CN111260623A - Picture evaluation method, device, equipment and storage medium - Google Patents
Picture evaluation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111260623A CN111260623A CN202010038652.XA CN202010038652A CN111260623A CN 111260623 A CN111260623 A CN 111260623A CN 202010038652 A CN202010038652 A CN 202010038652A CN 111260623 A CN111260623 A CN 111260623A
- Authority
- CN
- China
- Prior art keywords
- picture
- evaluated
- similarity
- standard
- pixel
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 106
- 238000012937 correction Methods 0.000 claims abstract description 80
- 239000011159 matrix material Substances 0.000 claims description 40
- 238000000034 method Methods 0.000 claims description 34
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000003702 image correction Methods 0.000 claims description 10
- 238000012015 optical character recognition Methods 0.000 claims description 7
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 19
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000012550 audit Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000003811 curling process Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002788 crimping Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
- 239000002699 waste material Substances 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
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application discloses a picture evaluation method, a device, equipment and a storage medium, which relate to the technical field of artificial intelligence and comprise the following steps: acquiring a picture to be evaluated; carrying out deformation correction on the picture to be evaluated through a picture correction model to obtain a corrected picture; and calculating the similarity between the corrected picture and each standard picture in a standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity. By adopting the scheme, the technical problem that the auditing result of the picture cannot be quickly and efficiently obtained in the prior art can be solved.
Description
Technical Field
The embodiment of the application relates to the technical field of artificial intelligence, in particular to a picture evaluation method, a device, equipment and a storage medium.
Background
Nowadays, intelligent technology has been widely applied to various fields of people's life. For example, in an indoor shopping scenario, a user may determine where the smart device is located through application software with a positioning function. For example, the smart watch determines its location through a positioning function, displays the location, and transmits the location to the associated smart phone, so that the user of the smart phone can confirm the location of the smart watch. In order to enable the user to accurately and comprehensively determine the position information, store pictures of shops at the position can be synchronously displayed in the smart watch or the smart phone as display information. In the prior art, a picture as display information usually needs to be manually taken and reviewed to display a picture with high quality to a user. However, in order to ensure the success rate of the positioning result, a large number of pictures are stored in the background server of the application software with the positioning function, which not only needs to invest a large amount of human resources, but also has a long auditing period. Meanwhile, the manual review has subjectivity, and the accuracy of the picture review result is influenced.
In conclusion, how to obtain the auditing result of the picture quickly and efficiently becomes a problem which needs to be solved urgently.
Disclosure of Invention
The application provides a picture evaluation method, a device, equipment and a storage medium, which aim to solve the technical problem that the auditing result of a picture cannot be obtained quickly and efficiently in the prior art.
In a first aspect, an embodiment of the present application provides an image evaluation method, including:
acquiring a picture to be evaluated;
carrying out deformation correction on the picture to be evaluated through a picture correction model to obtain a corrected picture;
and calculating the similarity between the corrected picture and each standard picture in a standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity.
Further, the performing deformation correction on the picture to be evaluated through the picture correction model to obtain a corrected picture includes:
inputting the picture to be evaluated into a picture correction model;
indicating the picture correction model to fold and/or curl each pixel point in the picture to be evaluated so as to obtain at least one distorted picture;
indicating the picture correction model to determine a pixel matrix of a distorted picture according to the picture to be evaluated and the distorted picture, wherein the pixel matrix comprises a gray value of each pixel point in the distorted picture, a moving direction and a moving distance of each pixel point on an x axis, and a moving direction and a moving distance of each pixel point on a y axis;
and instructing the picture correction model to input the distorted picture containing the pixel matrix into a neural network containing the hole convolution so as to obtain a corrected picture.
Further, after the instructing the picture modification model to determine the pixel matrix of the warped picture according to the picture to be evaluated and the warped picture, the method further includes:
instructing the picture correction model to determine blank pixel points in the warped picture based on the pixel matrix;
and indicating the picture correction model to perform neighbor interpolation based on neighbor pixel points of the blank pixel points so as to obtain gray values of the blank pixel points, and updating the pixel matrix.
Further, the calculating the similarity between the corrected picture and each standard picture in the standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity includes:
acquiring a pixel area containing text information in the corrected picture, wherein the text information is obtained by utilizing optical character recognition;
calculating the similarity between the pixel area and each standard picture in a standard picture library;
and selecting the maximum similarity from the calculated similarities, and taking the maximum similarity as an evaluation score of the picture to be evaluated.
Further, the calculating the similarity between the pixel region and each standard picture in a standard picture library includes:
obtaining the local similarity between the pixel region and a standard picture in a standard picture library by using a structural similarity algorithm;
and calculating the average similarity of the local similarities by combining the resolution dimensions of the picture to be evaluated so as to obtain the similarity between the pixel region and the corresponding standard picture.
Further, the calculating an average similarity of the local similarities by combining the resolution dimensions of the picture to be evaluated includes:
confirming the resolution dimension of a sub-pixel region corresponding to the local similarity in the picture to be evaluated;
searching the weight corresponding to the resolution dimension;
and calculating the average similarity according to each local similarity and the corresponding weight.
Further, after the calculating the similarity between the corrected picture and each standard picture in the standard picture library and obtaining the evaluation score of the picture to be evaluated according to the similarity, the method further includes:
if the evaluation score is larger than or equal to a score threshold value, confirming the picture to be evaluated as an effective picture;
and uploading the effective pictures and the text information contained in the effective pictures to a database so that a user can conveniently check the effective pictures and the text information through the database.
In a second aspect, an embodiment of the present application further provides an image evaluation device, including:
the image acquisition module is used for acquiring an image to be evaluated;
the image correction module is used for carrying out deformation correction on the image to be evaluated through an image correction model so as to obtain a corrected image;
and the score calculating module is used for calculating the similarity between the corrected picture and each standard picture in the standard picture library and obtaining the evaluation score of the picture to be evaluated according to the similarity.
In a third aspect, an embodiment of the present application further provides a picture evaluation device, including:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the picture evaluation method according to the first aspect.
In a fourth aspect, embodiments of the present application further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the picture evaluation method according to the first aspect.
According to the picture evaluation method, the device, the equipment and the storage medium, through the technical means that the picture to be evaluated is obtained, the picture to be evaluated is subjected to deformation correction by using the picture correction model to obtain the corrected picture, then the similarity between the corrected picture and each standard picture in the standard picture library is calculated, and the evaluation score of the picture to be evaluated is further obtained, the technical problem that the picture audit result cannot be quickly and efficiently obtained in the prior art can be solved, the picture is automatically evaluated by using the picture correction and the picture similarity calculation, a large amount of manpower resources can be saved, the audit period is shortened, the subjectivity of manual audit of the picture can be prevented, and the picture audit quality is ensured.
Drawings
Fig. 1 is a flowchart of a picture evaluation method according to an embodiment of the present application;
fig. 2 is a flowchart of a picture evaluation method according to an embodiment of the present application;
FIG. 3 is a schematic representation of a folding and/or crimping process provided in accordance with an embodiment of the present application;
fig. 4 is a schematic structural diagram of a picture evaluation apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a picture evaluation device according to an 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 for purposes of illustration and not limitation. 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.
The picture evaluation method provided in the embodiments may be executed by a picture evaluation apparatus, which may be implemented in software and/or hardware and integrated in a picture evaluation device. The image evaluation device can be an intelligent device with data processing and analyzing capabilities, such as a tablet computer and a desktop computer.
Fig. 1 is a flowchart of a picture evaluation method according to an embodiment of the present application. Referring to fig. 1, the picture evaluation method specifically includes:
and step 110, obtaining a picture to be evaluated.
The picture to be evaluated is a picture which is shot manually and needs to be evaluated by picture evaluation equipment, and the content of the picture to be evaluated can be set according to the actual situation. For example, in a shop search scene, the picture to be evaluated may be a shop picture; under a scene search scene, the picture to be evaluated can be a scene picture; under the travel note display scene, the pictures to be evaluated can be scene pictures, site pictures and the like. In the embodiment, the picture to be evaluated is taken as a shop picture as an example, and at this time, the content such as the name of the shop and/or the logo is displayed in the picture to be evaluated. In the embodiment, the description will be given by taking the example that the name and logo of the shop are displayed in the picture to be evaluated.
Further, the embodiment of the method for acquiring the picture to be evaluated is not limited. For example, the picture evaluation apparatus is provided with an image capture device (such as a camera), and obtains a picture to be evaluated through the image capture device. For another example, the picture evaluation device may perform data communication with other devices (such as a mobile phone, a camera, a tablet computer, etc.) configured with the image acquisition apparatus to acquire the picture to be evaluated. For another example, the other device configured with the image capturing device uploads the picture to be evaluated to a specific storage location (e.g., a cloud disk) of the internet, and the picture evaluating device may obtain the picture to be evaluated through the specific storage location of the internet.
And 120, carrying out deformation correction on the picture to be evaluated through the picture correction model to obtain a corrected picture.
Considering that when a user shoots a picture to be evaluated, the shot picture is deformed to a certain extent compared with the actual content due to the limitation of the shooting angle and the shooting level. For example, the store name of the store is usually located above the store entrance, when the user takes a picture of the store, the image capturing device needs to be tilted to include the complete store name, and at this time, the picture to be evaluated taken by the image capturing device has an effect of looking up, that is, the store image in the picture to be evaluated has an effect of being wider at the top and narrower at the bottom than the actual store. Therefore, in order to effectively evaluate the picture to be evaluated, the deformation in the picture to be evaluated needs to be corrected first. The size of the corrected picture is equal to that of the picture to be evaluated.
Specifically, the deformation correction may be implemented by a picture correction model. The embodiment of the specific construction method of the image correction model is not limited. For example, the distortion transformation as one of the deformation corrections may be implemented by at least one operation of folding, curling, moving a pixel point, and the like, at this time, a calculation rule corresponding to each operation may be set in the picture correction model, for example, a folding formula, a curling formula, and a moving formula of the pixel point are set in the picture correction model, and a formula parameter may be modified in combination with the picture to be evaluated, so as to implement the deformation correction through the above formula. For another example, a large number of known pictures to be evaluated and corrected pictures are trained by using a neural network in an artificial intelligence mode to obtain a picture correction model. For another example, the image correction model is obtained by combining the calculation rule and the neural network.
Optionally, in the deformation correction process, blank pixel points may appear in the corrected picture, and at this time, in order to ensure the quality of the corrected picture, a neighbor interpolation method may be adopted to assign pixel values to the blank pixel points.
And step 130, calculating the similarity between the corrected picture and each standard picture in a standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity.
In one embodiment, the standard picture library stores a plurality of standard pictures. The names and/or the corresponding logos of the shops appear in each standard picture, and the names and/or the logos in the standard pictures are in a regular pattern. It can be understood that if the names and/or the corresponding logos of a plurality of stores are the same, one standard picture can be shared. Furthermore, the collection range of the standard pictures in the standard picture library can be set according to the actual situation. For example, the names and/or corresponding logos of stores in provinces are collected by taking the province as a unit, so as to obtain standard pictures of the stores and form a standard picture library. For another example, taking the country as a unit, the names and/or corresponding logos of various shops throughout the country are collected to obtain standard pictures of the various shops, and the standard pictures form a standard picture library. It should be noted that, the embodiment of the standard image acquisition method is not limited. In the embodiment, the description is made by taking an example that a standard picture includes a name and a logo.
Specifically, the higher the similarity between the name and logo of the store in the corrected picture and a standard picture is, the clearer and more accurate the name and logo of the store in the corrected picture are, and correspondingly, the better the quality of the picture to be evaluated is and the higher the evaluation score is. On the contrary, the lower the similarity between the corrected picture and the standard picture is, the more inaccurate the shop name and logo in the corrected picture is, and correspondingly, the lower the quality of the picture to be evaluated is, the lower the evaluation score is. Therefore, in the embodiment, the evaluation score of the picture to be evaluated is obtained by calculating the similarity between the corrected picture and each standard picture in the standard picture library.
For example, the embodiment of the similarity calculation method between the corrected picture and the standard picture is not limited. For example, the similarity between the corrected picture and the standard picture is calculated using Structural Similarity Index (SSIM). As another example, the similarity between the corrected picture and the standard picture is calculated based on the cosine similarity. Furthermore, each standard picture has a similarity obtained by calculation with the corrected picture, and the higher the similarity is, the more similar the corrected picture and the corresponding standard picture is, the more accurate the corrected picture is, therefore, the maximum similarity among all the similarities obtained by calculation is selected as the evaluation score of the picture to be evaluated.
Optionally, after the evaluation score of the picture to be evaluated is obtained, the score to be evaluated may be compared with a preset score threshold. Wherein, the score threshold value can be set according to the actual situation. When the evaluation score is greater than or equal to the score threshold, the quality of the picture to be evaluated is better, and the picture to be evaluated can be considered to be approved and can be used subsequently. When the evaluation score is smaller than the score threshold, the quality of the score to be evaluated is poor, the picture to be evaluated can be considered to be not approved, and at the moment, the picture cannot be used subsequently.
According to the technical means, the problem that in the prior art, the checking result of the picture cannot be obtained quickly and efficiently is solved, automatic picture evaluation is achieved by utilizing the picture correction and the picture similarity calculation, a large amount of manpower resources can be saved, the checking period can be shortened, the subjectivity of manual picture checking can be prevented, and the quality of picture checking is guaranteed.
Fig. 2 is a flowchart of a picture evaluation method according to an embodiment of the present application. The picture evaluation method provided in this embodiment is embodied on the basis of the above-described embodiments. In this embodiment, a description is given by taking an example in which a picture to be evaluated is used for displaying to a user. Specifically, referring to fig. 2, the picture evaluation method provided in this embodiment includes:
Specifically, the picture to be evaluated is used as the input of the picture correction model. It can be understood that the picture to be evaluated input into the picture correction model is an uncompressed distortion-free image without other processing.
And 203, indicating the picture correction model to fold and/or curl each pixel point in the picture to be evaluated so as to obtain at least one distorted picture.
In the embodiment, the warping is divided into folding and curling, that is, the warped picture may be a picture obtained by folding and/or curling the picture to be evaluated, the number of the warped picture is at least one, and the specific number of the warped picture may be set according to actual situations.
Specifically, when the image correction model folds the image to be evaluated, a folding formula can be used:
wherein, w1To the extent of folding, α1Being a hyper-parameter in the folding process, d1Is a harmonic parameter in the folding process. d1It can be set according to actual conditions, and can refer to historical empirical data, and optionally, through adjustment α1Different w can be obtained1And further obtain the distorted pictures with different folding degrees. When the image to be evaluated is curled, a curling formula can be utilized:
wherein, w2To a degree of curling α2A hyper-parameter in the crimping process, d2Is a harmonic parameter in the curling process. d2It can be set according to actual conditions, and can refer to historical empirical data, and optionally, through adjustment α2Different w can be obtained2In practice, the folding and/or curling process may be used in combination with the actual situation to obtain a distorted image, it being understood that when both folding and curling processes are used, α1And α2The same parameters or different parameters may be set.
Optionally, when obtaining the distorted picture, the picture to be evaluated is firstly converted into a P-V thermodynamic diagram, and then the distorted picture is obtained through α1And/or α2Obtaining corresponding w by using folding formula and curling formula1And/or w2. Then based on w1And/or w2And warping the P-V thermodynamic diagram, and mapping the gray value of each pixel point in the picture to be evaluated to the corresponding pixel point in the warped P-V thermodynamic diagram to obtain the corresponding warped picture. It can be understood that, at this time, the warped picture is a grayscale image.
And 204, indicating the picture correction model to determine a pixel matrix of the distorted picture according to the picture to be evaluated and the distorted picture, wherein the pixel matrix comprises the gray value of each pixel point in the distorted picture, the moving direction and the moving distance of each pixel point on the x axis, and the moving direction and the moving distance of each pixel point on the y axis.
In the embodiment, the label of each pixel point in the distorted picture is embodied through the pixel matrix. The pixel matrix can be obtained by comparing the picture to be evaluated with the distorted picture, and specifically, the picture correction model finds pixel points corresponding to the pixel points in the distorted picture in the picture to be evaluated, so as to obtain the pixel matrix. The pixel matrix is a three-dimensional matrix and is used for storing the gray value of each pixel point in the distorted picture, the moving direction and the moving distance of each pixel point on the x axis, and the moving direction and the moving distance of each pixel point on the y axis. The moving direction and the moving distance respectively refer to the direction and the pixel distance that pixel points in the distorted picture are mapped into the picture to be evaluated and should move. At this time, the pixel matrix may include the gray value, the moving direction, and the moving distance of all the pixel points in the distorted picture, that is, each pixel point in the distorted picture may find a corresponding label in the pixel matrix.
Specifically, the distorted picture and the pixel matrix are identified through a neural network, and then a corrected picture is output. At this time, the neural network can convert the pixel-level classification problem into the pixel-level regression problem by utilizing semantic learning, and further realize the correction of the picture to be evaluated to obtain the corrected picture.
It is understood that the specific structure of the neural network can be set according to actual conditions. In one embodiment, a neural network is employed that includes a hole convolution. The hole Convolution (scaled Convolution) is to inject holes into a standard Convolution kernel to increase the reception field (reconstruction field) and reduce the distortion of the corrected picture to some extent. At the moment, each pixel point can see the information of more peripheral pixel points, so that a more accurate result is obtained. For example, when the hole convolution is 1, i.e., 1-scaled conv, the convolutional layer operates as a normal convolutional layer. When the cavity convolution is 2, i.e., 2-scaled conv, if the convolution kernel size is 3 × 3, the receptive field of the convolution layer can reach 7 × 7, and at this time, the size of the convolution kernel and the size of the receptive field have an exponential relationship. Therefore, the receptive field can be increased under the condition of not performing pooling loss information, the number of parameters of the neural network can not be increased, the occurrence of the overfitting phenomenon is reduced, and the training speed is accelerated. Optionally, the neural network including the hole convolution may be a multi-scale U-net network, and it may include a parallel network and a serial network, in which case, both the parallel network and the serial network include the hole convolution.
It is understood that the above-mentioned picture correction model can be obtained by training. That is, a large amount of training data is selected in advance, wherein an original picture taken by a user and a corresponding corrected picture are used as a set of training data. Then, the picture correction model is trained based on a large amount of training data to adjust parameters (such as hyper-parameters, number of void volumes, etc.) involved in the picture correction model. After the model is trained stably, a certain amount of verification data can be collected, wherein an original picture shot by a user and a corresponding corrected picture are used as a group of verification data. It should be noted that the validation data and the training data are different, for example, a large amount of data is collected, 80% of which is used as training data and 20% of which is used as validation data. And then, verifying the picture correction model based on the verification data to determine the correction effect of the picture correction model. When the picture correction model passes the verification, the picture correction model can be used for showing that the correction result of the picture correction model is stable. In this embodiment, the verified picture correction model may be directly applied to obtain the corrected picture. It should be noted that, when the image correction model is trained and verified, the processing procedure of the image correction model is similar to the processing procedure when the image correction model is applied mentioned in steps 203 to 205, except that the parameters in the application procedure are fixed, and the parameters in the training procedure need to be adjusted.
It can be understood that the picture correction model can also be implemented in other manners, such as adopting deep lab-CRF as the rear end of the picture partition, thereby ensuring the prediction accuracy of the picture semantic partition.
And step 206, acquiring a pixel area containing text information in the corrected picture, wherein the text information is obtained by optical character recognition.
Optical Character Recognition (OCR) refers to a process of determining the shape of a Character in an image by detecting dark and light patterns, and then translating the shape into a computer text by a Character Recognition method. In an embodiment, by recognizing the corrected picture through OCR, text information contained in the corrected picture and a pixel area of the text information in the corrected picture can be determined. The text information may be information obtained by identifying a text included in the corrected picture, and the text information may include contents such as characters, numbers, and characters. For example, the picture to be evaluated is a shop picture, and the text information may include the name of the shop, logo, and the like. The pixel region of the text information in the corrected picture refers to a region formed by pixel points for displaying the text information in the corrected picture. It is understood that a pixel region is a region that is smaller than or equal to the modified picture size.
And step 207, calculating the similarity between the pixel region and each standard picture in the standard picture library.
The name and the logo of the store obtained by shooting are contained in the pixel area, and the name and the logo of the standard are contained in the standard picture, so that the similarity between the corrected picture and the standard picture can be determined by calculating the similarity between the pixel area and the standard picture.
Specifically, a structural similarity calculation method may be used to calculate the similarity. At this time, the step specifically includes step 2071 to step 2072:
step 2071, obtaining the local similarity between the pixel region and the standard picture in the standard picture library by using a structural similarity algorithm.
Specifically, the SSIM obtains the similarity by comparing the brightness, contrast, and structure of the corrected picture and the standard picture. When performing SSIM calculation, a window of size N × N is taken, where N may be set according to actual conditions and is usually a positive integer. Then, the window is slid over the pixel region and the standard picture, respectively, to traverse the entire pixel region and the standard picture. The sliding amplitude of the window during sliding can be set according to actual conditions, for example, the sliding amplitude is 1, that is, the window slides one pixel point at a time. Further, since the window needs to slide for multiple times to traverse all the pixel regions and the standard picture, after the window slides once, the similarity between the sub-pixel region of the window in the pixel region and the region of the window in the standard picture needs to be calculated. That is, each time the window slides, a new local similarity is obtained, in other words, a plurality of local similarities can be obtained between the pixel region and a standard picture. It should be noted that, in a local similarity calculation process, the sub-pixel area of the window in the pixel area is the same as the pixel coordinate range of the area of the window in the standard picture. The local similarity of the pixel region and each standard picture can be calculated according to the method.
And 2072, calculating the average similarity of the local similarities by combining the resolution dimensions of the picture to be evaluated to obtain the similarity between the pixel region and the corresponding standard picture.
For example, for each local similarity obtained by calculating a standard picture and a pixel region, an average value of the local similarities is taken as the similarity between the standard picture and the pixel region, and at this time, the average value of the local similarities may be recorded as an MS-SSIM index. In consideration of the fact that in practical application, the resolutions of the pictures to be evaluated acquired by different image acquisition devices may be different, and different resolutions may affect the finally obtained evaluation score, therefore, in order to ensure the accuracy of the evaluation score, in the embodiment, when the similarity is calculated, a resolution dimension is added. Namely, the resolution of the current picture to be evaluated is considered when the similarity is calculated. At this time, the step specifically includes step 20721 to step 20723:
step 20721, determining the resolution dimension of the sub-pixel region corresponding to the local similarity in the picture to be evaluated.
Specifically, different resolution ranges are divided in advance, and each resolution range corresponds to one resolution dimension. The embodiment of the partition rule is not limited. In the step, the resolution corresponding to each sub-pixel region can be determined, and then the resolution range to which the resolution belongs can be determined, so that the resolution dimension corresponding to the resolution can be determined.
Step 20722, find the weight corresponding to the resolution dimension.
Specifically, weights corresponding to different resolution dimensions are preset, wherein the embodiment of the setting rule is not limited. The influence of different resolutions on the evaluation score can be balanced by the weights. In the embodiment, after the resolution dimension corresponding to each local similarity is determined, the weight corresponding to each local similarity is obtained according to the corresponding relation between the resolution dimension and the weight.
Step 20723, calculate the average similarity according to the local similarities and the corresponding weights.
Specifically, when the average similarity is calculated, the average similarity may be obtained in a weighted average manner by combining the weights, and the calculated average similarity is used as the similarity between the pixel region and the corresponding standard picture.
And 208, selecting the maximum similarity from the calculated similarities, and taking the maximum similarity as an evaluation score of the picture to be evaluated.
Specifically, the higher the similarity is, the more similar the corrected picture is to the corresponding standard picture, the more accurate the text information in the corrected picture is, and the higher the quality of the corresponding picture to be evaluated is. Therefore, in the embodiment, after the similarity between the corrected picture and each standard picture is calculated, the maximum similarity is selected from all the similarities. And then, taking the selected maximum similarity as an evaluation score of the picture to be evaluated.
It can be understood that, in practical application, an evaluation score model may be constructed, and at this time, after the correction picture is input to the evaluation score model, the evaluation score model may output the maximum similarity based on the processing procedure.
Specifically, the score threshold may be set according to an actual situation, and is used to divide the quality of the picture to be evaluated. When the evaluation score is greater than or equal to the score threshold, it indicates that the quality of the picture to be evaluated is good, and step 210 is executed, and when the evaluation score is less than the score threshold, it indicates that the quality of the picture to be evaluated is poor, and step 212 is executed. For example, the score threshold is set to 0.5, if the evaluation score is greater than or equal to 0.5, step 210 is executed, otherwise, step 212 is executed.
And step 210, confirming the picture to be evaluated as an effective picture.
Specifically, when the evaluation score is greater than or equal to the score threshold, the picture to be evaluated is determined as an effective picture, that is, the picture to be evaluated is determined to be approved for subsequent use.
In one embodiment, the effective picture (i.e., the picture to be evaluated) is uploaded to a database, where the database may be a database configured by the picture evaluation device itself, or a database configured in other devices or cloud storage, and a specific database form embodiment is not limited. Further, the user can view the data stored in the database by accessing the database.
Optionally, when the effective picture is uploaded to the database, text information (such as the name of a store and/or logo) in the effective picture is uploaded at the same time. It can be understood that other information can be uploaded synchronously in combination with the application scenario of the database, so that a user can conveniently view text information and effective pictures. For example, assuming that the effective picture is a shop picture, in a shop display scene, the effective picture and text information may be stored in the database, and at this time, the user may view the corresponding effective picture by inputting the text information. For another example, for an indoor positioning scene, the specific geographic position of the store is also stored in the database, and at this time, the database can determine the store position closest to the user by acquiring the position of the user, and then feed back the corresponding effective picture and text information, so that the user can conveniently check the effective picture and text information. It should be noted that, the accessing of the database by the user means that the user performs data communication with the device configured with the database through the used device, so as to access the database. Since the valid pictures are all the pictures which are approved, the user only can see the pictures with small deformation.
And step 212, confirming the picture to be evaluated as an invalid picture.
Specifically, when the evaluation score is smaller than the score threshold, the picture to be evaluated is determined to be an invalid picture, that is, a picture which cannot be audited is determined. At this time, the picture to be evaluated can be collected again and evaluated, and whether the picture to be evaluated passes the audit can be confirmed in a manual audit mode.
The method comprises the steps of obtaining a picture to be evaluated, obtaining a distorted picture of the picture to be evaluated through a picture correction model, then obtaining a pixel matrix of the distorted picture by comparing the picture to be evaluated with the distorted picture, namely adding a label to the distorted picture, then taking the distorted picture and the pixel matrix as input of a neural network containing cavity convolution to obtain a corrected picture, obtaining local similarity between a pixel region of text information in the corrected picture and a standard picture by utilizing a structural similarity algorithm, calculating average similarity of the local similarity by combining resolution dimensions of the picture to be evaluated, further obtaining similarity between the pixel region and the standard picture, taking the maximum similarity as an evaluation score of the picture to be evaluated after obtaining the similarity of all the standard pictures and the pixel region in a standard picture library, and then if the evaluation score is larger than or equal to a score threshold value, the picture to be evaluated is confirmed as an effective picture, the effective picture and the text information contained in the effective picture are uploaded to a database, so that a user can conveniently check the effective icon and the text information, the technical problem that the checking result of the picture cannot be obtained quickly and efficiently in the prior art is solved, the picture is automatically evaluated by utilizing picture correction and picture similarity calculation, a large amount of manpower resources can be saved, the checking period can be shortened, the subjectivity of manual checking of the picture can be prevented, and the quality of picture checking is ensured. Meanwhile, when the picture is corrected, labels are added to the distorted picture through the pixel matrix, the corrected picture can be obtained in a neural network mode, the mode has generalization, and the pixel level classification problem is converted into the pixel level regression problem. Meanwhile, the neural network comprises the cavity convolution, so that the receptive field can be increased, and the accuracy of a processing result is ensured. In addition, when similarity calculation is carried out, the influence of different resolutions on the similarity is considered, so that the similarity can be ensured to be more accurate, namely, the evaluation accuracy of the picture to be evaluated is improved. Furthermore, after the pictures are automatically evaluated, the effective pictures can be input into the database, so that the user can conveniently inquire the effective pictures, the database does not need to be manually input, and the waste of human resources can be further reduced.
It will be appreciated that after the folding and/or curling process, there may be some black spots or lines in the distorted picture. This is because there is a rounding operation when performing folding and/or curling, which may leave one column free between two or two columns of originally adjacent pixels, and further cause the pixels of these pixels in the distorted picture to be empty, i.e., appear as black dots or black lines. For example, fig. 3 is a schematic diagram before and after the folding and/or curling process according to an embodiment of the present application, referring to fig. 3, a region 21 is a pixel region in a picture to be evaluated, each square represents a pixel point, at this time, a pixel value of a first row of pixel points is a, a pixel value of a second row of pixel points is B, there is a rounding operation during the folding and/or curling transformation, at this time, the region 21 becomes a region 22, and as can be seen from fig. 3, the second row of pixel points is a blank pixel point, then, in the distorted picture, a black line is displayed at the position of the row of pixel points. At this time, in order to prevent the black dots or black lines from affecting the subsequent processing process, in an embodiment, after setting and indicating the picture correction model to perform folding and/or curling processing on each pixel point in the picture to be evaluated to obtain a pixel matrix, the method further includes:
and step 213, instructing the picture correction model to determine blank pixel points based on the pixel matrix.
Specifically, since the gray value of each pixel point in the distorted picture is recorded in the pixel matrix, at this time, a blank pixel point can be determined by checking each pixel value in the pixel matrix. Since the blank pixel is displayed as black, that is, the gray value is 0, the pixel with the gray value of 0 can be determined as the blank pixel.
And step 214, indicating the picture correction model to perform neighbor interpolation based on neighbor pixel points of the blank pixel points to obtain gray values of the blank pixel points, and updating the pixel matrix.
Specifically, a neighbor interpolation method is adopted to obtain the gray value of the blank pixel point. The gray value of the blank pixel point is obtained through the gray value of the adjacent pixel point of the blank pixel point, wherein the gray value determination mode can be set according to actual conditions, for example, the gray value of a certain adjacent pixel point is selected as the gray value of the blank pixel point. And if so, calculating the gray average value of the adjacent pixel points, and rounding to obtain the gray value of the blank pixel point. Or obtaining the gray value of the blank pixel point by adopting other modes. Then, the gray value of each blank pixel point in the pixel matrix can be updated. The updated pixel matrix is then input into the network model.
According to the mode of neighbor interpolation, blank pixel points in the distorted picture can be avoided, and the subsequent processing accuracy is further ensured. It can be understood that, besides the neighbor interpolation method, other methods may be used to repair the blank pixel, and the embodiment is not limited thereto.
Fig. 4 is a schematic structural diagram of an image evaluation device according to an embodiment of the present application. Referring to fig. 4, the picture evaluation apparatus provided in the present embodiment includes: a picture acquisition module 301, a picture modification module 302 and a score calculation module 303.
The image obtaining module 301 is configured to obtain an image to be evaluated; the picture correction module 302 is configured to perform deformation correction on the picture to be evaluated through a picture correction model to obtain a corrected picture; and the score calculating module 303 is configured to calculate similarity between the corrected picture and each standard picture in the standard picture library, and obtain an evaluation score of the picture to be evaluated according to the similarity.
According to the technical means, the picture to be evaluated is obtained, the picture to be evaluated is subjected to deformation correction by using the picture correction model to obtain the corrected picture, then the similarity between the corrected picture and each standard picture in the standard picture library is calculated, and the evaluation score of the picture to be evaluated is further obtained, so that the technical problem that the checking result of the picture cannot be obtained quickly and efficiently in the prior art can be solved, the picture is automatically evaluated by using the picture correction and the picture similarity calculation, a large amount of manpower resources can be saved, the checking period can be shortened, the subjectivity of manual checking of the picture can be prevented, and the quality of picture checking can be ensured.
On the basis of the above embodiment, the picture modification module 302 includes: the data input unit is used for inputting the picture to be evaluated to a picture correction model; the distorted picture obtaining unit is used for indicating the picture correction model to fold and/or curl each pixel point in the picture to be evaluated so as to obtain at least one distorted picture; the matrix determining unit is used for indicating the picture correction model to determine a pixel matrix of a distorted picture according to the picture to be evaluated and the distorted picture, wherein the pixel matrix comprises a gray value of each pixel point in the distorted picture, a moving direction and a moving distance of each pixel point on an x axis, and a moving direction and a moving distance of each pixel point on a y axis; and the corrected picture acquisition unit is used for indicating the picture correction model to input the distorted picture containing the pixel matrix into the neural network containing the hole convolution so as to obtain the corrected picture.
On the basis of the above embodiment, the method further includes: the blank pixel searching module is used for indicating the picture correction model to determine a pixel matrix of a distorted picture according to the picture to be evaluated and the distorted picture and then indicating the picture correction model to determine blank pixel points in the distorted picture based on the pixel matrix; and the neighbor interpolation module is used for indicating the picture correction model to carry out neighbor interpolation on the basis of neighbor pixel points of the blank pixel points so as to obtain the gray value of the blank pixel points and update the pixel matrix.
On the basis of the above embodiment, the score calculating module 303 includes: the area acquisition unit is used for acquiring a pixel area containing text information in the corrected picture, wherein the text information is obtained by optical character recognition; the similarity calculation unit is used for calculating the similarity between the pixel region and each standard picture in a standard picture library; and the score selection unit is used for selecting the maximum similarity from the calculated similarities and taking the maximum similarity as the evaluation score of the picture to be evaluated.
On the basis of the above embodiment, the similarity calculation unit includes: the local similarity calculation operator unit is used for obtaining the local similarity between the pixel region and the standard pictures in the standard picture library by using a structural similarity algorithm; and the average similarity calculation operator unit is used for calculating the average similarity of the local similarities by combining the resolution dimensions of the picture to be evaluated so as to obtain the similarity between the pixel region and the corresponding standard picture.
On the basis of the above embodiment, the average similarity degree operator unit includes: a resolution dimension determining grandchild unit, configured to determine a resolution dimension in which a sub-pixel region corresponding to the local similarity in the picture to be evaluated falls; the weight searching unit is used for searching the weight corresponding to the resolution dimension; and the computing unit is used for computing the average similarity according to each local similarity and the corresponding weight.
On the basis of the above embodiment, the method further includes: the score comparison module is used for calculating the similarity between the corrected picture and each standard picture in a standard picture library, obtaining the evaluation score of the picture to be evaluated according to the similarity, and determining the picture to be evaluated as an effective picture if the evaluation score is greater than or equal to a score threshold value; and the data uploading module is used for uploading the effective pictures and the text information contained in the effective pictures to a database so that a user can conveniently check the effective pictures and the text information through the database.
The picture evaluation device provided by the embodiment is included in the picture evaluation device, can be used for executing the picture evaluation method provided by any of the above embodiments, and has corresponding functions and beneficial effects.
It should be noted that, in the embodiment of the image evaluation apparatus, the included units and modules 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 units are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the application.
Fig. 5 is a schematic structural diagram of a picture evaluation device according to an embodiment of the present application. Specifically, as shown in fig. 5, the picture evaluation apparatus includes a processor 40, a memory 41, an input device 42, an output device 43, and a communication device 44; the number of the processors 40 in the picture evaluation device may be one or more, and one processor 40 is taken as an example in fig. 5; the processor 40, the memory 41, the input device 42, the output device 43, and the communication device 44 in the picture evaluation apparatus may be connected by a bus or other means, and fig. 5 illustrates an example of connection by a bus.
The memory 41, as a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules in the picture evaluation method in the embodiments of the present application (e.g., the picture acquisition module 301, the picture correction module 302, and the score calculation module 303 in the picture evaluation apparatus). The processor 40 executes various functional applications and data processing of the picture evaluation device by running software programs, instructions and modules stored in the memory 41, namely, implements the picture evaluation method provided by any of the above embodiments.
The memory 41 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 picture evaluation apparatus, and the like. Further, the memory 41 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, memory 41 may further include memory located remotely from processor 40, which may be connected to the picture evaluation device via 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 42 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the picture evaluation apparatus, and may also be through an image capture device (e.g., a camera), an audio capture device (e.g., a microphone), and the like. The output device 43 may include a display screen, a speaker, etc. The communication means 44 is used for data communication with other devices.
The picture evaluation device can be used for executing the picture evaluation method provided by any embodiment, and has corresponding functions and beneficial effects.
Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for picture evaluation, the method including:
acquiring a picture to be evaluated;
carrying out deformation correction on the picture to be evaluated through a picture correction model to obtain a corrected picture;
and calculating the similarity between the corrected picture and each standard picture in a standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity.
Of course, the storage medium provided in the embodiments of the present application and containing computer-executable instructions is not limited to the method operations described above, and may also perform related operations in the picture evaluation method provided in any embodiment of the present application.
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, and the computer software product 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 to enable a computer device (which may be a personal computer, a server, or a network device) to execute the picture evaluation method according to the embodiments of the present 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 evaluation method is characterized by comprising the following steps:
acquiring a picture to be evaluated;
carrying out deformation correction on the picture to be evaluated through a picture correction model to obtain a corrected picture;
and calculating the similarity between the corrected picture and each standard picture in a standard picture library, and obtaining the evaluation score of the picture to be evaluated according to the similarity.
2. The picture evaluation method according to claim 1, wherein the performing deformation correction on the picture to be evaluated through the picture correction model to obtain a corrected picture comprises:
inputting the picture to be evaluated into a picture correction model;
indicating the picture correction model to fold and/or curl each pixel point in the picture to be evaluated so as to obtain at least one distorted picture;
indicating the picture correction model to determine a pixel matrix of a distorted picture according to the picture to be evaluated and the distorted picture, wherein the pixel matrix comprises a gray value of each pixel point in the distorted picture, a moving direction and a moving distance of each pixel point on an x axis, and a moving direction and a moving distance of each pixel point on a y axis;
and instructing the picture correction model to input the distorted picture containing the pixel matrix into a neural network containing the hole convolution so as to obtain a corrected picture.
3. The method according to claim 2, wherein after instructing the picture modification model to determine a pixel matrix of a warped picture according to the picture to be evaluated and the warped picture, the method further comprises:
instructing the picture correction model to determine blank pixel points in the warped picture based on the pixel matrix;
and indicating the picture correction model to perform neighbor interpolation based on neighbor pixel points of the blank pixel points so as to obtain gray values of the blank pixel points, and updating the pixel matrix.
4. The picture evaluation method according to claim 1, wherein the calculating of the similarity between the corrected picture and each standard picture in a standard picture library and the obtaining of the evaluation score of the picture to be evaluated according to the similarity comprises:
acquiring a pixel area containing text information in the corrected picture, wherein the text information is obtained by utilizing optical character recognition;
calculating the similarity between the pixel area and each standard picture in a standard picture library;
and selecting the maximum similarity from the calculated similarities, and taking the maximum similarity as an evaluation score of the picture to be evaluated.
5. The method according to claim 4, wherein the calculating the similarity between the pixel region and each standard picture in a standard picture library comprises:
obtaining the local similarity between the pixel region and a standard picture in a standard picture library by using a structural similarity algorithm;
and calculating the average similarity of the local similarities by combining the resolution dimensions of the picture to be evaluated so as to obtain the similarity between the pixel region and the corresponding standard picture.
6. The picture evaluation method according to claim 5, wherein the calculating an average similarity of the local similarities, in combination with the resolution dimension of the picture to be evaluated, comprises:
confirming the resolution dimension of a sub-pixel region corresponding to the local similarity in the picture to be evaluated;
searching the weight corresponding to the resolution dimension;
and calculating the average similarity according to each local similarity and the corresponding weight.
7. The picture evaluation method according to claim 1, wherein after the calculating of the similarity between the corrected picture and each standard picture in a standard picture library and obtaining the evaluation score of the picture to be evaluated according to the similarity, the method further comprises:
if the evaluation score is larger than or equal to a score threshold value, confirming the picture to be evaluated as an effective picture;
and uploading the effective pictures and the text information contained in the effective pictures to a database so that a user can conveniently check the effective pictures and the text information through the database.
8. A picture evaluation apparatus, comprising:
the image acquisition module is used for acquiring an image to be evaluated;
the image correction module is used for carrying out deformation correction on the image to be evaluated through an image correction model so as to obtain a corrected image;
and the score calculating module is used for calculating the similarity between the corrected picture and each standard picture in the standard picture library and obtaining the evaluation score of the picture to be evaluated according to the similarity.
9. A picture evaluation apparatus characterized by comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the picture evaluation method of any of claims 1-7.
10. A storage medium containing computer-executable instructions for performing the picture evaluation method of any one of claims 1-7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010038652.XA CN111260623B (en) | 2020-01-14 | 2020-01-14 | Picture evaluation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010038652.XA CN111260623B (en) | 2020-01-14 | 2020-01-14 | Picture evaluation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111260623A true CN111260623A (en) | 2020-06-09 |
| CN111260623B CN111260623B (en) | 2023-07-25 |
Family
ID=70943955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010038652.XA Active CN111260623B (en) | 2020-01-14 | 2020-01-14 | Picture evaluation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260623B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075208A (en) * | 2021-03-24 | 2021-07-06 | 贵州省草业研究所 | Intelligent cattle and sheep fermented feed quality evaluation method and device based on picture collection |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080025638A1 (en) * | 2006-07-31 | 2008-01-31 | Eastman Kodak Company | Image fusion for radiation therapy |
| US20080056609A1 (en) * | 2004-03-26 | 2008-03-06 | Centre National D'etudes Spatiales | Fine Stereoscopic Image Matching And Dedicated Instrument Having A Low Stereoscopic Coefficient |
| CN106940798A (en) * | 2017-03-08 | 2017-07-11 | 深圳市金立通信设备有限公司 | The modification method and terminal of a kind of Text region |
| CN109118470A (en) * | 2018-06-26 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of image quality evaluating method, device, terminal and server |
| CN109598299A (en) * | 2018-11-29 | 2019-04-09 | 微梦创科网络科技（中国）有限公司 | A kind of image similarity determines method, apparatus and electronic equipment |
| CN109858410A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Service evaluation method, apparatus, equipment and storage medium based on Expression analysis |
| CN109871841A (en) * | 2019-02-14 | 2019-06-11 | 腾讯科技（深圳）有限公司 | Image processing method, device, terminal and storage medium |
-
2020
- 2020-01-14 CN CN202010038652.XA patent/CN111260623B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080056609A1 (en) * | 2004-03-26 | 2008-03-06 | Centre National D'etudes Spatiales | Fine Stereoscopic Image Matching And Dedicated Instrument Having A Low Stereoscopic Coefficient |
| US20080025638A1 (en) * | 2006-07-31 | 2008-01-31 | Eastman Kodak Company | Image fusion for radiation therapy |
| CN106940798A (en) * | 2017-03-08 | 2017-07-11 | 深圳市金立通信设备有限公司 | The modification method and terminal of a kind of Text region |
| CN109118470A (en) * | 2018-06-26 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of image quality evaluating method, device, terminal and server |
| CN109598299A (en) * | 2018-11-29 | 2019-04-09 | 微梦创科网络科技（中国）有限公司 | A kind of image similarity determines method, apparatus and electronic equipment |
| CN109858410A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Service evaluation method, apparatus, equipment and storage medium based on Expression analysis |
| CN109871841A (en) * | 2019-02-14 | 2019-06-11 | 腾讯科技（深圳）有限公司 | Image processing method, device, terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 吕泽江: "基于POCS算法的人脸检测研究", pages 1 - 47 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113075208A (en) * | 2021-03-24 | 2021-07-06 | 贵州省草业研究所 | Intelligent cattle and sheep fermented feed quality evaluation method and device based on picture collection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111260623B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052787B (en) | Target detection method and device based on artificial intelligence and electronic equipment | |
| US20220092882A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN111914834B (en) | Image recognition method, device, computer equipment and storage medium | |
| US8750573B2 (en) | Hand gesture detection | |
| CN109815770B (en) | Two-dimensional code detection method, device and system | |
| CN110009027B (en) | Image comparison method and device, storage medium and electronic device | |
| CN111259889A (en) | Image text recognition method and device, computer equipment and computer storage medium | |
| US11790499B2 (en) | Certificate image extraction method and terminal device | |
| CN109919971B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN112101386B (en) | Text detection method, device, computer equipment and storage medium | |
| CN111985465A (en) | Text recognition method, device, equipment and storage medium | |
| CN111353325A (en) | Key point detection model training method and device | |
| CN111414910A (en) | Small target enhancement detection method and device based on double convolutional neural network | |
| CN113971644A (en) | Image identification method and device based on data enhancement strategy selection | |
| CN110516731B (en) | Visual odometer feature point detection method and system based on deep learning | |
| CN114092938B (en) | Image recognition processing method and device, electronic equipment and storage medium | |
| CN116977674A (en) | Image matching method, related device, storage medium and program product | |
| CN111260623B (en) | Picture evaluation method, device, equipment and storage medium | |
| CN112784494A (en) | Training method of false positive recognition model, target recognition method and device | |
| CN116246161A (en) | Method and device for identifying target fine type of remote sensing image under guidance of domain knowledge | |
| CN115272428A (en) | Image alignment method and device, computer equipment and storage medium | |
| CN114511877A (en) | Behavior recognition method and device, storage medium and terminal | |
| CN113870210A (en) | Image quality evaluation method, device, equipment and storage medium | |
| CN116612474B (en) | Object detection method, device, computer equipment and computer readable storage medium | |
| CN116704513B (en) | Text quality detection method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |