CN111476730A - Image restoration processing method and device - Google Patents
Image restoration processing method and device Download PDFInfo
- Publication number
- CN111476730A CN111476730A CN202010246945.7A CN202010246945A CN111476730A CN 111476730 A CN111476730 A CN 111476730A CN 202010246945 A CN202010246945 A CN 202010246945A CN 111476730 A CN111476730 A CN 111476730A
- Authority
- CN
- China
- Prior art keywords
- data
- signal data
- image signal
- repair
- image
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 31
- 238000004891 communication Methods 0.000 claims abstract description 118
- 230000008439 repair process Effects 0.000 claims abstract description 80
- 230000005540 biological transmission Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000001228 spectrum Methods 0.000 claims description 45
- 238000009826 distribution Methods 0.000 claims description 20
- 238000003062 neural network model Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000011084 recovery Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 3
- 238000013144 data compression Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 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
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The application relates to the embodiment of the application and provides a processing method and a device for image restoration, wherein the method comprises the following steps: acquiring original image information needing communication transmission; generating first image signal data from the original image information; determining a data restoration model obtained by pre-training corresponding to the communication equipment; obtaining restoration data corresponding to the first image signal data through a data restoration model; compensating the first image signal data by the repair data to obtain second image signal data; and obtaining the repaired image information according to the second image signal data. By adopting the method in the embodiment, the data loss caused by the communication equipment can be repaired only by acquiring the trained data repair model corresponding to the communication equipment without considering the difference of the specific types of the communication equipment for communication transmission; the problem of image distortion caused by unstable noise and data compression in communication transmission can be solved; and further, the communication transmission quality of the image can be effectively improved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a processing method and an apparatus for image restoration.
Background
Image inpainting refers to a technique of restoring a lost portion of an image and reconstructing the image based on background information. In image processing techniques, sophisticated application algorithms are used to replace missing or damaged parts of the image data.
The existing image restoration technology mainly comprises the following steps: the method of repairing based on structure information diffusion and texture block copying mainly deals with the repairing of the missing part of the image. When the loss part is large, the method cannot produce good repairing effect. In addition, with the development of science and technology, high-resolution and high-quality image acquisition becomes a necessary trend; however, in the process of uploading a large amount of image data, the image data is too large, and therefore the image data needs to be uploaded through image compression. In this process, high-quality image data is more likely to be lost by noise or interference signals generated in the communication apparatus due to compression or the like.
In view of the technical problems in the related art, no effective solution is provided at present.
Disclosure of Invention
In order to solve the technical problem or at least partially solve the technical problem, the present application provides a processing method and apparatus for image restoration.
In a first aspect, the present application provides a processing method for image restoration, including:
acquiring original image information needing communication transmission;
generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment;
determining a data restoration model obtained by pre-training corresponding to the communication equipment;
obtaining repair data corresponding to the first image signal data through the data repair model, wherein the repair data is used for compensating data lost when the first image signal data is transmitted in the communication equipment;
compensating the first image signal data through the repair data so that the communication equipment outputs second image signal data according to the first image signal data and the repair data;
and obtaining the repaired image information according to the second image signal data.
Optionally, as in the foregoing processing method, the obtaining, by the data restoration model, restoration data corresponding to the first image signal data includes:
determining distortion data of the first image signal data after transmission in the communication device;
and inputting the distortion data into the data restoration model to obtain restoration data for compensating the distortion data.
Optionally, as in the foregoing processing method, the method for establishing the data recovery model includes:
acquiring pre-collected sample distortion data, wherein the sample distortion data is obtained according to sample image information and distortion image information after the sample image information is transmitted in communication equipment;
inputting the sample distortion data into a preset neural network model for training to obtain a trained neural network model;
and verifying the trained neural network model through the sample image information and the distorted image information, and obtaining the data restoration model after a verification result meets a preset requirement.
Optionally, as in the foregoing processing method, the acquiring of the pre-collected sample distortion data includes:
determining two-dimensional digital matrix data of the sample image information;
converting the two-dimensional digital matrix data into one-dimensional sequence data;
performing Fourier transform on the one-dimensional sequence data to obtain corresponding frequency spectrum information;
acquiring distorted sample image information obtained after the sample image information is transmitted through the communication equipment;
obtaining corresponding distorted frequency spectrum information according to the distorted sample image information;
and obtaining the sample distortion data according to the frequency spectrum information and the distorted frequency spectrum information.
Optionally, as in the foregoing processing method, the acquiring of the pre-collected sample distortion data includes:
converting the sample image information into first color distribution energy spectrum information;
acquiring distorted sample image information obtained after the sample image information is transmitted through the communication equipment;
converting the distorted sample image information into second color distribution energy spectrum information;
and obtaining the sample distortion data according to the first color distribution energy spectrum information and the second color distribution energy spectrum information.
Optionally, as in the foregoing processing method, the determining a data recovery model obtained by pre-training corresponding to the communication device includes:
determining preset corresponding relations between different preset communication devices and preset data restoration models;
and matching according to the preset corresponding relation to obtain the data repair model corresponding to the communication equipment.
Optionally, as in the foregoing processing method, the compensating the first image signal data by the repair data includes:
determining minimum unit signal data which needs to be compensated in the first image signal data;
determining minimum unit repair signal data corresponding to each minimum unit signal data in the repair data, and obtaining a data corresponding relation;
and loading each minimum unit repair signal data into the corresponding minimum unit signal data according to the data corresponding relation.
In a second aspect, the present application provides an image inpainting processing apparatus, comprising:
the acquisition module is used for acquiring original image information needing communication transmission;
the first conversion module is used for generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment;
the determining module is used for determining a data restoration model obtained by pre-training corresponding to the communication equipment;
a repair data generation module, configured to obtain repair data corresponding to the first image signal data through the data repair model, where the repair data is used to compensate data lost when the first image signal data is transmitted in the communication device;
a compensation module, configured to compensate the first image signal data by the repair data, so that the communication device outputs second image signal data according to the first image signal data and the repair data;
and the second conversion module is used for obtaining the repaired image information according to the second image signal data.
In a third aspect, the present application provides an electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the processing method according to any one of the preceding claims when executing the computer program.
In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the processing method according to any one of the preceding claims.
The embodiment of the application provides a processing method and a device for image restoration, wherein the method comprises the following steps: acquiring original image information needing communication transmission; generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment; determining a data restoration model obtained by pre-training corresponding to the communication equipment; obtaining repair data corresponding to the first image signal data through the data repair model, wherein the repair data is used for compensating data lost when the first image signal data is transmitted in the communication equipment; compensating the first image signal data through the repair data so that the communication equipment outputs second image signal data according to the first image signal data and the repair data; and obtaining the repaired image information according to the second image signal data. By adopting the method in the embodiment, the data loss caused by the communication equipment can be repaired only by acquiring the trained data repair model corresponding to the communication equipment without considering the difference of the specific types of the communication equipment for communication transmission; the problem of image distortion caused by unstable noise and data compression in communication transmission can be solved; and further, the communication transmission quality of various images can be effectively improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a processing method for image restoration according to an embodiment of the present application;
fig. 2 is a flowchart of a processing method for image restoration according to another embodiment of the present application;
fig. 3 is a flowchart of a processing method for image restoration according to another embodiment of the present application;
fig. 4 is a block diagram of a processing apparatus for image restoration according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a first aspect provided by an embodiment of the present application, and the present application provides a processing method for image restoration, including the following steps S1 to S6:
s1, acquiring original image information needing communication transmission.
Specifically, the original image information is: image information prior to the communication transmission; and the data format of the original image information may be bmp, jpg, png, tif, gif, pcx, tga, exif, fpx, svg, psd, cdr, pcd, dxf, ufo, eps, ai, raw, wmf, webp, and so on.
The communication transmission may be by bluetooth, WiFi, mobile communication network, etc.
And S2, generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment.
Specifically, when performing communication transmission, the original image information cannot be transmitted according to the original format thereof, so that it needs to be converted into a data format that can be transmitted by the communication device; therefore, the first image signal data is data corresponding to a data format that can be transmitted by the communication device. And the communication device may include a wired communication device and a wireless communication device; as long as data transmission can be achieved.
And S3, determining a data restoration model obtained by pre-training corresponding to the communication equipment.
Specifically, when different communication devices transmit image signal data, the first image signal data may be distorted due to signal interference or transmission stability; the data repair model is used for compensating and repairing distorted data, so that the data output by the communication equipment and the input data are kept as real as possible.
In addition, since the communication devices are different from each other in terms of interference susceptibility and transmission stability, the communication devices need to have corresponding data recovery models.
Generally, since the data restoration model is obtained based on the deep neural network model, it needs to be trained, and after reaching a preset accuracy, the expected use effect can be reached.
And S4, obtaining repair data corresponding to the first image signal data through the data repair model, wherein the repair data is used for compensating data lost when the first image signal data is transmitted in the communication equipment.
Specifically, when data transmission is performed through the communication device, the essence of the data transmission is transmission of an electronic signal, so that the electronic signal is lost during transmission, and the electronic signal is a concrete expression form of data transmission, so that the electronic signal can be repaired through repair data, and the lost data can be compensated for by: when the electronic signal is lower than the normal value, the signal is lifted to the normal value; when the electronic signal is higher than the normal value, the signal is reduced to the normal value.
And S5, compensating the first image signal data through the repair data so that the communication equipment outputs second image signal data according to the first image signal data and the repair data.
Specifically, after the first image signal data is compensated by the repair data, data lost by the first image signal data in the communication device can be compensated, so that the second image signal data output by the communication device can be obtained by repairing the first image data by the repair data.
Alternatively, the repair data may compensate the first image signal data before or after the loss occurs.
And S6, obtaining the repaired image information according to the second image signal data.
Specifically, the data type of the second image signal data is generally consistent with that of the first image signal data, so that it is not in a normal image format and needs to be converted to obtain the corresponding repaired image information.
By adopting the method in the embodiment, the data loss caused by the communication equipment can be repaired only by acquiring the trained data repair model corresponding to the communication equipment without considering the difference of the specific types of the communication equipment for communication transmission; the problem of image distortion caused by unstable noise and data compression in communication transmission can be solved; and further, the communication transmission quality of various images can be effectively improved.
In some embodiments, as the aforementioned processing method, the step S4 obtains the repair data corresponding to the first image signal data through the data repair model, including the steps S41 and S42 as follows:
step S41, distortion data of the first image signal data after transmission in the communication equipment is determined.
Specifically, since the present application repairs a transmission image of a fixed communication device, the position of distortion generated when the communication device transmits signal data is relatively fixed, for example: when a communication device is used to transmit a spectrum of information I (in turn including: signal data A, B, C, D, E), D is distorted; when the communication device transmits another spectrum information II (sequentially including: signal data a ', B', C ', D', E '), it is D' that is distorted; the distortion data may be original data in which distortion occurs in the first image signal data; or the data may be distorted after the first image signal data is transmitted; and also can be the original data with distortion and the data after distortion.
And S42, inputting the distortion data into a data restoration model to obtain restoration data for compensating the distortion data.
Specifically, the data restoration model is obtained by training the sample distortion data before training, so that the corresponding restoration data can be obtained through the input distortion data.
As shown in fig. 2, in some embodiments, as the aforementioned processing method, the data recovery model establishing method includes the following steps a1 to A3:
a1, obtaining sample distortion data collected in advance, wherein the sample distortion data is obtained according to sample image information and distortion image information after the sample image information is transmitted in communication equipment.
Specifically, the sample distortion data is obtained by data comparison, and the distorted image information after the transmission of the sample image information in the communication device is compared with the sample image information before the transmission. Typically, the sample distortion data will comprise a plurality of sets.
And step A2, inputting the sample distortion data into a preset neural network model for training to obtain the trained neural network model.
And A3, verifying the trained neural network model through the sample image information and the distorted image information, and obtaining a data restoration model after a verification result meets a preset requirement.
Specifically, the neural network model herein may be a DNN model (deep neural network model), and generally, the DNN model may include an input layer, a plurality of network layers may be connected in series after the input layer, and an output layer is connected finally; when the sample distortion data is input into the neural network model, the repair data for data compensation is obtained through output of the output layer; meeting the preset requirements may be: when the trained neural network model passes through the repair data obtained by verifying the data, the distorted image information is consistent with the sample image information after being repaired by the repair data or the distortion rate is in a preset range, the trained neural network model can be judged to meet the performance requirement and be used.
In some embodiments, as in the previous processing method, step A1 obtains pre-collected sample distortion data, including steps a 111-a 116 as follows:
step A111, determining two-dimensional digital matrix data of sample image information;
step A112, converting the two-dimensional digital matrix data into one-dimensional sequence data;
step A113, performing Fourier transform on the one-dimensional sequence data to obtain corresponding frequency spectrum information;
step A114, obtaining distorted sample image information obtained after the sample image information is transmitted through communication equipment;
a115, obtaining corresponding distorted spectrum information according to the distorted sample image information;
and step A116, obtaining sample distortion data according to the spectrum information and the distorted spectrum information.
Specifically, one of the optional implementation methods may be:
1) acquiring n original images with high resolution and high quality, and analyzing and processing the digital images by adopting a matrix theory and a matrix algorithm because the digital image data can be represented by a matrix. Since digital images can be represented in the form of a matrix, in computer digital image processing programs, two-dimensional matrix data is often used to store imagesAnd (4) data. Respectively converting the two-dimensional matrix data of each original image to obtain corresponding data SiThen from each SiConcatemerization into one-dimensional sequence data S:
S＝S0∪S1∪S2∪....∪Sn；
2) when one-dimensional sequence data S of each image is regarded as signal data and Fourier transform is performed by signal processing, the data is processed for each SiObtaining spectral data MiThen according to each spectrum data MiObtaining the spectrum information M in sequence for spectrum information analysis:
M＝M0∪M1∪M2∪....∪Mn；
3) after each image data is transmitted by the fixed communication equipment, the Fourier transform is carried out on the image data in a signal processing mode again, and the frequency spectrum data after distortion is recorded as NiThen according to each spectrum data NiObtaining distorted spectrum information N in sequence for spectrum information analysis:
N＝N0∪N1∪N2∪....∪Nn；
4) and obtaining sample distortion data according to the spectrum information M and the distorted spectrum information N of each piece of image data, and taking the sample distortion data as the input of the neural network model to be trained, namely M-N.
In some embodiments, as in the foregoing processing method, step A1 obtains pre-collected sample distortion data, including steps a121 to a123 as follows:
step A121, converting the sample image information into first color distribution energy spectrum information;
step A122, obtaining distorted sample image information obtained after the sample image information is transmitted through communication equipment;
step A123, converting the image information of the distorted sample into second color distribution energy spectrum information;
and A124, obtaining sample distortion data according to the first color distribution energy spectrum information and the second color distribution energy spectrum information.
Specifically, the step of converting the sample image information into the first color distribution energy spectrum information may be: converting the sample image information into energy spectrum information of different color distributions, for example, when the image is a black-and-white image, obtaining first color distribution energy spectrum information according to the change of gray values corresponding to each pixel; when the color image is a color image, the distribution energy spectrum information of three colors of RGB can be used as the first color distribution energy spectrum information, and optionally, the energy spectrums of the respective colors can be linearly connected to obtain one-dimensional energy spectrum information.
And after obtaining the second color distribution energy spectrum information, sample distortion data can be obtained according to the first color distribution energy spectrum information and the second color distribution energy spectrum information.
In some embodiments, as in the foregoing processing method, the step S3 of determining the pre-trained data repair model corresponding to the communication device includes the following steps S31 and S32:
and S31, determining preset corresponding relations between different preset communication devices and the preset data restoration models.
And S32, matching according to a preset corresponding relation to obtain a data restoration model corresponding to the communication equipment.
Specifically, the loss degree and frequency of different communication devices are different, so that it is difficult to compensate the loss of all communication devices through one data recovery model; in this embodiment, preset data repair models corresponding to different preset communication devices are pre-established, and a correspondence between the two is determined; the preset corresponding relation can be realized in a form of a data table, and links between serial numbers of the preset communication devices and the preset data recovery models can be recorded in the data table, so that the data recovery models corresponding to the communication devices can be quickly called and obtained when specific data recovery models need to be used.
As shown in fig. 3, in some embodiments, the step S5 of compensating the first image signal data by the repair data as the aforementioned processing method includes the following steps S51 to S53:
and S51, determining the minimum unit signal data which needs to be compensated in the first image signal data.
Specifically, the minimum unit signal data is signal data that needs to be compensated, and the minimum unit signal data is data of the minimum unit of the first image signal data, that is, the minimum unit signal data cannot be decomposed any more.
And S52, determining the minimum unit repair signal data corresponding to each minimum unit signal data in the repair data, and obtaining a data corresponding relation.
Specifically, the minimum unit repair signal data is data constituting the minimum unit of repair data.
Since the repair data is data for compensating the first image signal data that is not lost or the first image signal data that is lost, but the signal data of each minimum unit is not necessarily repaired in the first image signal data that is not lost or the first image signal data that is lost, it is not possible to repair the signal data if the data correspondence relationship between each minimum unit signal data and the minimum unit repair signal data is not determined, or even the loss increases because the non-corresponding minimum unit signal data is repaired.
The method for acquiring the data corresponding relation may be:
when generating the repair data, the feature information of each minimum unit signal data (which may be present in the acquired minimum unit signal data itself or obtained by marking the minimum unit signal data) is determined, and when generating the minimum unit repair signal data, each minimum unit repair signal data is marked by the feature information, so that a data correspondence relationship can be established.
And S53, loading each minimum unit repair signal data into corresponding minimum unit signal data according to the data corresponding relation.
Specifically, since each minimum unit signal data is generally transmitted in the form of a wave, the minimum unit repair signal data is also data in a corresponding form, and can be implemented in a superposition manner when being loaded.
As shown in fig. 4, in a second aspect, the present application provides a processing apparatus for image restoration, including:
the acquisition module 1 is used for acquiring original image information needing communication transmission;
a first conversion module 2 configured to generate first image signal data according to original image information, the first image signal data being data that can be transmitted by a communication device;
the determining module 3 is used for determining a data restoration model obtained by pre-training corresponding to the communication equipment;
the repair data generation module 4 is configured to obtain repair data corresponding to the first image signal data through a data repair model, where the repair data is used to compensate data lost when the first image signal data is transmitted in the communication device;
a compensation module 5, configured to compensate the first image signal data by the repair data, so that the communication device outputs second image signal data according to the first image signal data and the repair data;
and the second conversion module 6 is used for obtaining the repaired image information according to the second image signal data.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
According to another embodiment of the present application, there is also provided an electronic apparatus including: as shown in fig. 5, the electronic device may include: the system comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 complete communication with each other through the communication bus 1504.
A memory 1503 for storing a computer program;
the processor 1501 is configured to implement the steps of the above-described method embodiments when executing the program stored in the memory 1503.
The bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the steps of the above-described method embodiments.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for image restoration processing, comprising:
acquiring original image information needing communication transmission;
generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment;
determining a data restoration model obtained by pre-training corresponding to the communication equipment;
obtaining repair data corresponding to the first image signal data through the data repair model, wherein the repair data is used for compensating data lost when the first image signal data is transmitted in the communication equipment;
compensating the first image signal data by the repair data to cause the communication device to output second image signal data in accordance with the first image signal data and the repair data;
and obtaining the repaired image information according to the second image signal data.
2. The processing method according to claim 1, wherein the obtaining repair data corresponding to the first image signal data by the data repair model includes:
determining distortion data of the first image signal data after transmission in the communication device;
and inputting the distortion data into the data restoration model to obtain restoration data for compensating the distortion data.
3. The processing method according to claim 1, wherein the data recovery model establishing method comprises:
acquiring pre-collected sample distortion data, wherein the sample distortion data is obtained according to sample image information and distortion image information after the sample image information is transmitted in communication equipment;
inputting the sample distortion data into a preset neural network model for training to obtain a trained neural network model;
and verifying the trained neural network model through the sample image information and the distorted image information, and obtaining the data restoration model after a verification result meets a preset requirement.
4. The process of claim 3, wherein said obtaining pre-collected sample distortion data comprises:
determining two-dimensional digital matrix data of the sample image information;
converting the two-dimensional digital matrix data into one-dimensional sequence data;
performing Fourier transform on the one-dimensional sequence data to obtain corresponding frequency spectrum information;
acquiring distorted sample image information obtained after the sample image information is transmitted through the communication equipment;
obtaining corresponding distorted frequency spectrum information according to the distorted sample image information;
and obtaining the sample distortion data according to the frequency spectrum information and the distorted frequency spectrum information.
5. The process of claim 3, wherein said obtaining pre-collected sample distortion data comprises:
converting the sample image information into first color distribution energy spectrum information;
acquiring distorted sample image information obtained after the sample image information is transmitted through the communication equipment;
converting the distorted sample image information into second color distribution energy spectrum information;
and obtaining the sample distortion data according to the first color distribution energy spectrum information and the second color distribution energy spectrum information.
6. The processing method according to claim 1, wherein the determining the pre-trained data recovery model corresponding to the communication device comprises:
determining preset corresponding relations between different preset communication devices and preset data restoration models;
and matching according to the preset corresponding relation to obtain the data repair model corresponding to the communication equipment.
7. The processing method according to claim 1, wherein said compensating the first image signal data by the repair data comprises:
determining minimum unit signal data which needs to be compensated in the first image signal data;
determining minimum unit repair signal data corresponding to each minimum unit signal data in the repair data, and obtaining a data corresponding relation;
and loading each minimum unit repair signal data into the corresponding minimum unit signal data according to the data corresponding relation.
8. A processing apparatus for image restoration, comprising:
the acquisition module is used for acquiring original image information needing communication transmission;
the first conversion module is used for generating first image signal data according to the original image information, wherein the first image signal data is data which can be transmitted through communication equipment;
the determining module is used for determining a data restoration model obtained by pre-training corresponding to the communication equipment;
a repair data generation module, configured to obtain repair data corresponding to the first image signal data through the data repair model, where the repair data is used to compensate data lost when the first image signal data is transmitted in the communication device;
a compensation module, configured to compensate the first image signal data by the repair data, so that the communication device outputs second image signal data according to the first image signal data and the repair data;
and the second conversion module is used for obtaining the repaired image information according to the second image signal data.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, implementing the processing method of any one of claims 1-7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the processing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246945.7A CN111476730B (en) | 2020-03-31 | 2020-03-31 | Image restoration processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246945.7A CN111476730B (en) | 2020-03-31 | 2020-03-31 | Image restoration processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111476730A true CN111476730A (en) | 2020-07-31 |
| CN111476730B CN111476730B (en) | 2024-02-13 |
Family
ID=71750383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010246945.7A Active CN111476730B (en) | 2020-03-31 | 2020-03-31 | Image restoration processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476730B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488330A (en) * | 2020-11-27 | 2021-03-12 | 成都市更新家具有限公司 | Paint damage repair method based on smart home and smart home |
| CN114615222A (en) * | 2022-03-16 | 2022-06-10 | 航天科工通信技术研究院有限责任公司 | Time-delay braking system based on RabbitMQ and braking method thereof |
| CN117950903A (en) * | 2024-03-21 | 2024-04-30 | 深圳软牛科技集团股份有限公司 | Repair method and device for damaged WebP file and related components |
| CN117950903B (en) * | 2024-03-21 | 2024-06-04 | 深圳软牛科技集团股份有限公司 | Repair method and device for damaged WebP file and related components |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765339A (en) * | 2018-05-29 | 2018-11-06 | 上海大学 | A kind of networking vision reversible pendulum system image information loss restorative procedure |
| US20190282120A1 (en) * | 2018-03-14 | 2019-09-19 | Canon Medical Systems Corporation | Medical image diagnostic apparatus, medical signal restoration method, and model training method |
| CN110555808A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | Image processing method, device, equipment and machine-readable storage medium |
| CN110636289A (en) * | 2019-09-27 | 2019-12-31 | 北京金山云网络技术有限公司 | Image data transmission method, system, device, electronic equipment and storage medium |
-
2020
- 2020-03-31 CN CN202010246945.7A patent/CN111476730B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190282120A1 (en) * | 2018-03-14 | 2019-09-19 | Canon Medical Systems Corporation | Medical image diagnostic apparatus, medical signal restoration method, and model training method |
| CN108765339A (en) * | 2018-05-29 | 2018-11-06 | 上海大学 | A kind of networking vision reversible pendulum system image information loss restorative procedure |
| CN110555808A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | Image processing method, device, equipment and machine-readable storage medium |
| CN110636289A (en) * | 2019-09-27 | 2019-12-31 | 北京金山云网络技术有限公司 | Image data transmission method, system, device, electronic equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488330A (en) * | 2020-11-27 | 2021-03-12 | 成都市更新家具有限公司 | Paint damage repair method based on smart home and smart home |
| CN114615222A (en) * | 2022-03-16 | 2022-06-10 | 航天科工通信技术研究院有限责任公司 | Time-delay braking system based on RabbitMQ and braking method thereof |
| CN117950903A (en) * | 2024-03-21 | 2024-04-30 | 深圳软牛科技集团股份有限公司 | Repair method and device for damaged WebP file and related components |
| CN117950903B (en) * | 2024-03-21 | 2024-06-04 | 深圳软牛科技集团股份有限公司 | Repair method and device for damaged WebP file and related components |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111476730B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046644B (en) | Certificate anti-counterfeiting method and device, computing equipment and storage medium | |
| Chierchia et al. | Epigraphical projection and proximal tools for solving constrained convex optimization problems | |
| CN109872305B (en) | No-reference stereo image quality evaluation method based on quality map generation network | |
| CN111476730B (en) | Image restoration processing method and device | |
| CN109920021B (en) | Face sketch synthesis method based on regularized width learning network | |
| CN104021529B (en) | Blurred image non-blind restoration method | |
| CN108399620B (en) | Image quality evaluation method based on low-rank sparse matrix decomposition | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN110246090B (en) | Image processing method and device | |
| JP2006295877A5 (en) | ||
| Punnappurath et al. | A little bit more: Bitplane-wise bit-depth recovery | |
| JP2017517222A (en) | System for identifying a photo camera model associated with a JPEG compressed image, and related methods implemented in such a system, its use and application | |
| Wei et al. | Non-homogeneous haze removal via artificial scene prior and bidimensional graph reasoning | |
| Lin et al. | Non-blind optical degradation correction via frequency self-adaptive and finetune tactics | |
| US7586627B2 (en) | Method and system for optimizing print-scan simulations | |
| CN106709915A (en) | Image resampling operation detection method | |
| JP2022046219A5 (en) | ||
| Bhatnagar et al. | Multi-sensor fusion based on local activity measure | |
| Xu et al. | Detecting image splicing using merged features in chroma space | |
| JP2016064634A5 (en) | ||
| Bhaskar | Probabilistic low-rank matrix recovery from quantized measurements: Application to image denoising | |
| CN112669240B (en) | High-definition image restoration method and device, electronic equipment and storage medium | |
| JP2005091730A5 (en) | ||
| KR102537207B1 (en) | Method for processing image based on machine learning and apparatus therefof | |
| TWI359389B (en) | Method for halftone image transformation, printing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |