Image processing method and apparatus, and electronic device and storage medium

Abstract

Provided in the embodiments of the present disclosure are an image processing method and apparatus, and an electronic device and a storage medium. The method comprises: receiving an object image of at least one display object in an image to be processed and object description information comprising the at least one display object; on the basis of the object description information, determining a target fusion image from among at least one fusion image to be selected; and on the basis of the object description information and target fusion information of the target fusion image, fusing the object image into the target fusion image, so as to obtain a target image, wherein the object description information corresponds to fusion object information in the target fusion information, and the fusion object information corresponds to a fusion object displayed in the target fusion image.

Description

Image processing method, device, electronic device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number 202410039053.8, filed on January 10, 2024, entitled “Image processing method, device, electronic device and storage medium”. The entire contents of that application are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to image processing technology, and more particularly to an image processing method, apparatus, electronic device, and storage medium. Background Art

[0004] With the development of information technology, the application of image processing technology has become more and more popular. Through image processing technology, photos with different background images can be created to provide users with different photo effects. Summary of the Invention

[0005] The present disclosure provides an image processing method, device, electronic device and storage medium to achieve the purpose of meeting users' diverse and rich image effect requirements.

[0006] In a first aspect, an embodiment of the present disclosure provides an image processing method, comprising:

[0007] receiving an object image of at least one display object in an image to be processed and object description information including the at least one display object;

[0008] determining a target fused image from at least one fused image to be selected based on the object description information;

[0009] fusing the object image into the target fused image based on the object description information and the target fusion information of the target fused image to obtain a target image;

[0010] The object description information corresponds to the fusion object information in the target fusion information, and the fusion object information corresponds to the fusion object displayed in the target fusion image.

[0011] In a second aspect, an embodiment of the present disclosure further provides an image processing device, the device comprising:

[0012] An image receiving module, configured to receive an object image of at least one display object in an image to be processed and object description information including the at least one display object;

[0013] a target fused image determining module, configured to determine a target fused image from at least one fused image to be selected based on the object description information;

[0014] an object image fusion module, configured to fuse the object image into the target fusion image based on the object description information and the target fusion information of the target fusion image to obtain a target image;

[0015] The object description information corresponds to the fusion object information in the target fusion information, and the fusion object information corresponds to the fusion object displayed in the target fusion image.

[0016] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image processing method described in any one of the embodiments of the present disclosure.

[0020] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the image processing method described in any one of the embodiments of the present disclosure when executed.

[0021] In an embodiment of the present disclosure, an object image of at least one displayed object in an image to be processed and object description information including at least one displayed object are received; a target fused image is determined from at least one fused image to be selected based on the object description information; and the object image is fused into the target fused image based on the object description information and target fusion information of the target fused image to obtain a target image; wherein the object description information corresponds to fused object information in the target fusion information; and the fused object information corresponds to the fused object displayed in the target fused image. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0023] FIG1 is a flow chart of an image processing method provided by an embodiment of the present disclosure;

[0024] FIG2 is a flow chart of an image processing method provided by an embodiment of the present disclosure;

[0025] FIG3 is a flow chart of an image processing method provided by an embodiment of the present disclosure;

[0026] FIG4 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure;

[0027] FIG5 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0035] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0036] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0037] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0038] In related art, image processing techniques are often applied to single-object fusion, creating photos of a single object with different background images. However, these techniques suffer from at least the following technical issues: Because they can only fuse single objects, their application scenarios are limited and they cannot meet users' diverse and rich image effects needs.

[0039] Before introducing the technical solution, an example of the application scenario can be first explained. This technical solution can be applied to a scenario in which at least one object image is fused into a fused image displaying at least one fused object. This technical solution can realize multi-object fusion and obtain a target image containing image information of at least one object image and image information of a fused image. Exemplarily, the object image may be a partial image of an object, an image of a partial part of a person, and an image of a partial part of an animal; at least one object image can be fused into the fused image, and the fused image includes a foreground part and a background part, and the background part may include natural scenery, a solid color background, and illustrations, etc. The solution based on this embodiment can not only meet the image fusion of a single object; but also, in the case where there are multiple object images, multiple object images can be fused into one fused image, realizing multi-object fusion, improving the breadth of application, and meeting the user's diverse and rich image effect needs.

[0040] Figure 1 is a flow chart of an image processing method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the situation where at least one object image is fused into a fused image to obtain a target image. The method can be executed by an image processing device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0041] As shown in FIG1 , the method includes:

[0042] S110: Receive an object image of at least one display object in an image to be processed and object description information including at least one display object.

[0043] The image to be processed is an image containing an object image of a display object. The display object is the object in the image to be processed that needs to be displayed in the fused target image. For example, when obtaining a user portrait, the display object is the user to be displayed in the user portrait. The object image can correspond to the display object.

[0044] In this embodiment, the object image corresponds to at least one target part of the displayed object, or may correspond to the displayed object as a whole. For example, if the displayed object is a person, the object image may correspond to at least one target part of the face, legs, abdomen, back, or feet. This allows the object image to reflect the characteristics of the target part of the displayed object, enabling fusion of images of the target part of the displayed object. Alternatively, the object image may be an image corresponding to the entire person, thereby completing fusion of images of the entire person. This embodiment enables the displayed object to correspond to at least one target part, thereby facilitating the fusion of images corresponding to any part of the displayed object, increasing the flexibility of the image processing process and better meeting user needs.

[0045] In this embodiment, the object image may be an image of the display object from the same image to be processed, or may be an image of the display object from different images to be processed. That is, the number of images to be processed may be one or more.

[0046] Exemplarily, the image to be processed A includes object image 1, object image 2 and object image 3; the image to be processed B includes object image 4. In order to have the target image obtained after fusion include object image 1, object image 2, object image 3 and object image 4 at the same time, object image 1, object image 2 and object image 3 from image to be processed A can be received, and object image 4 from image to be processed B can be received to generate a target image based on object image 1, object image 2, object image 3 and object image 4.

[0047] It should be noted that those skilled in the art may set the correspondence between the object image and the image to be processed according to actual application conditions, and this embodiment does not limit this. For example, for a scene of a large group photo of people, in order to better meet the actual needs of the user, the object images from different images to be processed can be received and each object image can be fused into the same image, thereby improving the convenience of the user in obtaining the group photo.

[0048] In this embodiment, the object description information includes data of at least one display object in at least one reference dimension, and describes the characteristics of the display object in detail and clearly in at least one reference dimension.

[0049] Optionally, the reference dimension includes at least one of an object category dimension, a dimension of the number of individual objects within different object categories, a dimension of the total number of objects, and a dimension of the maturity of individual objects within different object categories. The data within each reference dimension may reflect the distribution of the number of objects displayed within that reference dimension.

[0050] Among them, the object category dimension is divided according to the different types of displayed objects. For example, the object category dimension can divide the displayed objects into animals, people and plants. The single object quantity dimension is used to reflect the number of a single object contained in each object category. For example, if the object category is people, the single object quantity dimension can include the number of males and / or the number of females. The total object quantity dimension can be the total number of displayed objects. The single object maturity dimension is used to reflect the maturity of a single object contained in each object category; for example, when the object category dimension is people, the single object maturity dimension can be the age distribution range of people; if the object category dimension is trees, the single object maturity dimension can be the number of tree rings, and the number of tree rings is used to reflect the maturity of the tree.

[0051] This embodiment provides at least one reference dimension among the object category dimension, the single object quantity dimension under different object categories, the total object quantity dimension and the single object maturity dimension under different object categories, so as to facilitate the object description information to comprehensively describe the displayed object from multiple different reference dimensions, which is conducive to improving the accuracy of image fusion of object images.

[0052] S120: Determine a target fused image from at least one fused image to be selected based on the object description information.

[0053] The image to be selected for fusion is a pre-provided base image for fusion with the object image; the target fusion image is the final image to be fused with the object. It should be noted that the image to be processed can be either a 3D stereo image or a 2D image. To ensure a more vivid and realistic target image after image fusion, the target fusion image must be of the same type as the image to be processed. If the image to be processed is a 3D stereo image, the target fusion image must also be a 3D stereo image.

[0054] In this embodiment, based on at least one reference dimension described in the object description information, a fused image to be selected that matches the object image in that reference dimension may be determined as the target fused image. Specifically, if the object description information describes only one reference dimension, only that single reference dimension is considered, and among the at least one fused image to be selected, the fused image to be selected that matches the object image in that reference dimension is determined as the target fused image. If the object description information describes multiple reference dimensions, each reference dimension is considered, and among the at least one fused image to be selected, the fused image to be selected that matches the object image in each reference dimension is determined as the target fused image.

[0055] For example, when the reference dimension described in the object description information is an object category dimension, a target fused image is selected from the at least one target fused image that matches the object image in the object category dimension. For example, if the object description information indicates that the total number of objects in the person category is 5, then an image that can fuse all 5 people can be selected from the at least one target fused image as the target fused image.

[0056] In this embodiment, based on the object description information, a target fused image is determined from at least one fused image to be selected, including: determining a fusion attribute between the object description information and the fusion information to be matched of the at least one fused image to be selected; based on the fusion attribute, determining the target fusion information, and using the fused image to be selected corresponding to the target fusion information as the target fused image.

[0057] The to-be-matched fusion information is determined after pre-processing the image to be fused and includes fusion object information and key point information of at least one target part of the fusion object. The fusion object information includes data of at least one fusion object in at least one reference dimension. The fusion attribute reflects the degree of match between the object description information and the fusion object information in the to-be-matched fusion information. Specifically, when the target part corresponds to a facial part, the key point information includes the key points of the facial part of the fusion object.

[0058] To increase the range of target fused images available for selection, the fusion properties between the object description information and the to-be-matched fusion information of each fused image to be selected can be determined. If the number of fused images to be selected is large and determining the target fused image is time-consuming, a predetermined number of fused images to be selected can be identified from the fused images to be selected, and the fusion properties between the to-be-matched fusion information of the selected fused images and the object description information can be determined.

[0059] It should be noted that a higher fusion attribute indicates a higher degree of match between the object description information and the fusion information to be matched for the image to be selected; conversely, a lower degree of match indicates a lower degree of match between the object description information and the fusion information to be matched for the image to be selected. Since the object description information corresponds to the fusion object information, the degree of match between the object description information and the fusion information to be matched for the image to be selected can be understood as the degree of match between the object description information and the fusion object information of the fusion information to be matched for the image to be selected.

[0060] To determine the target fused image that best matches the object description information, the target fused information is determined based on fusion attributes. The method includes: selecting the candidate fused information with the highest fusion attribute as the target fused information. Alternatively, any candidate fused information with a fusion attribute greater than a preset threshold is randomly selected as the target fused information. After the target fused information is determined, the candidate fused image corresponding to the target fused information can be used as the target fused image.

[0061] This embodiment determines the target fused image by determining the fusion attributes, thereby taking into account the matching degree between the object description information and the fused information to be matched when determining the target fused image, which is conducive to determining the target fused image that best matches the object description information.

[0062] In this embodiment, determining the fusion attribute between the object description information and the to-be-matched fusion information of at least one to-be-selected fusion image includes: determining the fusion attribute between the at least one to-be-matched fusion information and the object description information by performing data similarity processing under different reference dimensions in the object description information and the at least one to-be-matched fusion information; correspondingly, determining the target fusion information based on the fusion attribute, including: if there are multiple fusion attributes that meet preset conditions, determining the target fusion information based on preset rules.

[0063] It should be noted that the object description information corresponds to the reference dimension of the fused object information in the to-be-matched fusion information. In order to comprehensively and accurately determine the fusion attributes between the to-be-matched fusion information and the object description information, the fusion sub-attributes between the to-be-matched fusion information and the object description information can be determined separately for each reference dimension in the to-be-matched fusion information, so as to determine the fusion attributes based on the fusion sub-attributes.

[0064] The fusion sub-attribute reflects the degree of match between the to-be-matched fusion information and the object description information at that reference dimension. The fusion sub-attribute determines the fusion attribute between the object description information and the to-be-matched fusion information of at least one to-be-selected fusion image at each reference dimension.

[0065] In a specific implementation, the fusion sub-attribute can be determined by performing similar processing on the object description information and the to-be-matched fusion information within the current reference dimension, and determining the resulting processing result reflecting the degree of matching as the fusion sub-attribute; and determining the fusion attribute based on the fusion sub-attribute corresponding to each reference dimension. For example, each fusion sub-attribute can be integrated to obtain the fusion attribute; or, alternatively, any fusion sub-attribute can be determined as the fusion attribute.

[0066] In this embodiment, if the fusion attribute is greater than the preset attribute value, it can be determined that the fusion attribute meets the preset condition; alternatively, the values ​​of the fusion attributes corresponding to each fusion information to be matched can be sorted in descending order, and the fusion attribute with the largest number of preset attributes can be determined as the fusion attribute that meets the preset condition.

[0067] In a specific implementation, if there are multiple fusion attributes that meet the preset conditions, one of the to-be-matched fusion information corresponding to the fusion attributes that meet the preset conditions must be determined as the target fusion information according to the preset rules. For example, determining the target fusion information according to the preset rules can be achieved by: selecting any one of the to-be-matched fusion information corresponding to the fusion attributes that meet the preset conditions as the target fusion information; or determining the to-be-matched fusion information with the largest fusion attribute value as the target fusion information.

[0068] In this embodiment, in the case where there are multiple fusion attributes that meet the preset conditions, target fusion information can be quickly determined according to the preset rules, which is conducive to improving image processing efficiency.

[0069] Furthermore, the method also includes: if there is no fusion attribute that meets the preset conditions, then according to the priority of at least one reference dimension set in advance, the fusion attributes of at least one to-be-matched fusion image relative to the object description information under the same reference dimension are determined in sequence to determine the target fusion information based on the fusion attributes.

[0070] In a specific implementation, if no fusion attributes meet the preset conditions, to ensure that the target image is output for the user, the target fusion information can be determined based on the preset priority of at least one reference dimension. The priority reflects the degree of influence of each reference dimension on the determination of the target fusion information. The higher the priority, the greater the influence of the reference dimension on the determination of the target fusion information; conversely, the influence is smaller.

[0071] Specifically, the fusion sub-attribute between the fusion information to be matched and the object description information of at least one fusion image to be matched under the reference dimension corresponding to the current priority can be determined in order from high to low priority, and the fusion sub-attribute can be determined as the fusion attribute of the object description information and the fusion information to be matched under the reference dimension.

[0072] After determining the corresponding fusion attributes for each reference dimension according to priority, the reference dimensions are sorted in descending order of priority. Based on the sorting order, the fusion attributes that meet the preset dimension conditions for the first reference dimension are determined. If there is only one fusion attribute that meets the preset dimension conditions, the to-be-matched fusion information corresponding to that fusion attribute can be determined as the target fusion information. The preset dimension conditions are pre-set conditions for filtering fusion attributes for each reference dimension. For example, the preset dimension conditions correspond to the preset conditions.

[0073] Furthermore, if there are multiple fusion attributes that meet the preset dimensional conditions under the first reference dimension, the fusion information to be matched corresponding to the fusion attributes that meet the preset dimensional conditions is determined as the alternative fusion information; then, in the alternative fusion information, the fusion attributes that meet the preset dimensional conditions under the remaining reference dimensions are determined respectively in the sorting order, and finally, the alternative fusion information with the most fusion attributes that meet the preset dimensional conditions is determined as the target fusion information.

[0074] Furthermore, if no fusion attribute satisfies the preset dimensional conditions under the first reference dimension, a fusion attribute that satisfies the preset dimensional conditions under the second reference dimension may be determined, and the corresponding to-be-matched fusion information is used as candidate fusion information, and the target fusion information is determined from the candidate fusion information. It should be noted that if no fusion attribute satisfies the preset dimensional conditions under the second reference dimension, a determination may be made in descending order of priority whether a fusion attribute satisfies the preset dimensional conditions under the next reference dimension, until a fusion attribute that satisfies the preset dimensional conditions is determined.

[0075] To ensure the accuracy and effectiveness of the generated target image, if it is determined that no fusion attributes meet the preset conditions exist, a prompt message can be generated and fed back to the user end, informing them that if image processing is continued, the maturity and object category of the objects displayed in the target image may be incorrect. If the user end provides feedback indicating that processing should continue, the target fusion information can be determined according to the above steps, and the target image can be generated based on the target fusion information.

[0076] In this embodiment, in the case where there are no fusion attributes that meet the preset conditions, the target fusion information can be determined based on the priority of the pre-set reference dimension to ensure that the target image can be provided to the user; and prompt information can also be generated and sent to the user end to indicate the existing risks and better meet the actual needs of the user.

[0077] S130 : Based on the object description information and the target fusion information of the target fusion image, fuse the object image into the target fusion image to obtain a target image.

[0078] The target fused image displays a fused object, and the fused object information corresponds to the fused object displayed in the target fused image. The target fused information includes fused object information of at least one fused object in the target fused image and key point information of at least one target part of the fused object. The fused object information can reflect data of the at least one fused object in at least one reference dimension.

[0079] In this embodiment, the object description information corresponds to the fused object information in the target fusion information, that is, the reference dimension described in the object description information matches the reference dimension described in the fused object information. In a specific implementation, the object image may be fused into the target fused image based on the object description information and the target fusion information of the target fused image. The method may include: determining whether the number of object images is consistent with the number of fused objects in the target fused image based on the object description information and the target fusion information of the target fused image; if they are consistent, determining the correspondence between the fused objects displayed in the target fused image and the displayed objects based on the data of each reference dimension described in the object description information and the fused object information; fusion of the object image corresponding to each displayed object into the target fused image according to the correspondence; and determining the target fused image fused with the object image as the target image.

[0080] Alternatively, the object image may be fused into the target fused image by fusing the object image with some of the fused objects in the target fused image to obtain the target image when the number of the object images is less than the number of fused objects.

[0081] Specifically, the target fusion image can be randomly selected from a number of fusion objects equal to the number of the object images, and the object images can be fused with the selected target fusion objects. Alternatively, based on the object description information and the data of each reference dimension described by the fusion object information, matching fusion objects that match the object images can be determined in the target fusion image. Among the matching fusion objects, target fusion objects that match the number of the object images can be selected. The corresponding relationship between the display objects and the target fusion objects can be determined. Based on this corresponding relationship, each object image can be fused into the target fusion image to obtain the target image.

[0082] This embodiment sets a method for obtaining a target image in response to a situation where the number of object images is less than the number of fusion objects, thereby effectively obtaining the target image in response to different situations, ensuring that the needs of users can be met.

[0083] Furthermore, the method further includes: determining a portion of the fused object of the object image in the target fused image according to a preset second fusion reference dimension.

[0084] The second fusion reference dimension may be at least one of an object category dimension, a single object quantity dimension under different object categories, a total object quantity dimension, and a single object maturity dimension under different object categories.

[0085] It should be noted that a second fusion reference dimension can be pre-set based on its importance to the target image, thereby enabling the determination of the target image based on the second fusion reference dimension. Specifically, based on the second fusion reference dimension, at least one fusion object matching each target image in the target fusion image can be determined. From these matching fusion objects, one fusion object is selected as the target fusion object, and the target fusion object corresponding to each target image is used to form the fusion object. It should be noted that no duplicate fusion objects exist among the selected target fusion objects.

[0086] This embodiment pre-sets the second fusion reference dimension, so that the second fusion reference dimension is taken into consideration when determining a partial fusion object, which can better meet the needs of users.

[0087] Alternatively, the object image can be fused into the target fused image in the following manner: if the number of fused objects is less than the number of displayed objects, an exception message can be generated and fed back to the user end to prompt that the number of object images exceeds the range and whether to continue the image processing operation.

[0088] The technical solution of the embodiment of the present disclosure is as follows: receiving an object image of at least one display object in an image to be processed and object description information including at least one display object; determining a target fusion image from at least one fusion image to be selected based on the object description information; fusing the object image into the target fusion image based on the object description information and the target fusion information of the target fusion image to obtain a target image; wherein the object description information corresponds to the fusion object information in the target fusion information; since the fusion object information corresponds to the fusion object displayed in the target fusion image, it indicates that a fusion object is provided in the target fusion image, and when the target image is obtained based on the object description information and the target fusion information, a single object can be fused into the target fusion image, or multiple objects can be fused into the target fusion image based on the number of display objects contained in the image to be processed, thereby solving the problem in the prior art that only a single object can be fused, improving the breadth of application, and meeting the user's diverse and rich image effect requirements.

[0089] FIG2 is a flow chart of an image processing method provided by an embodiment of the present disclosure. Based on the aforementioned embodiments, the fusion position of at least one display object in a target fusion image can be determined based on object description information and target fusion information, and then the target image can be obtained based on the fusion position. Explanations of terms that are identical or corresponding to those in the aforementioned embodiments are omitted here.

[0090] As shown in FIG2 , the method includes:

[0091] S210: Receive an object image of at least one display object in an image to be processed and object description information including at least one display object.

[0092] S220: Determine a target fused image from at least one fused image to be selected based on the object description information.

[0093] In practical applications, in order to quickly determine the target fused image when performing image fusion, it also includes: receiving the to-be-matched fusion information of at least one image to be fused, and generating a configuration file based on the to-be-matched fusion information, so as to determine the target fused image from at least one image to be selected based on the to-be-matched fusion information and object description information in the configuration file.

[0094] In a specific implementation, before determining the target fusion image, the fusion information to be matched of at least one image to be fused may be determined. The image to be fused is an image used for fusion processing with the object image; for example, a landscape background image, a science fiction background image, etc. The fusion information to be matched includes the fusion object information and the key point information of at least one target part of the fusion object. The fusion object information includes data of at least one fusion object in at least one reference dimension. Exemplarily, when the target part is a face, the key point information may include position information such as the nose tip position, the center of the eyebrows position, the corner of the mouth position, the eye position, and the ear position of the face. The fusion object information may be consistent with the reference dimension described by the object description information. Exemplarily, when the object description information describes the data of the display object in the object category dimension, the fusion object information may also describe the data of the fusion object in the object category dimension.

[0095] In this embodiment, at least one image to be fused is received, and detection is performed on the at least one image to be fused based on a part detection algorithm to determine information to be matched and fused. For example, when the fusion object is a human face, the information to be matched and fused may include information such as facial maturity and the total number of faces; it may also include information about key points of facial parts.

[0096] Specifically, the determined fusion information to be matched can be written, and the file in which the fusion information to be matched is written can be determined as a configuration file. Furthermore, the configuration file can be compressed and packaged, and the configuration file can be updated based on the file obtained after compression and packaging. When determining the target fusion image, the fusion information to be matched in the configuration file can be called, and the target fusion image can be determined by selecting the fusion image to be selected corresponding to the fusion information to be matched that matches the object description information. In this embodiment, the target fusion image is determined directly based on the fusion information to be matched and the object description information in the configuration file, without the need to re-detect each image to be fused, which is conducive to improving the speed of generating the target image.

[0097] S230. Determine a fusion position of at least one display object in a target fusion image based on the object description information and the target fusion information; fuse the object image of the display object to the fusion position based on the key point information of the fusion object in the target fusion information to obtain a target image.

[0098] In a specific implementation, in order to make the target image more consistent with the distribution requirements of the display objects during image fusion, the method of determining the fusion position may include: determining the fusion position of at least one display object in the target fusion image based on the object description information, the target fusion information and the object information of the display object; wherein the object information includes information such as the object category and the object maturity.

[0099] When determining the fusion position, a preset image processing method for single-object fusion can be used for each displayed object. Furthermore, based on the correspondence between the fusion object and the fusion position in the target fusion image, the key point information corresponding to each fusion position is determined. The object images of the displayed objects are aligned based on the key point information, and the aligned object images are fused to the corresponding fusion position to obtain the target image.

[0100] For example, when the displayed object is a face, for each face to be fused, the fusion position corresponding to the face to be fused is determined in the target fused image. Based on the facial key point information corresponding to each fusion position, the key points of the nose, mouth, eyes, eyebrows, and ears in the facial image to be fused are adjusted so that the key point positions in the adjusted facial image are consistent with the key point information of the corresponding fusion position. The adjusted facial image is then fused to the corresponding fusion position. After the image fusion operation is completed for all faces, the target image is obtained.

[0101] In this embodiment, the fusion position of at least one display object in the target fusion image can be quickly determined through object description information and target fusion information; and the object image to be fused is adjusted based on the key point information of the part, so as to ensure that the object image can be fused according to the key point requirements of the target fusion image, which is conducive to improving the target image after the fusion operation of the object image, making it more ornamental and improving the user experience.

[0102] In actual applications, for different reference dimensions, the fusion position determined for the same object image may be different. In order to better meet user needs, the fusion position of at least one display object in the target fusion image is determined based on the object description information and the target fusion information, including: determining the fusion position of the object image in the target fusion image based on a pre-set first fusion reference dimension, object description information and target fusion information.

[0103] Among them, the first fusion reference dimension corresponds to the object category dimension.

[0104] In a specific implementation, the object category of the display object fused into the target fused image can be determined by pre-setting the first fusion reference dimension. Exemplarily, if the first fusion reference dimension is a person, the object image of the display object belonging to the person can be fused into the target fused image. Specifically, based on the pre-set first fusion reference dimension, the first data corresponding to the first fusion reference dimension in the object description information and the second data corresponding to the first fusion reference dimension in the target fusion information can be determined, and the fusion position of the object image in the target fused image can be determined based on the first data and the second data. Exemplarily, if the first fusion reference dimension is a person, the first data is the total number of person images in the object image, and the total number can be 5, and the second data is the total number of person images in the fused image, and the total number can be greater than or equal to 5, then 5 positions can be arbitrarily selected from the corresponding positions of the fused image as the fusion positions corresponding to the object image.

[0105] In this embodiment, by presetting the first fusion reference dimension and determining the fusion position based on the first fusion reference dimension, the personalized needs of the user can be better met.

[0106] The above describes in detail the embodiments corresponding to the image processing method. In order to make those skilled in the art further understand the technical solution of the method, the following describes it in detail with reference to the scenario of fusing facial images.

[0107] In this embodiment, the target part corresponds to the facial part, the object image corresponds to the facial image of the display object, the part key point information includes the facial part key points of the fused object, the background information of the target fused image is different from the background information of the image to be processed, and the fused images to be matched correspond to different style types.

[0108] The background information represents the remaining image after removing the displayed object. The images to be matched and fused correspond to different styles. For example, the styles of the images to be matched and fused include solid color, landscape, science fiction, and animation.

[0109] For a clearer and more detailed explanation of the facial image fusion process, please refer to Figure 3. The method provided in this embodiment can be applied to the server. In a specific implementation, to improve image processing performance, a configuration file can be pre-generated before performing facial image fusion. Specifically, at least one image to be fused is pre-stored. A part detection algorithm is used to determine image information such as maturity, object category, and key point locations for each facial image in each fused image. For example, 106 key point locations can be determined for each facial image; for example, these may include the location of the nose tip, the center of the eyebrows, and the corners of the mouth. Based on the determined maturity, object category, and key point locations, image data such as the number of people in each fused image, the number of people corresponding to each object category, and the maturity distribution can be determined. For example, the maturity distribution includes the number of adolescents, the number of middle-aged people, and the number of elderly people. Furthermore, within the reference dimension of each object category, the images can be sorted in ascending order of maturity. The determined image information and image data can be written into the configuration file, and the image to be fused can be used as the image to be selected for fusion, compressed, packaged and transferred to obtain an image package. In the subsequent multi-face fusion matching process, the image information and image data in the configuration file can be directly used without using the part detection algorithm again, which greatly improves the speed of image generation.

[0110] In practical applications, after receiving the facial image and corresponding object description information for image fusion sent by the user end, a target fused image that matches the object description information can be determined from the fused images to be selected through an image retrieval and matching algorithm. It should be noted that if there are multiple fused images to be selected that match the object description information, one of the fused images to be selected can be randomly selected to be the target fused image, and information such as the object category and facial key points of the fused object in the target fused image can be obtained. Using the part fusion algorithm, object category, and facial key points, the facial image to be fused is matched one-to-one with the facial key points in the target fused image, and an image fusion operation is performed to obtain the target image.

[0111] In a specific implementation, if there are multiple facial images to be fused, the above method can be used to loop through the image corresponding to each fusion object in the target fusion image multiple times to achieve the fusion operation between multiple facial images and the target fusion image.

[0112] This embodiment can match target parts to facial parts and the object image to the facial image of the displayed object, thereby fusing the facial image with the target fused image to achieve a facial fusion effect. Pre-generating a matching file improves image processing performance and enables the fusion of single or multiple objects into the target fused image, increasing its applicability and meeting users' diverse and rich image effect needs.

[0113] FIG4 is a flowchart of another image processing method provided by an embodiment of the present disclosure. As shown in FIG4 , the apparatus includes: an image receiving module 410 , a target fused image determining module 420 , and an object image fusion module 430 .

[0114] An image receiving module 410 is configured to receive an object image of at least one display object and object description information including at least one display object in an image to be processed;

[0115] a target fused image determining module 420, configured to determine a target fused image from at least one fused image to be selected based on the object description information;

[0116] An object image fusion module 430 is configured to fuse the object image into the target fusion image based on the object description information and the target fusion information of the target fusion image to obtain a target image;

[0117] The object description information corresponds to the fusion object information in the target fusion information, and the fusion object information corresponds to the fusion object displayed in the target fusion image.

[0118] On the basis of the above optional technical solutions, optionally, the following further aspects are included:

[0119] The configuration file generation module is configured to receive the to-be-matched fusion information of at least one to-be-fused image and generate a configuration file based on the to-be-matched fusion information, so as to determine a target fused image from the at least one to-be-selected fused image based on the to-be-matched fusion information and the object description information in the configuration file.

[0120] Based on the above-mentioned optional technical solutions, optionally, the object image corresponds to at least one target part of the display object, the object description information includes data of at least one display object in at least one reference dimension, the fusion information to be matched includes fusion object information and part key point information of at least one target part of the fusion object, and the fusion object information includes data of at least one fusion object in at least one reference dimension.

[0121] Based on the above optional technical solutions, optionally, the reference dimension includes at least one of an object category dimension, a single object quantity dimension under different object categories, a total object quantity dimension, and a single object maturity dimension under different object categories.

[0122] Based on the above optional technical solutions, optionally, the target fused image determination module 420 includes:

[0123] a fusion attribute determination submodule, configured to determine a fusion attribute between the object description information and the to-be-matched fusion information of at least one to-be-selected fusion image; wherein the to-be-matched fusion information is determined after pre-processing the to-be-selected fusion image;

[0124] A target fusion information determination submodule is used to determine the target fusion information based on the fusion attribute, and use the to-be-selected fusion image corresponding to the target fusion information as the target fusion image;

[0125] The to-be-matched fusion information includes fusion object information of at least one fusion object in the to-be-selected fusion image.

[0126] Based on the above optional technical solutions, optionally, the fusion attribute determination submodule includes:

[0127] a fusion attribute determining unit, configured to determine a fusion attribute between the at least one fusion information to be matched and the object description information by performing similarity processing on data under different reference dimensions in the object description information and the at least one fusion information to be matched;

[0128] Correspondingly, the target fusion information determination submodule includes:

[0129] The first target fusion information determining unit is configured to determine the target fusion information based on a preset rule if there are multiple fusion attributes that meet a preset condition.

[0130] On the basis of the above optional technical solutions, optionally, the following further aspects are included:

[0131] The second target fusion information determination unit is used to determine, in sequence, the fusion attributes of at least one to-be-matched fusion image relative to the object description information under the same reference dimension according to the priority of at least one pre-set reference dimension if there is no fusion attribute that meets the preset conditions, so as to determine the target fusion information based on the fusion attributes.

[0132] Based on the above optional technical solutions, optionally, the object image fusion module 430 includes:

[0133] a fusion position determination submodule, configured to determine a fusion position of at least one display object in a target fusion image based on the object description information and the target fusion information;

[0134] The image fusion submodule is used to fuse the object image of the display object to the fusion position according to the key point information of the fusion object in the target fusion information to obtain the target image.

[0135] On the basis of the above optional technical solutions, optionally, the fusion position determination submodule includes:

[0136] a fusion position determining unit, configured to determine a fusion position of the object image in the target fusion image according to a preset first fusion reference dimension, object description information, and target fusion information;

[0137] Among them, the first fusion reference dimension corresponds to the object category dimension.

[0138] Based on the above optional technical solutions, optionally, the object image fusion module 430 includes:

[0139] The fusion submodule is used to fuse the object image with some of the fused objects in the target fused image to obtain the target image when the number of the object images is less than the number of fused objects.

[0140] On the basis of the above-mentioned optional technical solutions, optionally, the fusion submodule is further configured to determine a portion of the fused objects of the object image in the target fused image according to a preset second fusion reference dimension.

[0141] Based on the above-mentioned optional technical solutions, optionally, the target part corresponds to the facial part, the object image corresponds to the facial image of the display object, the part key point information includes the facial part key points of the fusion object, the background information of the target fusion image is different from the background information of the image to be processed, and the fusion images to be matched correspond to different style types.

[0142] The technical solution provided by the embodiment of the present disclosure receives an object image of at least one display object in an image to be processed and object description information including at least one display object; based on the object description information, determines a target fusion image from at least one fusion image to be selected; based on the object description information and target fusion information of the target fusion image, fuses the object image into the target fusion image to obtain a target image; wherein, the object description information corresponds to the fusion object information in the target fusion information; since the fusion object information corresponds to the fusion object displayed in the target fusion image, it means that a fusion object is provided in the target fusion image, and when the target image is obtained based on the object description information and the target fusion information, a single object can be fused into the target fusion image, or multiple objects can be fused into the target fusion image based on the number of display objects contained in the image to be processed, thereby solving the problem in the prior art that only a single object can be fused, improving the breadth of application, and meeting the user's diverse and rich image effect requirements.

[0143] The image processing device provided by the embodiments of the present disclosure can execute the image processing method provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0144] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0145] FIG5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Referring to FIG5 , a schematic diagram of the structure of an electronic device (such as a terminal device or server in FIG5 ) 500 suitable for implementing an embodiment of the present disclosure is shown below. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG5 is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0146] As shown in FIG5 , the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An edit / output (I / O) interface 505 is also connected to the bus 504.

[0147] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although FIG5 shows the electronic device 500 with various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may alternatively be implemented or present.

[0148] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0149] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0150] The electronic device provided by the embodiment of the present disclosure and the image processing method provided by the above embodiment have the same concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0151] An embodiment of the present disclosure provides a computer storage medium having a computer program stored thereon. When the program is executed by a processor, the image processing method provided by the above embodiment is implemented.

[0152] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0153] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0154] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0155] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0156] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: receives an object image of at least one display object in the image to be processed and object description information including at least one display object; based on the object description information, determines a target fused image from at least one fused image to be selected; based on the object description information and target fusion information of the target fused image, fuses the object image into the target fused image to obtain a target image; wherein the object description information corresponds to the fused object information in the target fusion information, and the fused object information corresponds to the fused object displayed in the target fused image.

[0157] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0158] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0160] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0161] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0163] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0164] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. An image processing method, comprising: Receiving an object image of at least one display object in an image to be processed and object description information including the at least one display object; Determining a target fusion image from at least one candidate fusion image based on the object description information; And Fusing the object image into the target fusion image based on the object description information and target fusion information of the target fusion image to obtain a target image; Wherein, the fusion object information in the object description information and the target fusion information corresponds, and the fusion object information corresponds to the fusion object displayed in the target fusion image.

2. The method according to claim 1, further comprising: Receiving candidate fusion information of the at least one candidate fusion image and generating a configuration file based on the candidate fusion information, so as to determine a target fusion image from at least one candidate fusion image based on the candidate fusion information and the object description information in the configuration file.

3. The method according to claim 1 or 2, wherein the object image corresponds to at least one target part of the display object, the object description information includes data of the at least one display object in at least one reference dimension, the candidate fusion information includes fusion object information and part key point information of at least one target part of the fusion object, and the fusion object information includes data of the at least one fusion object in the at least one reference dimension.

4. The method according to claim 3, wherein the reference dimension includes at least one of an object category dimension, a single object quantity dimension under different object categories, a total object quantity dimension, and a single object maturity dimension under different object categories.

5. The method according to claim 3, wherein determining a target fusion image from at least one candidate fusion image based on the object description information includes: Determining a fusion attribute between the object description information and candidate fusion information of the at least one candidate fusion image; wherein the candidate fusion information is determined after pre-processing the candidate fusion image; and Determining the target fusion information based on the fusion attribute and using the candidate fusion image corresponding to the target fusion information as the target fusion image; Wherein, the candidate fusion information includes fusion object information of at least one fusion object in the candidate fusion image.

6. The method according to claim 5, wherein determining the fusion attribute between the object description information and candidate fusion information of the at least one candidate fusion image includes: Determining a fusion attribute between at least one of the candidate fusion information and the object description information by performing data similarity processing on data in different reference dimensions of the object description information and at least one of the candidate fusion information; Correspondingly, determining the target fusion information based on the fusion attribute includes: If there are multiple fusion attributes meeting preset conditions, determining the target fusion information based on a preset rule.

7. The method according to claim 6, further comprising: If there is no fusion attribute that meets the preset conditions, then according to the priority of at least one pre-set reference dimension, the fusion attributes of the at least one to-be-matched fusion image with respect to the object description information under the same reference dimension are determined in sequence, so as to determine the target fusion information based on the fusion attributes.

8. The method according to claim 1, wherein the fusing the object image into the target fusion image based on the target fusion information of the object description information and the target fusion image to obtain a target image includes: Determining the fusion position of the at least one display object in the target fusion image according to the object description information and the target fusion information; And Fusing the object image of the display object to the fusion position according to the part key point information of the fusion object in the target fusion information to obtain the target image.

9. The method according to claim 8, wherein the determining the fusion position of the at least one display object in the target fusion image according to the object description information and the target fusion information includes: Determining the fusion position of the object image in the target fusion image according to a pre-set first fusion reference dimension, the object description information, and the target fusion information; Wherein, the first fusion reference dimension corresponds to the object category dimension.

10. The method according to claim 1, wherein the fusing the object image into the target fusion image to obtain a target image includes: When the number of the object images is less than the number of the fusion objects, fusing the object images with some of the fusion objects in the target fusion image to obtain the target image.

11. The method according to claim 10 further includes: Determining the partial fusion objects of the object image in the target fusion image according to a pre-set second fusion reference dimension.

12. The method according to claim 3, wherein the target part corresponds to a facial part, the object image corresponds to the facial image of the display object, the part key point information includes the facial part key points of the fusion object, the background information of the target fusion image is different from the background information of the to-be-processed image, and the to-be-matched fusion image corresponds to different style types.

13. An image processing apparatus, comprising: An image receiving module, configured to receive the object images of at least one display object in the to-be-processed image and the object description information including the at least one display object; A target fusion image determining module, configured to determine a target fusion image from at least one to-be-selected fusion image based on the object description information; And An object image fusing module, configured to fuse the object image into the target fusion image based on the target fusion information of the object description information and the target fusion image to obtain a target image; Wherein, the fusion object information in the object description information and the target fusion information corresponds, and the fusion object information corresponds to the fusion object displayed in the target fusion image.

14. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the image processing method according to any one of claims 1-12.

15. A storage medium containing computer-executable instructions, the computer-executable instructions being used to execute the image processing method according to any one of claims 1-12 when executed by a computer processor.

Images