Image processing method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to an image processing method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring a currently shot target image, acquiring scene feature data according to the target image, and acquiring target magnification data corresponding to the target image; according to the scene feature data and the target magnification data, an image zooming processing instruction under the current magnification is obtained, the image zooming processing instruction at least comprises the zooming magnification of each image processing module in the electronic equipment, and each image processing module is used for executing image processing tasks in different stages; and in response to the image zooming processing instruction, performing image zooming processing on the target image through each image processing module. By adopting the method, the image quality of the zoomed image can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an image processing method, device, electronic device, storage medium and program product. Background Art

[0002] At present, more and more electronic devices have image capture functions, and most electronic devices also support zoom function during image capture. Zoom is generally divided into optical zoom and digital zoom. The zoom function allows users to adjust the shooting angle and the size of the shooting picture without changing the shooting position.

[0003] Taking digital zoom as an example, in the related art, after the user sets the desired image zoom ratio, the electronic device crops and upsamples the captured image according to the ratio, thereby achieving a zoom effect by changing the size of the imaging surface.

[0004] However, the above method has the problem that the image quality after zooming is poor. Summary of the invention

[0005] The embodiments of the present application provide an image processing method, device, electronic device, storage medium and program product, which can improve the image quality of a zoomed image.

[0006] In a first aspect, the present application provides an image processing method. The method comprises:

[0007] Acquire a currently captured target image, acquire scene feature data according to the target image, and acquire target magnification data corresponding to the target image;

[0008] According to the scene feature data and the target magnification data, an image zoom processing instruction at a current magnification is obtained, wherein the image zoom processing instruction at least includes a zoom factor of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages;

[0009] In response to the image zoom processing instruction, each of the image processing modules performs image zoom processing on the target image.

[0010] In a second aspect, the present application also provides an image processing device. The device comprises:

[0011] A first acquisition module is used to acquire a currently captured target image, acquire scene feature data according to the target image, and acquire target magnification data corresponding to the target image;

[0012] A second acquisition module is used to acquire an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data, wherein the image zoom processing instruction at least includes a zoom factor of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages;

[0013] The processing module is used to respond to the image zoom processing instruction and perform image zoom processing on the target image through each of the image processing modules.

[0014] In a third aspect, the present application further provides an electronic device, wherein the electronic device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] The above-mentioned image processing method, device, electronic device, storage medium and program product obtain the target image currently being shot, obtain scene feature data based on the target image, and obtain target magnification data corresponding to the target image, and then obtain the image zoom processing instruction at the current magnification based on the scene feature data and the target magnification data, and the image zoom processing instruction at least includes the zoom multiple of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages. Then, in response to the image zoom processing instruction, each image processing module performs image zoom processing on the target image. In this way, the embodiment of the present application can dynamically adjust the zoom multiple of each image processing module according to the scene feature data. The scene feature data can represent the complexity of the shooting scene of the electronic device. For example, when the scene feature data represents that the shooting scene is relatively complex, the image processing module with better image detail retention is reduced. For example, if the pre-processing module retains better image details during the image processing process, the zoom factor of the pre-processing module is reduced. This can avoid the problem of excessive image quality loss caused by the pre-processing module cropping out too much image area (the larger the zoom factor, the more image area is cropped out, and the less image area is retained after cropping) to reduce the image quality loss. In addition, the zoom factors of other image processing modules (such as the post-processing module) are increased to meet the magnification requirements corresponding to the target magnification data. This can retain more image details and avoid the problem that the zoom ratio of each image processing module in the traditional technology is fixed, and there may be an image processing module with better image detail retention that crops out too much image area, resulting in loss of image details, resulting in poor image quality after zoom, especially in complex shooting scenes. The embodiment of the present application can improve the image quality of the zoomed image. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flowchart of an image processing method in one embodiment;

[0020] Figure 2 is a flowchart of step 102 in another embodiment;

[0021] Figure 3 is a schematic diagram of each image processing module in another embodiment;

[0022] Figure 4is a flowchart of step 103 in another embodiment;

[0023] Figure 5 A schematic diagram of an exemplary default cropping area position and an adjusted cropping area position in another embodiment;

[0024] Figure 6 A schematic diagram of an exemplary default cropping area position and an adjusted cropping area position in another embodiment;

[0025] Figure 7 is a structural block diagram of an image processing device in one embodiment;

[0026] Figure 8 FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] Currently, more and more electronic devices have image capture functions, and most electronic devices also support zoom functions during image capture. Generally, a larger zoom factor is more suitable for telephoto shooting. A larger zoom factor means a smaller FOV (Field of View).

[0029] At present, there are usually two ways to change the field of view: one is to change the focal length of the lens, which is to change the relative position of each lens in the lens; the other is to change the size of the imaging surface, that is, to change the diagonal length of the imaging surface.

[0030] The first method mentioned above is called optical zoom, and the second method is called digital zoom. Although both optical zoom and digital zoom can pull the image in (or magnify it) and reduce the FOV, the difference in zoom principles will cause the clarity of the zoomed image to be quite different.

[0031] For the above two zoom methods, although both help to magnify distant objects when telephoto shooting, only optical zoom can support adding more pixels after the subject is imaged, making the subject not only larger but also relatively clearer. This is because the optical zoom lens is designed the same as that of traditional cameras. Optical zoom is achieved by adjusting the positions of the lens, object and focus. When the imaging surface moves in the horizontal direction, the vision and focal length will change, and the farther the scene, the clearer it becomes, giving people the feeling of objects approaching. Therefore, the resolution and image quality after optical zoom processing will not change.

[0032] Digital zoom can only reduce the size of the original image, making the cropped image "larger" on the screen, but it does not help make details clearer, because digital zoom does not change the focal length of the lens. It only changes the field of view by changing the diagonal angle of the imaging surface, thereby producing an effect "equivalent to" a change in the focal length of the lens.

[0033] In daily life, we can see that some digital devices with longer lenses have more space for the lenses and photosensors to move, so the zoom ratio is also greater. However, some ultra-thin digital devices generally do not have optical zoom function because the movement of the photosensitive devices is not allowed inside their bodies.

[0034] Due to the limitations of lens length and size, digital zoom is usually used in electronic devices. Currently, after the user sets the required image zoom ratio, the electronic device allocates the required ratio to each image processing module according to a fixed zoom ratio. Each image processing module crops and upsamples the captured image according to the allocated ratio, thereby achieving a zoom effect by changing the size of the imaging surface. However, this method has the problem of low image quality after zooming, which is more obvious in complex shooting scenes.

[0035] In view of this, the embodiment of the present application obtains the target image currently being photographed, obtains scene feature data based on the target image, and obtains target magnification data corresponding to the target image, and then obtains an image zoom processing instruction at the current magnification based on the scene feature data and the target magnification data, wherein the image zoom processing instruction at least includes the zoom multiples of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages. Then, in response to the image zoom processing instruction, each image processing module performs image zoom processing on the target image. In this way, the embodiment of the present application can dynamically adjust the zoom multiples of each image processing module based on the scene feature data. The scene feature data can characterize the complexity of the shooting scene of the electronic device. For example, when the scene feature data characterizes that the shooting scene is relatively complex, the zoom multiple of the image processing module that retains better image details is reduced, for example If the pre-processing module retains better image details during the image processing process, the zoom factor of the pre-processing module is reduced. This can avoid the problem of excessive image quality loss caused by the pre-processing module cropping out too much image area (the larger the zoom factor, the more image area is cropped, and the less image area is retained after cropping) to reduce the image quality loss. In addition, the zoom factors of other image processing modules (such as the post-processing module) are increased to meet the magnification requirements corresponding to the target magnification data. This can retain more image details and avoid the problem that the zoom ratio of each image processing module in the traditional technology is fixed, and there may be an image processing module with better image detail retention cropping out too much image area, resulting in loss of image details, resulting in poor image quality after zoom, especially in complex shooting scenes. The embodiment of the present application can improve the image quality of the zoomed image.

[0036] The image processing method provided in the embodiments of the present application can be applied to electronic devices, and the electronic devices may be, but are not limited to, various smart phones, laptop computers, tablet computers, smart watches, smart bracelets, smart glasses, etc.

[0037] In one embodiment, Figure 1 As shown, an image processing method is provided, and the method is applied to an electronic device for illustration. It can be understood that the method can also be applied to a system including an electronic device and a server, and is implemented through the interaction between the electronic device and the server.

[0038] In this embodiment, the method includes the following steps:

[0039] Step 101 : The electronic device obtains a currently captured target image, obtains scene feature data according to the target image, and obtains target magnification data corresponding to the target image.

[0040] A shooting component may be provided in the electronic device, and the electronic device captures an image through the shooting component to obtain a target image.

[0041] It should be noted that the image capture mentioned here may refer to image capture during the photo taking process, image capture during the video recording process, or image capture during the photo preview or video recording preview process, and no specific limitation is made here.

[0042] The electronic device obtains scene feature data of the current shooting scene based on the captured target image. The scene feature data can characterize the complexity of the shooting scene of the electronic device. For example, the size of the scene feature data is positively correlated with the complexity of the shooting scene of the electronic device. That is, the larger the scene feature data, the higher the complexity of the shooting scene of the electronic device. Conversely, the smaller the scene feature data, the lower the complexity of the shooting scene of the electronic device.

[0043] Exemplarily, the electronic device may calculate the scene feature data based on the target image using a preset scene complexity algorithm, or may also calculate the scene feature data based on the target image and historical images using a preset scene complexity algorithm, and so on.

[0044] As an implementation method, the scene feature data may be a scene complexity level. For example, the scene complexity level is low, medium or high, wherein a low level represents that the complexity of the current shooting scene is low, that is, the shooting scene is relatively simple, such as a single-color picture background; a medium level represents that the complexity of the current shooting scene is medium; a high level represents that the complexity of the current shooting scene is high, such as a complex picture background, and so on.

[0045] Of course, the scene feature data may also be a specific quantitative value, and the form of the scene feature data is not limited here.

[0046] In an embodiment of the present application, the electronic device may periodically acquire scene feature data of the shooting scene. For example, the electronic device acquires scene feature data once every 10 frames. Alternatively, the electronic device may also acquire scene feature data of the shooting scene when zooming is required (for example, a zoom trigger operation is detected), and so on.

[0047] In this way, the electronic device obtains the scene feature data of the current shooting scene. In the embodiment of the present application, the electronic device can also obtain the target magnification data corresponding to the target image, which can be the magnification requirement data input by the user or the default image zoom magnification.

[0048] In addition, it should be noted that the target image in the embodiment of the present application can be an initial image taken by the electronic device, or it can be an initial image taken by the electronic device in the current shooting scene. The electronic device is provided with a zoom sensor inzoom sensor component, and the electronic device adjusts the magnification of the initial image through the inzoom sensor component to obtain the target image.

[0049] Among them, the advantage of using the inzoom sensor component to zoom in is that the image clarity is better, but the inzoom sensor component has a limited magnification problem (generally only 2 times can be magnified). Therefore, the target image is magnified based on the image processing method of the embodiment of the present application.

[0050] Optionally, the target magnification data acquired by the electronic device may be magnification requirement data input by the user for the target image after the inzoom sensor component has magnified. Of course, the user may also input initial magnification requirement data for the initial image taken by the electronic device. The electronic device divides the initial magnification requirement data by the magnification of the inzoom sensor component to obtain the target magnification data mentioned in step 101.

[0051] Step 102: The electronic device obtains an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data. The image zoom processing instruction at least includes the zoom magnification of each image processing module in the electronic device.

[0052] Generally speaking, during the entire image zoom processing process, there will be multiple image processing modules supporting the zoom processing function, and each image processing module is used to perform image processing tasks at different stages. Therefore, the effect of retaining image details in the image processing process by each image processing module is also different.

[0053] For example, taking the image processing modules as the pre-processing module and the post-processing module in ISP (Image Signal Processing), the pre-processing module is mainly used for image noise reduction in the RAW domain, and the post-processing module is mainly used for image noise reduction in the YUV domain. Compared with the post-processing module, the pre-processing module retains better image details during the image processing process, especially in complex shooting scenes. Retaining more image details can greatly improve image quality.

[0054] In view of this, in an embodiment of the present application, the electronic device can dynamically adjust the image zoom processing instructions at the current magnification based on the acquired scene feature data and target magnification data, and the image zoom processing instructions may include the zoom magnification of each image processing module in the electronic device.

[0055] In a possible implementation of step 102, the mapping relationship between each scene feature data, each target magnification data and each image zoom processing instruction can be manually pre-configured to obtain a configuration file. In this way, the electronic device can search for the image zoom processing instruction corresponding to the current scene feature data and target magnification data in the preset configuration file based on the scene feature data and target magnification data obtained in step 101.

[0056] In another possible implementation of step 102, the prediction model may be pre-trained, and the electronic device inputs the acquired scene feature data and target magnification data into the trained prediction model to obtain the image zoom processing instruction output by the prediction model.

[0057] In other possible implementations of step 102, the above-mentioned scene characteristic data can be used to determine the ratio of the zoom magnification of each image processing module (the sum of the ratios of the zoom magnifications of each image processing module is 1). The larger the scene characteristic data (that is, the more complex the shooting scene is), the smaller the ratio of the zoom magnification of the image processing module that better preserves the image details. Then, the ratio of the zoom magnification of each image processing module is multiplied by the target magnification data to obtain the zoom magnification of each image processing module.

[0058] Here, there is no limitation on the specific implementation manner in which the electronic device obtains the image zoom processing instruction according to the scene feature data and the target magnification data.

[0059] Exemplarily, as described above, the image processing module may include a pre-processing module and a post-processing module, and the scene feature data is used to characterize the complexity of the shooting scene of the electronic device. In the image zoom processing instruction, the zoom factor of the pre-processing module is negatively correlated with the size of the scene feature data, and the zoom factor of the post-processing module is positively correlated with the size of the scene feature data.

[0060] That is, the more complex the shooting scene represented by the scene feature data is, the smaller the zoom factor of the pre-processing module is, so as to avoid the problem of excessive image quality loss caused by the pre-processing module cropping out too much image area, and the larger the zoom factor of the post-processing module is, so as to ensure that the product of the zoom factor of the pre-processing module and the zoom factor of the post-processing module can be equal to the target magnification data to meet the magnification requirement.

[0061] The following describes the relationship between the image zoom processing instruction at the current magnification determined by the electronic device according to the scene feature data and the target magnification data through an example.

[0062] Assume that the scene feature data is the scene complexity level, and the scene complexity level is a high level, and the target magnification data is 10 (i.e., magnification 10 times). For example, the image zoom processing instructions at the current magnification may include a zoom magnification of 2 times for the pre-processing module and a zoom magnification of 5 times for the post-processing module.

[0063] In other possible implementations, the image processing module may also be set with a magnification limit, or a zoom magnification limit, that is, a magnification upper limit is set for the image processing module to avoid problems such as unsatisfactory effects or module instability after a certain magnification. Therefore, in other possible implementations of step 102, the electronic device may also determine the initial zoom magnification of each image processing module based on the scene feature data and the target magnification data, and then adjust the initial zoom magnification in combination with the magnification limit of the image processing module to obtain the zoom magnification of each image processing module. Of course, it is also possible to keep the initial zoom magnification unchanged, that is, directly use the initial zoom magnification as the zoom magnification of the image processing module, and so on.

[0064] Step 103: the electronic device performs image zoom processing on the target image through each image processing module in response to the image zoom processing instruction.

[0065] At the current magnification, the electronic device performs image zoom processing on the target image through each image processing module in sequence according to the hierarchical relationship of each image processing module based on the zoom magnification of each image processing module in the acquired image zoom processing instruction, wherein the input of the latter image processing module is the output of the previous image processing module.

[0066] Exemplarily, in a possible implementation of step 103, the electronic device may perform image zoom processing on the target image through each image processing module according to the zoom factor of each image processing module indicated by the image zoom processing instruction, that is, for each image processing module, the image zoom processing instruction indicates the zoom factor of the image processing module, so that the electronic device performs image zoom processing according to the zoom factor through the image processing module.

[0067] Continuing with the example that each image processing module includes a pre-processing module and a post-processing module, assuming that the zoom factor of the pre-processing module is 2 and the zoom factor of the post-processing module is 5, the electronic device first performs image zoom processing on the target image through the pre-processing module, such as performing noise reduction processing in the RAW domain, and magnifying the image after noise reduction processing by 2 times to obtain an enlarged image. Then, the electronic device continues to perform image zoom processing on the enlarged image through the post-processing module, such as performing noise reduction processing in the YUV domain, and magnifying the image after noise reduction processing by 5 times to obtain a final image magnified 10 times.

[0068] Since the zoom factor of the pre-processing module is small, that is, the image area retained after cropping when the image is enlarged is larger, more image details can be retained, and the image clarity of the final result can also be guaranteed after upsampling interpolation processing.

[0069] It should be noted that the above embodiments are described based on the assumption that each image processing module includes a pre-processing module and a post-processing module. In other embodiments, more stages (i.e., more image processing modules) may be divided according to magnification requirements for graded processing.

[0070] The above-mentioned embodiment obtains the target image currently being photographed, obtains scene feature data based on the target image, and obtains target magnification data corresponding to the target image. Then, based on the scene feature data and the target magnification data, obtains an image zoom processing instruction at the current magnification. The image zoom processing instruction includes at least the zoom multiple of each image processing module in the electronic device. Each image processing module is used to perform image processing tasks at different stages. Then, in response to the image zoom processing instruction, each image processing module performs image zoom processing on the target image. In this way, the embodiment of the present application can dynamically adjust the zoom multiple of each image processing module according to the scene feature data. The scene feature data can characterize the complexity of the shooting scene of the electronic device. For example, when the scene feature data characterizes that the shooting scene is relatively complex, the zoom multiple of the image processing module that retains better image details is reduced. For example, the previous processing If the pre-processing module retains better image details during the image processing process, the zoom factor of the pre-processing module is reduced. This can avoid the problem of excessive image quality loss caused by the pre-processing module cropping out too much image area (the larger the zoom factor, the more image area is cropped, and the less image area is retained after cropping) to reduce the image quality loss. In addition, the zoom factors of other image processing modules (such as the post-processing module) are increased to meet the magnification requirements corresponding to the target magnification data. This can retain more image details and avoid the problem that the zoom ratio of each image processing module in the traditional technology is fixed, and there may be an image processing module with better image detail retention cropping out too much image area, resulting in loss of image details, resulting in poor image quality after zoom, especially in complex shooting scenes. The embodiment of the present application can improve the image quality of the zoomed image.

[0071] In one embodiment, based on Figure 1In the embodiment shown, when the current shooting scene is full-scene shooting, the number of target images is multiple, and step 103 can be implemented by the following steps A1 and A2: Step A1, in response to the image zoom processing instruction, the electronic device performs image processing on each target image through each image processing module according to the zoom multiple of each image processing module indicated by the image zoom processing instruction to obtain each processed target image. Step A2, the electronic device performs full-scene fusion processing on each processed target image.

[0072] That is, if the electronic device is currently in full-scene photo taking, full-scene preview (photo taking preview or video recording preview) or full-scene video recording, the electronic device can take multiple target images at a time. The electronic device can use the image processing method of the embodiment of the present application to zoom in and out on each target image respectively, and then perform fusion processing after magnification. This not only achieves optimization for brightness, but also can improve clarity to a certain extent.

[0073] In one embodiment, based on Figure 1 The embodiment shown, see Figure 2 This embodiment relates to the timing at which the electronic device obtains the image zoom processing instruction at the current magnification according to the scene feature data and the target magnification data. Figure 2 As shown, step 102 may include Figure 2 Step 201 and step 202 are shown:

[0074] Step 201: The electronic device detects whether an image zoom processing instruction configuration condition is met.

[0075] Step 202: When the image zoom processing instruction configuration conditions are met, the electronic device obtains the image zoom processing instruction according to the scene feature data and the target magnification data.

[0076] In an embodiment of the present application, before obtaining an image zoom processing instruction, the electronic device first detects whether the image zoom processing instruction configuration conditions are met, that is, only when the image zoom processing instruction configuration conditions are met, the electronic device will obtain the image zoom processing instruction at the current magnification.

[0077] Exemplarily, step 201 may include: the electronic device detecting whether a zoom trigger operation is received; or the electronic device detecting whether a shooting scene of the electronic device changes.

[0078] Optionally, the zoom trigger operation can be triggered by the user. For example, after the user turns on the camera, when zooming is required (for example, magnification is required) during preview or video recording, the user enters target magnification data in the electronic device, that is, enters a magnification value. When the target magnification data is greater than the default magnification value of the shooting component of the electronic device, it is determined that the zoom trigger operation has been received.

[0079] Exemplarily, the shooting component of the electronic device may have multiple lenses, and different lens types may correspond to different default magnification values. For example, the default magnification value of the ultra-wide-angle lens is 0.6X, the default magnification value of the wide-angle lens is 1X, and the default magnification value of the telephoto lens is 3X.

[0080] After the electronic device determines that a zoom trigger operation has been received, it indicates that zooming is required, and the electronic device obtains an image zoom processing instruction according to the scene feature data and the target magnification data to perform zooming.

[0081] Of course, the zoom trigger operation can also be triggered by the electronic device itself. For example, in some shooting modes, the electronic device outputs an enlarged image by default. Therefore, after the electronic device captures the original target image, the zoom trigger operation is triggered to enlarge the target image by the default zoom multiple.

[0082] Optionally, the electronic device can also detect whether the shooting scene of the electronic device has changed. For example, the electronic device can detect the similarity between the target image and the previous frame image of the target image. If the similarity is less than a preset similarity threshold, it is determined that the shooting scene of the electronic device has changed, indicating that zooming is required. The electronic device obtains an image zoom processing instruction based on the scene feature data and the target magnification data to perform zooming.

[0083] It should be noted that after the electronic device detects that the image zoom processing instruction configuration conditions are currently met, it obtains the image zoom processing instructions at the current magnification based on the scene feature data and the target magnification data. Before the next detection that the image zoom processing instruction configuration conditions are met, for each frame of the target image taken, each image processing module performs image processing on the target image according to the currently acquired image zoom processing instructions to achieve zoom, until it is detected that the image zoom processing instruction configuration conditions are met again, and then the image zoom processing instructions are updated.

[0084] In this way, the embodiment of the present application obtains the image zoom processing instruction based on the scene feature data and the target magnification data only when the image zoom processing instruction configuration conditions are met. If the image zoom processing instruction configuration conditions are not met, the steps of the image processing method of the present application can be exited, thereby saving system power consumption and obtaining better image effects on the basis of low power consumption.

[0085] In one embodiment, based on the above embodiment, the image zoom processing instruction obtained by the electronic device of this embodiment according to the scene feature data and the target magnification data also includes whether each image processing module needs to perform image super-resolution processing during the image processing process.

[0086] Image super-resolution processing, also known as super-resolution processing, refers to restoring a high-resolution image from a low-resolution image or image sequence.

[0087] Optionally, in order to improve image quality, the image zoom processing instruction may include that each image processing module needs to perform image super-resolution processing during the image processing process. In this way, when the electronic device performs image processing on the target image through each image processing module according to the image zoom processing instruction, the image processing module first crops and upsamples the input image (that is, the target image or the image output by the previous image processing module) according to the corresponding zoom factor, and then performs super-resolution processing on the upsampled image to improve image clarity in preparation for the next image enlargement. Finally, the obtained image is subjected to subsequent image processing.

[0088] In this way, on the basis of super-resolution processing, the image is subjected to the next stage of cropping and upsampling. Since the image has been processed by super-resolution in advance, the clarity has been improved, and then cropping is performed. That is, although cropping is done, the clarity can still be guaranteed to a certain extent.

[0089] Among them, super-resolution processing can not only be directly processed using algorithms, but also historical frames adjacent to the target image can be cached to improve the effect of super-resolution processing, and images of the same area in the historical frames can be used to super-resolution enhance the target image.

[0090] The following, combined Figure 3 , the image processing process of this embodiment is described.

[0091] See also Figure 3 Taking each image processing module including a pre-processing module and a post-processing module as an example, when the image zoom processing instruction configuration conditions are met, the electronic device obtains the image zoom processing instruction according to the scene feature data and the target magnification data. The image zoom processing instruction includes the zoom multiple of each image processing module and whether each image processing module needs to perform image super-resolution processing (i.e., super-resolution processing). Then, the electronic device sends the image zoom processing instruction to each image processing module, and each image processing module processes the target image according to the instruction of the image zoom processing instruction to achieve zoom.

[0092] In the embodiment of the present application, whether each image processing module needs to perform image super-resolution processing can be determined based on the scene characteristics. Generally, images with higher scene complexity require higher clarity (i.e., better image quality) to reflect the details of the image.

[0093] In a possible implementation, when the scene feature data is less than the first feature threshold, that is, the scene complexity length is low, considering the power consumption saving problem of the electronic device, the image zoom processing instruction may include a pre-processing module prohibiting image super-resolution processing of the target image during the image processing process, and a post-processing module performing image super-resolution processing on the target image during the image processing process. For example, if the current shooting scene has relatively simple colors and details, super-resolution may be performed only in the final stage, thereby saving power consumption of the pre-processing module performing image super-resolution processing.

[0094] And / or, when the scene feature data is greater than or equal to the first feature threshold, that is, the scene complexity is high, in order to ensure image quality, the image zoom processing instruction includes a pre-processing module and a post-processing module to perform image super-resolution processing on the target image respectively during the image processing process.

[0095] In another possible implementation, the scene feature data includes regional feature data corresponding to each image area in the target image. When the target area feature data in each regional feature data is greater than a second feature threshold, the image zoom processing instruction includes a pre-processing module and a post-processing module which perform image super-resolution processing on the target image area corresponding to the target area feature data during the image processing process.

[0096] The target image area may be the image area that needs to be zoomed, rather than the edge area.

[0097] In this way, the electronic device can perform image zoom processing on the target image through each image processing module, according to the zoom factor of each image processing module indicated by the image zoom processing instruction and whether each image processing module needs to perform image super-resolution processing during the image processing process, so as to realize the process of the above-mentioned step 103.

[0098] That is, the embodiments of the present application can determine scene characteristics by region. For example, in the same image, there may be image regions with higher scene complexity and there may also be image regions with lower scene complexity. For image regions with higher scene complexity, image super-resolution processing can be performed, while for image regions with lower scene complexity, image super-resolution processing may not be performed, thereby ensuring image quality while saving power consumption of electronic equipment.

[0099] In this way, the magnification requirements of the user can be met and the clarity of the final output image can be improved as much as possible, that is, the image quality is improved. At the same time, it will not cause too much pressure on the hardware processing of the electronic device and save the power consumption of the electronic device.

[0100] In one embodiment, based on Figure 1 The embodiment shown, see Figure 4 This embodiment relates to how an electronic device responds to an image zoom processing instruction and performs image zoom processing on a target image through each image processing module according to the image zoom processing instruction. Figure 4 As shown, step 103 includes Figure 4 Step 401, step 402 and step 403 shown:

[0101] Step 401: The electronic device obtains zoom positioning information corresponding to a target image, and obtains a default cropping area position corresponding to a zoom factor of each image processing module.

[0102] Before the electronic device performs image zoom processing on the target image according to the image zoom processing instruction through each image processing module, the electronic device can also adjust the default cropping area position corresponding to the zoom factor of each image processing module. For example, if the zoom factor of the image processing module is 10, the default cropping area position corresponding to the zoom factor of the image processing module is usually 1 / 10 of the center of the image.

[0103] However, the center of the image may not be the position the user wants to zoom in. Therefore, the default cropping area position corresponding to the zoom factor of the image processing module needs to be adjusted based on the zoom positioning information input by the user. The zoom positioning information includes the zoom positioning position or the zoom positioning area.

[0104] Among them, the zoom positioning position can be the focus position input by the user for the target image, or the zoom positioning position is the center point position of the main object in the target image. The focus position input by the user can be the focus position manually clicked by the user on the screen of the electronic device, or it can be the focus position of the user's pupil on the screen of the electronic device.

[0105] Similarly, the zoom positioning area is a focus area input by a user for a target image, or the zoom positioning area is an object area of ​​a main object in the target image, and so on.

[0106] Step 402: The electronic device adjusts the default cropping area position according to the zoom positioning information to obtain an adjusted cropping area position.

[0107] Exemplarily, the electronic device may use the zoom positioning information as the center of the cropping area, and perform an offset process on the default cropping area position to obtain an adjusted cropping area position.

[0108] For example, see Figure 5 , Figure 5 A schematic diagram of an exemplary default cropping area position and an adjusted cropping area position, Figure 5 The RQI area in may be a user interest area corresponding to the zoom positioning information input by the user.

[0109] For example, see Figure 6 , Figure 6 is a schematic diagram of another exemplary default cropping area position and an adjusted cropping area position, Figure 6 The key area in the image may be an image area corresponding to the center point position of the main object in the target image.

[0110] Step 403, in response to the image zoom processing instruction, the electronic device performs image zoom processing on the target image through each image processing module according to the zoom multiples of each image processing module indicated by the image zoom processing instruction and the positions of each adjusted cropping area.

[0111] In this way, when each image processing module amplifies the input image according to the configured zoom multiple, it first crops the input image according to the adjusted cropping area position, and then performs upsampling processing on the cropped image, and performs subsequent possible super-resolution processing, etc.

[0112] In this way, the embodiment of the present application fully considers the impact of scene characteristics on the cropping effect and dynamically adjusts the zoom factor of the image processing module. It also fine-tunes the position of the default cropping area according to the zoom positioning information, so that the final image magnification result can better adapt to scene changes on the basis of meeting the magnification requirements, taking into account clarity and user shooting needs and preferences. Moreover, this adjustment can be performed quickly and easily, usually meeting timeliness requirements, and the power consumption will not be too high.

[0113] In general, in the related technologies, the zoom processing of electronic devices is simply cropping and upsampling, which may affect the final image quality and cause a significant decrease in image clarity. If some scenes with excessive magnification are directly cropped, the image clarity may be lost too much, affecting the user experience.

[0114] The embodiment of the present application improves the above-mentioned problem of reduced image clarity, especially for high-magnification usage scenarios. The embodiment of the present application performs staged image zoom processing and then performs super-resolution processing to ensure the clarity of the zoomed image, making it close to the clarity effect after optical magnification. In addition, since the embodiment of the present application can adjust the position of the cropping area at different stages in real time according to the changes in the shooting scene, the final image processing effect can better adapt to the changes in the shooting scene, avoiding the situation where the final magnification effect deviates from the user's shooting needs due to the fixed default cropping area, so that the final shooting experience is better.

[0115] In one embodiment, an image processing method is provided, comprising:

[0116] Step a, obtaining a currently captured target image, obtaining scene feature data according to the target image, and obtaining target magnification data corresponding to the target image;

[0117] Step b, detects whether the image zoom processing instruction configuration conditions are met. If the image zoom processing instruction configuration conditions are met, the image zoom processing instruction at the current magnification corresponding to the scene feature data and the target magnification data is searched in a preset configuration file according to the scene feature data and the target magnification data.

[0118] The image zoom processing instruction configuration condition includes receiving a zoom trigger operation or detecting a change in the shooting scene of the electronic device.

[0119] The image zoom processing instruction includes the zoom multiple of each image processing module in the electronic device, and whether each image processing module needs to perform image super-resolution processing during the image processing process.

[0120] Among them, the image processing module includes a pre-processing module and a post-processing module; in the image zoom processing instruction, the zoom factor of the pre-processing module is negatively correlated with the size of the scene feature data, and the zoom factor of the post-processing module is positively correlated with the size of the scene feature data.

[0121] Optionally, when the scene feature data is less than a first feature threshold, the image zoom processing instruction includes the pre-processing module prohibiting image super-resolution processing on the target image during the image processing process, and the post-processing module performing image super-resolution processing on the target image during the image processing process; and / or, when the scene feature data is greater than or equal to the first feature threshold, the image zoom processing instruction includes the pre-processing module and the post-processing module respectively performing image super-resolution processing on the target image during the image processing process.

[0122] Optionally, the scene feature data includes regional feature data corresponding to each image area in the target image; when the target area feature data in each regional feature data is greater than a second feature threshold, the image zoom processing instruction includes a pre-processing module and a post-processing module which perform image super-resolution processing on the target image area corresponding to the target area feature data during the image processing process.

[0123] Step c, obtaining zoom positioning information corresponding to the target image, and obtaining the default cropping area position corresponding to the zoom multiple of each image processing module.

[0124] The zoom positioning information includes a zoom positioning position or a zoom positioning area.

[0125] The zoom positioning position is the focus position input by the user for the target image, or the zoom positioning position is the center point position of the main object in the target image;

[0126] The zoom positioning area is a focus area input by a user for a target image, or the zoom positioning area is an object area of ​​a main object in the target image.

[0127] Step d, taking the zoom positioning information as the center of the cropping area, performing an offset process on the default cropping area position to obtain an adjusted cropping area position;

[0128] Step e: in response to the image zoom processing instruction, the target image is subjected to image zoom processing by each image processing module according to the zoom multiple of each image processing module indicated by the image zoom processing instruction and the position of each adjusted cropping area.

[0129] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiment of the present application also provides an image processing device for implementing the above-mentioned image processing method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more image processing device embodiments provided below can refer to the limitations on the image processing method above, and will not be repeated here.

[0131] In one embodiment, Figure 7 As shown, an image processing device is provided, comprising:

[0132] The first acquisition module 701 is used to acquire a currently captured target image, acquire scene feature data according to the target image, and acquire target magnification data corresponding to the target image;

[0133] A second acquisition module 702 is used to acquire an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data, wherein the image zoom processing instruction at least includes a zoom factor of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages;

[0134] The processing module 703 is used to respond to the image zoom processing instruction and perform image zoom processing on the target image through each of the image processing modules.

[0135] In one embodiment, the second acquisition module 702 includes:

[0136] A detection unit, used to detect whether the image zoom processing instruction configuration conditions are met;

[0137] The first acquisition unit is used to acquire the image zoom processing instruction according to the scene feature data and the target magnification data when the configuration condition of the image zoom processing instruction is met.

[0138] In one of the embodiments, the detection unit is specifically used to detect whether a zoom trigger operation is received; or, detect whether a shooting scene of the electronic device changes.

[0139] In one embodiment, the second acquisition module 702 includes:

[0140] A search unit is used to search for the image zoom processing instruction corresponding to the scene feature data and the target magnification data in a preset configuration file according to the scene feature data and the target magnification data.

[0141] In one embodiment, the image processing module includes a pre-processing module and a post-processing module, and the scene feature data is used to characterize the complexity of the shooting scene of the electronic device; in the image zoom processing instruction, the zoom factor of the pre-processing module is negatively correlated with the size of the scene feature data, and the zoom factor of the post-processing module is positively correlated with the size of the scene feature data.

[0142] In one embodiment, the processing module 703 is specifically configured to perform image zoom processing on the target image through each of the image processing modules according to the zoom multiple of each of the image processing modules indicated by the image zoom processing instruction.

[0143] In one of the embodiments, the image zoom processing instruction also includes whether each of the image processing modules needs to perform image super-resolution processing during the image processing process.

[0144] In one of the embodiments, when the scene feature data is less than a first feature threshold, the image zoom processing instruction includes the pre-processing module prohibiting the target image from being subjected to image super-resolution processing during the image processing process, and the post-processing module performing image super-resolution processing on the target image during the image processing process; and / or

[0145] In a case where the scene feature data is greater than or equal to the first feature threshold, the image zoom processing instruction includes the pre-processing module and the post-processing module performing image super-resolution processing on the target image respectively during the image processing process.

[0146] In one of the embodiments, the scene feature data includes region feature data corresponding to each image region in the target image;

[0147] When the target area feature data in each of the area feature data is greater than the second feature threshold, the image zoom processing instruction includes the pre-processing module and the post-processing module performing image super-resolution processing on the target image area corresponding to the target area feature data during the image processing process.

[0148] In one embodiment, the processing module 703 is specifically used to perform image zoom processing on the target image through each image processing module, according to the zoom factor of each image processing module indicated by the image zoom processing instruction and whether each image processing module needs to perform image super-resolution processing during the image processing process.

[0149] In one embodiment, when the current shooting scene is full scene shooting, the number of the target images is multiple, and the processing module 703 includes:

[0150] A first processing unit is used for, in response to the image zoom processing instruction, performing image processing on each of the target images respectively according to the zoom multiples of each of the image processing modules indicated by the image zoom processing instruction to obtain each processed target image;

[0151] The fusion unit is used to perform full-scene fusion processing on each of the processed target images.

[0152] In one embodiment, the processing module 703 includes:

[0153] A second acquisition unit is used to acquire zoom positioning information corresponding to the target image, and acquire a default cropping area position corresponding to the zoom multiple of each image processing module, wherein the zoom positioning information includes a zoom positioning position or a zoom positioning area;

[0154] An adjusting unit, configured to adjust the default cropping area position according to the zoom positioning information to obtain an adjusted cropping area position;

[0155] The second processing unit is used to respond to the image zoom processing instruction and perform image zoom processing on the target image through each image processing module according to the zoom multiple of each image processing module indicated by the image zoom processing instruction and the adjusted cropping area position.

[0156] In one of the embodiments, the adjustment unit is specifically configured to use the zoom positioning position or the center position of the zoom positioning area as the center of the cropping area, and perform an offset process on the default cropping area position to obtain the adjusted cropping area position.

[0157] In one of the embodiments, the zoom positioning position is a focus position input by a user for the target image, or the zoom positioning position is a center point position of a main object in the target image;

[0158] The zoom positioning area is a focus area input by a user for the target image, or the zoom positioning area is an object area of ​​a main object in the target image.

[0159] In one embodiment, the electronic device is provided with a zoom sensor assembly, and the device further comprises:

[0160] A shooting module, used for shooting and obtaining an initial image in a current shooting scene of the electronic device;

[0161] The magnification adjustment module is used to perform magnification adjustment processing on the initial image through the zoom sensor component to obtain the target image.

[0162] Each module in the above-mentioned image processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in an electronic device in the form of hardware, or can be stored in a memory in an electronic device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0163] In one embodiment, an electronic device is provided. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The electronic device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and an external device. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an image processing method is implemented. The display unit of the electronic device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the electronic device casing, or an external keyboard, touchpad or mouse.

[0164] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0165] The embodiment of the present application further provides a computer-readable storage medium, one or more non-volatile computer-readable storage media containing computer-executable instructions, which, when executed by one or more processors, enable the processors to perform the steps of the image processing method.

[0166] The embodiment of the present application also provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the image processing method.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0169] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image processing method, characterized in that: include: Acquire a currently captured target image, acquire scene feature data according to the target image, and acquire target magnification data corresponding to the target image; According to the scene feature data and the target magnification data, an image zoom processing instruction at a current magnification is obtained, wherein the image zoom processing instruction at least includes a zoom factor of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages; In response to the image zoom processing instruction, each of the image processing modules performs image zoom processing on the target image.

2. The method according to claim 1, characterized in that The step of obtaining an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data includes: Detect whether the image zoom processing instruction configuration conditions are met; When the image zoom processing instruction configuration condition is met, the image zoom processing instruction is acquired according to the scene feature data and the target magnification data.

3. The method according to claim 2, characterized in that The detecting whether the image zoom processing instruction configuration condition is met includes: Detect whether a zoom trigger operation is received; Alternatively, it is detected whether the shooting scene of the electronic device changes.

4. The method according to claim 1, characterized in that The step of obtaining an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data includes: According to the scene feature data and the target magnification data, the image zoom processing instruction corresponding to the scene feature data and the target magnification data is searched in a preset configuration file.

5. The method according to claim 1, characterized in that The image processing module includes a pre-processing module and a post-processing module, and the scene feature data is used to characterize the complexity of the shooting scene of the electronic device; In the image zoom processing instruction, the zoom factor of the pre-processing module is negatively correlated with the size of the scene feature data, and the zoom factor of the post-processing module is positively correlated with the size of the scene feature data.

6. The method according to any one of claims 1 to 5, characterized in that: In response to the image zoom processing instruction, performing image zoom processing on the target image through each of the image processing modules includes: The target image is subjected to image zoom processing by each of the image processing modules according to the zoom multiple of each of the image processing modules indicated by the image zoom processing instruction.

7. The method according to claim 5, characterized in that The image zoom processing instruction also includes whether each of the image processing modules needs to perform image super-resolution processing during the image processing process.

8. The method according to claim 7, characterized in that In a case where the scene feature data is less than a first feature threshold, the image zoom processing instruction includes the post-processing module performing image super-resolution processing on the target image during the image processing process; and / or In a case where the scene feature data is greater than or equal to the first feature threshold, the image zoom processing instruction includes the pre-processing module and the post-processing module performing image super-resolution processing on the target image respectively during the image processing process.

9. The method according to claim 7, characterized in that: The scene feature data includes region feature data corresponding to each image region in the target image; When the target area feature data in each of the area feature data is greater than the second feature threshold, the image zoom processing instruction includes the pre-processing module and the post-processing module performing image super-resolution processing on the target image area corresponding to the target area feature data during the image processing process.

10. The method according to any one of claims 7 to 9, characterized in that: In response to the image zoom processing instruction, performing image zoom processing on the target image through each of the image processing modules includes: The target image is subjected to image zoom processing by each of the image processing modules according to the zoom multiple of each of the image processing modules indicated by the image zoom processing instruction and whether each of the image processing modules needs to perform image super-resolution processing during the image processing process.

11. The method according to claim 1, characterized in that: In the case where the shooting scene of the electronic device is full-scene shooting, the number of the target images is multiple, and in response to the image zoom processing instruction, performing image zoom processing on the target images by each of the image processing modules includes: In response to the image zoom processing instruction, each of the image processing modules performs image processing on each of the target images according to the zoom multiples of each of the image processing modules indicated by the image zoom processing instruction to obtain each processed target image; The processed target images are subjected to full scene fusion processing.

12. The method according to claim 1, characterized in that In response to the image zoom processing instruction, performing image zoom processing on the target image through each of the image processing modules includes: Obtaining zoom positioning information corresponding to the target image, and obtaining a default cropping area position corresponding to the zoom multiple of each image processing module, wherein the zoom positioning information includes a zoom positioning position or a zoom positioning area; Adjusting the default cropping area position according to the zoom positioning information to obtain an adjusted cropping area position; In response to the image zoom processing instruction, the target image is subjected to image zoom processing by each of the image processing modules according to the zoom factors of each of the image processing modules indicated by the image zoom processing instruction and the positions of each of the adjusted cropping areas.

13. The method according to claim 12, characterized in that The step of adjusting the default cropping area position according to the zoom positioning information to obtain an adjusted cropping area position includes: The zoom positioning position or the center position of the zoom positioning area is taken as the cropping area center, and the default cropping area position is offset to obtain the adjusted cropping area position.

14. The method according to claim 10, characterized in that The zoom positioning position is a focus position input by a user for the target image, or the zoom positioning position is a center point position of a main object in the target image; The zoom positioning area is a focus area input by a user for the target image, or the zoom positioning area is an object area of ​​a main object in the target image.

15. The method according to claim 1, characterized in that The electronic device is provided with a zoom sensor assembly, and the method further comprises: Capturing an initial image in a current shooting scene of the electronic device; The target image is obtained by performing magnification adjustment processing on the initial image through the zoom sensor component.

16. An image processing device, characterized in that: include: A first acquisition module is used to acquire a currently captured target image, acquire scene feature data according to the target image, and acquire target magnification data corresponding to the target image; A second acquisition module is used to acquire an image zoom processing instruction at a current magnification according to the scene feature data and the target magnification data, wherein the image zoom processing instruction at least includes a zoom factor of each image processing module in the electronic device, and each image processing module is used to perform image processing tasks at different stages; The processing module is used to respond to the image zoom processing instruction and perform image zoom processing on the target image through each of the image processing modules.

17. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 15.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 15 are implemented.

19. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 15 are implemented.

Images