CN115546037A - Image processing method and device, electronic equipment and storage medium - Google Patents
Image processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115546037A CN115546037A CN202110737951.7A CN202110737951A CN115546037A CN 115546037 A CN115546037 A CN 115546037A CN 202110737951 A CN202110737951 A CN 202110737951A CN 115546037 A CN115546037 A CN 115546037A
- Authority
- CN
- China
- Prior art keywords
- image
- noise reduction
- compressed image
- picture loss
- reduction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 31
- 230000009467 reduction Effects 0.000 claims abstract description 186
- 238000012545 processing Methods 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000007906 compression Methods 0.000 claims abstract description 37
- 230000006835 compression Effects 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 14
- 230000001502 supplementing effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000005192 partition Methods 0.000 description 6
- 239000000047 product Substances 0.000 description 6
- 238000011084 recovery Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 241000255925 Diptera Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/001—Model-based coding, e.g. wire frame
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/20—Contour coding, e.g. using detection of edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the disclosure discloses an image processing method, an image processing device, an electronic device and a storage medium, wherein the method comprises the following steps: determining the picture loss degree of the compressed image; determining a target noise reduction model matched with the picture loss degree, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is; and carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image. By the image processing scheme provided by the embodiment of the disclosure, the targeted noise removal of the compressed images with different image loss degrees is realized, so that the image quality of the compressed images is improved.
Description
Technical Field
The present disclosure relates to the field of information technologies, and in particular, to an image processing method and apparatus, an electronic device, and a storage medium.
Background
Because the data volume of the image is large, in order to save the transmission bandwidth and improve the transmission speed, when the image is transmitted, the image is compressed firstly by adopting a compression technology and then transmitted. Among them, JPEG (Joint Photographic Experts Group) is one of the image compression techniques and standards commonly used at present.
However, compressing an image results in a different degree of picture loss, i.e., compression noise, such as blocking, ringing, etc. The presence of compression noise affects the quality of the image, and therefore, in order to improve the quality of the compressed image, the compression noise needs to be removed in a certain manner.
Disclosure of Invention
In order to solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide an image processing method, an image processing apparatus, an electronic device, and a storage medium, which implement targeted noise removal on compressed images with different degrees of picture loss, thereby improving image quality of the compressed images.
In a first aspect, an embodiment of the present disclosure provides an image processing method, including:
determining the picture loss degree of the compressed image;
determining a target noise reduction model matched with the picture loss degree, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is;
and carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
In a second aspect, an embodiment of the present disclosure further provides an image processing apparatus, including:
the first determining module is used for determining the picture loss degree of the compressed image;
a second determining module, configured to determine a target noise reduction model matching the picture loss degree, where the larger the picture loss degree is, the larger a noise reduction amplitude of the target noise reduction model is;
and the processing module is used for carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the image processing method as described above.
In a fourth aspect, the disclosed embodiments also provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the image processing method as described above.
In a fifth aspect, the disclosed embodiments also provide a computer program product comprising a computer program or instructions which, when executed by a processor, implement the image processing method as described above.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has at least the following advantages:
according to the image processing method provided by the embodiment of the disclosure, the target noise reduction model matched with the picture loss degree is selected according to the picture loss degree of the compressed image, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is, so that the compressed images with different picture loss degrees are subjected to targeted noise removal, and the picture quality of the compressed image is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
FIG. 1 is a flow chart of an image processing method in an embodiment of the present disclosure;
FIG. 2 is a flow chart of another image processing method in an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein is intended to be open-ended, i.e., "including but not limited to". The term "based on" is "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"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
Fig. 1 is a flowchart of an image processing method in an embodiment of the present disclosure, where the image processing method is applied to an application scenario of performing compression noise removal on a compressed image obtained through compression processing, and is intended to improve the picture quality of the compressed image and reduce image picture loss caused by the compression processing as much as possible. The image processing method can be executed by an image processing device, the device can be realized in a software and/or hardware mode, and the device can be configured in terminal equipment, such as a tablet computer, a smart phone, a palm computer, wearable equipment with a display screen, a desktop computer, a notebook computer, an all-in-one machine, smart home equipment and the like.
As shown in fig. 1, the image processing method may specifically include the following steps:
In image compression, the image file size is exchanged at the expense of image picture quality, and the smaller the file of the compressed image obtained by the compression processing is, the more image picture information is lost, and the worse the picture quality of the obtained compressed image is. In the process of one-time compression processing, a user can set the file size of a compressed image after compression according to actual business requirements, or set a specific picture loss degree representing the picture quality of the compressed image, wherein the lower the picture loss degree, the better the picture quality of the obtained compressed image is, and the larger the file of the corresponding compressed image is.
In one embodiment, the degree of picture loss of the compressed image may be determined based on the compression parameters thereof. It can be understood that, when the original image is compressed to obtain a compressed image, the corresponding degree of picture loss is stored in association with the compressed image in the form of a compression parameter, and when the degree of picture loss of the compressed image is determined, the degree of picture loss can be determined by obtaining the compression parameter. In the process of one-time compression processing, a user can set appropriate compression parameters according to actual service requirements.
In another embodiment, determining a picture loss level of a compressed image comprises: and inputting the compressed image into the trained regression model to obtain the picture loss degree of the compressed image. The regression model functions like a scorer to score the degree of picture loss of the compressed image. The training samples of the regression model include a third sample compressed image and a picture loss degree of the third sample compressed image. And the third sample compressed image can be obtained by compressing the original image according to the set picture loss degree through image compression software. In other words, in the training phase, the input of the regression model is a compressed image with a picture loss degree of Q, the learning true value (i.e., ground Truth) is Q, and the value range of Q is a set range, which is usually 0 to 100. The degree of picture loss of the compressed image is predicted through the regression model, and a prediction result with high precision can be obtained.
And step 120, determining a target noise reduction model matched with the picture loss degree.
The larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is, that is, the stronger the noise reduction capability of the target noise reduction model is, and more compression noise in the compressed image can be removed.
In one embodiment, determining a target noise reduction model that matches the picture loss level comprises: and determining a target noise reduction model matched with the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is positioned. Specifically, if the picture loss degree of the compressed image is in a first score interval, determining the trained mild noise reduction model as the target noise reduction model; if the picture loss degree of the compressed image is in a second value-dividing interval, determining the trained depth noise reduction model as the target noise reduction model; and the picture loss degree in the first score interval is lower than that in the second score interval, and the noise reduction amplitude of the light noise reduction model is smaller than that of the deep noise reduction model. For example, if the degree of loss of picture of a compressed image is in the score range of 0 to 40, the compressed image is considered to be a sharp image, and the degree of loss of picture is low, and therefore, such a compressed image is not processed. If the picture loss degree of the compressed image is in the score range of 40-80, the compressed image is considered to be a slightly lost picture, namely, the picture loss of the image caused by the compression processing is not large, so that the matched target noise reduction model can be determined to be a slightly noise reduction model. If the picture loss degree of the compressed image is in the score interval of 80-100, the compressed image is considered to be a picture serious loss image, namely, the image picture loss caused by the compression processing is serious, so that the matched target noise reduction model can be determined to be a depth noise reduction model. The training samples of the mild noise reduction model comprise a first sample compressed image with a picture loss degree in the first score interval and a first uncompressed original image corresponding to the first sample compressed image, and the first sample compressed image is obtained by compressing the first uncompressed original image. In other words, in the training phase, the input of the light noise reduction model is the first sample compressed image with the picture loss degree in the first score interval, and the learning true value is the first uncompressed original image corresponding to the first sample compressed image. For example, in the training phase, the input of the light noise reduction model is a first sample compressed image with a picture loss degree Q, the learning true value (i.e., the Ground true value) is a first uncompressed original image corresponding to the first sample compressed image, i.e., a high-definition image before compression, and the numerical range of the picture loss degree Q is 40-80. The training samples of the depth noise reduction model comprise a second sample compressed image with the picture loss degree in the second value division interval and a second uncompressed original image corresponding to the second sample compressed image, and the second sample compressed image is obtained by compressing the second uncompressed original image. In a training stage, the input of the deep noise reduction model is a second sample compressed image with a picture loss degree in the second value division interval, and a learning true value is a second uncompressed original image corresponding to the second sample compressed image. For example, in the training phase, the input of the deep noise reduction model is a low-quality image stored after a high-definition image passes through a single JPEG compression process (the compressed picture loss degree is Q), the learning true value (i.e. the group try) is a high-definition image before compression, and the value range of the picture loss degree Q is 80-100.
In another embodiment, for example, if the degree of picture loss of the compressed image is 80, the noise reduction model corresponding to 80 is determined as the target noise reduction model; if the picture loss degree of the compressed image is 70, determining a noise reduction model corresponding to 70 as a target noise reduction model; if the degree of loss of the picture of the compressed image is 60, the noise reduction model corresponding to 60 is determined as the target noise reduction model. Namely, the corresponding noise reduction model is trained in advance according to each specific picture loss degree, so that the noise reduction effect is further improved. It is to be understood that, if there is no trained noise reduction model corresponding to the current picture loss degree, the trained noise reduction model corresponding to the value closest to the current picture loss degree is determined as the target noise reduction model matching the current picture loss degree. For example, for compressed images with picture loss degrees of 70 and 80, respectively, there should be trained noise reduction models, while the current picture loss degree is 69, and since there is no trained noise reduction model corresponding to 69, the trained noise reduction model corresponding to the picture loss degree 70 closest to 69 (instead of the picture loss degree 80) is determined as the target noise reduction model matching the current picture loss degree 69.
And step 130, performing noise reduction processing on the compressed image through the target noise reduction model to remove the compression noise of the compressed image.
It is understood that when the original image is compressed, different degrees of image loss are caused, i.e. compression noise, such as ringing noise, mosquito noise, blocking effect, step effect, etc., is introduced into the original image. In order to improve the picture quality of a compressed image obtained by compression processing, a slightly-lost compressed image (for example, a compressed image whose picture loss degree is lower than a threshold value) is subjected to noise reduction processing by a slight noise reduction model; for a compressed image with serious loss (for example, a compressed image with a picture loss degree higher than a threshold value), the image is subjected to noise reduction processing by a depth noise reduction model. The noise reduction processing is carried out by using the noise reduction models with different noise reduction amplitudes aiming at the compressed images with different picture loss degrees, so that the purpose of keeping the image detail information as much as possible while removing the noise can be realized. This is because more image detail information is often retained for a slightly-lost compressed image, and if a deep noise reduction model is used for noise reduction processing, the retained image detail information is usually removed as noise, thereby reducing the picture quality of the compressed image. For a compressed image with a serious loss, if a slight noise reduction model is used for noise reduction processing, only part of noise is usually removed, but more noise cannot be removed, and the picture quality of the compressed image cannot be ensured. Therefore, in the technical solution of this embodiment, noise reduction models with different noise reduction amplitudes are selected according to the picture loss degree of the compressed image to perform noise reduction processing, so that not only more noise in the compressed image with serious loss can be removed, but also image details of the compressed image with slight loss can be retained, thereby achieving the purpose of improving the picture quality of the compressed image.
According to the image processing method provided by the embodiment of the disclosure, the target noise reduction model matched with the picture loss degree is selected according to the picture loss degree of the compressed image, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is, so that the compressed images with different picture loss degrees are subjected to targeted noise removal, and the picture quality of the compressed image is improved.
Fig. 2 is a flowchart of another image processing method in an embodiment of the present disclosure, and on the basis of the technical solutions of the foregoing embodiments, in order to further improve the picture quality of a compressed image, if it is determined that a mild noise reduction model is a target noise reduction model, after performing noise reduction processing on the compressed image through the target noise reduction model, the following steps are added in the technical solution of this embodiment: and performing image feature recovery processing on the processed image after the noise reduction processing. This is because a slightly lost compressed image often retains more image features, and some image features are removed as noise in the process of performing noise reduction processing on such a compressed image, and therefore, in order to improve the picture quality of the compressed image, after performing noise reduction processing on the compressed image by the target noise reduction model, a step of performing image feature recovery processing on the processed image after the noise reduction processing is added to recover the image features removed as noise. For the same or similar contents, reference may be made to the explanations in the foregoing embodiments, and details are not repeated in this embodiment.
As shown in fig. 2, the image processing method includes the steps of:
And step 220, determining the mild noise reduction model as a target noise reduction model matched with the picture loss degree.
And 230, performing noise reduction processing on the compressed image through a mild noise reduction model to remove the compression noise of the compressed image.
In one embodiment, the purpose of determining image features of the phase difference between the compressed image and the processed image is to determine image features missing from the processed image compared to the compressed image, i.e. image features lost from the compressed image by the noise reduction process. For example, a compressed image is marked as img, noise reduction processing is performed on the compressed image img through a mild noise reduction model, namely, the input of the mild noise reduction model is the compressed image img, the output of the mild noise reduction model is a processed image res, image feature recovery processing is performed on the processed image res, firstly, the difference between the img and the res is obtained, namely, the difference between pixel values of corresponding pixels in two images is obtained: diff = img-res. The essence of diff is the missing image features of the processed image res compared to the compressed image img. And supplementing the image characteristics to the processed image to recover the image characteristics of the processed image which are missing compared with the compressed image, and obtaining a target image.
Further, in one embodiment, supplementing the image features to the processed image to obtain a target image, includes: determining an absolute value of a laplacian edge value of the processed image; carrying out binarization processing on the absolute value of the Laplace edge value; performing expansion processing based on the absolute value of the Laplace edge value after binarization processing, and obtaining an area mask through negation operation so as to shield the existing image features of the processed image; and determining each pixel point of the target image by utilizing the product of the pixel point of the image characteristic of the difference between the compressed image and the processed image and the pixel point of the regional mask and the sum of each pixel point of the processed image so as to recover the image details of the processed image.
Specifically, the absolute value of the laplacian edge value of the processed image is determined based on the following equation (1):
edge＝abs(Laplacian(res,ksize))(1)
where edge represents an absolute value of a Laplacian edge value of the processed image res, abs () represents a function for taking the absolute value, laplacian (res, ksize) represents a function for obtaining the Laplacian edge value of the processed image res by using a Laplacian edge operator, and ksize is a preset parameter.
And (3) carrying out binarization processing on the absolute value of the Laplace edge value according to a set threshold value based on the following formula (2):
edge[edge<T]＝0，edge[edge>＝T]＝1(2)
and if the absolute value edge of the Laplacian edge value is smaller than T, setting the absolute value edge to be 0, otherwise, setting the absolute value to be 1.
Performing expansion processing based on the absolute value of the laplacian edge value after binarization processing by the following formula (3), and obtaining an area mask by inversion operation to block the existing image information of the processed image:
mask＝1-cv2.dilate(edge)(3)
wherein mask represents a region mask, cv2. Partition (edge) represents an expansion process based on an absolute value edge of a laplacian edge value after the binarization process to process discontinuous weak edges into continuous strong edges, 1-cv2. Partition (edge) represents an inversion operation to block existing image information, that is, the existing image information is processed into 0, and cv2. Partition () represents a function to perform the expansion process.
Determining each pixel point of a post-processing image by using the product of the pixel point of the image feature and the pixel point of the regional mask and the sum of each pixel point of the processed image based on the following formula (4) to recover the image details of the processed image, wherein the post-processing image is a compressed image with recovered image details:
final_res＝res+diff*mask(4)
wherein res represents a processed image, final _ res represents a target image, diff represents a pixel point of an image feature of a phase difference between the compressed image img and the processed image res, and mask represents the region mask. Equation (4) above indicates that the missing image features are supplemented to the processed image res to restore the image detail information in the processed image res.
Absolute value of processed image laplacian edge value
In the method provided by the embodiment of the present disclosure, on the basis of the above technical solutions of the embodiments, in order to further improve the picture quality of the compressed image, if the mild noise reduction model is determined as the target noise reduction model, after performing noise reduction processing on the compressed image through the target noise reduction model, the following steps are added in the technical solution of the embodiment: and performing image characteristic restoration processing on the processed image after the noise reduction processing. This is because a slightly lost compressed image often retains more image detail information, and some image detail information is removed as noise in the process of performing noise reduction processing on such a compressed image, and therefore, in order to improve the picture quality of the compressed image, after performing noise reduction processing on the compressed image by the target noise reduction model, a step of performing image feature recovery processing on the processed image after the noise reduction processing is added to recover the image detail information removed as noise.
Fig. 3 is a schematic structural diagram of an image processing apparatus in an embodiment of the present disclosure. The device provided by the embodiment of the disclosure can be configured in the terminal equipment. As shown in fig. 3, the apparatus specifically includes: a first determination module 310, a second determination module 320, and a processing module 330.
The first determining module 310 is configured to determine a picture loss degree of the compressed image; a second determining module 320, configured to determine a target noise reduction model matching the picture loss degree, where the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is; and the processing module 330 is configured to perform noise reduction processing on the compressed image through the target noise reduction model to remove compression noise of the compressed image.
Optionally, the second determining module 320 includes: and the first determining unit is used for determining a target noise reduction model matched with the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is positioned.
Optionally, the first determining unit is specifically configured to: if the picture loss degree of the compressed image is in a first score interval, determining the trained mild noise reduction model as the target noise reduction model; if the picture loss degree of the compressed image is in a second value-dividing interval, determining the trained depth noise reduction model as the target noise reduction model; wherein, the picture loss degree in the first value-dividing interval is lower than the picture loss degree in the second value-dividing interval.
Optionally, the training samples of the mild noise reduction model include a first sample compressed image with a picture loss degree in the first fractional value interval and a first uncompressed original image corresponding to the first sample compressed image, where the first sample compressed image is obtained by performing compression processing on the first uncompressed original image; the training samples of the depth noise reduction model comprise a second sample compressed image with the picture loss degree in the second value division interval and a second uncompressed original image corresponding to the second sample compressed image, and the second sample compressed image is obtained by compressing the second uncompressed original image.
Optionally, the apparatus further comprises: the third determining module is used for determining the image characteristics of the phase difference between the compressed image and the processed image obtained after the noise reduction processing is carried out on the compressed image through the mild noise reduction model; and the supplementing module is used for supplementing the image characteristics to the processed image to obtain a target image.
Optionally, the supplementary module includes:
a determination unit configured to determine an absolute value of a laplacian edge value of the processed image based on the following equation (1):
edge＝abs(Laplacian(res,ksize))(1)
where edge represents an absolute value of a Laplacian edge value of the processed image res, abs () represents a function to take the absolute value, laplacian (res, ksize) represents a function to obtain the Laplacian edge value of the processed image res by using a Laplacian edge operator, and ksize is a preset parameter.
A binarization processing unit configured to perform binarization processing on an absolute value of the laplacian edge value according to a set threshold based on the following equation (2):
edge[edge<T]＝0，edge[edge>＝T]＝1(2)
and if the absolute value edge of the Laplace edge value is smaller than T, setting the absolute value edge to be 0, otherwise, setting the absolute value to be 1.
An expansion processing unit configured to perform expansion processing based on an absolute value of the laplacian edge value after the binarization processing by following equation (3), and obtain an area mask by inversion operation to block image information existing in the processed image:
mask＝1-cv2.dilate(edge)(3)
where mask represents a region mask, cv2. Partition (edge) represents an expansion process based on an absolute value edge of a laplacian edge value after the binarization process, 1-cv2. Partition (edge) represents an inversion operation, and cv2. Partition () represents a function for performing the expansion process.
A recovery unit, configured to determine each pixel point of the target image based on a product of the pixel point of the image feature and the pixel point of the region mask, and a sum of each pixel point of the processed image, according to the following equation (4):
final_res＝res+diff*mask(4)
wherein res represents a processed image, final _ res represents a target image, diff represents a pixel point of the image characteristic, and mask represents the region mask.
Optionally, the first determining module 310 is specifically configured to: and inputting the compressed image into a trained regression model to obtain the picture loss degree of the compressed image.
Optionally, the training samples of the regression model include a third sample compressed image and a picture loss degree of the third sample compressed image.
According to the image processing device provided by the embodiment of the disclosure, the target noise reduction model matched with the picture loss degree is selected according to the picture loss degree of the compressed image, so that the compressed images with different picture loss degrees are subjected to targeted noise removal, and the picture quality of the compressed image is improved.
The apparatus provided in the embodiment of the present disclosure may perform the method steps provided in the embodiment of the method of the present disclosure, and the advantageous effects are not described herein again.
Fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Referring now specifically to fig. 4, a schematic diagram of an electronic device 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device 500 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), a wearable electronic device, and the like, and fixed terminals such as a digital TV, a desktop computer, a smart home device, and the like. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 4, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes to implement the methods of embodiments as described in this disclosure in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, the processes described above with reference to the flow diagrams may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present 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 method illustrated by the flow chart, thereby implementing the method as described above. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 501.
It should be noted that the computer readable medium of 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 electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:
determining the picture loss degree of the compressed image;
determining a target noise reduction model matched with the picture loss degree, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is;
and carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
Optionally, when the one or more programs are executed by the electronic device, the electronic device may further perform other steps described in the above embodiments.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C + +, including conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of 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 the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, 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 a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
According to one or more embodiments of the present disclosure, an embodiment of the present disclosure provides an image processing method, including: determining the picture loss degree of the compressed image; determining a target noise reduction model matched with the picture loss degree; and carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
According to one or more embodiments of the present disclosure, in the image processing method provided in an embodiment of the present disclosure, optionally, the determining a target noise reduction model matching the picture loss degree includes: and determining a target noise reduction model matched with the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is located.
According to one or more embodiments of the present disclosure, in the image processing method provided in an embodiment of the present disclosure, optionally, the determining a target noise reduction model matching the degree of picture loss based on a preset score interval in which the degree of picture loss of the compressed image is located includes: if the picture loss degree of the compressed image is in a first score interval, determining the trained mild noise reduction model as the target noise reduction model; if the picture loss degree of the compressed image is in a second value-dividing interval, determining the trained deep noise reduction model as the target noise reduction model; and the picture loss degree in the first score interval is lower than that in the second score interval, and the noise reduction amplitude of the light noise reduction model is smaller than that of the deep noise reduction model.
According to one or more embodiments of the present disclosure, in the image processing method provided in an embodiment of the present disclosure, optionally, the training samples of the mild noise reduction model include a first sample compressed image with a picture loss degree in the first fractional value interval and a first uncompressed original image corresponding to the first sample compressed image, where the first sample compressed image is obtained by compressing the first uncompressed original image; the training samples of the depth noise reduction model comprise a second sample compressed image with the picture loss degree in the second value division interval and a second uncompressed original image corresponding to the second sample compressed image, and the second sample compressed image is obtained by compressing the second uncompressed original image.
According to one or more embodiments of the present disclosure, in the image processing method provided in the embodiments of the present disclosure, optionally, if it is determined that the mild noise reduction model is the target noise reduction model, after performing noise reduction processing on the compressed image by using the target noise reduction model, the method further includes: determining image characteristics of a phase difference between the compressed image and a processed image obtained after the noise reduction processing; and supplementing the image characteristics to the processed image to obtain a target image.
According to one or more embodiments of the present disclosure, in the method provided by the present disclosure, optionally, the supplementing the image feature to the processed image to obtain a target image includes: determining an absolute value of a laplacian edge value of the processed image; carrying out binarization processing on the absolute value of the Laplace edge value according to a set threshold value; performing expansion processing based on the absolute value of the Laplace edge value after binarization processing, and obtaining an area mask through negation operation so as to shield the existing image features of the processed image; and determining each pixel point of the target image by using the product of the pixel point of the image characteristic and the pixel point of the area mask and the sum of each pixel point of the processed image.
According to one or more embodiments of the present disclosure, in the method provided by the present disclosure, optionally, the determining the picture loss degree of the compressed image includes: and inputting the compressed image into a trained regression model to obtain the picture loss degree of the compressed image.
According to one or more embodiments of the present disclosure, in the method provided by the present disclosure, optionally, the training samples of the regression model include a third sample compressed image and a picture loss degree of the third sample compressed image.
According to one or more embodiments of the present disclosure, an embodiment of the present disclosure provides an image processing apparatus including: the first determining module is used for determining the picture loss degree of the compressed image; a second determining module, configured to determine a target noise reduction model matching the picture loss degree, where the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is; and the processing module is used for carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the second determining module includes: and the first determining unit is used for determining a target noise reduction model matched with the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is positioned.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the first determining unit is specifically configured to: if the picture loss degree of the compressed image is in a first score interval, determining the trained mild noise reduction model as the target noise reduction model; if the picture loss degree of the compressed image is in a second value-dividing interval, determining the trained depth noise reduction model as the target noise reduction model; and the picture loss degree in the first score interval is lower than that in the second score interval, and the noise reduction amplitude of the light noise reduction model is smaller than that of the deep noise reduction model.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the training sample of the mild noise reduction model includes a first sample compressed image with a picture loss degree in the first fractional value interval and a first uncompressed original image corresponding to the first sample compressed image, where the first sample compressed image is obtained by compressing the first uncompressed original image; the training samples of the depth noise reduction model comprise a second sample compressed image with the picture loss degree in the second value division interval and a second uncompressed original image corresponding to the second sample compressed image, and the second sample compressed image is obtained by compressing the second uncompressed original image.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the apparatus further includes: a third determination unit configured to determine an image feature of a phase difference between the compressed image and a processed image obtained after the noise reduction processing; and the supplement module is used for supplementing the image characteristics to the processed image to obtain a target image.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the supplementary module includes: a determination unit configured to determine an absolute value of a laplacian edge value of the processed image; a binarization processing unit configured to perform binarization processing on an absolute value of the laplacian edge value according to a set threshold based on equation (2) below; an expansion processing unit, configured to perform expansion processing based on an absolute value of the laplacian edge value after binarization processing, and obtain an area mask by negation operation, so as to block existing image information of the processed image; and the recovery unit is used for determining each pixel point of the target image by utilizing the product of the pixel point of the image characteristic and the pixel point of the area mask and the sum of each pixel point of the processed image.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the first determining module is specifically configured to: and inputting the compressed image into a trained regression model to obtain the picture loss degree of the compressed image.
According to one or more embodiments of the present disclosure, in an image processing apparatus provided in an embodiment of the present disclosure, optionally, the training samples of the regression model include a third sample compressed image and a picture loss degree of the third sample compressed image.
According to one or more embodiments of the present disclosure, an embodiment of the present disclosure provides an electronic device including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement any of the image processing methods provided by the present disclosure.
According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements an image processing method as any one of the image processing methods provided by the present disclosure.
Embodiments of the present disclosure also provide a computer program product comprising a computer program or instructions which, when executed by a processor, implement the image processing method as described above.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other combinations of features described above or equivalents thereof without departing from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to 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 disclosed as example forms of implementing the claims.
Claims (11)
1. An image processing method, characterized in that the method comprises:
determining the picture loss degree of the compressed image;
determining a target noise reduction model matched with the picture loss degree, wherein the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is;
and carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
2. The method of claim 1, wherein determining a target noise reduction model that matches the picture loss level comprises:
and determining a target noise reduction model matched with the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is positioned.
3. The method according to claim 2, wherein the determining a target noise reduction model matching the picture loss degree based on a preset score interval in which the picture loss degree of the compressed image is located comprises:
if the picture loss degree of the compressed image is in a first score interval, determining the trained mild noise reduction model as the target noise reduction model;
if the picture loss degree of the compressed image is in a second value-dividing interval, determining the trained depth noise reduction model as the target noise reduction model;
and the picture loss degree in the first score interval is lower than that in the second score interval, and the noise reduction amplitude of the light noise reduction model is smaller than that of the deep noise reduction model.
4. The method according to claim 3, wherein the training samples of the light noise reduction model include a first sample compressed image with a picture loss degree in the first score interval and a first uncompressed original image corresponding to the first sample compressed image, and the first sample compressed image is obtained by compressing the first uncompressed original image;
the training samples of the depth noise reduction model comprise a second sample compressed image with the picture loss degree in the second value division interval and a second uncompressed original image corresponding to the second sample compressed image, and the second sample compressed image is obtained by compressing the second uncompressed original image.
5. The method according to claim 1, wherein if the mild noise reduction model is determined as the target noise reduction model, after performing noise reduction processing on the compressed image by the target noise reduction model, the method further comprises:
determining image characteristics of a phase difference between the compressed image and a processed image obtained after the noise reduction processing;
and supplementing the image characteristics to the processed image to obtain a target image.
6. The method of claim 5, wherein supplementing the image features to the processed image to obtain a target image comprises:
determining an absolute value of a laplacian edge value of the processed image;
carrying out binarization processing on the absolute value of the Laplace edge value according to a set threshold value;
performing expansion processing based on the absolute value of the Laplace edge value after binarization processing, and obtaining an area mask through negation operation so as to shield the existing image features of the processed image;
and determining each pixel point of the target image by using the product of the pixel point of the image characteristic of the difference between the compressed image and the processed image and the pixel point of the regional mask and the sum of each pixel point of the processed image.
7. The method according to any one of claims 1-6, wherein determining the degree of picture loss of the compressed image comprises:
and inputting the compressed image into a trained regression model to obtain the picture loss degree of the compressed image.
8. The method of claim 7, wherein the training samples of the regression model comprise a third sample compressed image and a picture loss level of the third sample compressed image.
9. An image processing apparatus characterized by comprising:
the first determining module is used for determining the picture loss degree of the compressed image;
a second determining module, configured to determine a target noise reduction model matching the picture loss degree, where the larger the picture loss degree is, the larger the noise reduction amplitude of the target noise reduction model is;
and the processing module is used for carrying out noise reduction processing on the compressed image through the target noise reduction model so as to remove the compression noise of the compressed image.
10. An electronic device, characterized in that the electronic device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the image processing method of any one of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the image processing method according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110737951.7A CN115546037A (en) | 2021-06-30 | 2021-06-30 | Image processing method and device, electronic equipment and storage medium |
| PCT/CN2022/100647 WO2023274005A1 (en) | 2021-06-30 | 2022-06-23 | Image processing method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110737951.7A CN115546037A (en) | 2021-06-30 | 2021-06-30 | Image processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115546037A true CN115546037A (en) | 2022-12-30 |
Family
ID=84690725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110737951.7A Pending CN115546037A (en) | 2021-06-30 | 2021-06-30 | Image processing method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115546037A (en) |
| WO (1) | WO2023274005A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116188346B (en) * | 2023-05-04 | 2023-07-11 | 安翰科技(武汉)股份有限公司 | Image quality enhancement method and device for endoscope image |
| CN117036197A (en) * | 2023-08-18 | 2023-11-10 | 杭州食方科技有限公司 | Image denoising model generation method, device, equipment and computer readable medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPWO2017060951A1 (en) * | 2015-10-05 | 2018-07-05 | 株式会社日立製作所 | Image compression apparatus, image decoding apparatus, and image processing method |
| CN106875342B (en) * | 2015-12-11 | 2024-06-11 | 上海联影医疗科技股份有限公司 | Computer tomogram processing method and device |
| WO2019112084A1 (en) * | 2017-12-06 | 2019-06-13 | 한국과학기술원 | Method for removing compression distortion by using cnn |
| KR20210017185A (en) * | 2019-08-07 | 2021-02-17 | 한국전자통신연구원 | Method and apparatus for removing compressed poisson noise of an image based on deep neural network |
| CN111369477A (en) * | 2020-05-27 | 2020-07-03 | 杭州微帧信息科技有限公司 | Method for pre-analysis and tool self-adaptation of video recovery task |
| CN111738952B (en) * | 2020-06-22 | 2023-10-10 | 京东方科技集团股份有限公司 | Image restoration method and device and electronic equipment |
| CN112950491B (en) * | 2021-01-26 | 2024-02-13 | 上海视龙软件有限公司 | Video processing method and device |
-
2021
- 2021-06-30 CN CN202110737951.7A patent/CN115546037A/en active Pending
-
2022
- 2022-06-23 WO PCT/CN2022/100647 patent/WO2023274005A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023274005A1 (en) | 2023-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023274005A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN111784712B (en) | Image processing method, device, equipment and computer readable medium | |
| CN111586473B (en) | Video clipping method, device, equipment and storage medium | |
| CN110349107B (en) | Image enhancement method, device, electronic equipment and storage medium | |
| CN112561839B (en) | Video clipping method and device, storage medium and electronic equipment | |
| CN110705511A (en) | Blurred image recognition method, device, equipment and storage medium | |
| CN112330788A (en) | Image processing method, image processing device, readable medium and electronic equipment | |
| CN110310293B (en) | Human body image segmentation method and device | |
| CN113038176B (en) | Video frame extraction method and device and electronic equipment | |
| CN114339447B (en) | Method, device and equipment for converting picture into video and storage medium | |
| CN114037716A (en) | Image segmentation method, device, equipment and storage medium | |
| CN112257598B (en) | Method and device for identifying quadrangle in image, readable medium and electronic equipment | |
| CN111783632B (en) | Face detection method and device for video stream, electronic equipment and storage medium | |
| CN110378282B (en) | Image processing method and device | |
| CN111756953A (en) | Video processing method, device, equipment and computer readable medium | |
| CN111258582A (en) | Window rendering method and device, computer equipment and storage medium | |
| CN110765304A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN111815535B (en) | Image processing method, apparatus, electronic device, and computer readable medium | |
| CN111696041B (en) | Image processing method and device and electronic equipment | |
| CN112418233B (en) | Image processing method and device, readable medium and electronic equipment | |
| CN114972021A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN114170341A (en) | Image processing method, device, equipment and medium | |
| CN112488947A (en) | Model training and image processing method, device, equipment and computer readable medium | |
| CN113177176A (en) | Feature construction method, content display method and related device | |
| CN111680754A (en) | Image classification method and device, electronic equipment and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |