CN114219774A - Image quality evaluation method, device, terminal and computer readable storage medium - Google Patents
Image quality evaluation method, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN114219774A CN114219774A CN202111442432.4A CN202111442432A CN114219774A CN 114219774 A CN114219774 A CN 114219774A CN 202111442432 A CN202111442432 A CN 202111442432A CN 114219774 A CN114219774 A CN 114219774A
- Authority
- CN
- China
- Prior art keywords
- image
- preprocessed
- evaluated
- quality evaluation
- determining
- 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
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image quality evaluation method, an image quality evaluation device, a terminal and a computer readable storage medium, wherein the image quality evaluation method comprises the following steps: carrying out contrast adjustment processing on an image to be evaluated to obtain an image sequence, wherein the image sequence comprises a plurality of preprocessed images with different contrasts; respectively extracting the characteristic information of a plurality of preprocessed images; and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images. According to the image quality evaluation method and device, the contrast adjustment processing is carried out on the image to be evaluated, so that a plurality of preprocessing images with different contrasts are obtained, the discrete degree of the image sequence is measured according to the difference between the characteristic information of the plurality of preprocessing images and the characteristic information of the processed image by extracting the characteristic information of the plurality of preprocessing images, the quality of the image to be evaluated is scored, the quality of the image to be evaluated can be quantized, the purpose of effectively distinguishing the quality of the contrast distortion image can be achieved, and meanwhile the range of an applicable scene can be improved.
Description
Technical Field
The present invention relates to the field of image quality evaluation technologies, and in particular, to an image quality evaluation method, an image quality evaluation device, a terminal, and a computer-readable storage medium.
Background
Contrast distortion of an image is a very common type of image distortion that can significantly affect the human eye or computer's acquisition of useful information in a contrast-distorted image. Meanwhile, with the continuous development of modern technology, image data is showing an exponential growth trend, wherein more contrast-distorted images are included. Therefore, in order to effectively distinguish the quality of the contrast-distorted image and screen out a high-quality image capable of effectively acquiring information, a contrast image quality evaluation method is required to provide effective reference for human eyes or a computer.
Disclosure of Invention
The invention mainly solves the technical problem of providing an image quality evaluation method, an image quality evaluation device, a terminal and a computer readable storage medium, and solves the problem that the quality of contrast distortion images cannot be effectively distinguished in the prior art.
In order to solve the technical problems, the first technical scheme adopted by the invention is as follows: provided is an image quality evaluation method including: carrying out contrast adjustment processing on an image to be evaluated to obtain an image sequence, wherein the image sequence comprises a plurality of preprocessed images with different contrasts; respectively extracting the characteristic information of a plurality of preprocessed images; and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images.
The method for adjusting the contrast of the image to be evaluated to obtain the image sequence comprises the following steps: obtaining original histogram information by traversing all pixels in an image to be evaluated; determining the pixel number range of the image to be evaluated according to the original histogram information; wherein the range of the number of the pixels is from the minimum number of the pixels to the maximum number of the pixels; extracting a plurality of pixel numbers within the pixel number range according to a preset value to obtain a pixel number threshold value; respectively preprocessing original histogram information according to each pixel number threshold value, and determining preprocessed histogram information corresponding to the pixel number threshold value; and carrying out equalization processing on the preprocessed histogram information to obtain a preprocessed image.
The method for preprocessing the original histogram information according to the pixel number threshold value and determining the preprocessed histogram information corresponding to the pixel number threshold value comprises the following steps: acquiring a pixel number threshold; and distributing the pixel number of each gray level in the original histogram information between the pixel number threshold and the maximum pixel number between the pixel number threshold and the minimum pixel number to obtain the preprocessed histogram information.
Wherein the characteristic information comprises at least one of a gray dynamic range, an information entropy and a brightness; respectively extracting the characteristic information of a plurality of preprocessed images, comprising: counting the number of pixels corresponding to the gray level of each preprocessed image to obtain pixel distribution information corresponding to the preprocessed images; determining the gray dynamic range of the corresponding preprocessed image according to the maximum effective gray level and the minimum effective gray level of the preprocessed image in the pixel distribution information; determining a quality evaluation value of an image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images, wherein the determining comprises the following steps: and determining the gray dynamic range variance of the corresponding image to be evaluated according to the gray dynamic ranges respectively corresponding to the plurality of preprocessed images.
Wherein, extract the characteristic information of a plurality of preliminary treatment images respectively, still include: determining the probability density of the number of pixels corresponding to each gray level in the preprocessed image according to the pixel distribution information; determining the information entropy of the preprocessed image according to the probability density of the number of pixels corresponding to each gray level; determining a quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images, and further comprising: and determining the information entropy variance of the corresponding image to be evaluated according to the information entropy corresponding to the plurality of preset images respectively.
Wherein, extract the characteristic information of a plurality of preliminary treatment images respectively, still include: determining each gray level in the preprocessed image, the number of pixels corresponding to the gray level and the total number of pixels according to the pixel distribution information, and determining the brightness of the preprocessed image; determining a quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images, and further comprising: and determining the brightness variance of the image to be evaluated according to the brightness corresponding to the plurality of preset images respectively.
The method for determining the quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images further comprises the following steps: and determining the quality evaluation value of the image to be evaluated according to at least one of the gray dynamic range variance, the information entropy variance and the brightness variance of the image to be evaluated.
In order to solve the above technical problems, the second technical solution adopted by the present invention is: provided is an image quality evaluation apparatus including: the contrast adjusting module is used for carrying out contrast adjusting processing on the image to be evaluated to obtain an image sequence, and the image sequence comprises a plurality of preprocessed images with different contrasts; the characteristic extraction module is used for respectively extracting the characteristic information of a plurality of preprocessed images; and the evaluation module is used for determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images.
In order to solve the above technical problems, the third technical solution adopted by the present invention is: there is provided a terminal comprising a memory, a processor and a computer program stored in the memory and running on the processor, the processor being configured to execute the sequence data to implement the steps in the image quality assessment method described above.
In order to solve the technical problems, the fourth technical scheme adopted by the invention is as follows: there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the above-described image quality evaluation method.
The invention has the beneficial effects that: different from the prior art, the image quality evaluation method, the image quality evaluation device, the terminal and the computer-readable storage medium are provided, and the image quality evaluation method comprises the following steps: carrying out contrast adjustment processing on an image to be evaluated to obtain an image sequence, wherein the image sequence comprises a plurality of preprocessed images with different contrasts; respectively extracting the characteristic information of a plurality of preprocessed images; and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images. According to the image quality evaluation method and device, the contrast adjustment processing is carried out on the image to be evaluated, so that a plurality of preprocessing images with different contrasts are obtained, the discrete degree of the image sequence is measured according to the difference between the characteristic information of the plurality of preprocessing images and the characteristic information of the processed image by extracting the characteristic information of the plurality of preprocessing images, the quality of the image to be evaluated is scored, the quality of the image to be evaluated can be quantized, the purpose of effectively distinguishing the quality of the contrast distortion image can be achieved, and meanwhile the range of an applicable scene can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of an image quality evaluation method provided by the present invention;
FIG. 2 is a flowchart illustrating an embodiment of an image quality evaluation method according to the present invention;
FIG. 3 is a schematic block diagram of an image quality evaluation apparatus provided by the present invention;
FIG. 4 is a schematic block diagram of one embodiment of a terminal provided by the present invention;
FIG. 5 is a schematic block diagram of one embodiment of a computer-readable storage medium provided by the present invention.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
In order to make those skilled in the art better understand the technical solution of the present invention, an image quality evaluation method provided by the present invention is further described in detail below with reference to the accompanying drawings and the detailed description.
Referring to fig. 1, fig. 1 is a schematic flow chart of an image quality evaluation method according to the present invention. The present embodiment provides an image quality evaluation method, which includes the following steps.
S11: and carrying out contrast adjustment processing on the image to be evaluated to obtain an image sequence.
Specifically, a contrast gradient image sequence is generated by a contrast enhancement algorithm and by adopting a parameter adjustment mode. In one embodiment, original histogram information is obtained by traversing all pixels in an image to be evaluated; determining the pixel number range of the image to be evaluated according to the original histogram information; wherein the range of the number of the pixels is from the minimum number of the pixels to the maximum number of the pixels; extracting a plurality of pixel numbers within the pixel number range according to a preset value to obtain a pixel number threshold value; respectively preprocessing original histogram information according to each pixel number threshold value, and determining preprocessed histogram information corresponding to the pixel number threshold value; and carrying out equalization processing on the preprocessed histogram information to obtain a preprocessed image. The image sequence corresponding to the image to be evaluated is formed by the plurality of preprocessed images with different contrasts.
In a specific embodiment, a pixel number threshold is obtained; and distributing the pixel number of each gray level in the original histogram information between the pixel number threshold and the maximum pixel number between the pixel number threshold and the minimum pixel number to obtain the preprocessed histogram information.
S12: and respectively extracting the characteristic information of the plurality of preprocessed images.
Specifically, the characteristic information includes at least one of a gray-scale dynamic range, an information entropy, and a luminance.
In one embodiment, the number of pixels corresponding to the gray level of each preprocessed image is counted to obtain pixel distribution information corresponding to the preprocessed images; determining the gray dynamic range of the corresponding preprocessed image according to the maximum effective gray level and the minimum effective gray level of the preprocessed image in the pixel distribution information; and determining the gray dynamic range variance of the corresponding image to be evaluated according to the gray dynamic ranges respectively corresponding to the plurality of preprocessed images.
In one embodiment, the probability density of the number of pixels corresponding to each gray level in the preprocessed image is determined according to the pixel distribution information; determining the information entropy of the preprocessed image according to the probability density of the number of pixels corresponding to each gray level; and determining the information entropy variance of the corresponding image to be evaluated according to the information entropy corresponding to the plurality of preset images respectively.
In one embodiment, determining each gray level, the number of pixels corresponding to the gray level and the total number of pixels in the preprocessed image according to the pixel distribution information, and determining the brightness of the preprocessed image; and determining the brightness variance of the image to be evaluated according to the brightness corresponding to the plurality of preset images respectively.
S13: and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images.
Specifically, the quality evaluation value of the image to be evaluated is obtained according to the sum of the gray dynamic range variance, the information entropy variance and the brightness variance of the image to be evaluated.
The image quality evaluation method provided by the embodiment comprises the steps of carrying out contrast adjustment processing on an image to be evaluated to obtain an image sequence, wherein the image sequence comprises a plurality of preprocessed images with different contrasts; respectively extracting the characteristic information of a plurality of preprocessed images; and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images. According to the image quality evaluation method and device, the contrast adjustment processing is carried out on the image to be evaluated, so that a plurality of preprocessed images with different contrasts are obtained, the discrete degree of the image sequence is measured according to the difference between the characteristic information of the preprocessed images and the characteristic information of the processed images by extracting the characteristic information of the preprocessed images, the quality of the image to be evaluated is scored, the quality of the image to be evaluated is quantized, the purpose of effectively distinguishing the quality of the contrast distortion image can be achieved, and meanwhile the range of an applicable scene can be improved.
Referring to fig. 2, fig. 2 is a schematic flow chart of an embodiment of an image quality evaluation method according to the present invention. The present embodiment provides an image quality evaluation method, which includes the following steps.
S21: and acquiring an image to be evaluated.
Specifically, a contrast-distorted image is acquired, and the acquired contrast-distorted image is determined as an image to be evaluated. An evaluation of the quality of the contrast-distorted image is required.
S22: and traversing all pixels in the image to be evaluated to obtain the original histogram information.
Specifically, feature data in the image to be evaluated are extracted, the gray level of the image to be evaluated and the number of pixels corresponding to each gray level are counted according to the extracted feature data, and an original histogram of the image to be evaluated is constructed according to the gray level and the number of pixels of each gray level. The original histogram information reflects the gray level of the image to be evaluated and the number of pixels of each gray level.
S23: and determining the pixel number range of the image to be evaluated according to the original histogram information.
Specifically, the maximum number of pixels and the minimum number of pixels can be determined from the original histogram information. The range from the minimum pixel number to the maximum pixel number can be used as the pixel number range of the image to be evaluated.
S24: and extracting a plurality of pixel numbers within the pixel number range according to a preset value to obtain a pixel number threshold value.
Specifically, preset values are preset, and a plurality of pixel numbers are extracted within a pixel number range according to the preset values to obtain a plurality of pixel number thresholds. In a specific embodiment, a preset value is added to the minimum pixel number to obtain a first threshold of the pixel number, a preset value is added to the first threshold of the pixel number to obtain a second threshold of the pixel number, and the operations are repeated until the threshold exceeds the range of the pixel number, so that a plurality of thresholds of the pixel number can be obtained.
S25: and respectively preprocessing the original histogram information according to each pixel number threshold value, and determining the preprocessed histogram information corresponding to the pixel number threshold value.
Specifically, the original histogram information is respectively enhanced through different pixel number thresholds to obtain preprocessed histogram information with different enhancement degrees. In a specific embodiment, in order to ensure that the total number of pixels is not changed, a threshold value is obtained according to the number of the obtained multiple pixels; and distributing the pixel number of each gray level in the original histogram information between the pixel number threshold and the maximum pixel number between the pixel number threshold and the minimum pixel number to obtain the preprocessed histogram information. In a preferred embodiment, the original histogram is truncated from the threshold of the number of pixels, and all the pixel numbers of the gray levels in the original histogram information between the threshold of the number of pixels and the maximum number of pixels are evenly distributed between the threshold of the minimum number of pixels and the threshold of the number of pixels, so as to obtain the preprocessed histogram information corresponding to different threshold values of the number of pixels.
S26: and carrying out equalization processing on the preprocessed histogram information to obtain a preprocessed image.
Specifically, the equalization process is to change the preprocessed histogram information from a certain gray level interval in the comparison set to a uniform distribution in the entire gray level range. That is, the equalization process is to perform nonlinear stretching on the preprocessed histogram information and to reassign pixel values so that the number of pixels in a certain gradation range is substantially the same. Images with too bright or too dark backgrounds and foregrounds can be balanced through equalization processing, and then preprocessed images corresponding to the preprocessed histogram information are obtained. The pre-processed image is an image which is subjected to contrast enhancement on the image to be evaluated.
Because the pixel number threshold is gradually increased from small to large, the contrast of the preprocessed images respectively corresponding to the pixel number thresholds is different and gradually changed, and therefore, the image sequence corresponding to the image to be evaluated is formed by the preprocessed images with gradually changed contrasts.
S27: and respectively extracting the characteristic information of the plurality of preprocessed images.
Specifically, feature data in the preprocessed image are respectively extracted, the gray level of the preprocessed image and the number of pixels corresponding to each gray level are counted according to the extracted feature data, and a histogram of the preprocessed image is determined according to the gray level and the number of pixels of each gray level. The histogram reflects the gray level of the preprocessed image and the number of pixels of each gray level. And counting the number of pixels corresponding to the gray level of each preprocessed image according to the histogram to obtain pixel distribution information corresponding to the preprocessed images. Wherein the characteristic information includes at least one of a gray dynamic range, an information entropy, and a brightness. The gray scale dynamic range, the information entropy and the brightness of the preprocessed image can be determined according to the pixel distribution information corresponding to the preprocessed image.
In one embodiment, the gray dynamic range of the corresponding preprocessed image is determined according to the maximum effective gray level and the minimum effective gray level of the preprocessed image in the pixel distribution information. Wherein, the number of the pixels of the maximum effective gray level and the minimum effective gray level is not zero. Specifically, the difference between the maximum effective gray level and the minimum effective gray level in the histogram is calculated, and the difference is divided by the theoretical maximum gray level of the image to carry out normalization processing, so as to obtain the gray dynamic range R of the preprocessed imaget。
Wherein, the gray dynamic range R can be calculated by formula 1t：
Rt＝(Limg_max-Limg_min)/Lmax(formula 1)
In the formula: rtIs the gray scale dynamic range; l isimg-maxIs the maximum effective gray level; l isimg-minIs the minimum effective gray level; l ismaxIs the theoretical maximum gray level of the image.
Respectively calculating the gray dynamic range of each preprocessed image through formula 1Rt。
In a specific embodiment, the probability density of the number of pixels corresponding to each gray level in the preprocessed image is determined according to the pixel distribution information; and determining the information entropy of the preprocessed image according to the probability density of the number of pixels corresponding to each gray level. In a specific embodiment, the probability density of the number of pixels corresponding to each gray level in the histogram is calculated, and then a one-dimensional image information entropy formula is adopted for calculation. Finally, dividing the image by 8 for normalization to obtain the information entropy E of the preprocessed imaget。
Wherein, the information entropy E can be calculated by formula 2t：
In the formula: etIs the information entropy; piIs the probability density of the number of pixels; i is the gray level.
Respectively calculating the gray dynamic range E of each preprocessed image through a formula 2t。
In a specific embodiment, the brightness of the preprocessed image is determined by determining each gray level, the number of pixels corresponding to the gray level and the total number of pixels in the preprocessed image according to the pixel distribution information. In a specific embodiment, the product of each gray level in the histogram and the corresponding number of pixels is calculated and summed, then divided by the total number of pixels in the pre-processed image. Finally, dividing the image by the theoretical maximum gray level of the image for normalization to obtain the brightness L of the preprocessed imaget。
Wherein, the brightness L can be calculated by formula 3t：
In the formula: l istIs the brightness; h isiIs the number of pixels; i is a gray level; l ismaxIs the theoretical maximum gray level of the image.
Calculating each pretreatment separately by equation 3Luminance L of physical imaget。
S28: and obtaining the quality evaluation value of the image to be evaluated according to the sum of the gray dynamic range variance, the information entropy variance and the brightness variance of the image to be evaluated.
In one embodiment, the gray scale dynamic ranges R corresponding to a plurality of preprocessed images included in an image sequence corresponding to an image to be evaluated are determinedtCalculating the gray dynamic range variance V of the corresponding image to be evaluatedrangeAnd then determining the difference of the gray dynamic ranges of the plurality of preprocessed images corresponding to the image to be evaluated.
In a specific embodiment, the information entropy variance V of the corresponding image to be evaluated is calculated according to the information entropy corresponding to each of a plurality of preprocessed images included in the image sequence corresponding to the image to be evaluatedentropyAnd then determining the difference of the information entropy of a plurality of preprocessed images corresponding to the image to be evaluated.
In an embodiment, the luminance variance V of the corresponding image to be evaluated is calculated according to the luminance corresponding to each of a plurality of preprocessed images included in the image sequence corresponding to the image to be evaluatedlaveAnd then determining the difference of the brightness of a plurality of preprocessed images corresponding to the image to be evaluated.
And obtaining the quality evaluation value of the image to be evaluated according to the sum of the gray dynamic range variance, the information entropy variance and the brightness variance of the image to be evaluated.
Specifically, the quality evaluation value S of the image to be evaluated is obtained by formula 4.
S＝Vrange+Ventropy+Vlave(formula 4)
In the formula: s is a quality evaluation value of the image to be evaluated; vrangeIs the gray scale dynamic range variance; ventropyIs the information entropy variance; vlaveIs the variance of the luminance.
In a specific embodiment, since different feature information has different degrees of influence on image quality, weights can be respectively assigned to the gray dynamic range variance, the information entropy variance and the brightness variance, so as to obtain a quality evaluation value of an image to be evaluated. In a preferred embodiment, the weights respectively allocated to the gray dynamic range variance, the information entropy variance and the brightness variance are 1/3, and the gray dynamic range variance, the information entropy variance and the brightness variance are multiplied by the weights respectively and then added to obtain the quality evaluation value of the image to be evaluated.
According to the method and the device, the quality evaluation value of the image to be evaluated can be determined without using a reference image, and the range of an applicable scene is widened. And the contrast information of the preprocessed image is described by adopting three kinds of characteristic information, namely gray dynamic range, information entropy and brightness, so that the contrast distortion phenomenon of the image to be evaluated is reflected more comprehensively, and the quality of the image to be evaluated is more conveniently distinguished.
According to the image quality evaluation method and device, the contrast adjustment processing is carried out on the image to be evaluated to obtain a plurality of preprocessed images with different contrasts, the discrete degree of the image sequence is measured by extracting the characteristic information of the preprocessed images according to the difference between the characteristic information of the preprocessed images and the characteristic information of the processed images, the quality of the image to be evaluated is scored, the quality of the image to be evaluated can be quantized, the purpose of effectively distinguishing the quality of the contrast distortion image can be achieved, and meanwhile the range of an applicable scene can be enlarged.
Referring to fig. 3, fig. 3 is a schematic block diagram of an image quality evaluation apparatus provided in the present invention. In the present embodiment, an image quality evaluation apparatus 30 is provided, and the image quality evaluation apparatus 30 includes a contrast adjustment module 31, a feature extraction module 32, and an evaluation module 33.
The contrast adjusting module 31 is configured to perform contrast adjustment processing on an image to be evaluated to obtain an image sequence, where the image sequence includes a plurality of preprocessed images with different contrasts.
The feature extraction module 32 is configured to extract feature information of a plurality of preprocessed images respectively.
The evaluation module 33 is configured to determine a quality evaluation value of the image to be evaluated based on a difference between feature information corresponding to the plurality of preprocessed images.
According to the image quality evaluation method and device, the contrast adjustment processing is carried out on the image to be evaluated to obtain a plurality of preprocessed images with different contrasts, the discrete degree of the image sequence is measured by extracting the characteristic information of the preprocessed images according to the difference between the characteristic information of the preprocessed images and the characteristic information of the processed images, the quality of the image to be evaluated is scored, the quality of the image to be evaluated can be quantized, the purpose of effectively distinguishing the quality of the contrast distortion image can be achieved, and meanwhile the range of an applicable scene can be enlarged.
Referring to fig. 4, fig. 4 is a schematic block diagram of an embodiment of a terminal provided in the present invention. The terminal 70 in this embodiment includes: the processor 71, the memory 72, and a computer program stored in the memory 72 and capable of running on the processor 71 are not repeated herein to avoid repetition in the above-mentioned image quality evaluation method implemented by the computer program executed by the processor 71.
Referring to fig. 5, fig. 5 is a schematic block diagram of an embodiment of a computer-readable storage medium provided by the present invention. The embodiment of the present application further provides a computer-readable storage medium 90, the computer-readable storage medium 90 stores a computer program 901, the computer program 901 includes program instructions, and a processor executes the program instructions to implement the image quality assessment method provided by the embodiment of the present application.
The computer-readable storage medium 90 may be an internal storage unit of the computer device of the foregoing embodiment, such as a hard disk or a memory of the computer device. The computer-readable storage medium 90 may also be an external storage device of the computer device, such as a plug-in hard disk provided on the computer device, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An image quality evaluation method, characterized by comprising:
carrying out contrast adjustment processing on an image to be evaluated to obtain an image sequence, wherein the image sequence comprises a plurality of preprocessed images with different contrasts;
respectively extracting the characteristic information of a plurality of preprocessed images;
and determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images.
2. The image quality evaluation method according to claim 1,
the method for adjusting the contrast of the image to be evaluated to obtain an image sequence comprises the following steps:
obtaining original histogram information by traversing all pixels in an image to be evaluated;
determining the pixel number range of the image to be evaluated according to the original histogram information; wherein the range of the number of the pixels is from the minimum number of the pixels to the maximum number of the pixels;
extracting a plurality of pixel numbers within the pixel number range according to a preset value to obtain a pixel number threshold value;
respectively preprocessing the original histogram information according to each pixel number threshold value, and determining preprocessed histogram information corresponding to the pixel number threshold value;
and carrying out equalization processing on the preprocessed histogram information to obtain the preprocessed image.
3. The image quality evaluation method according to claim 2,
the pre-processing the original histogram information according to each pixel number threshold value, and determining the pre-processed histogram information corresponding to the pixel number threshold value, includes:
acquiring the threshold value of the number of the pixels;
and distributing the pixel number of each gray level in the original histogram information between the pixel number threshold and the maximum pixel number between the pixel number threshold and the minimum pixel number to obtain the preprocessed histogram information.
4. The image quality evaluation method according to claim 1, wherein the characteristic information includes at least one of a gray-scale dynamic range, an information entropy, and a brightness;
the extracting the feature information of the plurality of preprocessed images respectively includes:
counting the number of pixels corresponding to the gray level of each preprocessed image to obtain pixel distribution information corresponding to the preprocessed image;
determining the gray dynamic range of the corresponding preprocessed image according to the maximum effective gray level and the minimum effective gray level of the preprocessed image in the pixel distribution information;
the determining the quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images comprises the following steps:
and determining the gray scale dynamic range variance of the corresponding image to be evaluated according to the gray scale dynamic ranges respectively corresponding to the plurality of preprocessed images.
5. The image quality evaluation method according to claim 4,
the extracting the feature information of the plurality of preprocessed images respectively further includes:
determining the probability density of the number of the pixels corresponding to each gray level in the preprocessed image according to the pixel distribution information;
determining the information entropy of the preprocessed image according to the probability density of the number of the pixels corresponding to each gray level;
the determining the quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images further comprises:
and determining the information entropy variance of the corresponding image to be evaluated according to the information entropy corresponding to the plurality of preset images respectively.
6. The image quality evaluation method according to claim 5,
the extracting the feature information of the plurality of preprocessed images respectively further includes:
determining each gray level in the preprocessed image, the number of pixels corresponding to the gray level and the total number of pixels according to the pixel distribution information, and determining the brightness of the preprocessed image;
the determining the quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images further comprises:
and determining the brightness variance of the image to be evaluated according to the brightness corresponding to the plurality of preset images respectively.
7. The image quality evaluation method according to claim 6,
the determining the quality evaluation value of the image to be evaluated based on the difference of the feature information corresponding to the plurality of preprocessed images further comprises:
and determining the quality evaluation value of the image to be evaluated according to at least one of the gray dynamic range variance, the information entropy variance and the brightness variance of the image to be evaluated.
8. An image quality evaluation apparatus characterized by comprising:
the contrast adjusting module is used for carrying out contrast adjusting processing on the image to be evaluated to obtain an image sequence, and the image sequence comprises a plurality of preprocessed images with different contrasts;
the characteristic extraction module is used for respectively extracting the characteristic information of the plurality of preprocessed images;
and the evaluation module is used for determining the quality evaluation value of the image to be evaluated based on the difference of the characteristic information corresponding to the plurality of preprocessed images.
9. A terminal, characterized in that the terminal comprises a memory, a processor and a computer program stored in the memory and running on the processor, the processor being configured to execute sequence data to implement the steps in the image quality assessment method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the image quality assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442432.4A CN114219774B (en) | 2021-11-30 | 2021-11-30 | Image quality evaluation method, device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442432.4A CN114219774B (en) | 2021-11-30 | 2021-11-30 | Image quality evaluation method, device, terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114219774A true CN114219774A (en) | 2022-03-22 |
| CN114219774B CN114219774B (en) | 2023-03-28 |
Family
ID=80698940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111442432.4A Active CN114219774B (en) | 2021-11-30 | 2021-11-30 | Image quality evaluation method, device, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219774B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114882042A (en) * | 2022-07-12 | 2022-08-09 | 江苏布罗信息技术有限公司 | Internet of things transmission method based on image quality evaluation |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345891A (en) * | 2008-08-25 | 2009-01-14 | 重庆医科大学 | Non-reference picture quality appraisement method based on information entropy and contrast |
| US20110311147A1 (en) * | 2009-02-12 | 2011-12-22 | Dolby Laboratories Licensing Corporation | Quality Evaluation of Sequences of Images |
| US20120020415A1 (en) * | 2008-01-18 | 2012-01-26 | Hua Yang | Method for assessing perceptual quality |
| CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
| CN102945552A (en) * | 2012-10-22 | 2013-02-27 | 西安电子科技大学 | No-reference image quality evaluation method based on sparse representation in natural scene statistics |
| CN103338380A (en) * | 2013-06-06 | 2013-10-02 | 宁波大学 | Adaptive image quality objective evaluation method |
| CN106600597A (en) * | 2016-12-22 | 2017-04-26 | 华中科技大学 | Non-reference color image quality evaluation method based on local binary pattern |
| CN107292830A (en) * | 2016-12-28 | 2017-10-24 | 首都师范大学 | Low-light (level) image enhaucament and evaluation method |
| CN108109147A (en) * | 2018-02-10 | 2018-06-01 | 北京航空航天大学 | A kind of reference-free quality evaluation method of blurred picture |
| CN109360194A (en) * | 2018-09-27 | 2019-02-19 | 北京印刷学院 | A kind of image quality evaluating method based on discrete inseparable shearing wave conversion and human-eye visual characteristic |
| US20200077017A1 (en) * | 2016-12-07 | 2020-03-05 | Zte Corporation | Photograph-capture method, apparatus, terminal, and storage medium |
-
2021
- 2021-11-30 CN CN202111442432.4A patent/CN114219774B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120020415A1 (en) * | 2008-01-18 | 2012-01-26 | Hua Yang | Method for assessing perceptual quality |
| CN101345891A (en) * | 2008-08-25 | 2009-01-14 | 重庆医科大学 | Non-reference picture quality appraisement method based on information entropy and contrast |
| US20110311147A1 (en) * | 2009-02-12 | 2011-12-22 | Dolby Laboratories Licensing Corporation | Quality Evaluation of Sequences of Images |
| CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
| CN102945552A (en) * | 2012-10-22 | 2013-02-27 | 西安电子科技大学 | No-reference image quality evaluation method based on sparse representation in natural scene statistics |
| CN103338380A (en) * | 2013-06-06 | 2013-10-02 | 宁波大学 | Adaptive image quality objective evaluation method |
| US20200077017A1 (en) * | 2016-12-07 | 2020-03-05 | Zte Corporation | Photograph-capture method, apparatus, terminal, and storage medium |
| CN106600597A (en) * | 2016-12-22 | 2017-04-26 | 华中科技大学 | Non-reference color image quality evaluation method based on local binary pattern |
| CN107292830A (en) * | 2016-12-28 | 2017-10-24 | 首都师范大学 | Low-light (level) image enhaucament and evaluation method |
| CN108109147A (en) * | 2018-02-10 | 2018-06-01 | 北京航空航天大学 | A kind of reference-free quality evaluation method of blurred picture |
| CN109360194A (en) * | 2018-09-27 | 2019-02-19 | 北京印刷学院 | A kind of image quality evaluating method based on discrete inseparable shearing wave conversion and human-eye visual characteristic |
Non-Patent Citations (5)
| Title |
|---|
| JIA YAN 等: "No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancement", 《ARXIV》 * |
| YIMING ZHU 等: "No-Reference Image Quality Assessment for Contrast Distorted Images", 《INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS》 * |
| 汪子玉 等: "基于图像序列分析的全局直方图均衡", 《信号处理》 * |
| 程光权 等: "基于几何结构失真模型的图像质量评价研究", 《自动化学报》 * |
| 高方远 等: "基于深度网络和视觉特性的无参考图像质量评价方法", 《南京师大学报(自然科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114882042A (en) * | 2022-07-12 | 2022-08-09 | 江苏布罗信息技术有限公司 | Internet of things transmission method based on image quality evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114219774B (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Agrawal et al. | A novel joint histogram equalization based image contrast enhancement | |
| CN106296600B (en) | A kind of contrast enhancement process decomposed based on wavelet image | |
| US10963993B2 (en) | Image noise intensity estimation method, image noise intensity estimation device, and image recognition device | |
| CN109325922B (en) | Image self-adaptive enhancement method and device and image processing equipment | |
| Sun et al. | Fast single image haze removal via local atmospheric light veil estimation | |
| CN110969046B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
| CN109859257B (en) | Skin image texture evaluation method and system based on texture directionality | |
| CN109584198B (en) | Method and device for evaluating quality of face image and computer readable storage medium | |
| CN113592776A (en) | Image processing method and device, electronic device and storage medium | |
| CN110189266B (en) | Self-adaptive rapid image enhancement method | |
| CN110458792B (en) | Method and device for evaluating quality of face image | |
| CN113596573B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN114219774B (en) | Image quality evaluation method, device, terminal and computer readable storage medium | |
| Singh et al. | Naturalness balance contrast enhancement using adaptive gamma with cumulative histogram and median filtering | |
| CN110378860A (en) | Method, apparatus, computer equipment and the storage medium of restored video | |
| US11501404B2 (en) | Method and system for data processing | |
| CN110136085B (en) | Image noise reduction method and device | |
| CN117314766A (en) | Method and system for enhancing surface image of toughened glass film of mobile phone | |
| CN109636749B (en) | Image processing method | |
| CN111754413A (en) | Image processing method, device, equipment and storage medium | |
| CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
| Zhou et al. | An improved algorithm using weighted guided coefficient and union self‐adaptive image enhancement for single image haze removal | |
| CN113160103B (en) | Image processing method and device, storage medium and terminal | |
| Jasper et al. | Natural image enhancement using a biogeography based optimization enhanced with blended migration operator | |
| CN110852977B (en) | Image enhancement method for fusing edge gray level histogram and human eye visual perception characteristics |
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 |