+ / -[0,r*w],y*+ / -[0,r*h]).

[0097] The aforementioned position can be a coordinate position in an image coordinate system or a coordinate position in a pixel coordinate system; this application embodiment does not impose any limitation on this.

[0098] In summary, the location of the recommended shooting point is determined by combining the actual location of the recommended shooting point with the size of the image. This recommended window not only provides a center point but also a specific area range, allowing users to more accurately place the subject in the ideal shooting position, thereby improving the accuracy of the composition. For example, if the subject is not within the recommended window, users can quickly adjust the shooting angle or the actual position of the subject based on the boundaries of the recommended window to ensure that the final image meets the expected composition requirements.

[0099] The recommendation method in this application analyzes the composition information of the background image and provides recommended shooting points (such as optimal shooting points) that match the composition information. This significantly reduces the time and difficulty for users to manually adjust, while effectively improving the overall quality and aesthetics of the captured image. The recommendation window displays the recommended shooting area for the subject within the frame, making the composition process more intuitive and convenient. Even users without photography experience can easily capture high-quality images using this function, greatly enhancing the user's shooting experience. Furthermore, this method has broad applicability, not only meeting the needs of professional photographers for efficient composition but also helping ordinary users get started quickly, lowering the technical barrier to photography.

[0100] This application provides another recommended method. Figure 3 This is a flowchart illustrating the third recommended method provided in the embodiments of this application.

[0101] It should be noted that the recommended method can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiments of this application, or it can be executed together with any technical solution in the related technology. The embodiments of this application do not limit this.

[0102] like Figure 3 As shown, the recommended method may include the following steps S301 to S307:

[0103] Step S301: In response to the shooting operation, the captured image is acquired; wherein the image includes a background image.

[0104] It should be noted that the explanation of step S301 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0105] Step S302: Based on the composition information of the background image, determine whether the background image has a symmetrical composition. If yes, proceed to step S303; otherwise, proceed to steps S304 to S306.

[0106] It should be noted that the explanation of the composition information in the foregoing embodiments also applies to this embodiment, and will not be repeated here.

[0107] It should also be noted that step S303 and steps S304 to S306 are two parallel implementation methods, and one of them can be selected for execution.

[0108] Step S303: Determine a recommended shooting point that matches the symmetrical composition based on the center point of the image.

[0109] The recommended shooting point indicates the best or ideal shooting position for the subject within the frame. Using a person as an example, the recommended shooting point can also be called the recommended standing position, the best standing position, or the ideal standing position.

[0110] In this embodiment of the application, when the composition information indicates that the background image has a symmetrical composition, a recommended shooting point matching the symmetrical composition can be determined based on the center point of the image. For example, the center point of the image can be used as the recommended shooting point.

[0111] Step S304: Detect target vertical lines and salient target regions from the background image; wherein, the salientity of the image content in the salient target regions is higher than the salientity of the image content in other regions.

[0112] Among them, the target vertical line includes the most important vertical line in the background image; that is, the target vertical line can be the vertical line with the highest importance in the background image.

[0113] The saliency region includes the most prominent target area in the background image; that is, the saliency of the content in the saliency region is higher than that in other areas. The other areas refer to all areas in the background image other than the saliency region.

[0114] In this embodiment of the application, when the composition information indicates that the background image has an asymmetrical composition, the target vertical line can be detected from the background image. For example, edge detection algorithms, Hough Transform, Line Segment Detector (LSD), and other methods can be used to detect the target vertical line from the background image.

[0115] In this embodiment, when the composition information indicates that the background image has an asymmetrical composition, a salient target region can also be detected from the background image. For example, a salient target region can be detected from the background image based on an attention detection mechanism.

[0116] Step S305: Based on the first distance between multiple visual interest points in the image and the target vertical line, and the second distance between multiple visual interest points and the significant target area, determine the pre-selected shooting point from multiple visual interest points.

[0117] Visual interest points, also known as visual focal points or points of attention, are the locations in an image that most attract the viewer's attention. Visual interest points guide the viewer's eye, focusing their attention on key visual elements within the image.

[0118] For example, visual points of interest may include multiple visual points of interest that match an asymmetric composition strategy associated with the subject. Asymmetric composition strategies include, but are not limited to, the rule of thirds, the grid composition, etc.

[0119] In this application, the asymmetrical composition strategy can be the same or different depending on the subject being photographed. Taking a person as an example, the asymmetrical composition strategy can include the rule of thirds. The visual interest points include the four intersection points of the rule of thirds (golden ratio positions). That is, the rule of thirds divides the image into three equal parts by two horizontal and two vertical lines, forming nine areas. The four intersection points of the lines create four visual interest points.

[0120] This allows us to identify the most eye-catching position in the image as a visual point of interest, quickly attracting the viewer's attention and focusing on the core visual elements, thus avoiding information overload.

[0121] In this embodiment of the application, the distance between multiple visual interest points in the image and the target vertical line can be calculated based on a distance calculation algorithm. This distance is referred to as the first distance in this application. The distance between multiple visual interest points and the center point of the significant target area can also be calculated. This distance is referred to as the second distance in this application. Then, a pre-selected shooting point can be determined from multiple visual interest points based on the first distance and the second distance.

[0122] For example, the second distance between the pre-selected shooting point and the salient target area is relatively small, while the first distance between the pre-selected shooting point and the target vertical line is relatively large.

[0123] Step S306: Based on the pre-selected shooting points, determine the recommended shooting points in the image that match the asymmetrical composition.

[0124] The recommended shooting point is used to indicate the recommended shooting position of the subject in the frame.

[0125] In this embodiment of the application, a recommended shooting point that matches the asymmetrical composition can be determined from the image based on the pre-selected shooting point.

[0126] As an example, recommended shooting points can be determined directly based on pre-selected shooting points. For instance, pre-selected shooting points can be used as recommended shooting points.

[0127] As another example, recommended shooting points can be indirectly determined based on pre-selected shooting points. For instance, a neighborhood of the pre-selected shooting points can be determined from the image, and a recommended shooting point that matches the asymmetrical composition can be randomly selected from that neighborhood.

[0128] It should be noted that the human visual system has a natural tolerance threshold for perceiving changes in object size, angle shifts, and light and shadow (e.g., fluctuations of ±15° in horizontal viewing angle and ±20% in light and shadow intensity can be imperceptibly accepted). Small displacement points within the neighborhood of a pre-selected shooting point can generate visually similar but more impactful images. Based on this characteristic, randomly selecting recommended shooting points from the neighborhood of a pre-selected shooting point has at least the following advantages: enhanced dynamic environment adaptation, utilizing the redundancy of the neighborhood to quickly respond to sudden changes in light (e.g., cloud movement, cloud cover causing a sudden drop in light intensity), dynamic shifts of the subject (e.g., random movement of people), or physical obstructions (e.g., crowd interference, sudden increase in crowd density), significantly reducing the reshoot rate; and creative uniqueness, by introducing controllable randomness around the pre-selected shooting point, it can capture unexpected compositions or activate hidden compositional opportunities (e.g., a picture-in-picture effect created by foreground reflections, or a halo effect caused by side-backlighting), enhancing the artistic expression of the captured image.

[0129] Step S307: Based on the recommended shooting points, display a recommendation window in the image; wherein, the recommendation window is used to indicate the recommended shooting area of ​​the subject in the image.

[0130] It should be noted that the explanation of step S307 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0131] The recommended method in this application, for background images with asymmetrical compositions, extracts target vertical lines (as structured visual guiding axes, such as sloping building outlines or the extension lines of dynamic figures' limbs) and significant target areas (as content focus anchors, such as faces or high-contrast landmarks). Based on the geometric correlation between visual interest points and extracted elements (i.e., the alignment of the first distance constraint point of interest with the target vertical line and the focus of the second distance constraint point of interest with the significant target area), pre-selected shooting points are determined. This method can automate visual balance (while preserving the conflict tension of the asymmetrical composition, reducing the viewer's perception of imbalance through geometric constraints) and precisely control attention guidance, thereby improving the efficiency of guiding viewer's attention.

[0132] This application provides another recommended method. Figure 4 This is a flowchart illustrating the fourth recommended method provided in the embodiments of this application.

[0133] It should be noted that the recommended method can be executed alone, or it can be executed together with any embodiment or possible implementation in the embodiments of this application, or it can be executed together with any technical solution in the related technology. The embodiments of this application do not limit this.

[0134] like Figure 4 As shown, the recommended method may include the following steps S401 to S407:

[0135] Step S401: In response to the shooting operation, the captured image is obtained; wherein the image includes a background image.

[0136] It should be noted that the explanation of step S401 can be found in the relevant description in any embodiment of this application, and will not be repeated here.

[0137] Step S402: In response to the composition information indicating that the background image is asymmetrical, detect the target vertical line from the background image.

[0138] Among them, the target vertical line includes the most important vertical line in the background image; that is, the target vertical line can be the vertical line with the highest importance in the background image.

[0139] In this embodiment of the application, when the composition information indicates that the background image has an asymmetrical composition, the target vertical line can be detected from the background image. For example, edge detection algorithms, Hough Transform, Line Segment Detector (LSD), and other methods can be used to detect the target vertical line from the background image.

[0140] In any embodiment of this application, the target vertical line can be detected using the following steps A to C:

[0141] Step A: Extract at least one candidate vertical line from the background image.

[0142] For example, edge detection algorithms, Hough Transform, Line Segment Detector (LSD) and other methods can be used to extract all vertical lines from the background image as candidate vertical lines.

[0143] Step B: Determine the importance of each candidate vertical line in the background image based on the shooting scene to which the background image belongs and / or the attribute information of each candidate vertical line.

[0144] The shooting locations include, but are not limited to, architectural scenes and landscape scenes.

[0145] The attribute information includes, but is not limited to: length, position, contrast, and sharpness.

[0146] For example, firstly, the importance of each attribute to the shooting scene can be determined based on the shooting scene to which the background image belongs. Then, the salience score of each candidate vertical line can be calculated based on each attribute and its corresponding importance. For example, for any candidate vertical line, different weights can be assigned according to the importance of different attributes, and the different attributes of the candidate vertical line can be weighted according to the weights of different attributes to obtain the salience score of the candidate vertical line. Finally, the importance of the candidate vertical line in the background image can be determined based on the salience score of each candidate vertical line.

[0147] Among them, the importance score is positively correlated with the significance score, that is, the higher the significance score, the higher the importance score.

[0148] For example, in architectural scenes, long vertical lines located in the center of the frame may be of greater importance, while in landscape photography, clear and high-contrast vertical lines are of greater importance.

[0149] Step C: Based on the importance of each candidate vertical line, determine the target vertical line from among the candidate vertical lines.

[0150] For example, the candidate vertical line with the highest importance can be used as the target vertical line.

[0151] In summary, it can not only effectively identify key vertical lines in background images, but also ensure that the selected vertical lines best meet the composition requirements and aesthetic standards of specific shooting scenarios, thereby improving the user's shooting experience.

[0152] Step S403: Detect significant target regions from the background image.

[0153] The saliency region includes the most prominent target area in the background image; that is, the saliency of the content in the saliency region is higher than that in other areas. The other areas refer to all areas in the background image other than the saliency region.

[0154] In this embodiment, when the composition information indicates that the background image has an asymmetrical composition, a salient target region can also be detected from the background image. For example, a salient target region can be detected from the background image based on an attention detection mechanism.

[0155] In any embodiment of this application, the saliency region can be detected using the following steps D to F:

[0156] Step D: Based on the attention mechanism, feature extraction is performed on the background image to obtain multi-scale features, and the multi-scale features are fused to obtain a fused feature map.

[0157] Multi-scale features include, but are not limited to: low-level features (low-level visual features) and high-level features (high-level semantic features).

[0158] For example, firstly, the background image can be processed to extract low-level features (such as color, brightness contrast, edge information, etc.) and high-level features (semantic features extracted through deep learning techniques). During this process, an attention mechanism is used to dynamically adjust the importance of different features to strengthen the representation of salient target regions. Then, methods such as weighted fusion or nonlinear transformation can be used to fuse the low-level and high-level features to generate a fused feature map.

[0159] Step E: Generate a saliency map based on the fused feature map; wherein, the value of a pixel in the saliency map is used to indicate the probability that the corresponding pixel in the background image belongs to a salient target region.

[0160] For example, firstly, attention mechanisms (such as channel attention, spatial attention, or self-attention) can be used to further enhance the fused feature map to obtain an enhanced feature map that highlights relevant information about salient target regions. Then, the enhanced feature map can be mapped to the spatial dimension of the saliency map (typically the size of the input background image) to obtain a mapped feature map. For instance, convolutional layers and upsampling operations can be used to adjust the enhanced feature map to the resolution of the background image to obtain the mapped feature map. Finally, an activation function (such as the sigmoid function) can be applied to the mapped feature map to compress the value of each pixel to the [0, 1] interval, representing the probability that the pixel belongs to a salient target region.

[0161] Step F: Identify salient target regions from the background image based on the saliency map.

[0162] In summary, the attention-based detection mechanism for identifying salient target regions combines low-level features with high-level semantic information, enabling effective and accurate identification of salient target regions in background images. Introducing mechanisms such as self-attention, channel attention, and spatial attention can further enhance detection performance, thereby improving the accuracy and reliability of the detection results.

[0163] Step S404: Based on the first distance between multiple visual interest points in the image and the target vertical line, determine at least one candidate shooting point from the multiple visual interest points.

[0164] It should be noted that the explanation of visual interest points in the foregoing embodiments also applies to this embodiment, and will not be repeated here.

[0165] In this embodiment of the application, the distance between multiple visual interest points in the image and the target vertical line can be calculated based on a distance calculation algorithm. This distance is referred to as the first distance in this application. Based on the first distance between the multiple visual interest points, at least one candidate shooting point is determined from the multiple visual interest points.

[0166] In any embodiment of this application, at least one visual point of interest with the largest first distance can be used as a candidate shooting point, that is, the visual point of interest farthest from the target vertical line can be used as a candidate shooting point. Taking the visual point of interest including the four intersections of the rule of thirds (golden section positions) as an example, the number of visual point of interest farthest from the target vertical line is 2, and they are located on the same vertical line.

[0167] Step S405: Determine the pre-selected shooting points from the candidate shooting points based on the second distance between each candidate shooting point and the significant target area.

[0168] In this embodiment of the application, the distance between each candidate shooting point and the center point of the target salient area can be calculated based on the distance calculation algorithm. This distance is denoted as the second distance in this application. Based on the second distance of each candidate shooting point, the pre-selected shooting point is determined from each candidate shooting point.

[0169] In any embodiment of this application, the candidate shooting point with the smallest second distance can be used as the pre-selected shooting point, that is, the candidate shooting point closest to the significant target area can be used as the pre-selected shooting point.

[0170] Step S406: Based on the pre-selected shooting points, determine the recommended shooting points in the image that match the asymmetrical composition.

[0171] The recommended shooting point is used to indicate the recommended shooting position of the subject in the frame.

[0172] Step S407: Based on the recommended shooting points, display a recommendation window in the image; wherein, the recommendation window is used to indicate the recommended shooting area of ​​the subject in the image.

[0173] It should be noted that the explanations of steps S406 to S407 can be found in the relevant descriptions in any embodiment of this application, and will not be repeated here.

[0174] The recommended method in this application embodiment firstly selects the candidate shooting point with the largest first distance from multiple visual interest points, that is, selects the position that is farthest from the target vertical line, so as to use the "reverse stretching" effect of the target vertical line of the point to strengthen the conflict tension of the asymmetrical composition. Then, among the candidate shooting points with the maximum conflict tension, the second pre-selected shooting point with the smallest second distance is further selected, that is, the point that is closest to the prominent target area is selected, so as to achieve the dynamic balance of the image in the release of tension through the spatial gravity game between the "conflict anchor point" (target vertical line) and the "focus anchor point" (prominent target area).

[0175] In any embodiment of this application, taking a person as the subject of the photograph as an example, a better person's position can be recommended to the user based on an attention detection mechanism and classic composition theory. The implementation principle is as follows: Figure 5 As shown, the main steps include:

[0176] Step S51: Determine whether the background image in the picture is symmetrical. If yes, proceed to step S52; otherwise, proceed to step S53.

[0177] Step S52: If the background image is symmetrical, then symmetrical composition is recommended, the center point of the person is output (referred to as the recommended shooting point in this application, such as the center point of the image), and the recommendation window is output.

[0178] Step S53: If the background image is asymmetrical, detect the vertical lines in the background image, select the main vertical lines (referred to as target vertical lines in this application), calculate the salient target region saliency of the background image, and confirm the center point coordinates of the saliency.

[0179] Step S54: Calculate the distance between the four intersection points (also known as visual attention points) of the rule of thirds and the target vertical line, and select the intersection point with the farthest distance as the candidate shooting point.

[0180] Step S55: Calculate the distance between each candidate shooting point and the center point of the saliency, and select the candidate shooting point with the closest distance as the pre-selected shooting point.

[0181] Step S56: Randomly select a center point of the person (i.e., a recommended shooting point) within the neighborhood of the pre-selected shooting point, and output a recommendation window. The coordinates of the center point of the person (i.e., the recommended shooting point) are marked as (x*, y*), and the coordinates of the recommendation window are (x*+ / -[0, r*w], y*+ / -[0, r*h]). Here, r is a set ratio, for example, 0.01.

[0182] In summary, the solution provided in this application has at least the following advantages: based on the attention detection mechanism and classic composition strategies, it can simply and efficiently handle the recommendation problem of portrait positioning, and can meet most shooting scenarios of daily, portrait and sports photography.

[0183] To implement the above embodiments, this application also proposes a recommended device.

[0184] Figure 6 This is a schematic diagram of a recommended device provided in an embodiment of this application.

[0185] like Figure 6 As shown, the recommendation device 600 may include an acquisition module 610 and a display module 620.

[0186] The acquisition module 610 is used to acquire the captured image in response to the shooting operation; the image includes a background image.

[0187] The display module 620 is used to display a recommendation window in the image based on the composition information of the background image; wherein, the recommendation window is used to indicate the recommended photography area of ​​the subject in the image.

[0188] Furthermore, in one implementation of this application embodiment, the recommendation window includes recommended shooting points that match the composition information; wherein, the recommended shooting points are used to indicate the recommended shooting position of the subject in the frame.

[0189] In one implementation of this application, the recommended shooting point is determined using the following modules:

[0190] The first determining module is used to determine a recommended shooting point that matches the symmetrical composition based on the center point of the image, in response to the composition information indicating that the background image is symmetrical.

[0191] In one implementation of this application, the recommended shooting point is determined using the following modules:

[0192] The detection module is used to detect target vertical lines and salient target regions from the background image in response to the composition information indicating that the background image is asymmetrically composed; wherein, the salientity of the image content in the salient target region is higher than the salientity of the image content in other regions.

[0193] The second determining module is used to determine the pre-selected shooting point from multiple visual interest points based on the first distance between multiple visual interest points in the image and the target vertical line, and the second distance between multiple visual interest points and the significant target area.

[0194] The third determining module is used to determine recommended shooting points from the image that match the asymmetrical composition based on the pre-selected shooting points.

[0195] In one implementation of this application, the second determining module is configured to: determine at least one candidate shooting point from multiple visual interest points based on a first distance between multiple visual interest points and the target vertical line; and determine a pre-selected shooting point from each candidate shooting point based on a second distance between each candidate shooting point and the significant target area.

[0196] In one implementation of this application, the second determining module is used to: select at least one visual interest point with the largest first distance as a candidate shooting point; and select the candidate shooting point with the smallest second distance as a pre-selected shooting point.

[0197] In one implementation of this application, the third determining module is used to: determine the neighborhood of the pre-selected shooting point from the image based on the pre-selected shooting point; and randomly select a recommended shooting point that matches the asymmetric composition from the neighborhood.

[0198] In one implementation of this application, the detection module is configured to: extract at least one candidate vertical line from the background image; determine the importance of each candidate vertical line in the background image based on the shooting scene to which the background image belongs and / or the attribute information of each candidate vertical line; and determine the target vertical line from each candidate vertical line based on the importance of each candidate vertical line.

[0199] In one implementation of this application, the detection module is used to: extract features from the background image based on an attention mechanism to obtain multi-scale features, and fuse the multi-scale features to obtain a fused feature map; generate a saliency map based on the fused feature map; wherein the value of a pixel in the saliency map is used to indicate the probability that the corresponding pixel in the background image belongs to a salient target region; and determine a salient target region from the background image based on the saliency map.

[0200] In one implementation of this application, the second determining module is further configured to: determine multiple visual interest points in the image that match the asymmetric composition strategy based on the asymmetric composition strategy associated with the subject being photographed.

[0201] In one implementation of this application, the display module 620 is used to: use the recommended shooting point as the center of the recommended window; determine the size of the recommended window according to the set ratio and the size of the image; and display the recommended window in the image according to the center and size of the recommended window.

[0202] It should be noted that the foregoing explanation of the recommended method embodiment also applies to the recommended device of this embodiment, and will not be repeated here.

[0203] In the recommendation device of this application embodiment, by analyzing the composition information of the background image and providing a recommendation window that matches the composition information, the recommended shooting area of ​​the subject in the shooting scene is intuitively indicated, making the composition process more intuitive and convenient. Even users without photography experience can easily shoot high-quality images with the help of this function, greatly enhancing the user's shooting experience. At the same time, this method has wide applicability, not only meeting the needs of professional photographers for efficient composition, but also helping ordinary users get started quickly, lowering the technical threshold of photography, reducing the time and difficulty of manual adjustments, and effectively improving the overall quality and aesthetics of the captured image.

[0204] To implement the above embodiments, this application also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the recommended method as described in any of the foregoing embodiments.

[0205] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example, the electronic device 700 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0206] Reference Figure 7The electronic device 700 may include one or more of the following components: processing component 702, memory 704, power component 706, multimedia component 708, audio component 710, input / output (I / O) interface 712, sensor component 714, and communication component 716.

[0207] Processing component 702 typically controls the overall operation of electronic device 700, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 702 may include one or more modules to facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702.

[0208] Memory 704 is configured to store various types of data to support the operation of electronic device 700. Examples of this data include instructions for any application or method operating on electronic device 700, contact data, phonebook data, messages, pictures, videos, etc. Memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, 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 storage, flash memory, magnetic disk, or optical disk.

[0209] Power component 706 provides power to various components of electronic device 700. Power component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 700.

[0210] Multimedia component 708 includes a screen that provides an output interface between the electronic device 700 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 touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 708 includes a front-facing camera and / or a rear-facing camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0211] Audio component 710 is configured to output and / or input audio signals. For example, audio component 710 includes a microphone (MIC) configured to receive external audio signals when electronic device 700 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 704 or transmitted via communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

[0212] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0213] Sensor assembly 714 includes one or more sensors for providing state assessments of various aspects of electronic device 700. For example, sensor assembly 714 can detect the on / off state of electronic device 700, the relative positioning of components such as the display and keypad of electronic device 700, changes in position of electronic device 700 or a component of electronic device 700, the presence or absence of user contact with electronic device 700, orientation or acceleration / deceleration of electronic device 700, and temperature changes of electronic device 700. Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 714 may also include an optical sensor, such as a complementary metal-oxide-semiconductor (CMOS) or charge-coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, sensor assembly 714 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0214] Communication component 716 is configured to facilitate wired or wireless communication between electronic device 700 and other devices. Electronic device 700 can access wireless networks based on communication standards, such as WiFi, 4G, or 5G, or combinations thereof. In one exemplary embodiment, communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 716 also includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), Bluetooth, and other technologies.

[0215] In an exemplary embodiment, the electronic device 700 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, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0216] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, which can be executed by a processor 720 of an electronic device 700 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0217] To implement the above embodiments, this application also proposes a chip, wherein the chip includes an interface circuit and a processing circuit coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is configured to perform the recommended method as provided in any of the foregoing embodiments.

[0218] Figure 8 This is a schematic diagram of another chip structure proposed in an embodiment of this application. See also... Figure 8 The diagram shown is a schematic representation of the structure of chip 800, but is not limited to this.

[0219] Chip 800 includes processing circuitry 801, which is configured to perform any of the recommended methods described above.

[0220] In some embodiments, the chip 800 further includes one or more interface circuits 802. Optionally, the interface circuit 802 is connected to the memory 803, and the interface circuit 802 can be used to receive signals from the memory 803 or other devices, and the interface circuit 802 can be used to send signals to the memory 803 or other devices. For example, the interface circuit 802 can read instructions stored in the memory 803 and send the instructions to the processing circuit 801.

[0221] In some embodiments, the interface circuit 802 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processing circuit 801 performs other steps.

[0222] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0223] In some embodiments, chip 800 further includes one or more memories 803 for storing instructions. Optionally, all or part of the memories 803 may be located outside of chip 800.

[0224] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the recommended method as described in any of the foregoing method embodiments.

[0225] To implement the above embodiments, this application also proposes a computer program product having a computer program stored thereon, which, when executed by a processor, implements the recommended method as described in any of the foregoing method embodiments.

[0226] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0227] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0228] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0229] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and compact disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0230] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0231] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0232] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0233] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A recommendation method characterized by comprising: The method comprises the following steps: in response to a shooting operation, acquiring a shot picture; wherein the picture comprises a background image; according to composition information of the background image, displaying a recommendation window in the picture; wherein the recommendation window is used to indicate a recommended photography area of a shooting subject in the picture, and the recommendation window comprises a recommended shooting point matching the composition information; wherein the recommended shooting point is used to indicate a recommended photography position of the shooting subject in the picture; the recommended shooting point is determined by the following steps: in response to the composition information indicating that the background image is a non-symmetrical composition, detecting a target vertical line and a significant target area from the background image; wherein the significant degree of picture content in the significant target area is higher than that of other areas, and the target vertical line is the vertical line with the highest importance in the background image; determining a pre-selected shooting point from a plurality of visual interest points in the picture according to a first distance between the plurality of visual interest points and the target vertical line, and a second distance between the plurality of visual interest points and the significant target area; determining the recommended shooting point matching the non-symmetrical composition from the picture according to the pre-selected shooting point.

2. The method of claim 1, wherein, the recommended shooting point is determined by the following steps: in response to the composition information indicating that the background image is a symmetrical composition, determining the recommended shooting point matching the symmetrical composition according to a center point of the picture.

3. The method of claim 1, wherein, the method of determining a pre-selected shooting point from a plurality of visual interest points in the picture according to a first distance between the plurality of visual interest points and the target vertical line, and a second distance between the plurality of visual interest points and the significant target area, comprises: determining at least one candidate shooting point from the plurality of visual interest points according to the first distance between the plurality of visual interest points and the target vertical line; determining the pre-selected shooting point from the at least one candidate shooting point according to the second distance between each of the candidate shooting points and the significant target area.

4. The method of claim 3, wherein, the method of determining at least one candidate shooting point from the plurality of visual interest points according to the first distance between the plurality of visual interest points and the target vertical line, comprises: taking at least one visual interest point with the largest first distance as the candidate shooting point; the method of determining the pre-selected shooting point from the at least one candidate shooting point according to the second distance between each of the candidate shooting points and the significant target area, comprises: taking the candidate shooting point with the smallest second distance as the pre-selected shooting point.

5. The method of claim 1, wherein, the method of determining the recommended shooting point matching the non-symmetrical composition from the picture according to the pre-selected shooting point, comprises: determining a neighborhood of the pre-selected shooting point from the picture according to the pre-selected shooting point; randomly selecting the recommended shooting point matching the non-symmetrical composition from the neighborhood.

6. The method of claim 1, wherein, the method of detecting a target vertical line from the background image, comprises: extracting at least one candidate vertical line from the background image; determining the importance of each of the candidate vertical lines in the background image according to the shooting scene to which the background image belongs and / or the attribute information of each of the candidate vertical lines; The target vertical line is determined from the candidate vertical lines based on importance of each of the candidate vertical lines.

7. The method of claim 1, wherein, Detecting a salient target region from the background image, comprising: Feature extraction is performed on the background image to obtain multi-scale features, and the multi-scale features are fused to obtain a fused feature map; An importance map is generated according to the fused feature map; wherein a value of a pixel point in the importance map is used to indicate a probability that a corresponding pixel point in the background image belongs to the salient target region; The salient target region is determined from the background image according to the importance map.

8. The method according to any one of claims 1-7, characterized in that, The multiple visual interest points are determined by the following steps: Based on an asymmetric composition strategy associated with the shooting subject, multiple visual interest points matching the asymmetric composition strategy are determined from the picture.

9. The method according to any one of claims 1-7, characterized in that, Displaying a recommendation window in the picture, comprising: Taking the recommended shooting point as a window center of the recommendation window; Determining a size of the recommendation window according to a set proportion and a size of the picture; Displaying the recommendation window in the picture according to the window center and the size of the recommendation window.

10. A recommendation apparatus characterized by comprising: Comprising: An acquisition module is configured to acquire a picture shot in response to a shooting operation, wherein the picture comprises a background image; A display module is configured to display a recommendation window in the picture according to composition information of the background image, wherein the recommendation window is used to indicate a recommended photography area of a shooting subject in the picture, and the recommendation window comprises a recommended shooting point matching the composition information, wherein the recommended shooting point is used to indicate a recommended photography position of the shooting subject in the picture; The recommended shooting point is determined by the following modules: A detection module is configured to detect a target vertical line and a salient target region from the background image in response to the composition information indicating that the background image is asymmetrically composed, wherein a saliency degree of picture content in the salient target region is higher than that of other regions, and the target vertical line is a vertical line with the highest importance in the background image; A second determination module is configured to determine a pre-selected shooting point from multiple visual interest points in the picture according to a first distance between the multiple visual interest points and the target vertical line, and a second distance between the multiple visual interest points and the salient target region; A third determination module is configured to determine the recommended shooting point matching the asymmetric composition from the picture according to the pre-selected shooting point.

11. An electronic device, comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the program to implement the steps of the method in any one of claims 1 to 9.

12. A non-transitory computer-readable storage medium having stored thereon computer program instructions, wherein, The program instructions are executed by the processor to implement the steps of the method in any one of claims 1 to 9.

13. A chip, characterized by The chip comprises an interface circuit and a processing circuit coupled with each other, the interface circuit is used for inputting or outputting signals, and the processing circuit is used for implementing the method in any one of claims 1 to 9.

14. A computer program product, characterised in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 9.

Images