CN113870210A - Image quality evaluation method, device, equipment and storage medium - Google Patents
Image quality evaluation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113870210A CN113870210A CN202111111417.1A CN202111111417A CN113870210A CN 113870210 A CN113870210 A CN 113870210A CN 202111111417 A CN202111111417 A CN 202111111417A CN 113870210 A CN113870210 A CN 113870210A
- Authority
- CN
- China
- Prior art keywords
- data
- quality
- image
- quality evaluation
- target 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.)
- Pending
Links
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001303 quality assessment method Methods 0.000 claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000013075 data extraction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image quality evaluation method, an image quality evaluation device, image quality evaluation equipment and a storage medium, wherein the method comprises the following steps: acquiring first characteristic data of a reference image, and determining first quality evaluation data of the reference image according to the first characteristic data, wherein the reference image is an image meeting a preset high-quality image standard; acquiring second characteristic data of a target image, and determining second quality evaluation data of the target image according to the second characteristic data; comparing the second quality assessment data with the first quality assessment data, and determining whether the target image is a high quality image according to a result of the comparison. The invention can realize the image quality evaluation which is easy to implement, can be rapidly carried out and simultaneously ensures the evaluation precision.
Description
Technical Field
The embodiment of the application relates to the technical field of image processing, in particular to an image quality evaluation method, device, equipment and storage medium.
Background
In the case where the image information technology is widely used, evaluation of image quality becomes a wide and fundamental problem. The meaning of the image quality comprises the fidelity of the image and the readable understandability of the image, wherein the fidelity of the image refers to the deviation degree of the evaluated image and the standard image, and the smaller the deviation is, the higher the fidelity is; the readability of an image refers to the ability of the image to provide information to a person or machine, which is not only related to the application requirements of the image system, but also often related to the subjective perception of the human eye, so that the image quality indicators include aspects of resolution, color depth, image distortion, and the like.
In view of the incomparable advantages of image information relative to other information, reasonable judgment of image information becomes an indispensable means in various fields, and in the process of acquiring, processing, transmitting and recording images, due to the imperfection of an imaging system, a processing method, a transmission medium, recording equipment and the like, and the reasons of object motion, noise pollution and the like, the fidelity of the images and the readable understandability of the images are inevitably influenced.
In image recognition, the quality of the acquired image directly affects the accuracy and reliability of the recognition result. Therefore, reasonable evaluation of image quality has very important application value, especially the balance between speed and accuracy of evaluation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, adapt to the practical requirements, and discloses an image quality evaluation method, an image quality evaluation device, image quality evaluation equipment and a storage medium, which are easy to implement, can be rapidly carried out and ensure the evaluation precision.
In a first aspect, an embodiment of the present application provides an image quality assessment method, where the method includes:
acquiring first characteristic data of a reference image, and determining first quality evaluation data of the reference image according to the first characteristic data, wherein the reference image is an image meeting a preset high-quality image standard;
acquiring second characteristic data of a target image, and determining second quality evaluation data of the target image according to the second characteristic data;
comparing the second quality assessment data with the first quality assessment data, and determining whether the target image is a high quality image according to a result of the comparison.
In a second aspect, an embodiment of the present application further provides an image quality evaluation apparatus, including:
the first quality evaluation data determination module is used for acquiring first characteristic data of a reference image and determining first quality evaluation data of the reference image according to the first characteristic data, wherein the reference image is an image meeting a preset high-quality image standard;
the second quality evaluation data module is used for acquiring second characteristic data of a target image and determining second quality evaluation data of the target image according to the second characteristic data;
and the high-quality image judging module is used for comparing the second quality evaluation data with the first quality evaluation data and determining whether the target image is a high-quality image according to the comparison result.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the above method when executing the program.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method described above.
The application has the following beneficial effects:
the image quality evaluation method comprises the steps of obtaining first characteristic data of a reference image, determining first quality evaluation data of the reference image according to the first characteristic data, obtaining second characteristic data of a target image according to the second characteristic data, comparing the second quality evaluation data with the first quality evaluation data, and determining whether the target image is a high-quality image according to a comparison result, wherein the first characteristic data of the reference image is an image meeting a preset high-quality image standard, the first quality evaluation data of the reference image is determined, the second quality evaluation data of the target image is compared with the first quality evaluation data, and whether the target image is a high-quality image is determined according to a comparison result.
Drawings
Fig. 1 is a flowchart of an embodiment of an image quality evaluation method provided in an embodiment of the present application;
fig. 2 is a block diagram of an embodiment of an image quality evaluation apparatus according to a second embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an embodiment of an image quality evaluation method according to an embodiment of the present disclosure.
When the image quality evaluation is performed and the high-quality and low-quality images need to be distinguished and screened, the image which meets the preset high-quality image standard can be used as a reference image. And comparing the reference image with the target image to judge whether the target image belongs to the category of high-quality images or low-quality images.
As shown in fig. 1, the present embodiment may include the following steps:
In this step, the first feature data of the reference image may include noise intensity, gradient pixels, and the like of the image.
In one implementation, the reference image may be first feature data obtained by randomly selecting a high-quality image from a high-quality image database and then extracting feature data according to the randomly selected high-quality image.
After the first feature data is obtained, one or more feature parameters may be selected from the first feature data, the selected feature parameters constitute first quality assessment data, and the size of the first quality assessment data may reflect the image quality.
In one embodiment, step 110 includes:
and inputting the first characteristic data into a pre-generated quality evaluation model, processing the first characteristic data by the quality evaluation model, and outputting first quality evaluation data.
In this step, a pre-generated quality evaluation model may be formed by training a large number of test images in advance, a plurality of quality evaluation models may be generated in the training process, the quality evaluation models may be tested, the determined high-quality images and low-quality images are input to the quality evaluation models, evaluation results of the quality evaluation models are collected, the evaluation results output by the quality evaluation models are compared with a pre-known standard answer, and a quality evaluation model with a higher accuracy than a certain threshold or a highest accuracy may be determined as a final quality evaluation model.
In one embodiment, the first feature data includes first gradient feature data and first noise feature data, the quality assessment model includes a gradient assessment submodel and a noise assessment submodel, and the processing the first feature data for the quality assessment model includes:
inputting the first noise characteristic data into a noise evaluation submodel, and obtaining noise intensity data output by the noise evaluation submodel;
and inputting the noise intensity data and the first gradient characteristic data into a gradient evaluation submodel, and obtaining first quality evaluation data output by the gradient evaluation submodel.
In this step, the quality evaluation model includes a gradient evaluation submodel and a noise evaluation submodel, the quality evaluation model may be a neural network model based on machine learning, the first noise feature data and the first gradient feature data are input into the neural network model for convolution processing, and the quality evaluation model may include a feature data extraction layer. After the first feature data is acquired, the first gradient feature data and the first noise feature data in the first feature data may be extracted respectively. The extracted first noise characteristic data may be input into a noise evaluation submodel to obtain noise intensity data, and then the obtained noise intensity data and the extracted first gradient characteristic data are input into a gradient evaluation submodel to obtain first quality evaluation data.
In another implementation, the noise evaluation submodel may include a first noise feature data extraction layer, where the first noise feature data is identified and acquired by the first noise feature data extraction layer of the noise evaluation submodel for the image feature data input to the quality evaluation model, and then the first noise feature data is input to a noise intensity data determination layer, where noise intensity calculation is performed on the first noise feature data, and finally the noise intensity data is output. The noise is often represented as an isolated pixel point or a pixel block causing a strong visual effect on an image, and the calculation of the noise intensity belongs to a conventional algorithm in the prior art, and can be classified into gaussian noise, rayleigh noise, gamma noise, exponential noise and uniform noise from the viewpoint of the probability distribution of the noise. Here, the noise intensity calculation process in the noise intensity data determination layer is not described in detail.
And inputting the noise intensity data and the first gradient characteristic data into a gradient evaluation submodel, and obtaining first quality evaluation data output by the gradient evaluation submodel. The gradient evaluation submodel may first calculate first gradient feature data, and when calculating, may regard the image as a two-dimensional discrete function, and the first gradient feature data may be a derivative of the two-dimensional discrete function, and the calculation formula is:
G(x,y)＝dx(i,j)+dy(i,j)；
dx(i,j)＝I(i+1,j)-I(i,j)；
dy(i,j)＝I(i,j+1)-I(i,j)；
where I is the value of an image pixel (e.g., RGB value) and (I, j) is the pixel's coordinates.
And step 120, acquiring second characteristic data of the target image, and determining second quality evaluation data of the target image according to the second characteristic data.
In this step, the second quality evaluation data may correspond to the first quality evaluation data, and the second feature data of the target image is input into the same quality evaluation model to obtain the second quality evaluation data of the target image.
And outputting first quality evaluation data and second quality evaluation data respectively aiming at the first characteristic data and the second characteristic data through a quality evaluation model, and comparing the first quality evaluation data and the second quality evaluation data. When the method is realized, corresponding weights can be set for different characteristic data in the comparison process to obtain a quality evaluation value of the target image, and the high-quality image can be judged when the quality evaluation value is greater than a set threshold value.
In another implementation, after setting corresponding weights for different feature data, the quality evaluation values of the acquired reference image and the target image may be determined separately, and then the quality evaluation values of the two may be compared, and if the quality evaluation value of the target image is greater than the quality evaluation value of the reference image or less than the quality evaluation value of the reference image, the difference is within a set error tolerance range, and the target image may also be determined as a high-quality image.
In one embodiment, step 130 includes the steps of:
calculating the similarity of the second quality evaluation data and the first quality evaluation data as a comparison result;
and when the similarity is greater than a preset threshold value, judging that the target image is a high-quality image.
In one manner in which the second quality assessment data is compared with the first quality assessment data, the similarity of the second quality assessment data to the first quality assessment data may be calculated as a result of the comparison. After the similarity calculation is performed, the greater the similarity is, the closer the quality of the target image is to the reference picture, that is, to the high-quality picture, and therefore, when the similarity is greater than the preset threshold, the target picture can be determined to be the high-quality picture.
When the similarity is calculated, the second quality evaluation data and the first quality evaluation data can be converted into vector data through cosine similarity, a cosine value of an included angle between two vectors in a vector space is used as a measure for measuring the difference of the two quality evaluation data, and the closer the value is to 1, the closer the angle is to 0 degrees, namely the more similar the two vectors are.
In one embodiment, the first quality assessment data of the reference image includes first gradient data and first noise data, the second quality assessment data of the target image includes second gradient data and second noise data, and step 130 may further include:
when the second noise data is smaller than the first noise data and the second gradient data is larger than the first gradient data, the target image is determined to be a high-quality image.
In this step, the first quality assessment data includes first gradient data and first noise data, and the second quality assessment data of the target image includes second gradient data and second noise data. In comparing the second quality evaluation data with the first quality evaluation data, the first noise data may also be compared with the second noise data, and if the second noise data is smaller than the first noise data and the second gradient data is larger than the first gradient data, the target image may be determined to be a high quality image.
In one implementation, a pre-determination may be performed before the comparison of the first noise data with the second noise data and the first gradient data with the second gradient data. The pre-determination may utilize a first pixel characteristic of the reference image and a second pixel characteristic of the target image for comparison. The pixel characteristics may include any one or any combination of the following parameters: original picture size, original color matrix or grayscale matrix, transformed color matrix or grayscale matrix, picture brightness distribution information, picture special effect statistical parameters, and original picture format and embedded information. When the first pixel feature is compared with the second pixel feature, the comparison can be completed through the histogram of oriented gradients feature, and the specific steps are as follows:
graying the target image and the reference image, wherein the grayed data of the image can rapidly judge the difference between the reference image and the target image;
the contrast of the normalized conditioning image of the color space of the target image and the reference image is stopped, the influence formed by the shadow and illumination change of the image part is reduced, and meanwhile, the interference of noise can be restrained;
respectively calculating the gradient of each pixel in the reference image and the target image, wherein the gradient of each pixel comprises the size and the direction, capturing contour information, and further weakening the interference of illumination;
dividing the reference image and the target image into a plurality of cell units, such as 8-by-8 pixels/cell unit;
counting the gradient histogram of each cell to form a feature descriptor of each cell;
forming units of the same image into one or more pixel blocks;
respectively determining the gradient histogram feature descriptors of the pixel blocks according to the gradient histograms of all units in the same pixel block;
and connecting the gradient histogram feature descriptors of all pixel blocks of the same image in series, and respectively determining the gradient histogram feature descriptors of the reference image and the target image.
And comparing the gradient histogram feature descriptors of the target image and the reference image, if the gradient histogram feature descriptor of the target image is larger than that of the reference image, judging that the target image is a passing image, the passing image is used for further comparing the first noise data with the second noise data, and judging whether the image is a high-quality image or not by comparing the first gradient data with the second gradient data. If the gradient histogram feature descriptor of the target image is smaller than that of the reference image, the target image is a failing image, and the failing image can be directly judged as a low-quality image without further judgment.
In one embodiment, the method may further include:
and if the target image is a high-quality image, adding the target image into a preset high-quality image database, wherein the high-quality image database is used for providing a reference image or optimizing a quality evaluation model.
In this step, when the target image is a high-quality image, the target image may be used for an application scene, and in addition, the target image may be added to a preset high-quality image database, and becomes a candidate reference image when a reference image is randomly selected from the high-quality image database next time. In addition, the method can be used for optimizing the quality evaluation model, and provides a high-quality data base for downstream data processing, so that the quality evaluation model becomes a quality evaluation model with higher high-quality image judgment precision.
In one embodiment, the method may further include:
and if the target image is judged to be the low-quality image, discarding the target image or storing the target image into a low-quality image database.
When the target image is a low-quality picture, different operations such as discarding, deleting or storing the low-quality picture into a low-quality picture database can be performed on the low-quality picture according to the corresponding application scene.
In the embodiment of the invention, the image quality evaluation which is easy to implement, can be performed quickly and ensures the evaluation precision is realized by acquiring the first characteristic data of the reference image, determining the first quality evaluation data of the reference image according to the first characteristic data, acquiring the second characteristic data of the target image according to the second characteristic data, comparing the second quality evaluation data with the first quality evaluation data, and determining whether the target image is a high-quality image according to the comparison result.
Example two
Fig. 2 is an image quality evaluation apparatus according to a second embodiment of the present invention, the apparatus including:
a first quality evaluation data determining module 210, configured to obtain first feature data of a reference image, and determine first quality evaluation data of the reference image according to the first feature data, where the reference image is an image meeting a preset high-quality image standard;
a second quality evaluation data module 220, configured to obtain second feature data of a target image, and determine second quality evaluation data of the target image according to the second feature data;
a high-quality image determining module 230, configured to compare the second quality evaluation data with the first quality evaluation data, and determine whether the target image is a high-quality image according to a result of the comparison.
In one embodiment, the first quality assessment data determination module 210 includes:
and the first quality evaluation data output submodule is used for inputting the first characteristic data into a pre-generated quality evaluation model, processing the first characteristic data by the quality evaluation model and outputting first quality evaluation data.
In one embodiment, the first feature data comprises first gradient feature data and first noise feature data, the quality assessment model comprises a gradient assessment submodel and a noise assessment submodel;
the first quality assessment data output sub-module includes:
the noise intensity data output unit is used for inputting the first noise characteristic data into the noise evaluation submodel and obtaining the noise intensity data output by the noise evaluation submodel;
and the first quality evaluation data output unit is used for inputting the noise intensity data and the first gradient characteristic data into the gradient evaluation submodel and obtaining first quality evaluation data output by the gradient evaluation submodel.
In one embodiment, the high quality image determination module 230 includes:
a similarity operator module for calculating a similarity of the second quality evaluation data and the first quality evaluation data as the comparison result;
and the high-quality image judgment sub-module is used for judging that the target image is a high-quality image when the similarity is greater than a preset threshold value.
In an embodiment, the first quality assessment data of the reference image includes first gradient data and first noise data, the second quality assessment data of the target image includes second gradient data and second noise data, and the high-quality image determination module 230 is further configured to:
when the second noise data is smaller than the first noise data and the second gradient data is larger than the first gradient data, determining that the target image is a high-quality image.
In one embodiment, further comprising:
and the target image forwarding module is used for adding the target image into a preset high-quality image database if the target image is a high-quality image, wherein the high-quality image database is used for providing the reference image or optimizing the quality evaluation model.
In one embodiment, further comprising:
and the low-quality image forwarding module is used for discarding the target image or storing the target image into a low-quality image database if the target image is judged to be the low-quality image.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application, as shown in fig. 3, the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of the processors 310 in the electronic device may be one or more, and one processor 310 is taken as an example in fig. 3; the processor 310, the memory 320, the input device 330 and the output device 340 in the electronic apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 3.
The memory device 320 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 320 may further include memory located remotely from the processor 310, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 330 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of an electronic apparatus. The output device 340 may include a display device such as a display screen.
Example four
A storage medium containing computer-executable instructions for performing the method in the method embodiments when executed by a computer processor is also provided.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods described in the embodiments of the present application.
It should be noted that, in the embodiment of the foregoing apparatus, the modules and modules included in the apparatus are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional modules are only used for distinguishing one functional module from another, and are not used for limiting the protection scope of the application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. An image quality evaluation method, characterized in that the method comprises:
acquiring first characteristic data of a reference image, and determining first quality evaluation data of the reference image according to the first characteristic data, wherein the reference image is an image meeting a preset high-quality image standard;
acquiring second characteristic data of a target image, and determining second quality evaluation data of the target image according to the second characteristic data;
comparing the second quality assessment data with the first quality assessment data, and determining whether the target image is a high quality image according to a result of the comparison.
2. The method of claim 1, wherein determining first quality assessment data for the reference image from the first feature data comprises:
and inputting the first characteristic data into a pre-generated quality evaluation model, processing the first characteristic data by the quality evaluation model, and outputting first quality evaluation data.
3. The method of claim 2, wherein the first feature data comprises first gradient feature data and first noise feature data, and the quality assessment model comprises a gradient assessment submodel and a noise assessment submodel;
the processing, by the quality assessment model, the first feature data comprises:
inputting the first noise characteristic data into the noise evaluation submodel, and obtaining noise intensity data output by the noise evaluation submodel;
and inputting the noise intensity data and the first gradient characteristic data into the gradient evaluation submodel, and obtaining first quality evaluation data output by the gradient evaluation submodel.
4. The method of claim 3, wherein comparing the second quality assessment data with the first quality assessment data and determining whether the target image is a high quality image based on a result of the comparison comprises:
calculating a similarity of the second quality assessment data and the first quality assessment data as the comparison result;
and when the similarity is larger than a preset threshold value, judging that the target image is a high-quality image.
5. The method of claim 4, further comprising:
and if the target image is a high-quality image, adding the target image into a preset high-quality image database, wherein the high-quality image database is used for providing the reference image or optimizing the quality evaluation model.
6. The method of claim 5, wherein the first quality assessment data for the reference image comprises first gradient data and first noise data, and the second quality assessment data for the target image comprises second gradient data and second noise data;
the comparing the second quality evaluation data with the first quality evaluation data and determining whether the target image is a high quality image according to a result of the comparing, further comprising:
when the second noise data is smaller than the first noise data and the second gradient data is larger than the first gradient data, determining that the target image is a high-quality image.
7. The method of claim 6, further comprising:
and if the target image is judged to be a low-quality image, discarding the target image or storing the target image into a low-quality image database.
8. An image quality evaluation apparatus characterized by comprising:
the first quality evaluation data determination module is used for acquiring first characteristic data of a reference image and determining first quality evaluation data of the reference image according to the first characteristic data, wherein the reference image is an image meeting a preset high-quality image standard;
the second quality evaluation data module is used for acquiring second characteristic data of a target image and determining second quality evaluation data of the target image according to the second characteristic data;
and the high-quality image judging module is used for comparing the second quality evaluation data with the first quality evaluation data and determining whether the target image is a high-quality image according to the comparison result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111417.1A CN113870210A (en) | 2021-09-18 | 2021-09-18 | Image quality evaluation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111417.1A CN113870210A (en) | 2021-09-18 | 2021-09-18 | Image quality evaluation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870210A true CN113870210A (en) | 2021-12-31 |
Family
ID=78993265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111111417.1A Pending CN113870210A (en) | 2021-09-18 | 2021-09-18 | Image quality evaluation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870210A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118037602A (en) * | 2024-04-15 | 2024-05-14 | 深圳市捷易科技有限公司 | Image quality optimization method, device, electronic equipment, medium and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090116713A1 (en) * | 2007-10-18 | 2009-05-07 | Michelle Xiao-Hong Yan | Method and system for human vision model guided medical image quality assessment |
| CN101996406A (en) * | 2010-11-03 | 2011-03-30 | 中国科学院光电技术研究所 | No-reference structure definition image quality evaluation method |
| CN107610093A (en) * | 2017-08-02 | 2018-01-19 | 西安理工大学 | Full-reference image quality evaluating method based on similarity feature fusion |
| CN108765407A (en) * | 2018-05-31 | 2018-11-06 | 上海依图网络科技有限公司 | A kind of portrait picture quality determination method and device |
| CN111798421A (en) * | 2020-06-29 | 2020-10-20 | 浙江同善人工智能技术有限公司 | Image quality judging method, device and storage medium |
-
2021
- 2021-09-18 CN CN202111111417.1A patent/CN113870210A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090116713A1 (en) * | 2007-10-18 | 2009-05-07 | Michelle Xiao-Hong Yan | Method and system for human vision model guided medical image quality assessment |
| CN101996406A (en) * | 2010-11-03 | 2011-03-30 | 中国科学院光电技术研究所 | No-reference structure definition image quality evaluation method |
| CN107610093A (en) * | 2017-08-02 | 2018-01-19 | 西安理工大学 | Full-reference image quality evaluating method based on similarity feature fusion |
| CN108765407A (en) * | 2018-05-31 | 2018-11-06 | 上海依图网络科技有限公司 | A kind of portrait picture quality determination method and device |
| CN111798421A (en) * | 2020-06-29 | 2020-10-20 | 浙江同善人工智能技术有限公司 | Image quality judging method, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118037602A (en) * | 2024-04-15 | 2024-05-14 | 深圳市捷易科技有限公司 | Image quality optimization method, device, electronic equipment, medium and program product |
| CN118037602B (en) * | 2024-04-15 | 2024-07-23 | 深圳市捷易科技有限公司 | Image quality optimization method, device, electronic equipment, medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111028213B (en) | Image defect detection method, device, electronic equipment and storage medium | |
| JP7051267B2 (en) | Image detection methods, equipment, electronic equipment, storage media, and programs | |
| CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
| US20160335523A1 (en) | Method and apparatus for detecting incorrect associations between keypoints of a first image and keypoints of a second image | |
| CN107272899B (en) | VR (virtual reality) interaction method and device based on dynamic gestures and electronic equipment | |
| CN112396050B (en) | Image processing method, device and storage medium | |
| CN112381092B (en) | Tracking method, tracking device and computer readable storage medium | |
| CN112633221A (en) | Face direction detection method and related device | |
| CN114331946A (en) | Image data processing method, device and medium | |
| CN116129195A (en) | Image quality evaluation device, image quality evaluation method, electronic device, and storage medium | |
| CN113870210A (en) | Image quality evaluation method, device, equipment and storage medium | |
| CN112883762A (en) | Living body detection method, device, system and storage medium | |
| CN115690747B (en) | Vehicle blind area detection model test method and device, electronic equipment and storage medium | |
| CN116597246A (en) | Model training method, target detection method, electronic device and storage medium | |
| CN108805883B (en) | Image segmentation method, image segmentation device and electronic equipment | |
| CN113012030A (en) | Image splicing method, device and equipment | |
| CN113315995B (en) | Method and device for improving video quality, readable storage medium and electronic equipment | |
| CN115345895A (en) | Image segmentation method and device for visual detection, computer equipment and medium | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN113822871A (en) | Target detection method and device based on dynamic detection head, storage medium and equipment | |
| CN108133210B (en) | Image format identification method and device | |
| CN116071625B (en) | Training method of deep learning model, target detection method and device | |
| CN111325670A (en) | Data enhancement method and device and electronic equipment | |
| CN114266749B (en) | TridentNet-based image processing method |
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 |