Method, device and equipment for identifying fuzzy image and storage medium

Abstract

This disclosure relates to a method, apparatus, device, and storage medium for recognizing blurred images. The method includes: acquiring a target texture image and associated texture images that share a common image region with the target texture image; for each associated texture image, determining the relative sharpness of the target texture image relative to the associated texture images based on the common image region between the target texture image and the associated texture images; and determining whether the target texture image is a blurred image based on the relative sharpness of the target texture image relative to each associated texture image. Embodiments of this disclosure can improve the accuracy of blurred image recognition.

Description

[0001] This application is a divisional application of the patent application with application number 202311095672.0, entitled "Blur image recognition method, device, equipment and storage medium", filed on August 28, 2023. TECHNICAL FIELD

[0002] Embodiments of the present disclosure relate to the field of three-dimensional scanning technology, in particular to a blur image recognition method, device, equipment and storage medium. BACKGROUND

[0003] In the process of scanning an object by a three-dimensional scanner, the texture images collected often have blur (motion blur, out-of-focus blur, etc.). If the blur image recognition is not performed on the texture images, the blurred texture images will affect the final mapping effect of the model.

[0004] Currently, the blur image recognition is usually performed on each texture image based on the texture image, that is, the blur image recognition is independently performed on each texture image based on the texture image. However, this detection method is very prone to misjudgment and has low accuracy. SUMMARY

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide a blur image recognition method, device, equipment and storage medium.

[0006] A first aspect of the embodiments of the present disclosure provides a blur image recognition method, which comprises: obtaining a target texture image and an associated texture image having a common image area with the target texture image; for each associated texture image, determining a relative sharpness of the target texture image relative to the associated texture image based on the common image area of the target texture image and the associated texture image; determining whether the target texture image is a blur image based on the relative sharpness of the target texture image relative to each associated texture image.

[0007] A second aspect of the embodiments of the present disclosure provides a blur image recognition device, which comprises: a first obtaining module configured to obtain a target texture image and an associated texture image having a common image area with the target texture image; a first determining module configured to, for each associated texture image, determine a relative sharpness of the target texture image relative to the associated texture image based on the common image area of the target texture image and the associated texture image; a second determining module configured to determine whether the target texture image is a blur image based on the relative sharpness of the target texture image relative to each associated texture image.

[0008] A third aspect of this disclosure provides an electronic device, the server comprising: a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the method of the first aspect described above.

[0009] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the method of the first aspect described above.

[0010] The technical solution provided in this disclosure has the following advantages compared with the prior art: This embodiment of the disclosure can acquire a target texture image and associated texture images that share a common image region with the target texture image. For each associated texture image, based on the common image region between the target texture image and the associated texture images, the relative sharpness of the target texture image relative to the associated texture images is determined. Based on the relative sharpness of the target texture image relative to each associated texture image, it is determined whether the target texture image is a blurred image. Therefore, by employing the above technical solution, the target texture image and associated texture images can be used together to detect whether the target texture image is a blurred image. Compared to blurry image recognition based solely on the target texture image, this increases the basis for blurry image recognition, thereby reducing the probability of misjudgment and improving the accuracy of blurry image recognition. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for recognizing blurred images provided in an embodiment of this disclosure; Figure 2 This is a flowchart of another method for recognizing blurred images provided in this disclosure embodiment; Figure 3 This is a schematic diagram illustrating a blurry image recognition process provided in an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of a blurred image recognition device provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0014] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0015] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0016] Figure 1 This is a flowchart illustrating a method for recognizing blurred images according to an embodiment of this disclosure. This method can be executed by an electronic device. The electronic device can be exemplarily understood as a scanner, camera (e.g., SLR camera, mirrorless camera, etc.), mobile phone, tablet computer, laptop computer, desktop computer, smart TV, etc. Figure 1 As shown, the method provided in this embodiment includes the following steps: S110, Obtain the target texture image and the associated texture image that shares a common image region with the target texture image.

[0017] Specifically, the target texture image is the texture image to be identified as whether it is a blurry image, the associated texture image is the texture image used to assist in detecting whether the target texture image is a blurry image, and the number of associated texture images is at least one, for example, the number of associated texture images is multiple.

[0018] Specifically, the common image region is the image region with the same image content in the target texture image and the associated texture image. In other words, the common image region is the image region obtained by scanning the same area on the surface of the object in the target texture image and the associated texture image respectively. For example, the target texture image includes the image region obtained by scanning area A on the surface of the object, and the associated texture image also includes the image region obtained by scanning area A on the surface of the object. Then the image region corresponding to area A on the surface of the object is the common image region of the target texture image and the associated texture image.

[0019] In some embodiments, S110 may include: S111, acquiring multiple original texture images, wherein the multiple original texture images include a target texture image and candidate texture images corresponding to the target texture image, and the multiple original texture images correspond to the target mesh model.

[0020] Specifically, the multiple original texture images are multiple texture images obtained by 3D scanning of an object, carrying the object's texture information. The target mesh model (i.e., the mesh model) is a 3D model obtained by 3D scanning of an object, carrying the object's geometric information. After determining the image sharpness of each original texture image, a clear original texture image can be used to apply a texture to the target mesh model.

[0021] Specifically, when identifying whether a certain original texture image among multiple original texture images is a blurred image, that original texture image is the target texture image, and the candidate original texture image is the candidate texture image corresponding to the target texture image. However, it is not limited to this. For example, a portion of the original texture images in the candidate original texture images can also be the candidate texture images corresponding to the target texture image.

[0022] S112. For each original texture image, determine the facets that are visible relative to the original texture image from the target mesh model.

[0023] Specifically, the target mesh model consists of multiple patches and the topological relationships between them. The patches can include triangular patches, quadrilateral patches, etc., but are not limited to these.

[0024] Specifically, when acquiring a certain original texture image, if a patch on an object corresponds to an image region that can be imaged in the original texture image, then the patch is visible relative to the original texture image.

[0025] Optionally, determining the visible facets relative to the original texture image from the target mesh model includes: determining the normal vector and viewing direction of each facet in the target mesh model based on the original texture image; for each facet, if the angle between the normal vector and the viewing direction of the facet is less than or equal to a second preset threshold, then determining that the facet is visible relative to the original texture image.

[0026] It should be noted that the specific value of the second preset threshold can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the second preset threshold can be 60°, 59°, etc., but is not limited to this.

[0027] It is understandable that when the angle between the normal vector of a patch and the viewing direction is greater than the second preset threshold, a region on the object corresponding to the patch cannot be well imaged in the original texture image, which may result in color distortion, unclear images, and other problems. Removing such patches from the patches that are visible relative to the original texture image can identify the patches corresponding to reliable image regions of the original texture image, which is beneficial for accurately identifying reliable common image regions in the future, and thus helps to improve the accuracy of recognizing blurry images.

[0028] Of course, the original texture image and the target mesh model can also be input into the trained first neural network model to obtain the patch that is visible relative to the original texture image output by the first neural network model. This application does not limit this.

[0029] S113. For each candidate texture image, if the number of common patches between the candidate texture image and the target texture image is greater than a first preset threshold, then the candidate texture image is determined as an associated texture image, and the image region corresponding to the common patch is determined as a common image region, wherein the common patch is a patch that is visible relative to both the target texture image and the candidate texture image.

[0030] It should be noted that the specific value of the first preset threshold can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the first preset threshold can be 1, 2, 3, 4, 5, etc., but is not limited to this.

[0031] Specifically, for a target texture image, it is possible to determine which 2D pixels in the target texture image correspond to the 3D points in the common patch, thereby determining the common image region in the target texture image; for an associated texture image, it is possible to determine which 2D pixels in the associated texture image correspond to the 3D points in the common patch, thereby determining the common image region in the associated texture image.

[0032] It is understandable that by setting the candidate texture image as an associated texture image if the number of common patches between the candidate texture image and the target texture image is greater than a first preset threshold, and the image region corresponding to the common patch is determined as a common image region, the determination method of the associated texture image corresponding to the target texture image and the determination method of the common image region between the target texture image and the associated texture image can be made simple, convenient and not cumbersome, which helps to reduce the implementation difficulty and also helps to reduce the performance requirements of electronic devices.

[0033] Of course, after acquiring multiple original texture images and determining the target texture image and candidate texture images from the multiple original texture images, the target texture image and candidate texture images can also be input into the trained second neural network model to obtain the associated texture image corresponding to the target texture image output by the second neural network model, as well as the common image region between the target texture image and each associated texture image. This application does not limit this.

[0034] S120. For each associated texture image, based on the common image area of ​​the target texture image and the associated texture image, determine the relative sharpness of the target texture image relative to the associated texture image.

[0035] Specifically, relative sharpness is used to characterize the sharpness of the target texture image relative to the associated texture image. It should be noted that whether a larger relative sharpness value indicates a sharper target texture image than the associated texture image, or a smaller relative sharpness value indicates a sharper target texture image than the associated texture image, can be set by those skilled in the art according to the actual situation, and is not limited here.

[0036] Since the image sharpness of the target texture image and the associated texture image may differ, the regional sharpness of the common image region in the target texture image and the regional sharpness of the common image region in the associated texture image may also differ. Therefore, in some embodiments, determining the relative sharpness of the target texture image relative to the associated texture image based on the common image region of the target texture image and the associated texture image may include: obtaining the relative sharpness of the target texture image relative to the associated texture image by comparing the regional sharpness of the common image region in the target texture image region and the associated texture image region, respectively.

[0037] Of course, the common image regions in the associated texture image and the common image regions in the target texture image can also be input into the trained third neural network model to obtain the relative clarity of the target texture image relative to the associated texture image output by the third neural network model. This application does not limit this.

[0038] S130. Based on the relative sharpness of the target texture image relative to each associated texture image, determine whether the target texture image is a blurry image.

[0039] In some embodiments, S130 may include: inputting the relative sharpness of the target texture image relative to each associated texture image into a trained fourth neural network model to obtain the judgment result output by the fourth neural network model.

[0040] Understandably, by setting a condition for each associated texture image to determine whether the target texture image is blurry, the sharpness of the target texture image can be compared with that of each associated texture image based on a common image area to obtain the relative sharpness of the target texture image relative to each associated texture image. By setting the relative sharpness of the target texture image relative to each associated texture image to determine whether the target texture image is blurry, more criteria are available for detecting whether the target texture image is blurry, which is beneficial to improving the accuracy of blurry image recognition.

[0041] This embodiment of the disclosure can acquire a target texture image and associated texture images that share a common image region with the target texture image. For each associated texture image, based on the common image region between the target texture image and the associated texture images, it is determined whether the target texture image is a blurred image. Based on the relative sharpness of the target texture image relative to each associated texture image, it is determined whether the target texture image is a blurred image. Therefore, by employing the above technical solution, the target texture image and associated texture images can be used together to detect whether the target texture image is a blurred image. Compared to blurry image recognition based solely on the target texture image, this increases the basis for blurry image recognition, thereby reducing the probability of false positives and improving the accuracy of blurry image recognition.

[0042] Figure 2 This is a flowchart illustrating another method for recognizing blurred images provided in this disclosure. This disclosure optimizes the above embodiments and can be combined with various optional solutions from one or more of the above embodiments.

[0043] like Figure 2 As shown, the method for recognizing the blurred image may include the following steps.

[0044] S210, Obtain the target texture image and the associated texture image that shares a common image region with the target texture image.

[0045] Specifically, S210 is similar to S110, and will not be described in detail here.

[0046] S220. For each associated texture image, determine the relative sharpness of the target texture image relative to the associated texture image based on the ratio of the regional sharpness of the common image region in the target texture image and the associated texture image, respectively.

[0047] Specifically, regional sharpness is used to characterize the sharpness of common image regions.

[0048] Specifically, there are several ways to determine the regional sharpness of a public image area, and typical examples are given below.

[0049] In some embodiments, the process of determining the regional sharpness of a common image region includes: obtaining the pixel sharpness of each pixel in the common image region; and summing the pixel sharpness of each pixel to obtain the regional sharpness of the common image region.

[0050] Specifically, pixel sharpness is used to characterize the sharpness of a pixel. Those skilled in the art can calculate pixel sharpness using methods such as gradient descent, DCT, and AI, but are not limited to these methods.

[0051] Specifically, when calculating the regional sharpness of a common image region in a target texture image, the pixel sharpness of each pixel covered by the common image region in the target texture image can be obtained, and the pixel sharpness of each pixel can be summed to obtain the regional sharpness of the common image region in the target texture image; when calculating the regional sharpness of a common image region in an associated texture image, the pixel sharpness of each pixel covered by the common image region in the associated texture image can be obtained, and the pixel sharpness of each pixel can be summed to obtain the regional sharpness of the common image region in the associated texture image.

[0052] In one example, the region sharpness of the common image region in the target texture image is determined (denoted as the first region sharpness); the region sharpness of the common image region in the associated texture image is determined (denoted as the second region sharpness); the ratio of the second region sharpness to the first region sharpness is taken as the relative sharpness of the target texture image relative to the associated texture image.

[0053] Of course, the pixel sharpness of each pixel can also be averaged to obtain the regional sharpness of the common image area, and this application does not limit this.

[0054] Optionally, before obtaining the pixel sharpness of each pixel in the common image region, the method further includes performing noise filtering on the common image region. This avoids the impact of noise on pixel sharpness and improves the accuracy of pixel sharpness.

[0055] Specifically, those skilled in the art can use any possible noise filtering method to perform noise filtering on the common image region in the target texture image and the associated texture image, without any limitations here.

[0056] It is understandable that by summing the pixel sharpness of each pixel in the common image area to obtain the regional sharpness of the common image area, the method of determining the regional sharpness can be simple, convenient and not cumbersome, which helps to reduce the implementation difficulty and also helps to reduce the performance requirements of electronic devices.

[0057] S230. Based on the relative sharpness of the target texture image relative to each associated texture image, determine whether the target texture image is a blurry image.

[0058] In some embodiments, S230 includes: weighting and summing the relative sharpness of the target texture image relative to each associated texture image to obtain the image sharpness of the target texture image; and determining whether the target texture image is a blurred image based on the image sharpness of the target texture image.

[0059] Specifically, image sharpness is used to characterize the clarity of the target texture image. It should be noted that whether a larger image sharpness value indicates a clearer target texture image, or a smaller image sharpness value indicates a clearer target texture image, can be set by those skilled in the art according to the actual situation, and is not limited here.

[0060] Optionally, if the target texture image is more blurred than the associated texture image, and thus has higher relative sharpness, then the weight value corresponding to the relative sharpness is positively correlated with the relative sharpness. For example, when the ratio of the regional sharpness of a common image region in the associated texture image to the regional sharpness of a common image region in the target texture image is used as the relative sharpness of the target texture image relative to the associated texture image, then the weight value corresponding to the relative sharpness is positively correlated with the relative sharpness. Accordingly, if the image sharpness of the target texture image is greater than a third preset threshold (which can be set by those skilled in the art according to actual conditions), then the target texture image is determined to be a blurred image.

[0061] Understandably, when the regional sharpness of the common image region in the associated texture image is greater than that in the target texture image, the closer the ratio is to 1, the closer the sharpness of the associated and target texture images are. Conversely, the greater the ratio is to 1, the greater the difference in sharpness between the associated and target texture images, the more blurred the target texture image is relative to the associated texture image, and the higher the probability that the target texture image is a blurred image. By setting a weight value corresponding to relative sharpness that is positively correlated with relative sharpness, and by weighting and summing the relative sharpness of the target texture image relative to each associated texture image, the contribution of associated texture images with a large difference in sharpness from the target texture image (or, in other words, associated texture images that are more likely to identify the target texture image as a blurred image) to the image sharpness of the target texture image can be amplified. This makes blurred image recognition more accurate and better able to identify blurred images.

[0062] Similarly, if the target texture image is clearer than the associated texture image, its relative clarity is higher, and the weight value corresponding to the relative clarity is negatively correlated with the relative clarity. Accordingly, if the image clarity of the target texture image is less than the fourth preset threshold (which can be set by those skilled in the art according to actual conditions), the target texture image is determined to be a blurred image.

[0063] This embodiment of the present disclosure can determine the relative sharpness of the target texture image relative to the associated texture image based on the ratio of the regional sharpness of the common image region in the target texture image and the associated texture image for each associated texture image. This makes the method of determining the relative sharpness simple, convenient and uncluttered, which helps to reduce the implementation difficulty and also helps to reduce the performance requirements of electronic devices.

[0064] The following detailed example illustrates the blurry image recognition method provided in this disclosure. Figure 3 This is a schematic diagram illustrating a blurry image recognition process provided in an embodiment of this disclosure. See also... Figure 3 The process of recognizing this blurred image includes the following steps: S310. Obtain multiple original texture images, and for each original texture image, determine the facets that are visible relative to the original texture images from the target mesh model.

[0065] Specifically, if the number of original texture images is N, then the set of faces (e.g., triangular faces) that are visible relative to the i-th original texture image can be denoted as Xi. For a face in Xi, if the angle between its normal and the viewing direction exceeds a second preset threshold, it is removed from Xi to obtain the final triangular face that is visible relative to the i-th original texture image, where 1≤i≤N.

[0066] S320. For each original texture image, calculate the pixel sharpness of each pixel in the original texture image.

[0067] Specifically, pixel sharpness can be calculated using methods such as gradient descent, DCT, and AI, but it is not limited to these. Of course, noise filtering can also be performed on the original texture image before calculating the pixel sharpness of each pixel.

[0068] S330. For each pair of original texture images, based on the visible patches corresponding to the two original texture images in the pair, determine the common patch of the two original texture images, and determine the common image region corresponding to the common patch in the two original texture images respectively.

[0069] Specifically, among multiple original texture images, every two original texture images constitute an original texture image pair.

[0070] S340. For each pair of original texture images, perform the following operations on each original texture image in the pair: obtain the pixel sharpness of each pixel in the common image region; sum the pixel sharpness of each pixel to obtain the region sharpness of the common image region.

[0071] S350. For each pair of original texture images, the ratio of the region sharpness of the common image region in the second original texture image of the pair to the region sharpness of the common image region in the first original texture image of the pair is the relative sharpness of the first original texture image relative to the second original texture image. The ratio of the region sharpness of the common image region in the first original texture image of the pair to the region sharpness of the common image region in the second original texture image of the pair is the relative sharpness of the second original texture image relative to the first original texture image.

[0072] S360. Take each of the multiple original texture images as a target texture image and perform the following operations: Take the original texture images other than the target texture images as candidate associated texture images. If the number of common patches between the candidate texture image and the target texture image is greater than a first preset threshold, then the candidate texture image is determined as an associated texture image. The relative sharpness of the target texture image relative to each associated texture image is weighted and summed to obtain the image sharpness of the target texture image. The weight value corresponding to the relative sharpness is positively correlated with the relative sharpness.

[0073] S370. For each original texture image, if the image clarity of the original texture image is greater than the third preset threshold, the original texture image is determined to be a blurred image.

[0074] Figure 4 This is a schematic diagram of the structure of a blurred image recognition device provided in an embodiment of this disclosure. This blurred image recognition device can be understood as the aforementioned electronic device or a functional module within the aforementioned electronic device. For example... Figure 4 As shown, the blurry image recognition device 400 includes: The first acquisition module 410 is used to acquire a target texture image and an associated texture image that shares a common image region with the target texture image; The first determining module 420 is used to determine the relative sharpness of the target texture image relative to the associated texture image for each associated texture image, based on the common image area of ​​the target texture image and the associated texture image; The second determining module 430 is used to determine whether the target texture image is a blurred image based on the relative sharpness of the target texture image relative to each of the associated texture images.

[0075] In another embodiment of this disclosure, the first acquisition module 410 may include: The first acquisition submodule is used to acquire multiple original texture images, wherein the multiple original texture images include the target texture image and candidate texture images corresponding to the target texture image, and the multiple original texture images correspond to the target mesh model; The first determining submodule is used to determine, for each of the original texture images, a facet that is visible relative to the original texture image from the target mesh model; The third determining submodule is used to determine the candidate texture image as the associated texture image if the number of common patches between the candidate texture image and the target texture image is greater than a first preset threshold for each candidate texture image, and to determine the image region corresponding to the common patch as the common image region, wherein the common patch is a patch that is visible relative to both the target texture image and the candidate texture image.

[0076] In yet another embodiment of this disclosure, the first determining submodule may include: The first determining unit is used to determine the normal vector and viewing direction of each facet in the target mesh model based on the original texture image; The second determining unit is configured to determine that, for each of the patches, if the angle between the normal vector of the patch and the viewing direction is less than or equal to a second preset threshold, the patch is visible relative to the original texture image.

[0077] In another embodiment of this disclosure, the first determining module 420 is specifically used to determine the relative sharpness of the target texture image relative to the associated texture image based on the ratio of the regional sharpness of the common image region in the target texture image and the associated texture image, respectively.

[0078] In another embodiment of this disclosure, the apparatus further includes a third determining module for determining the regional sharpness of the common image region, wherein the third determining module may include: The second acquisition submodule is used to acquire the pixel sharpness of each pixel in the public image region; The summation submodule is used to sum the pixel sharpness of each pixel to obtain the region sharpness of the common image region.

[0079] In another embodiment of this disclosure, the third determining module may further include: The noise filtering processing submodule is used to perform noise filtering processing on the common image region before obtaining the pixel sharpness of each pixel in the common image region.

[0080] In another embodiment of this disclosure, the second determining module 430 is specifically used to perform weighted summation of the relative sharpness of the target texture image relative to each of the associated texture images to obtain the image sharpness of the target texture image; and to determine whether the target texture image is a blurred image based on the image sharpness of the target texture image.

[0081] The apparatus provided in this embodiment can execute the methods of any of the above embodiments, and its execution method and beneficial effects are similar, so they will not be described again here.

[0082] This disclosure also provides an electronic device, which includes: a memory storing a computer program; and a processor for executing the computer program, wherein when the computer program is executed by the processor, it can implement the methods of any of the above embodiments.

[0083] Example, Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. See below for details. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device 500 in the embodiments of this disclosure. The electronic device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0084] like Figure 5 As shown, electronic device 500 may include a processing unit (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 read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of electronic device 500. Processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0085] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0086] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0087] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0088] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0089] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0090] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: Acquire the target texture image and the associated texture image that shares a common image region with the target texture image; For each associated texture image, based on the common image region between the target texture image and the associated texture image, determine whether the target texture image is a blurred image; Based on the relative sharpness of the target texture image relative to each associated texture image, it is determined whether the target texture image is a blurry image.

[0091] Computer program code for performing the operations of this disclosure can 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, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0094] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0095] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0096] This disclosure also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the methods of any of the above embodiments. The execution method and beneficial effects are similar, and will not be described again here.

[0097] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0098] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for recognizing blurred images, characterized in that, include: Acquire multiple original texture images and target mesh models obtained from 3D scanning of the object; For each original texture image, the relative sharpness of the original texture image relative to the associated texture image is determined, wherein the associated texture image is an image among multiple candidate texture images that shares a common image region with the original texture image, and the multiple candidate texture images are the remaining original texture images after removing the original texture image from the multiple original texture images; A sharp original texture image is selected based on the relative sharpness of each original texture image; The target mesh model is mapped using the clear, original texture image.

2. The method according to claim 1, characterized in that, The common image region is the image region obtained by scanning the same area on the surface of the object in the original texture image and the associated texture image respectively.

3. The method according to claim 1, characterized in that, The common image region is the image region in the original texture image and the associated texture image that has the same image content.

4. The method according to claim 1, characterized in that, The common image region is the image region corresponding to the common patch between the original texture image and the associated texture image.

5. The method according to claim 1, characterized in that, The associated texture image is a candidate texture image among the multiple candidate texture images whose number of common patches with the original texture image is greater than a first preset threshold.

6. The method according to claim 5, characterized in that, The process of determining the associated texture image includes: For each original texture image, determine the facets with visibility relative to each original texture image from the target mesh model; The image in which the number of common patches between the candidate texture images and the original texture image is greater than the first preset threshold is determined as the associated texture image of the original texture image.

7. The method according to claim 6, characterized in that, Determining the visible patches relative to the original texture image from the target mesh model includes: The original texture image and the target mesh model are input into the first neural network model to obtain a patch that is visible relative to the original texture image, output by the first neural network model.

8. The method according to claim 1, characterized in that, The process of determining the associated texture image includes: The original texture image and the multiple candidate texture images are input into a second neural network model to obtain the associated texture map corresponding to the original texture image output by the second neural network model, as well as the common image region of the original texture image and each of the associated texture images.

9. The method according to claim 1, characterized in that, Determining the relative sharpness of the original texture image relative to the associated texture image includes: The common image region in the associated texture image and the common image region in the original texture image are input into the third neural network model to obtain the relative sharpness output by the third neural network model.

10. The method according to claim 1, characterized in that, Determining the relative sharpness of the original texture image relative to the associated texture image includes: Determine the sharpness of the first region of the common image region in the original texture image; Determine the second region sharpness of the common image region in the associated texture image; The ratio of the sharpness of the second region to the sharpness of the first region is used as the relative sharpness.

11. An electronic device, characterized in that, include: A processor and a memory, wherein the memory stores a computer program that, when executed by the processor, performs the method of any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-10.

Images