CN114255187A - Multi-level and multi-level image optimization method and system based on big data platform - Google Patents
Multi-level and multi-level image optimization method and system based on big data platform Download PDFInfo
- Publication number
- CN114255187A CN114255187A CN202111582060.5A CN202111582060A CN114255187A CN 114255187 A CN114255187 A CN 114255187A CN 202111582060 A CN202111582060 A CN 202111582060A CN 114255187 A CN114255187 A CN 114255187A
- Authority
- CN
- China
- Prior art keywords
- image data
- optimization
- luminosity
- definition
- data
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 251
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 abstract description 22
- 230000000750 progressive effect Effects 0.000 abstract description 6
- 238000012935 Averaging Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000004323 axial length Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/73—
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention discloses a multilevel and multilevel image optimization method and system based on a big data platform. Wherein, the method comprises the following steps: acquiring original image data; splitting the original image data to obtain first image data and second image data; inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; and optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized image data. The invention solves the technical problems that the image optimization processing process in the prior art is only to carry out image optimization according to a fixed image optimization algorithm, such as a luminosity image component difference algorithm or a texture sharpening pixel progressive algorithm, and the optimization method in the prior art only carries out single optimization operation on original image data through a certain optimization method, if a plurality of optimization operations are needed, optimization calculation is needed to be carried out one by one, so that the optimization efficiency is reduced, and the calculation resources are wasted.
Description
Technical Field
The invention relates to the field of image processing, in particular to a multi-level and multi-level image optimization method and system based on a big data platform.
Background
Along with the continuous development of intelligent science and technology, people use intelligent equipment more and more among life, work, the study, use intelligent science and technology means, improved the quality of people's life, increased the efficiency of people's study and work.
At present, when an image is optimized, optimization operation is often performed on image data acquired originally through a certain luminosity optimization algorithm or a definition sharpening optimization algorithm, and an optimized result is fed back to a user terminal, so that a user can analyze and use the image subjected to certain optimization processing. However, in the image optimization processing process in the prior art, image optimization is performed only according to a fixed image optimization algorithm, such as a photometric image component difference algorithm or a texture sharpening pixel progressive algorithm, and the optimization method in the prior art performs only a single optimization operation on original image data through a certain optimization method, and if multiple optimization operations are required, optimization calculation needs to be performed one by one, which reduces optimization efficiency and wastes calculation resources.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a multi-level and multi-level image optimization method and system based on a big data platform, which at least solve the technical problems that in the prior art, the image optimization processing process is only image optimization according to a fixed image optimization algorithm, such as a photometric image component difference algorithm or a texture sharpening pixel progressive algorithm, and the prior art optimization method only performs single optimization operation on original image data through a certain optimization method, if multiple optimization operations are needed, optimization calculation needs to be performed one by one, so that the optimization efficiency is reduced, and the calculation resources are wasted.
According to an aspect of the embodiments of the present invention, there is provided a multi-level and multi-level image optimization method based on a big data platform, including: acquiring original image data; splitting the original image data to obtain first image data and second image data; inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; and optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized image data.
Further, after the splitting the original image data to obtain the first image data and the second image data, the method further includes: historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data.
Further, when the big data platform obtains the historical image data, data matching is carried out according to image optimization requirements, and the historical image data which can be used for training an optimization model are obtained.
Further, after the optimizing the original image data according to the sharpness optimization result and the luminosity optimization result to obtain optimized processed image data, the method further includes: and comparing the optimized image data with the original image data and outputting the image data to display equipment of a user terminal.
According to another aspect of the embodiments of the present invention, there is also provided a system for optimizing a multi-level and multi-level image based on a big data platform, including: the acquisition module is used for acquiring original image data; the splitting module is used for splitting the original image data to obtain first image data and second image data; the output module is used for inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; and the optimization module is used for optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized processing image data.
Further, the system further comprises: and the training module is used for acquiring historical image data of related acquisition equipment through a big data platform and training a definition optimization model and a luminosity optimization model according to the historical image data.
Further, when the big data platform obtains the historical image data, data matching is carried out according to image optimization requirements, and the historical image data which can be used for training an optimization model are obtained.
Further, the system further comprises: and the display module is used for comparing the optimized image data with the original image data and outputting the optimized image data and the original image data to display equipment of a user terminal.
According to another aspect of the embodiment of the present invention, a non-volatile storage medium is further provided, where the non-volatile storage medium includes a stored program, and the program controls, when running, a device in which the non-volatile storage medium is located to execute a multi-level and multi-level image optimization method based on a big data platform.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a processor and a memory; the memory is stored with computer readable instructions, and the processor is used for executing the computer readable instructions, wherein the computer readable instructions execute a multi-level and multi-level image optimization method based on a big data platform when running.
Compared with the prior art, the invention has the beneficial effects that:
in the embodiment of the invention, the method comprises the steps of acquiring original image data; splitting the original image data to obtain first image data and second image data; inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; the method for optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain the optimized processed image data solves the technical problems that the image optimization processing process in the prior art is only to perform image optimization according to a fixed image optimization algorithm, such as a luminosity image component difference algorithm or a texture sharpening pixel progressive algorithm, and the optimization method in the prior art only performs single optimization operation on the original image data through a certain optimization method, if multiple optimization operations are needed, optimization calculation needs to be performed one by one, so that the optimization efficiency is reduced, and the calculation resources are wasted.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flowchart of a multi-level and multi-level image optimization method based on a big data platform according to an embodiment of the present invention;
FIG. 2 is a block diagram of a multi-level and multi-level image optimization system based on a big data platform according to an embodiment of the present invention;
FIG. 3 is a flow chart of a photometric optimization algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with an embodiment of the present invention, there is provided a method embodiment of a large data platform-based multi-level image optimization method, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that illustrated herein.
Example one
Fig. 1 is a flowchart of a multilevel and multilevel image optimization method based on a big data platform according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, original image data is acquired.
Step S104, splitting the original image data to obtain first image data and second image data.
And S106, inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result.
And S108, optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized image data.
Optionally, after splitting the original image data to obtain first image data and second image data, the method further includes: historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data.
Optionally, when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
Optionally, after the original image data is optimized according to the sharpness optimization result and the luminosity optimization result to obtain optimized processed image data, the method further includes: and comparing the optimized image data with the original image data and outputting the image data to display equipment of a user terminal.
Specifically, in order to achieve the technical effect of performing optimization processing on an image in time, image data to be optimized originally needs to be acquired by an image acquisition device, and the acquired original image data is stored for a subsequent processor to perform optimization processing.
Splitting the original image data to obtain first image data and second image data, wherein the first image data is used for sharpness optimization preprocessing, and the second image is used for luminosity optimization preprocessing; specifically, the split image can be equally split by a pixel division calculation method, wherein the pixel division calculation method includes: acquiring pixel information of an image, taking specific pixel data of the image as a basis for averaging the image, and calculating an averaging cut point according to the value of the pixel, wherein F is the averaging cut point, and G is the axial length of the forward pixel coordinate of the image. The cut image is divided into two parts, one part is used for subsequent definition optimization, and the other part is used for subsequent luminosity optimization.
Historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data. Inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; specifically, after the image is segmented, historical optimization data of the image to be optimized can be acquired through an image data platform of big data, for example, the process of performing luminosity optimization on the image a to the image a' is performed, the process is used as historical data of luminosity optimization model training to perform characteristic vector input and output correspondence, and construction and training of the luminosity optimization model are completed. The luminosity optimization algorithm flowchart is shown in fig. 3, and includes the steps of S302 luminosity optimization image acquisition, S304 luminosity difference image comparison, S306 luminosity optimization strategy generation, and S308 input optimization code optimization, and the specific algorithm is as follows:
in addition, for the definition and luminosity optimization process, the calculation equation of the optimized scaling factor s is as follows: and s ═ k × Im + b, wherein k and b are taken and substituted into-4.3 × 10-5 × Im +0.018, wherein Im is a limiting reduction factor k as a coefficient, and b is a deviation.
Aiming at the optimization process, the calculation of the scaling factor s can be used for measuring the definition chromatogram calibration range and the luminosity lumen range, so that the dynamic threshold of the factor is analyzed and calculated by utilizing the expansion of lm + b, and the technical effect of multivariate data consideration in the image processing process is achieved.
Iω＝s*Min(255,Ratio(I,0.8)*1.25)
Iω＝(-4.3*10-5*Im+0.018)*Min(255,Ratio(I,0.8)*1.25)
Is(x,y)＝s*I(x,y)
I′＝Is1+Iγs*(Iγ-1ω+IsI2ω)
I′＝I*s*(Iγ-1ω+s*II2ω)1+(s*I)γ
Global adjustment factor:
f0(I)＝s*(Iγ-1ω+s*II2ω)1+(s*I)γ
i is the result of adaptive bilateral filtering, omega is the fitness of the optimization factor, Iabf is the result of dynamic threshold calculation, and gamma is the scaling linkage factor, specifically, the sequence of the video image can be read, and then the sequence value is assigned to an input variable to determine the size of the extracted block. The spatial variance is given randomly, then the pixel value of any point is calculated through the for cycle of the whole image block, then the variance of all the pixel values in a single block is calculated through the for cycle in the block, and then the standard deviation is obtained through the evolution, which is also the pixel domain variance value. As the experiment is to take the airspace space of 3-by-3 for filtering, the values near the x axis and the y axis of the current pixel point are obtained by using the for-cycle and are substituted into the formula for calculating the pixel domain distance weight to calculate the weight, then the airspace weight is calculated by using the difference value of the horizontal and vertical coordinates, and finally the total weight value is obtained.
f0(I)＝(-4.3*10-5*Im+0.018)*(Iγ-Iω+(-4.3*10-5*Im+0.018)*IabfI2ω)1+((-4.3*10-5*Im+0.018)*Iabf)γ
Optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized processing image data, specifically, gathering the two groups of data into (a1, a2 … aN) through a definition optimization parameter alpha in the definition optimization result and a lumen adjustment parameter gamma in the corresponding luminosity optimization result, wherein N is a Taylor expansion layer series for optimizing iteration degree, a is a natural positive integer, then obtaining a final original image data optimization strategy through aN alpha-gamma data linkage matrix, and by summarizing and processing multi-factor optimization variables, the defects of a single optimization scheme can be avoided, and the optimization performance is improved; it should be noted that, when the big data platform acquires historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
Through the embodiment, the technical problems that in the prior art, the image optimization processing process is only image optimization according to a fixed image optimization algorithm, such as a photometric image component difference algorithm or a texture sharpening pixel progressive algorithm, and the optimization method only performs a single optimization operation on original image data through a certain optimization method, if multiple optimization operations are needed, the optimization calculation needs to be performed one by one, so that the optimization efficiency is reduced, and the calculation resources are wasted are solved.
Example two
Fig. 2 is a block diagram of a multi-level and multi-level image optimization system based on a big data platform according to an embodiment of the present invention, as shown in fig. 2, the system includes:
an obtaining module 20, configured to obtain raw image data.
The splitting module 22 is configured to split the original image data to obtain first image data and second image data.
And the output module 24 is configured to input the first image data into a sharpness optimization model to obtain a sharpness optimization result, and input the second image data into a luminosity optimization model to obtain a luminosity optimization result.
And the optimization module 26 is configured to optimize the original image data according to the sharpness optimization result and the luminosity optimization result to obtain optimized image data.
Optionally, the system further includes: and the training module is used for acquiring historical image data of related acquisition equipment through a big data platform and training a definition optimization model and a luminosity optimization model according to the historical image data.
Optionally, when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
Optionally, the system further includes: and the display module is used for comparing the optimized image data with the original image data and outputting the optimized image data and the original image data to display equipment of a user terminal.
Specifically, in order to achieve the technical effect of performing optimization processing on an image in time, image data to be optimized originally needs to be acquired by an image acquisition device, and the acquired original image data is stored for a subsequent processor to perform optimization processing.
Splitting the original image data to obtain first image data and second image data, wherein the first image data is used for sharpness optimization preprocessing, and the second image is used for luminosity optimization preprocessing; specifically, the split image can be equally split by a pixel division calculation method, wherein the pixel division calculation method includes: acquiring pixel information of an image, taking specific pixel data of the image as a basis for averaging the image, and calculating an averaging cut point according to the value of the pixel, wherein F is the averaging cut point, and G is the axial length of the forward pixel coordinate of the image. The cut image is divided into two parts, one part is used for subsequent definition optimization, and the other part is used for subsequent luminosity optimization.
Historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data. Inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; specifically, after the image is segmented, historical optimization data of the image to be optimized can be acquired through an image data platform of big data, for example, the process of performing luminosity optimization on the image a to the image a' is performed, the process is used as historical data of luminosity optimization model training to perform characteristic vector input and output correspondence, and construction and training of the luminosity optimization model are completed. The luminosity optimization algorithm flowchart is shown in fig. 3, and includes the steps of S302 luminosity optimization image acquisition, S304 luminosity difference image comparison, S306 luminosity optimization strategy generation, and S308 input optimization code optimization, and the specific algorithm is as follows:
in addition, for the definition and luminosity optimization process, the calculation equation of the optimized scaling factor s is as follows: and s ═ k × Im + b, wherein k and b are taken and substituted into-4.3 × 10-5 × Im +0.018, wherein Im is a limiting reduction factor k as a coefficient, and b is a deviation.
Aiming at the optimization process, the calculation of the scaling factor s can be used for measuring the definition chromatogram calibration range and the luminosity lumen range, so that the dynamic threshold of the factor is analyzed and calculated by utilizing the expansion of lm + b, and the technical effect of multivariate data consideration in the image processing process is achieved.
Iω＝s*Min(255,Ratio(I,0.8)*1.25)
Iω＝(-4.3*10-5*Im+0.018)*Min(255,Ratio(I,0.8)*1.25)
Is(x,y)＝s*I(x,y)
I′＝Is1+Iγs*(Iγ-1ω+IsI2ω)
I′＝I*s*(Iγ-1ω+s*II2ω)1+(s*I)γ
Global adjustment factor:
f0(I)＝s*(Iγ-1ω+s*II2ω)1+(s*I)γ
i is the result of adaptive bilateral filtering, omega is the fitness of the optimization factor, Iabf is the result of dynamic threshold calculation, and gamma is the scaling linkage factor, specifically, the sequence of the video image can be read, and then the sequence value is assigned to an input variable to determine the size of the extracted block. The spatial variance is given randomly, then the pixel value of any point is calculated through the for cycle of the whole image block, then the variance of all the pixel values in a single block is calculated through the for cycle in the block, and then the standard deviation is obtained through the evolution, which is also the pixel domain variance value. As the experiment is to take the airspace space of 3-by-3 for filtering, the values near the x axis and the y axis of the current pixel point are obtained by using the for-cycle and are substituted into the formula for calculating the pixel domain distance weight to calculate the weight, then the airspace weight is calculated by using the difference value of the horizontal and vertical coordinates, and finally the total weight value is obtained.
f0(I)＝(-4.3*10-5*Im+0.018)*(Iγ-Iω+(-4.3*10-5*Im+0.018)*IabfI2ω)1+((-4.3*10-5*Im+0.018)*Iabf)γ
Optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized processing image data, specifically, gathering the two groups of data into (a1, a2 … aN) through a definition optimization parameter alpha in the definition optimization result and a lumen adjustment parameter gamma in the corresponding luminosity optimization result, wherein N is a Taylor expansion layer series for optimizing iteration degree, a is a natural positive integer, then obtaining a final original image data optimization strategy through aN alpha-gamma data linkage matrix, and by summarizing and processing multi-factor optimization variables, the defects of a single optimization scheme can be avoided, and the optimization performance is improved; it should be noted that, when the big data platform acquires historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
According to another aspect of the embodiment of the present invention, a non-volatile storage medium is further provided, where the non-volatile storage medium includes a stored program, and the program controls, when running, a device in which the non-volatile storage medium is located to execute a multi-level and multi-level image optimization method based on a big data platform.
Specifically, the method comprises the following steps: acquiring original image data; splitting the original image data to obtain first image data and second image data; inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; optimizing the original image data according to the sharpness optimization result and the luminosity optimization result to obtain optimized image data, optionally splitting the original image data to obtain first image data and second image data, and then: historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data. Optionally, when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model. Optionally, after the original image data is optimized according to the sharpness optimization result and the luminosity optimization result to obtain optimized processed image data, the method further includes: and comparing the optimized image data with the original image data and outputting the image data to display equipment of a user terminal.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a processor and a memory; the memory is stored with computer readable instructions, and the processor is used for executing the computer readable instructions, wherein the computer readable instructions execute a multi-level and multi-level image optimization method based on a big data platform when running.
Specifically, the method comprises the following steps: acquiring original image data; splitting the original image data to obtain first image data and second image data; inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result; optimizing the original image data according to the sharpness optimization result and the luminosity optimization result to obtain optimized image data, optionally splitting the original image data to obtain first image data and second image data, and then: historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data. Optionally, when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model. Optionally, after the original image data is optimized according to the sharpness optimization result and the luminosity optimization result to obtain optimized processed image data, the method further includes: and comparing the optimized image data with the original image data and outputting the image data to display equipment of a user terminal.
Through the embodiment, the technical problems that in the prior art, the image optimization processing process is only image optimization according to a fixed image optimization algorithm, such as a photometric image component difference algorithm or a texture sharpening pixel progressive algorithm, and the optimization method only performs a single optimization operation on original image data through a certain optimization method, if multiple optimization operations are needed, the optimization calculation needs to be performed one by one, so that the optimization efficiency is reduced, and the calculation resources are wasted are solved.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A multilevel and multilevel image optimization method based on a big data platform is characterized by comprising the following steps:
acquiring original image data;
splitting the original image data to obtain first image data and second image data;
inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result;
and optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized image data.
2. The method of claim 1, wherein after the splitting the original image data into the first image data and the second image data, the method further comprises: historical image data of related acquisition equipment is acquired through a big data platform, and a definition optimization model and a luminosity optimization model are trained according to the historical image data.
3. The method according to claim 2, wherein when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
4. The method of claim 1, wherein after said optimizing said raw image data based on said sharpness optimization result and said luminosity optimization result to obtain optimized processed image data, said method further comprises:
and comparing the optimized image data with the original image data and outputting the image data to display equipment of a user terminal.
5. A multilevel and multilevel image optimization system based on a big data platform is characterized by comprising:
the acquisition module is used for acquiring original image data;
the splitting module is used for splitting the original image data to obtain first image data and second image data;
the output module is used for inputting the first image data into a definition optimization model to obtain a definition optimization result, and simultaneously inputting the second image data into a luminosity optimization model to obtain a luminosity optimization result;
and the optimization module is used for optimizing the original image data according to the definition optimization result and the luminosity optimization result to obtain optimized processing image data.
6. The system of claim 5, further comprising: and the training module is used for acquiring historical image data of related acquisition equipment through a big data platform and training a definition optimization model and a luminosity optimization model according to the historical image data.
7. The system of claim 6, wherein when the big data platform obtains the historical image data, data matching is performed according to image optimization requirements, so as to obtain historical image data which can be used for training an optimization model.
8. The system of claim 5, further comprising:
and the display module is used for comparing the optimized image data with the original image data and outputting the optimized image data and the original image data to display equipment of a user terminal.
9. A non-volatile storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the non-volatile storage medium is located to perform the method of any one of claims 1 to 4.
10. An electronic device comprising a processor and a memory; the memory has stored therein computer readable instructions for execution by the processor, wherein the computer readable instructions when executed perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111582060.5A CN114255187A (en) | 2021-12-22 | 2021-12-22 | Multi-level and multi-level image optimization method and system based on big data platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111582060.5A CN114255187A (en) | 2021-12-22 | 2021-12-22 | Multi-level and multi-level image optimization method and system based on big data platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114255187A true CN114255187A (en) | 2022-03-29 |
Family
ID=80796762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111582060.5A Pending CN114255187A (en) | 2021-12-22 | 2021-12-22 | Multi-level and multi-level image optimization method and system based on big data platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255187A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842424A (en) * | 2022-06-07 | 2022-08-02 | 北京拙河科技有限公司 | Intelligent security image identification method and device based on motion compensation |
| CN115205313A (en) * | 2022-08-11 | 2022-10-18 | 北京拙河科技有限公司 | Picture optimization method and device based on least square algorithm |
| CN115511735A (en) * | 2022-09-20 | 2022-12-23 | 北京拙河科技有限公司 | Snow field gray level picture optimization method and device |
-
2021
- 2021-12-22 CN CN202111582060.5A patent/CN114255187A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842424A (en) * | 2022-06-07 | 2022-08-02 | 北京拙河科技有限公司 | Intelligent security image identification method and device based on motion compensation |
| CN115205313A (en) * | 2022-08-11 | 2022-10-18 | 北京拙河科技有限公司 | Picture optimization method and device based on least square algorithm |
| CN115511735A (en) * | 2022-09-20 | 2022-12-23 | 北京拙河科技有限公司 | Snow field gray level picture optimization method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114255187A (en) | Multi-level and multi-level image optimization method and system based on big data platform | |
| CN111031346B (en) | Method and device for enhancing video image quality | |
| CN108124489B (en) | Information processing method, apparatus, cloud processing device and computer program product | |
| JP2008542911A (en) | Image comparison by metric embedding | |
| CN108564541B (en) | Image processing method and device | |
| CN110827297A (en) | Insulator segmentation method for generating countermeasure network based on improved conditions | |
| CN112232889A (en) | User interest portrait extension method, device, equipment and storage medium | |
| Kim et al. | Deep blind image quality assessment by employing FR-IQA | |
| CN113450288A (en) | Single image rain removing method and system based on deep convolutional neural network and storage medium | |
| US10558900B2 (en) | Two-dimensional code processing method and apparatus | |
| CN114373444B (en) | Method, system and equipment for synthesizing voice based on montage | |
| CN107533760B (en) | Image segmentation method and device | |
| US7471825B2 (en) | System and method for utilizing a graphic equalizer in performing image search procedures | |
| US8001061B2 (en) | First and second unsupervised learning processes combined using a supervised learning apparatus | |
| CN112836807A (en) | Data processing method and device based on neural network | |
| CN117216591A (en) | Training method and device for three-dimensional model matching and multi-modal feature mapping model | |
| CN115907278B (en) | Intelligent processing and manufacturing method, system and medium based on digital twinning | |
| Wu et al. | A hybrid image retargeting approach via combining seam carving and grid warping | |
| CN111860287A (en) | Target detection method and device and storage medium | |
| Wang et al. | Mixed distortion image enhancement method based on joint of deep residuals learning and reinforcement learning | |
| Cruz et al. | Patch-based terrain synthesis | |
| CN110505485B (en) | Motion compensation method, motion compensation device, computer equipment and storage medium | |
| CN113313653A (en) | Image denoising method and device based on generative countermeasure network | |
| CN113781491A (en) | Training of image segmentation model, image segmentation method and device | |
| CN110298903B (en) | Curve editing method and device, computing equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: Room 1308, 13th floor, East Tower, 33 Fuxing Road, Haidian District, Beijing 100036 Applicant after: China Telecom Digital Intelligence Technology Co.,Ltd. Address before: Room 1308, 13th floor, East Tower, 33 Fuxing Road, Haidian District, Beijing 100036 Applicant before: CHINA TELECOM GROUP SYSTEM INTEGRATION Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |