CN112561890A - Image definition calculation method and device and computer equipment - Google Patents
Image definition calculation method and device and computer equipment Download PDFInfo
- Publication number
- CN112561890A CN112561890A CN202011511194.3A CN202011511194A CN112561890A CN 112561890 A CN112561890 A CN 112561890A CN 202011511194 A CN202011511194 A CN 202011511194A CN 112561890 A CN112561890 A CN 112561890A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- value
- analyzed
- calculating
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 60
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 46
- 238000010606 normalization Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000009499 grossing Methods 0.000 claims description 25
- 238000009825 accumulation Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001629 suppression Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000000452 restraining effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static 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
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Abstract
The application relates to the field of artificial intelligence, and discloses a method for calculating image definition, which comprises the following steps: acquiring an image to be analyzed; judging whether the image size of the image to be analyzed is consistent with a preset size or not; if not, normalizing the image size of the image to be analyzed to be consistent with the preset size; converting the image to be analyzed after the image size normalization processing into a gray image; respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm; and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm. All the images to be analyzed are normalized to the same size through image size normalization so as to adapt to images obtained by different shooting equipment in different scenes, the edge point calculation definition is extracted through two methods, the accuracy is improved, and the scene consistency and the equipment consistency are better.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method and an apparatus for calculating image sharpness, and a computer device.
Background
The image ambiguity calculation is applied to a plurality of fields, and the application in intelligent security operation and maintenance is urgent. However, the robustness of the existing judgment method based on image processing needs to be improved, and most of the existing image ambiguity detection algorithms cannot ensure the consistency of measurement results in various scenes. The inconsistency of the image fuzziness calculation results brings about not little difficulty to the popularization and application of the algorithm. Because the single ambiguity does not have application value, the comparison of the definitions of the two images and the judgment of the definition are needed in the application, and the ambiguity values in different scenes cannot be divided by using a uniform threshold value and cannot be uniformly applied to various business scenes.
Disclosure of Invention
The method mainly aims to provide image definition calculation and aims to solve the technical problem that image definition calculation results in different service scenes cannot be universal.
The application provides a method for calculating image definition, which comprises the following steps:
acquiring an image to be analyzed;
judging whether the image size of the image to be analyzed is consistent with a preset size or not;
if not, normalizing the image size of the image to be analyzed to be consistent with the preset size;
converting the image to be analyzed after the image size normalization processing into a gray image;
respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
Preferably, the step of normalizing the image size of the image to be analyzed to be consistent with the preset size comprises:
acquiring a resolution value to be compatible;
calculating the mean resolution corresponding to the resolution value to be compatible;
determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution;
and scaling the height of the image to be analyzed to the preset height value, and scaling the width of the image to be analyzed to the preset width value.
Preferably, the step of extracting the edge points of the grayscale image respectively through a Canny operator and a local dynamic binarization algorithm includes:
extracting edge points of the gray level image through a Canny operator to obtain a first edge point set;
processing the gray image through a local dynamic binarization algorithm to obtain a binarization gray image, wherein the binarization gray image comprises 1 and 0, marking pixel points with pixel values larger than a preset threshold value in the gray image as 1, and marking pixel points with pixel values smaller than or equal to the preset threshold value as 0;
forming a pixel point set by pixel points marked as 1 in the binary gray scale map;
and determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
Preferably, the step of extracting the edge points of the gray-scale image through a Canny operator to obtain a first edge point set includes:
smoothing the gray level image by means of pixel value accumulation;
calculating the gradient amplitude and the gradient direction of the smoothed gray-scale image through first-order partial derivative finite difference;
carrying out non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude;
and determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
Preferably, the step of smoothing the grayscale image by pixel value accumulation includes:
determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in a gray level image;
respectively calculating the pixel value difference of each adjacent pixel point and the appointed pixel point;
determining a minimum value of an absolute value of each of the pixel value differentials;
multiplying the minimum value of the absolute value by a specified multiple to obtain a smooth pixel value, wherein the specified multiple belongs to a (0,1) interval;
accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image;
and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
Preferably, the step of calculating the image sharpness according to the intersection set of the edge points extracted by the Canny operator and the local dynamic binarization algorithm includes:
calculating a union of the first edge point set and the pixel point set;
calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set;
and converting the intersection ratio into a percentage as the definition of the image to be analyzed.
The application also provides a device for calculating the image definition, which comprises:
the acquisition module is used for acquiring an image to be analyzed;
the judging module is used for judging whether the image size of the image to be analyzed is consistent with a preset size or not;
the normalization module is used for normalizing the image size of the image to be analyzed to be consistent with the preset size if the image size is not consistent with the preset size;
the conversion module is used for converting the image to be analyzed after the image size normalization processing into a gray image;
the extraction module is used for respectively extracting the edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
and the calculation module is used for calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method as described above.
According to the method, all the images to be analyzed are normalized to the same size through image size normalization, so that the image definition calculation is carried out under the same resolution ratio, the method is suitable for the images obtained by different shooting devices under different scenes, the image definition can be evaluated through the same evaluation standard, the industrial application field and the evaluation accuracy of the image definition are expanded, reference images are not needed to be used as standards, and the method has better scene consistency and device consistency.
Drawings
Fig. 1 is a schematic flow chart of a method for calculating image sharpness according to an embodiment of the present application;
FIG. 2 is a flow diagram of a system for computing sharpness of an image according to an embodiment of the present application;
fig. 3 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, a method for calculating image sharpness according to an embodiment of the present application includes:
s1: acquiring an image to be analyzed;
s2: judging whether the image size of the image to be analyzed is consistent with a preset size or not;
s3: if not, normalizing the image size of the image to be analyzed to be consistent with the preset size;
s4: converting the image to be analyzed after the image size normalization processing into a gray image;
s5: respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
s6: and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
According to the method and the device, all the images to be analyzed are normalized to the same size through image size normalization processing, so that the image definition calculation is carried out under the same resolution ratio, the images obtained under different scenes and different shooting devices are adapted, the image definition can be evaluated through the same evaluation standard, the industrial application field and the evaluation accuracy of the image definition are expanded, reference images are not needed to be used as standards, and the method and the device have better scene consistency and device consistency. The image size normalization method includes, but is not limited to, scaling or pixel mapping to a blank file of the same size, so as to realize image size normalization processing.
In order to reduce the calculation amount, the definition of the edge points of the image is calculated to be used as the definition of the whole image. Because the edge points are important components of the image and the sharpness of the edge is complementary to the sharpness of the image. By extracting the edge points and calculating the definition of the edge lines formed by connecting all the edge points, the image definition is obtained, the calculated amount is small, and the method is convenient to deploy in embedded equipment or applied to application scenes needing large-scale deployment.
Further, the step S3 of normalizing the image size of the image to be analyzed to be consistent with the preset size includes:
s31: acquiring a resolution value to be compatible;
s32: calculating the mean resolution corresponding to the resolution value to be compatible;
s33: determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution;
s34: and scaling the height of the image to be analyzed to the preset height value, and scaling the width of the image to be analyzed to the preset width value.
The preset size of the embodiment of the application is obtained by carrying out statistical analysis on the mean value of various resolution types which need to be compatible, so that the compatible effect on different resolutions is improved. For example, the average is obtained by summing all the resolution sums and then dividing by the resolution class. Or setting different weights according to the use frequency of different scenes with different resolutions, for example, the weight of the high use frequency is greater than the weight of the low use frequency, the sum of the weights corresponding to all resolution types is equal to 1, multiplying the resolutions by the weights corresponding to the resolutions respectively, then summing, and then dividing by the resolution types to obtain the weight resolution average value. Other embodiments of the present application may set the predetermined size to a suitable fixed size.
Further, the step S5 of extracting the edge points of the grayscale image respectively through a Canny operator and a local dynamic binarization algorithm includes:
s51: extracting edge points of the gray level image through a Canny operator to obtain a first edge point set;
s52: processing the gray image through a local dynamic binarization algorithm to obtain a binarization gray image, wherein the binarization gray image comprises 1 and 0, marking pixel points with pixel values larger than a preset threshold value in the gray image as 1, and marking pixel points with pixel values smaller than or equal to the preset threshold value as 0;
s53: forming a pixel point set by pixel points marked as 1 in the binary gray scale map;
s54: and determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
In the embodiment of the application, the Canny operator and the local dynamic binarization algorithm are used for jointly positioning the edge points, if the image definition is high, the edge points extracted by the two algorithms are approximately the same, the difference is small, otherwise, the image definition is low, the edge points are positioned by the two different algorithms, and different results with large difference can be obtained. The method has the advantages that the edge points are extracted through two or more than two algorithms, stability of the edge points is improved, robustness of the image definition calculation method is improved, calculation amount, rapid feedback and accuracy are considered, the Canny operator and the local dynamic binarization algorithm are selected to extract the edge points in a compromise mode, and an edge point intersection set obtained through the two methods is used as a final edge point set.
The process of the local adaptive dynamic binarization according to the embodiment of the application is as follows, for example: firstly, filtering an image; then selecting a sliding window with the size of w x h to carry out binarization on the image; calculating the average value a of the original gray level image in the sliding window; will be (a-k)4) As a local threshold, binarizing the pixel point falling at the central point in the sliding window, if the pixel value of the pixel point falling at the central point in the sliding window of the original gray image is larger than (a-k)4) The corresponding position in the copy of the original grey map is set to 1, otherwise, 0 is set. The above w and h pass through the window size coefficient K3Multiplied by the default original window size w0And h0The latter being obtained, i.e. a sliding window of width w and height h, e.g. K3Is 0.05. (a-k) above4) Expressed as dynamic threshold, by subtracting a constant k from the mean of the area pixel values within the sliding window4Is given by the constant k4Is 0.2 times of the global mean value, which is the mean value of the pixel values of the original grayscale image.
Further, the step S51 of extracting edge points of the gray-scale image through a Canny operator to obtain a first edge point set includes:
s511: smoothing the gray level image by means of pixel value accumulation;
s512: calculating the gradient amplitude and the gradient direction of the smoothed gray-scale image through first-order partial derivative finite difference;
s513: carrying out non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude;
s514: and determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
According to the method and the device, in the process of extracting the edge points of the gray level image through the Canny operator, the smoothing process of the image is improved, the image is smoothed in a pixel superposition mode, the original Gaussian blur smoothing process is abandoned, and the abstract deformation of the primary edge in the Gaussian blur smoothing process is avoided. The original existing state of the original edge point is reserved through the smooth image in the pixel superposition mode, the technical requirements for accurately determining the edge point are more fit, and the image definition value is calculated through the edge point more reliably and accurately.
The Canny operator function is expressed as void cv Canny (const CvArr image, CvArr edges, double threshold1, double threshold2, int alert _ size 3). The parameter CvArr image represents the input image, which must be a single-channel grayscale image. The parameter CvArr × edges represents the output edge image, which is a single-channel black-and-white image. The parameters double threshold1 and double threshold2 represent thresholds, of which the small threshold is used to control edge connection and the large threshold is used to control the initial segmentation of the edge, i.e. if the gradient magnitude of a pixel is greater than the upper threshold, it is considered as an edge pixel, and if it is less than the lower threshold, it is discarded. If the gradient amplitude of the point is between the two points, the point is reserved when being connected with the pixel point higher than the upper limit threshold value, and if not, the point is deleted. The parameter int alert _ size represents the size of the Sobel operator, and is 3 by default, i.e. represents a 3 × 3 matrix.
In this embodiment, the lower threshold is set to K1Multiple mean value, upper limit threshold set to K2Mean of multiple, K2Greater than k1. Preferably, the application verifies, based on experiments, that K is determined2＝1.6，K1When the pixel value is 0.6, the edge point is obtained with the best effect by the smooth gray image accumulated by the pixel values.
Further, the step S511 of smoothing the grayscale image by pixel value accumulation includes:
s5111: determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in a gray level image;
s5112: respectively calculating the pixel value difference of each adjacent pixel point and the appointed pixel point;
s5113: determining a minimum value of an absolute value of each of the pixel value differentials;
s5114: multiplying the minimum value of the absolute value by a specified multiple to obtain a smooth pixel value, wherein the specified multiple belongs to a (0,1) interval;
s5115: accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image;
s5116: and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
In the embodiment of the application, before the pixel value superposition smoothing, an appropriate smooth pixel value for superposition is determined. For example, a specified number of adjacent pixels adjacent to any one pixel, for example, the specified number is 8, is determined to obtain pixel values of all pixels around the pixel, so as to reduce the defect that the pixel value of any one pixel is inaccurate due to other factors. The pixel value of the pixel point is compared with the pixel values of the adjacent peripheral pixel points to obtain the pixel value difference degree to be smoothed, then the minimum value of the absolute value of the difference degree is multiplied by a specified multiple to obtain a smoothed pixel value, the specified multiple belongs to a (0,1) interval, and experiments prove that the pixel value is optimal when the pixel value is 0.5. Because the attribution of the target pixel points to be smoothed is uncertain, the pixel values with the minimum difference are classified into one class according to similarity clustering, and the classification can be restricted with each other, so that the minimum value of the absolute value of the difference is selected as a smoothing factor. For example, the pixel value of the current pixel point may contain noise, which is added with noise on the basis of the true value, and compared with the unknown pixel value, the true value plus another noise value is more likely to be the closest to the pixel value, so as to implement smoothing. And then, according to the one-to-one correspondence of the pixel point positions, forming a gray scale image formed by respectively adding the original pixel values to the smoothed pixel values on the blank image, namely the smoothed gray scale image.
Further, step S6 of calculating the image sharpness according to the intersection set of the edge points extracted by the Canny operator and the local dynamic binarization algorithm, includes:
s61: calculating a union of the first edge point set and the pixel point set;
s62: calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set;
s63: and converting the intersection ratio into a percentage as the definition of the image to be analyzed.
This application is achieved by
Calculating the cross-over ratio, wherein P1＝{(x,y)|C1(x,y)＝1}，P2＝{(x,y)|C2(x,y)＝1}，P1Representing a first set of edge points, C1Binary image, P, representing a Canny operator processed gray scale image2Representing a set of pixel points, C2And (2) expressing a gray level image subjected to local self-adaptive dynamic binarization processing, (x, y) expressing pixel points, and 1 expressing that the assignment of binarization corresponding to the pixel points is 1.
Referring to fig. 2, an image sharpness calculation apparatus according to an embodiment of the present application includes:
the acquisition module 1 is used for acquiring an image to be analyzed;
the judging module 2 is used for judging whether the image size of the image to be analyzed is consistent with a preset size;
the normalization module 3 is used for normalizing the image size of the image to be analyzed to be consistent with the preset size if the image size is not consistent with the preset size;
the conversion module 4 is used for converting the image to be analyzed after the image size normalization processing into a gray image;
the extraction module 5 is used for respectively extracting the edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
and the calculating module 6 is used for calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
According to the method and the device, all the images to be analyzed are normalized to the same size through image size normalization processing, so that the image definition calculation is carried out under the same resolution ratio, the images obtained under different scenes and different shooting devices are adapted, the image definition can be evaluated through the same evaluation standard, the industrial application field and the evaluation accuracy of the image definition are expanded, reference images are not needed to be used as standards, and the method and the device have better scene consistency and device consistency. The image size normalization method includes, but is not limited to, scaling or pixel mapping to a blank file of the same size, so as to realize image size normalization processing.
In order to reduce the calculation amount, the definition of the edge points of the image is calculated to be used as the definition of the whole image. Because the edge points are important components of the image and the sharpness of the edge is complementary to the sharpness of the image. By extracting the edge points and calculating the definition of the edge lines formed by connecting all the edge points, the image definition is obtained, the calculated amount is small, and the method is convenient to deploy in embedded equipment or applied to application scenes needing large-scale deployment.
Further, the normalization module 3 includes:
the obtaining submodule is used for obtaining a resolution value to be compatible;
the first calculation submodule is used for calculating the mean resolution corresponding to the resolution value to be compatible;
the first determining submodule is used for determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution;
and the scaling submodule is used for scaling the height of the image to be analyzed to the preset height value and scaling the width of the image to be analyzed to the preset width value.
The preset size of the embodiment of the application is obtained by carrying out statistical analysis on the mean value of various resolution types which need to be compatible, so that the compatible effect on different resolutions is improved. For example, the average is obtained by summing all the resolution sums and then dividing by the resolution class. Or setting different weights according to the use frequency of different scenes with different resolutions, for example, the weight of the high use frequency is greater than the weight of the low use frequency, the sum of the weights corresponding to all resolution types is equal to 1, multiplying the resolutions by the weights corresponding to the resolutions respectively, then summing, and then dividing by the resolution types to obtain the weight resolution average value. Other embodiments of the present application may set the predetermined size to a suitable fixed size.
Further, the extraction module 5 includes:
the extraction submodule is used for extracting the edge points of the gray level image through a Canny operator to obtain a first edge point set;
the processing submodule is used for processing the gray level image through a local dynamic binarization algorithm to obtain a binarization gray level image, wherein the binarization gray level image comprises 1 and 0, the pixel point of which the pixel value is greater than a preset threshold value in the gray level image is marked as 1, and the pixel point of which the pixel value is less than or equal to the preset threshold value is marked as 0;
the marking submodule is used for forming a pixel point set by the pixel points marked as 1 in the binary gray scale map;
and the second determining submodule is used for determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
In the embodiment of the application, the Canny operator and the local dynamic binarization algorithm are used for jointly positioning the edge points, if the image definition is high, the edge points extracted by the two algorithms are approximately the same, the difference is small, otherwise, the image definition is low, the edge points are positioned by the two different algorithms, and different results with large difference can be obtained. The method has the advantages that the edge points are extracted through two or more than two algorithms, stability of the edge points is improved, robustness of the image definition calculation method is improved, calculation amount, rapid feedback and accuracy are considered, the Canny operator and the local dynamic binarization algorithm are selected to extract the edge points in a compromise mode, and an edge point intersection set obtained through the two methods is used as a final edge point set.
The process of the local adaptive dynamic binarization according to the embodiment of the application is as follows, for example: firstly, filtering an image; then selecting a sliding window with the size of w x h to carry out binarization on the image; calculating the average value a of the original gray level image in the sliding window; will be (a-k)4) As a local threshold, binarizing the pixel point falling at the central point in the sliding window, if the pixel value of the pixel point falling at the central point in the sliding window of the original gray image is larger than (a-k)4) The corresponding position in the copy of the original grey map is set to 1, otherwise, 0 is set. The above w and h pass through the window size coefficient K3Multiplied by the default original window size w0And h0The latter being obtained, i.e. a sliding window of width w and height h, e.g. K3Is 0.05. (a-k) above4) Expressed as dynamic threshold, by subtracting a constant k from the mean of the area pixel values within the sliding window4Is given by the constant k4Is 0.2 times of the global mean value, which is the mean value of the pixel values of the original grayscale image.
Further, an extraction submodule, comprising:
a smoothing unit for smoothing the grayscale image by pixel value accumulation;
the calculation unit is used for calculating the gradient amplitude and the gradient direction of the smoothed gray level image through first-order partial derivative finite difference;
the suppression unit is used for performing non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude;
and the determining unit is used for determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
According to the method and the device, in the process of extracting the edge points of the gray level image through the Canny operator, the smoothing process of the image is improved, the image is smoothed in a pixel superposition mode, the original Gaussian blur smoothing process is abandoned, and the abstract deformation of the primary edge in the Gaussian blur smoothing process is avoided. The original existing state of the original edge point is reserved through the smooth image in the pixel superposition mode, the technical requirements for accurately determining the edge point are more fit, and the image definition value is calculated through the edge point more reliably and accurately.
The Canny operator function is expressed as void cv Canny (const CvArr image, CvArr edges, double threshold1, double threshold2, int alert _ size 3). The parameter CvArr image represents the input image, which must be a single-channel grayscale image. The parameter CvArr × edges represents the output edge image, which is a single-channel black-and-white image. The parameters double threshold1 and double threshold2 represent thresholds, of which the small threshold is used to control edge connection and the large threshold is used to control the initial segmentation of the edge, i.e. if the gradient magnitude of a pixel is greater than the upper threshold, it is considered as an edge pixel, and if it is less than the lower threshold, it is discarded. If the gradient amplitude of the point is between the two points, the point is reserved when being connected with the pixel point higher than the upper limit threshold value, and if not, the point is deleted. The parameter int alert _ size represents the size of the Sobel operator, and is 3 by default, i.e. represents a 3 × 3 matrix.
In this embodiment, the lower threshold is set to K1Multiple mean value, upper limit threshold set to K2Mean of multiple, K2Greater than k1. Preferably, the application verifies, based on experiments, that K is determined2＝1.6，K1When the pixel value is 0.6, the edge point is obtained with the best effect by the smooth gray image accumulated by the pixel values.
Further, a smoothing unit includes:
the first determining subunit is used for determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in the gray-scale image;
a calculating subunit, configured to calculate a pixel value difference between each of the adjacent pixel points and the designated pixel point;
a second determining subunit configured to determine a minimum value of absolute values of the respective pixel value differences;
a obtaining subunit, configured to multiply a minimum value of the absolute value by a specified multiple to obtain a smoothed pixel value, where the specified multiple belongs to a (0,1) interval;
an accumulation subunit: accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image;
a storage subunit: and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
In the embodiment of the application, before the pixel value superposition smoothing, an appropriate smooth pixel value for superposition is determined. For example, a specified number of adjacent pixels adjacent to any one pixel, for example, the specified number is 8, is determined to obtain pixel values of all pixels around the pixel, so as to reduce the defect that the pixel value of any one pixel is inaccurate due to other factors. The pixel value of the pixel point is compared with the pixel values of the adjacent peripheral pixel points to obtain the pixel value difference degree to be smoothed, then the minimum value of the absolute value of the difference degree is multiplied by a specified multiple to obtain a smoothed pixel value, the specified multiple belongs to a (0,1) interval, and experiments prove that the pixel value is optimal when the pixel value is 0.5. Because the attribution of the target pixel points to be smoothed is uncertain, the pixel values with the minimum difference are classified into one class according to similarity clustering, and the classification can be restricted with each other, so that the minimum value of the absolute value of the difference is selected as a smoothing factor. For example, the pixel value of the current pixel point may contain noise, which is added with noise on the basis of the true value, and compared with the unknown pixel value, the true value plus another noise value is more likely to be the closest to the pixel value, so as to implement smoothing. And then, according to the one-to-one correspondence of the pixel point positions, forming a gray scale image formed by respectively adding the original pixel values to the smoothed pixel values on the blank image, namely the smoothed gray scale image.
Further, the calculation module 6 includes:
the second calculation submodule is used for calculating the union of the first edge point set and the pixel point set;
the third calculation submodule is used for calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set;
and the submodule is used for converting the intersection ratio into a percentage as the definition of the image to be analyzed.
This application is achieved by
Calculating the cross-over ratio, wherein P1＝{(x,y)|C1(x,y)＝1}，P2＝{(x,y)|C2(x,y)＝1}，P1Representing a first set of edge points, C1Binary image, P, representing a Canny operator processed gray scale image2Representing a set of pixel points, C2And (2) expressing a gray level image subjected to local self-adaptive dynamic binarization processing, (x, y) expressing pixel points, and 1 expressing that the assignment of binarization corresponding to the pixel points is 1.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the calculation process of the image sharpness. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of calculating image sharpness.
The processor executes the method for calculating the image definition, and the method comprises the following steps: acquiring an image to be analyzed; judging whether the image size of the image to be analyzed is consistent with a preset size or not; if not, normalizing the image size of the image to be analyzed to be consistent with the preset size; converting the image to be analyzed after the image size normalization processing into a gray image; respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm; and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
According to the computer equipment, all the images to be analyzed are normalized to the same size through image size normalization, so that the image definition calculation is carried out under the same resolution, the computer equipment is suitable for the images obtained by different shooting equipment under different scenes, the image definition can be evaluated through the same evaluation standard, the industrial application field and the evaluation accuracy of the image definition are expanded, a reference image is not needed to be used as a standard, and the computer equipment has better scene consistency and equipment consistency.
In one embodiment, the step of normalizing the image size of the image to be analyzed to be consistent with the preset size by the processor includes: acquiring a resolution value to be compatible; calculating the mean resolution corresponding to the resolution value to be compatible; determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution; and scaling the height of the image to be analyzed to the preset height value, and scaling the width of the image to be analyzed to the preset width value.
In an embodiment, the step of extracting the edge points of the grayscale image by the processor through a Canny operator and a local dynamic binarization algorithm respectively includes: extracting edge points of the gray level image through a Canny operator to obtain a first edge point set; processing the gray image through a local dynamic binarization algorithm to obtain a binarization gray image, wherein the binarization gray image comprises 1 and 0, marking pixel points with pixel values larger than a preset threshold value in the gray image as 1, and marking pixel points with pixel values smaller than or equal to the preset threshold value as 0; forming a pixel point set by pixel points marked as 1 in the binary gray scale map; and determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
In an embodiment, the step of extracting, by the processor, edge points of the grayscale image through a Canny operator to obtain a first edge point set includes: smoothing the gray level image by means of pixel value accumulation; calculating the gradient amplitude and the gradient direction of the smoothed gray-scale image through first-order partial derivative finite difference; carrying out non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude; and determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
In one embodiment, the step of smoothing the grayscale image by the processor through pixel value accumulation includes: determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in a gray level image; respectively calculating the pixel value difference of each adjacent pixel point and the appointed pixel point; determining a minimum value of an absolute value of each of the pixel value differentials; multiplying the minimum value of the absolute value by a specified multiple to obtain a smooth pixel value, wherein the specified multiple belongs to a (0,1) interval; accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image; and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
In an embodiment, the step of calculating the image sharpness by the processor according to the union set of the edge points extracted by the Canny operator and the local dynamic binarization algorithm respectively includes: calculating a union of the first edge point set and the pixel point set; calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set; and converting the intersection ratio into a percentage as the definition of the image to be analyzed.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for calculating sharpness of an image, and the method includes: acquiring an image to be analyzed; judging whether the image size of the image to be analyzed is consistent with a preset size or not; if not, normalizing the image size of the image to be analyzed to be consistent with the preset size; converting the image to be analyzed after the image size normalization processing into a gray image; respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm; and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
According to the computer-readable storage medium, all images to be analyzed are normalized to the same size through image size normalization, so that image definition calculation is guaranteed to be carried out under the same resolution, images obtained under different scenes and different shooting devices are adapted, the image definition can be evaluated through the same evaluation standard, the industrial application field and the evaluation accuracy of the image definition are expanded, reference images are not needed to be used as standards, and better scene consistency and device consistency are achieved.
In one embodiment, the step of normalizing the image size of the image to be analyzed to be consistent with the preset size by the processor includes: acquiring a resolution value to be compatible; calculating the mean resolution corresponding to the resolution value to be compatible; determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution; and scaling the height of the image to be analyzed to the preset height value, and scaling the width of the image to be analyzed to the preset width value.
In an embodiment, the step of extracting the edge points of the grayscale image by the processor through a Canny operator and a local dynamic binarization algorithm respectively includes: extracting edge points of the gray level image through a Canny operator to obtain a first edge point set; processing the gray image through a local dynamic binarization algorithm to obtain a binarization gray image, wherein the binarization gray image comprises 1 and 0, marking pixel points with pixel values larger than a preset threshold value in the gray image as 1, and marking pixel points with pixel values smaller than or equal to the preset threshold value as 0; forming a pixel point set by pixel points marked as 1 in the binary gray scale map; and determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
In an embodiment, the step of extracting, by the processor, edge points of the grayscale image through a Canny operator to obtain a first edge point set includes: smoothing the gray level image by means of pixel value accumulation; calculating the gradient amplitude and the gradient direction of the smoothed gray-scale image through first-order partial derivative finite difference; carrying out non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude; and determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
In one embodiment, the step of smoothing the grayscale image by the processor through pixel value accumulation includes: determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in a gray level image; respectively calculating the pixel value difference of each adjacent pixel point and the appointed pixel point; determining a minimum value of an absolute value of each of the pixel value differentials; multiplying the minimum value of the absolute value by a specified multiple to obtain a smooth pixel value, wherein the specified multiple belongs to a (0,1) interval; accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image; and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
In an embodiment, the step of calculating the image sharpness by the processor according to the union set of the edge points extracted by the Canny operator and the local dynamic binarization algorithm respectively includes: calculating a union of the first edge point set and the pixel point set; calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set; and converting the intersection ratio into a percentage as the definition of the image to be analyzed.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method for calculating image sharpness is characterized by comprising the following steps:
acquiring an image to be analyzed;
judging whether the image size of the image to be analyzed is consistent with a preset size or not;
if not, normalizing the image size of the image to be analyzed to be consistent with the preset size;
converting the image to be analyzed after the image size normalization processing into a gray image;
respectively extracting edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
and calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
2. A method of calculating a sharpness of an image according to claim 1, wherein the step of normalizing the size of the image to be analyzed to be consistent with the preset size comprises:
acquiring a resolution value to be compatible;
calculating the mean resolution corresponding to the resolution value to be compatible;
determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution;
and scaling the height of the image to be analyzed to the preset height value, and scaling the width of the image to be analyzed to the preset width value.
3. A method for calculating a sharpness of an image according to claim 1, wherein the step of extracting edge points of the gray-scale image respectively by a Canny operator and a local dynamic binarization algorithm comprises:
extracting edge points of the gray level image through a Canny operator to obtain a first edge point set;
processing the gray image through a local dynamic binarization algorithm to obtain a binarization gray image, wherein the binarization gray image comprises 1 and 0, marking pixel points with pixel values larger than a preset threshold value in the gray image as 1, and marking pixel points with pixel values smaller than or equal to the preset threshold value as 0;
forming a pixel point set by pixel points marked as 1 in the binary gray scale map;
and determining the edge points of the gray image according to the intersection of the first edge point set and the pixel point set.
4. A method according to claim 3, wherein said step of extracting edge points of said gray-scale image by a Canny operator to obtain a first set of edge points comprises:
smoothing the gray level image by means of pixel value accumulation;
calculating the gradient amplitude and the gradient direction of the smoothed gray-scale image through first-order partial derivative finite difference;
carrying out non-maximum suppression on the gradient amplitude to obtain a suppressed gradient amplitude;
and determining the first edge point set according to the restrained gradient amplitude and the gradient amplitude before restraining.
5. A method of calculating a sharpness of an image in accordance with claim 4, wherein the step of smoothing the gray scale image by pixel value accumulation comprises:
determining a specified number of adjacent pixel points adjacent to a specified pixel point, wherein the specified pixel point is any one pixel point in a gray level image;
respectively calculating the pixel value difference of each adjacent pixel point and the appointed pixel point;
determining a minimum value of an absolute value of each of the pixel value differentials;
multiplying the minimum value of the absolute value by a specified multiple to obtain a smooth pixel value, wherein the specified multiple belongs to a (0,1) interval;
accumulating the smooth pixel values with the original pixel values in the gray level image respectively to obtain corrected pixel values of the gray level image;
and storing the corrected pixel values in pixel positions corresponding to the original pixel values in a blank image according to the one-to-one correspondence relationship between the corrected pixel values and the original pixel values to obtain the smoothed gray image.
6. A method for calculating a sharpness of an image according to claim 1, wherein the step of calculating the sharpness of the image according to an intersection set of edge points extracted by the Canny operator and the local dynamic binarization algorithm, respectively, comprises:
calculating a union of the first edge point set and the pixel point set;
calculating an intersection ratio according to the intersection of the first edge point set and the pixel point set and the union of the first edge point set and the pixel point set;
and converting the intersection ratio into a percentage as the definition of the image to be analyzed.
7. An apparatus for calculating image sharpness, comprising:
the acquisition module is used for acquiring an image to be analyzed;
the judging module is used for judging whether the image size of the image to be analyzed is consistent with a preset size or not;
the normalization module is used for normalizing the image size of the image to be analyzed to be consistent with the preset size if the image size is not consistent with the preset size;
the conversion module is used for converting the image to be analyzed after the image size normalization processing into a gray image;
the extraction module is used for respectively extracting the edge points of the gray level image through a Canny operator and a local dynamic binarization algorithm;
and the calculation module is used for calculating the image definition according to the intersection set of the edge points respectively extracted by the Canny operator and the local dynamic binarization algorithm.
8. A device for calculating image sharpness according to claim 7, wherein the normalization module comprises:
the obtaining submodule is used for obtaining a resolution value to be compatible;
the first calculation submodule is used for calculating the mean resolution corresponding to the resolution value to be compatible;
the first determining submodule is used for determining a preset height value and a preset width value corresponding to the preset size according to the mean resolution;
and the scaling submodule is used for scaling the height of the image to be analyzed to the preset height value and scaling the width of the image to be analyzed to the preset width value.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011511194.3A CN112561890A (en) | 2020-12-18 | 2020-12-18 | Image definition calculation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011511194.3A CN112561890A (en) | 2020-12-18 | 2020-12-18 | Image definition calculation method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561890A true CN112561890A (en) | 2021-03-26 |
Family
ID=75030466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011511194.3A Pending CN112561890A (en) | 2020-12-18 | 2020-12-18 | Image definition calculation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561890A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222814A (en) * | 2021-04-22 | 2021-08-06 | 平安国际智慧城市科技股份有限公司 | Image resolution processing method, device, equipment and storage medium |
| CN113286079A (en) * | 2021-05-10 | 2021-08-20 | 迈克医疗电子有限公司 | Image focusing method and device, electronic equipment and readable storage medium |
| CN113625440A (en) * | 2021-08-17 | 2021-11-09 | 新乡赛普瑞特环保科技有限公司 | Automatic focusing method for microscope |
| CN113640445A (en) * | 2021-08-11 | 2021-11-12 | 贵州中烟工业有限责任公司 | Characteristic peak identification method based on image processing, computing equipment and storage medium |
| CN115174807A (en) * | 2022-06-28 | 2022-10-11 | 上海艾为电子技术股份有限公司 | Anti-shake detection method and device, terminal equipment and readable storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100098338A1 (en) * | 2008-10-16 | 2010-04-22 | Keyence Corporation | Method for Deciding Image Data Reduction Ratio in Image Processing, Pattern Model Positioning Method in Image Processing, Pattern Model Creating Method in Image Processing, Image Processing Apparatus, Image Processing Program, and Computer Readable Recording Medium |
| CN101950418A (en) * | 2010-08-26 | 2011-01-19 | 北京中创信测科技股份有限公司 | Image quality evaluation method and device |
| CN102404602A (en) * | 2011-09-23 | 2012-04-04 | 浙江工业大学 | Vidicon definition detection method based on definition test card |
| CN102567990A (en) * | 2011-12-08 | 2012-07-11 | 宁波大学 | Stereo image objective quality estimation method |
| CN104732525A (en) * | 2015-02-10 | 2015-06-24 | 宁波永新光学股份有限公司 | Microscopic image definition evaluation method by combining pixel spacing method visual significance |
| CN105006001A (en) * | 2015-08-19 | 2015-10-28 | 常州工学院 | Quality estimation method of parametric image based on nonlinear structural similarity deviation |
| WO2016104990A1 (en) * | 2014-12-23 | 2016-06-30 | 삼성전자 주식회사 | Content providing apparatus, display apparatus and control method therefor |
| CN106384085A (en) * | 2016-08-31 | 2017-02-08 | 浙江众泰汽车制造有限公司 | Calculation method for yaw angle of unmanned vehicle |
| US20180074325A1 (en) * | 2016-09-13 | 2018-03-15 | Oculus Vr, Llc | Fresnel Lens with Dynamic Pitch |
| CN108830829A (en) * | 2018-05-08 | 2018-11-16 | 天津大学 | Combine the reference-free quality evaluation algorithm of a variety of edge detection operators |
| CN110473189A (en) * | 2019-08-02 | 2019-11-19 | 南通使爱智能科技有限公司 | A kind of definition of text images judgment method and system |
| CN110717922A (en) * | 2018-07-11 | 2020-01-21 | 普天信息技术有限公司 | Image definition evaluation method and device |
| CN110930363A (en) * | 2019-10-29 | 2020-03-27 | 北京临近空间飞行器系统工程研究所 | Method and device for determining sharpness evaluation value of curved-surface blurred image and storage medium |
| CN111612741A (en) * | 2020-04-22 | 2020-09-01 | 杭州电子科技大学 | Accurate non-reference image quality evaluation method based on distortion recognition |
| CN112037137A (en) * | 2020-07-21 | 2020-12-04 | 国网湖北省电力有限公司电力科学研究院 | Method and device for eliminating fuzzy region of insulator disc surface edge in infrared image |
-
2020
- 2020-12-18 CN CN202011511194.3A patent/CN112561890A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100098338A1 (en) * | 2008-10-16 | 2010-04-22 | Keyence Corporation | Method for Deciding Image Data Reduction Ratio in Image Processing, Pattern Model Positioning Method in Image Processing, Pattern Model Creating Method in Image Processing, Image Processing Apparatus, Image Processing Program, and Computer Readable Recording Medium |
| CN101950418A (en) * | 2010-08-26 | 2011-01-19 | 北京中创信测科技股份有限公司 | Image quality evaluation method and device |
| CN102404602A (en) * | 2011-09-23 | 2012-04-04 | 浙江工业大学 | Vidicon definition detection method based on definition test card |
| CN102567990A (en) * | 2011-12-08 | 2012-07-11 | 宁波大学 | Stereo image objective quality estimation method |
| WO2016104990A1 (en) * | 2014-12-23 | 2016-06-30 | 삼성전자 주식회사 | Content providing apparatus, display apparatus and control method therefor |
| CN104732525A (en) * | 2015-02-10 | 2015-06-24 | 宁波永新光学股份有限公司 | Microscopic image definition evaluation method by combining pixel spacing method visual significance |
| CN105006001A (en) * | 2015-08-19 | 2015-10-28 | 常州工学院 | Quality estimation method of parametric image based on nonlinear structural similarity deviation |
| CN106384085A (en) * | 2016-08-31 | 2017-02-08 | 浙江众泰汽车制造有限公司 | Calculation method for yaw angle of unmanned vehicle |
| US20180074325A1 (en) * | 2016-09-13 | 2018-03-15 | Oculus Vr, Llc | Fresnel Lens with Dynamic Pitch |
| CN108830829A (en) * | 2018-05-08 | 2018-11-16 | 天津大学 | Combine the reference-free quality evaluation algorithm of a variety of edge detection operators |
| CN110717922A (en) * | 2018-07-11 | 2020-01-21 | 普天信息技术有限公司 | Image definition evaluation method and device |
| CN110473189A (en) * | 2019-08-02 | 2019-11-19 | 南通使爱智能科技有限公司 | A kind of definition of text images judgment method and system |
| CN110930363A (en) * | 2019-10-29 | 2020-03-27 | 北京临近空间飞行器系统工程研究所 | Method and device for determining sharpness evaluation value of curved-surface blurred image and storage medium |
| CN111612741A (en) * | 2020-04-22 | 2020-09-01 | 杭州电子科技大学 | Accurate non-reference image quality evaluation method based on distortion recognition |
| CN112037137A (en) * | 2020-07-21 | 2020-12-04 | 国网湖北省电力有限公司电力科学研究院 | Method and device for eliminating fuzzy region of insulator disc surface edge in infrared image |
Non-Patent Citations (8)
| Title |
|---|
| D. SADYKOVA 等: "Quality assessment metrics for edge detection and edge-aware filtering: A tutorial review", 2017 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 4 December 2017 (2017-12-04), pages 2366 - 2369 * |
| HUAJIE X 等: "Scheduling for constantly-evolving data broadcasting in asymmetric communication networks", JOURNAL OF SHANGHAI UNIVERSITY (ENGLISH EDITION), vol. 12, no. 6, 13 January 2009 (2009-01-13), pages 508 - 514 * |
| MAGNIER, B 等: "Edge detection: a review of dissimilarity evaluations and a proposed normalized measure", MULTIMEDIA TOOLS AND APPLICATIONS, vol. 77, 20 September 2017 (2017-09-20), pages 9489, XP036487152, DOI: 10.1007/s11042-017-5127-6 * |
| THEAM NG 等: "Image reconstruction for quality assessment of edge detectors", 2008 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, 7 April 2009 (2009-04-07), pages 691 - 696 * |
| 刘波: "变电站设备铭牌识别系统设计与实现", 中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑), no. 2014, 15 January 2014 (2014-01-15), pages 042 - 386 * |
| 卢东兴 等: "边缘特征的光学图像清晰度判定与分析", 激光杂志, vol. 37, no. 7, 25 July 2016 (2016-07-25), pages 23 - 26 * |
| 胡玉兰 等: "基于马尔可夫模型优化的非经典感受野轮廓检测算法", 计算机应用与软件, vol. 34, no. 9, 15 September 2017 (2017-09-15), pages 294 - 298 * |
| 陈波: "基于数字图像技术的书本边缘提取", 中国优秀硕士学位论文全文数据库 (信息科技辑), no. 2016, 15 January 2016 (2016-01-15), pages 138 - 759 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222814A (en) * | 2021-04-22 | 2021-08-06 | 平安国际智慧城市科技股份有限公司 | Image resolution processing method, device, equipment and storage medium |
| CN113222814B (en) * | 2021-04-22 | 2023-08-04 | 深圳赛安特技术服务有限公司 | Resolution processing method, device, equipment and storage medium for image |
| CN113286079A (en) * | 2021-05-10 | 2021-08-20 | 迈克医疗电子有限公司 | Image focusing method and device, electronic equipment and readable storage medium |
| CN113286079B (en) * | 2021-05-10 | 2023-04-28 | 迈克医疗电子有限公司 | Image focusing method and device, electronic equipment and readable storage medium |
| CN113640445A (en) * | 2021-08-11 | 2021-11-12 | 贵州中烟工业有限责任公司 | Characteristic peak identification method based on image processing, computing equipment and storage medium |
| CN113625440A (en) * | 2021-08-17 | 2021-11-09 | 新乡赛普瑞特环保科技有限公司 | Automatic focusing method for microscope |
| CN115174807A (en) * | 2022-06-28 | 2022-10-11 | 上海艾为电子技术股份有限公司 | Anti-shake detection method and device, terminal equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112561890A (en) | Image definition calculation method and device and computer equipment | |
| CN110414507B (en) | License plate recognition method and device, computer equipment and storage medium | |
| CN114418957B (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
| CN109859227B (en) | Method and device for detecting flip image, computer equipment and storage medium | |
| CN110059700B (en) | Image moire recognition method and device, computer equipment and storage medium | |
| CN111523414A (en) | Face recognition method and device, computer equipment and storage medium | |
| CN109325959B (en) | Method for extracting infrared image details based on Hough transform and application thereof | |
| CN110378893B (en) | Image quality evaluation method and device and electronic equipment | |
| CN111768392A (en) | Target detection method and device, electronic equipment and storage medium | |
| US9824289B2 (en) | Exploiting color for license plate recognition | |
| CN111209908A (en) | Method and device for updating label box, storage medium and computer equipment | |
| CN111462178A (en) | Method, device and equipment for detecting living body flow direction based on thermal imaging and storage medium | |
| CN113744142A (en) | Image restoration method, electronic device and storage medium | |
| CN110751623A (en) | Joint feature-based defect detection method, device, equipment and storage medium | |
| CN115049713B (en) | Image registration method, device, equipment and readable storage medium | |
| CN111460944A (en) | Live body identification method, device and equipment based on thermal imaging and storage medium | |
| CN110796076A (en) | Hyperspectral image river detection method | |
| CN114973368A (en) | Face recognition method, device, equipment and storage medium based on feature fusion | |
| CN115100660A (en) | Method and device for correcting inclination of document image | |
| CN113298102B (en) | Training method and device for target classification model | |
| CN113298759A (en) | Water area detection method and device, electronic equipment and storage medium | |
| CN109644236B (en) | Angle detection method | |
| CN113793292A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN114973299B (en) | Building drawing component identification method and device, electronic equipment and storage medium | |
| CN116188568A (en) | Method, device, storage medium and processor for determining hook position |
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 |