An image processing method, apparatus and device

Abstract

The application discloses an image processing method, device and equipment, and the method comprises the following steps: acquiring an edge image block set of a preset reference image set; determining a middle-layer edge feature set according to a preset image training set and the edge image block set; obtaining an edge image block set of a test image according to the test image and the middle-layer edge feature set; and processing the edge image block set of the test image to obtain an edge image of the test image. Through the above method, the application realizes edge processing of the image under multiple scales, and improves the accuracy and noise resistance of edge detection.

Description

Technical Field

[0001] This invention relates to the field of image technology, and more specifically to an image processing method, apparatus, and device. Background Technology

[0002] For the human visual system, edge detection is a multi-scale process. The human eye can extract useful and desired information from different scales and produce optimal edge maps. Current technologies can fuse information from multiple scales of an image to obtain edge maps that better match the characteristics of human vision; this is known as multi-scale edge detection algorithms. Currently, multi-scale algorithms can be divided into three types: adaptive scale selection; fusing edge results from a single scale, such as multi-scale tracking strategies; and selecting different scales for certain pixels or regions of the image. For visual recognition, the features that bridge the gap between high-scale and low-scale information can be called mid-level edge features. These mid-level edge features can be manually labeled or learned in a supervised or unsupervised manner.

[0003] The existing method of manually annotating mid-level edge features results in complex features that are affected by scale parameters, leading to low accuracy in edge classification. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide an image processing method, apparatus, and device that overcomes or at least partially solves the above problems.

[0005] According to one aspect of the present invention, an image processing method is provided, the method comprising:

[0006] Obtain the set of edge image patches from the preset reference image set;

[0007] The middle-layer edge feature set is determined based on the preset image training set and the edge image patch set;

[0008] Based on the test image and the mid-layer edge feature set, the set of edge image patches of the test image is obtained;

[0009] The edge image patch set of the test image is processed to obtain the edge map of the test image.

[0010] According to another aspect of the present invention, an image processing apparatus is provided, the apparatus comprising:

[0011] The acquisition module is used to acquire a set of edge image patches from a preset reference image set;

[0012] The processing module is used to determine a mid-level edge feature set based on a preset image training set and the edge image patch set; to obtain an edge image patch set of the test image based on the test image and the mid-level edge feature set; and to process the edge image patch set of the test image to obtain the edge map of the test image.

[0013] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0014] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above image processing method.

[0015] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the image processing method described above.

[0016] The solution provided by the above embodiments of the present invention improves the accuracy of edge detection by obtaining an edge image patch set of a preset reference image set; determining a mid-level edge feature set based on a preset image training set and the edge image patch set; obtaining an edge image patch set of a test image based on a test image and the mid-level edge feature set; and processing the edge image patch set of the test image to obtain an edge map of the test image.

[0017] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more obvious and understandable, specific implementation methods of the embodiments of the present invention are described below. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0019] Figure 1 A flowchart of the image processing method provided in an embodiment of the present invention is shown;

[0020] Figure 2 A schematic diagram of an edge image patch obtained in an image processing method provided by another embodiment of the present invention is shown;

[0021] Figure 3a A schematic diagram of images in a preset image training set provided in another embodiment of the present invention;

[0022] Figure 3b Another embodiment of the present invention provides a preset image training set divided into 24 image blocks;

[0023] Figure 3c Another embodiment of the present invention provides a result image of edge detection of an image block to be tested;

[0024] Figure 3d Another embodiment of the present invention provides an edge map of the image block to be tested after clustering processing;

[0025] Figure 4 A schematic diagram of the structure of the image processing apparatus provided in an embodiment of the present invention is shown;

[0026] Figure 5 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0027] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0028] Figure 1 A flowchart of an image processing method provided by an embodiment of the present invention is shown. Figure 1 As shown, the method includes the following steps:

[0029] Step 11: Obtain the set of edge image patches from the preset reference image set;

[0030] Step 12: Determine the middle-layer edge feature set based on the preset image training set and the edge image patch set;

[0031] Step 13: Based on the test image and the middle layer edge feature set, obtain the edge image patch set of the test image;

[0032] Step 14: Process the set of edge image blocks of the test image to obtain the edge map of the test image.

[0033] In this embodiment, each image in the preset reference image set has the same size. Preferably, it can be a binary edge map of size a×a. By processing the binary edge map of each image in the preset reference image set, a set of typical edge images is obtained. In subsequent image detection, the influence of single-scale feature scale parameters is avoided, which would lead to single and inaccurate detection results.

[0034] Each image in the preset image training set has the same size as each image in the preset reference image set. Preferably, the preset image training set can be the BSDS dataset. Based on the preset image training set and the typical edge image set obtained from the preset reference image set, a mid-level edge feature set is determined to provide a basis for edge processing of the subsequent test image. The test image is processed with the mid-level edge feature set to improve the detection accuracy.

[0035] In an optional embodiment of the present invention, step 11 may include:

[0036] Step 111: Divide the images in the preset reference image set into N target image blocks according to a preset size;

[0037] Step 112: Process the N target image blocks at the i-th scale to obtain N edge image blocks, 1≤i≤n, where n is the preset number of scales;

[0038] Step 113: Based on the N target image blocks and the edge image blocks obtained by processing the N target image blocks at different scales, form the edge image block set.

[0039] In this embodiment, each image in the preset reference image set is divided according to a preset size to obtain N target image blocks, for example, labeled as M1, M2, M3…, M… N At n scales, the edges of N target image patches are quantitatively evolved at the i-th scale (where i = 1, 2, ..., n), resulting in edge image patches (M) for each target image patch. 1i M 2i M 3i M Ni The target image patch of each image in the preset reference image set is merged with the corresponding edge image patch after quantitative evolution at n scales. The resulting image patch set is the edge image patch set (i.e., M1, M2, M3, ..., M...). N M 1i M 2i M 3i …, M NiThis means that there are (N+N*n) image patches. By fusing information from multiple scales of the image, an edge map that better matches the visual characteristics of the human eye is obtained. Quantitative evolution processing of multi-scale images is performed, taking into account the relationship between image edges in scale space, making subsequent detection results more accurate. At the same time, the set of typical edge images at multiple scales has low feature complexity and can also solve the limitations of single-scale edge detection.

[0040] The binary edges of each image in the preset reference image set can be classified into three types: step edges, staircase edges, and impulse edges. The quantitative evolution results of different edge maps are closely related to the choice of scale parameters. As the scale parameters change, new edge points may appear, while original edge points may shift or disappear completely. Typical edges can represent the characteristics of an image in scale space. It should be noted that in reality, image edges are not limited to the types mentioned above; the actual edge types are much more diverse.

[0041] In an optional embodiment of the present invention, step 12 may include:

[0042] Step 121: Divide each image in the preset image training set into M image blocks according to a preset size;

[0043] Step 122: Obtain the similarity between the M image patches and the target image patch and edge image patch in the edge image patch set;

[0044] Step 123: Determine the middle layer edge feature set based on the similarity.

[0045] In this embodiment, the similarity can be calculated by the RGB distance between pixels between image blocks, or by other similarity calculation formulas such as SSIM and cosine similarity, which will not be elaborated here. In this embodiment, the BSDS dataset can be used. The preset image training set has 200 images, each with a manually annotated standard edge map. The 200 images can be divided into M image blocks of size n×n. The similarity between each training set and each image block in the edge image block set is calculated. The images in the preset image training set are classified according to the similarity, and a mid-level edge feature set is obtained. The manually annotated standard edge map is trained by comparison with the edge image block set and multi-scale fusion is used to improve the accuracy and noise resistance of the edges.

[0046] In an optional embodiment of the present invention, step 122 may include:

[0047] Step 1221: If the similarity between each image block in the M image blocks of the preset image training set and the target image block and a first number of image blocks in the edge image block set is greater than a first preset threshold, then the image block in the preset image training set is determined to be a first type image block; otherwise, the image block in the preset image training set is determined to be a second type image block.

[0048] Step 1222: Obtain the middle layer edge feature set based on the first type of image block and the second type of image block.

[0049] In this embodiment, the first preset threshold is 80%, and the first quantity should satisfy: the first quantity is greater than or equal to That is, when the first quantity is greater than or equal to half the number of all image patches in the edge image patch set, and the similarity is greater than the first preset threshold of 80%, the image patch in the preset image training set is determined to be a first type of image patch. The first type of image patch satisfies the image patch features in the edge image patch set, which is a valid image patch. Image patches in the preset image training set that do not meet this condition are recorded as second type of image patches, which are invalid image patches. The set of valid images and invalid images is the middle layer edge feature set, which is the set of the two types of images, the valid images and the invalid images, obtained after training.

[0050] In an optional embodiment of the present invention, step 13 may include:

[0051] Step 131: Obtain the edge image of the test image;

[0052] Step 132: Divide the edge image of the test image into L test image blocks according to a preset size; L is a positive integer.

[0053] Step 133: Cluster the L test image blocks with the image blocks in the middle layer edge feature set to obtain the edge image block set of the test image.

[0054] In this embodiment, the edge map of the test image is obtained using an existing algorithm. The edge map of the test image is divided into image blocks of size a×a, resulting in L test image blocks. Each of the L test image blocks is clustered with valid image blocks (such as the first type of image blocks mentioned above) and invalid image blocks (such as the second type of image blocks mentioned above) in the middle-layer edge feature set. Preferably, the K-means method can be used to cluster each test image block with the image blocks in the middle-layer edge feature set. The K-means method is simple in principle, easy to implement, and has a fast convergence speed. At the same time, the accuracy of edge pixels is improved through clustering, and the edge map is more consistent with the visual characteristics of the human eye.

[0055] Furthermore, if the similarity between each of the L test image blocks and the first type of image block in the middle layer edge feature set is greater than a second preset threshold, then the type of the test image block is marked as the first type, i.e., it is a valid image block; otherwise, the type of the test image block is marked as the second type, i.e., it is an invalid image block; the image blocks after all test image blocks are marked form the edge image block set of the test image. Optionally, the second preset threshold is 80%.

[0056] In an optional embodiment of the present invention, step 14 may include:

[0057] Step 141: Connect the image blocks in the edge image block set of the test image according to the preset edge connection algorithm to obtain the edge map of the test image.

[0058] In this embodiment, the Canny double threshold algorithm can be used to detect the image blocks in the edge image block set of the test image, and the image blocks in the detected edge image block set of the test image can be connected to obtain the edge map of the test image.

[0059] In the dual-threshold algorithm, the high threshold is used to distinguish the object whose contour is to be extracted from the background, just like the parameters of threshold segmentation, which determine the contrast between the target and the background; the low threshold is used to smooth the edge contour, which may be discontinuous or not smooth enough. The low threshold is used to smooth the contour line or connect the discontinuous parts. The image patches in the edge image patch set of the detected test image are connected to obtain the edge map of the final test image.

[0060] The above implementation method will be explained below with specific examples. Taking an image from the BSDS edge detection database as an example, the specific steps are as follows:

[0061] Step S1: Given a Gaussian scale of 2, the typical edge set consists of 6 images, such as... Figure 2 As shown, the first three images are the initial typical edge images, and the last three images are the images after Gaussian blur has been applied;

[0062] Step S2, take one original image from the training set (e.g.) Figure 3a The standard edge map (as shown) is divided into 24 image blocks of the same size as the typical edge images. Each image block is compared to the 6 typical edge images from step 1 for image similarity. If the similarity to 3 or more typical edge images reaches 80%, the image block is considered a valid image block. For example... Figure 3b As shown, similarity calculations are performed between 24 image patches and a typical edge set to obtain a mid-level edge feature set;

[0063] Step S3: Use the existing algorithm, the Canny algorithm, to perform edge detection on the input image. Divide the edge map obtained by the algorithm into image blocks of the same size as typical edge images, such as... Figure 3c As shown.

[0064] Step S4: Cluster each image patch and the mid-level edge feature set from Step 2 using the K-means method. Patches belonging to valid image patches are labeled as edges; otherwise, they are not edges. Then, connect the edges using a double threshold, such as... Figure 3d As shown, the final edge map is obtained.

[0065] In this embodiment, a simple mid-level edge feature is used: typical edge features. This feature integrates the quantitative evolution of typical edge features in scale space. The multi-scale approach retains the accuracy of low-scale edges while also providing the noise resistance of high-scale edges. At the same time, using typical edge features or multi-scale evolved typical edge features in manually annotated edge maps as training samples greatly improves the accuracy of edge classification, making the detected edges more consistent with human vision.

[0066] Figure 4 A schematic diagram of the image processing apparatus provided in an embodiment of the present invention is shown. Figure 4 As shown, the device 40 includes:

[0067] The acquisition module 41 is used to acquire a set of edge image blocks of a preset reference image set;

[0068] The processing module 42 is used to determine the middle-layer edge feature set according to the preset image training set and the edge image patch set; to obtain the edge image patch set of the test image according to the test image and the middle-layer edge feature set; and to process the edge image patch set of the test image to obtain the edge map of the test image.

[0069] Optionally, the acquisition module 41 is used to acquire a set of edge image patches of a preset reference image set, including:

[0070] The images in the preset reference image set are divided into N target image blocks according to a preset size;

[0071] The N target image patches are processed at the i-th scale to obtain N edge image patches, 1≤i≤n, where n is a preset number of scales;

[0072] The edge image patch set is formed based on the N target image patches and the edge image patches obtained by processing the N target image patches at different scales.

[0073] Optionally, the processing module 42 is configured to determine a mid-level edge feature set based on a preset image training set and the edge image patch set, including:

[0074] Each image in the preset image training set is divided into M image blocks according to a preset size;

[0075] Obtain the similarity between the M image patches and the target image patch and edge image patch in the edge image patch set;

[0076] The middle layer edge feature set is determined based on the similarity.

[0077] Optionally, the processing module 42 determines the mid-layer edge feature set based on the similarity, including:

[0078] If the similarity between each image block in the M image blocks of the preset image training set and the target image block and a first number of image blocks in the edge image set is greater than a first preset threshold, then the image block in the preset image training set is determined to be a first type image block; otherwise, the image block in the preset image training set is determined to be a second type image block.

[0079] The middle-layer edge feature set is obtained based on the first type of image patch and the second type of image patch.

[0080] Optionally, the processing module 42 obtains a set of edge image patches of the test image based on the test image and the mid-layer edge feature set, including:

[0081] Obtain the edge image of the test image;

[0082] The edge image of the test image is divided into L test image blocks according to a preset size; L is a positive integer.

[0083] The L test image blocks are clustered with the image blocks in the middle layer edge feature set to obtain the edge image block set of the test image.

[0084] Optionally, the processing module 42 performs clustering processing on the L test image blocks and the image blocks in the middle-layer edge feature set to obtain edge image blocks of the test image, including:

[0085] If the similarity between each of the L test image blocks and the first type of image block in the middle layer edge feature set is greater than a second preset threshold, then the type of the test image block is marked as the first type; otherwise, the type of the test image block is marked as the second type, thus obtaining the edge image block set of the test image.

[0086] Optionally, the processing module 42 processes the set of edge image blocks of the test image to obtain the edge map of the test image, including:

[0087] The edge map of the test image is obtained by connecting the image blocks in the set of edge image blocks of the test image according to a preset edge connection algorithm.

[0088] This device is the same as the method described above. All implementations of the method described above are applicable to the embodiments of this device and can achieve the same technical effect.

[0089] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the image processing method in any of the above method embodiments.

[0090] Figure 5 The diagram shows a structural schematic of a computing device provided in an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0091] like Figure 5 As shown, the computing device may include a processor, a communications interface, memory, and a communications bus.

[0092] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other network elements, such as clients or other servers. The processor executes programs, specifically the relevant steps described in the image processing method embodiment for computing devices.

[0093] Specifically, the program may include program code, which includes computer operation instructions.

[0094] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0095] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0096] Specifically, the program can be used to cause the processor to execute the image processing method in any of the above method embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units in the above image processing method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0097] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the embodiments of the present invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of the present invention.

[0098] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0099] Similarly, it should be understood that, in order to streamline the embodiments of the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0100] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0101] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0102] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0103] It should be noted that the above embodiments are illustrative of the present invention and not restrictive of the invention, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. An image processing method, characterized in that, The method includes: Obtain the set of edge image patches from the preset reference image set; The middle-layer edge feature set is determined based on the preset image training set and the edge image patch set; The step of determining the mid-level edge feature set based on the preset image training set and the edge image patch set further includes: Each image in the preset image training set is divided into M image blocks according to a preset size; the similarity between the M image blocks and the target image block and edge image block in the edge image block set is obtained; If the similarity between any image block in the M image blocks corresponding to the preset image training set and the target image block and a first number of image blocks in the edge image block set is greater than a first preset threshold, then the image block is determined to be a first type image block; otherwise, the image block is determined to be a second type image block; the middle-layer edge feature set is obtained based on the first type image block and the second type image block. Based on the test image and the mid-layer edge feature set, the set of edge image patches of the test image is obtained; The edge image patch set of the test image is processed to obtain the edge map of the test image.

2. The image processing method according to claim 1, characterized in that, Obtain the set of edge image patches from the preset reference image set, including: The images in the preset reference image set are divided into N target image blocks according to a preset size; The N target image patches are processed at the i-th scale to obtain N edge image patches, 1≤i≤n, where n is a preset number of scales; The edge image patch set is formed based on the N target image patches and the edge image patches obtained by processing the N target image patches at different scales.

3. The image processing method according to claim 1, characterized in that, Based on the test image and the mid-layer edge feature set, the set of edge image patches of the test image is obtained, including: Obtain the edge image of the test image; The edge image of the test image is divided into L test image blocks according to a preset size; L is a positive integer. The L test image blocks are clustered with the image blocks in the middle layer edge feature set to obtain the edge image block set of the test image.

4. The image processing method according to claim 3, characterized in that, The L test image blocks are clustered with the image blocks in the middle-layer edge feature set to obtain the edge image block set of the test image, including: If the similarity between each of the L test image blocks and the first type of image block in the middle layer edge feature set is greater than a second preset threshold, then the type of the test image block is marked as the first type; otherwise, the type of the test image block is marked as the second type, thus obtaining the edge image block set of the test image.

5. The image processing method according to claim 1, characterized in that, The edge image patch set of the test image is processed to obtain the edge map of the test image, including: The edge map of the test image is obtained by connecting the image blocks in the set of edge image blocks of the test image according to a preset edge connection algorithm.

6. An image processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire a set of edge image patches from a preset reference image set; The processing module is used to determine a mid-level edge feature set based on a preset image training set and the edge image patch set; obtain an edge image patch set of the test image based on the test image and the mid-level edge feature set; and process the edge image patch set of the test image to obtain the edge map of the test image. The processing module is further configured to: divide each image in the preset image training set into M image blocks according to a preset size; obtain the similarity between the M image blocks and the target image blocks and edge image blocks in the edge image block set; if the similarity between any image block in the M image blocks corresponding to the preset image training set and a first number of image blocks in the target image blocks and edge image blocks in the edge image block set is greater than a first preset threshold, then determine that the image block is a first type of image block; otherwise, determine that the image block is a second type of image block; and obtain the middle-layer edge feature set based on the first type of image blocks and the second type of image blocks.

7. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the image processing method as described in any one of claims 1-5.

8. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the image processing method as described in any one of claims 1-5.

Images