CN112561906A - Image processing method, device, equipment and medium - Google Patents
Image processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN112561906A CN112561906A CN202011552981.2A CN202011552981A CN112561906A CN 112561906 A CN112561906 A CN 112561906A CN 202011552981 A CN202011552981 A CN 202011552981A CN 112561906 A CN112561906 A CN 112561906A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- target
- pixel
- mapping
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 37
- 238000005286 illumination Methods 0.000 claims abstract description 159
- 238000013507 mapping Methods 0.000 claims abstract description 133
- 238000012545 processing Methods 0.000 claims abstract description 54
- 238000013441 quality evaluation Methods 0.000 claims description 49
- 238000000034 method Methods 0.000 claims description 19
- 230000003044 adaptive effect Effects 0.000 description 18
- 230000000007 visual effect Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses an image processing method, an image processing device, image processing equipment and an image processing medium, which relate to the technical field of Internet, wherein the image processing method comprises the following steps: when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image; determining mapping interval information according to the pixel quantile information; and carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image. The embodiment of the invention greatly reduces the time required by manually adjusting the image illumination link in the prior art and improves the image processing efficiency.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, an image processing device, and an image processing medium.
Background
With the rapid development of artificial intelligence technology, information processing systems such as machine vision systems are more and more popular, and great convenience is brought to life, work and learning of people.
In actual processing, an information processing system generally needs to process an input image to generate a processing result. In order to ensure the accuracy of the processing result, it is generally necessary to perform illumination adjustment on the image data input into the information processing system, thereby improving the image quality.
At present, the image illumination adjustment method mainly performs unified adjustment according to the existing brightness of an image. However, the brightness of the images is uneven, and the uniform brightness adjustment can cause the overexposure phenomenon of some images; when the original image is very dark and the quality of the image is very low, the images are uniformly adjusted in brightness, so that local distortion and extra stripe noise of the image occur, and the image quality is influenced; and in some images, when local brightness is too high and local brightness is too low, the image is easy to distort or is difficult to distinguish by unifying single images.
Therefore, when a complicated screenshot scene is faced by an auditor, the brightness and the contrast of the image often need to be manually adjusted, for example, because the brightness of the image is too dark, the brightness and the contrast of the image need to be manually adjusted to proper values, and then the content violation condition of the image can be normally judged. In the adjustment process, because the brightness differences of the images are different, the manual adjustment modes of each time are different, and the auditor needs to spend a certain time to adjust each image, for example, the adjustment time of each image to be adjusted needs about 8 seconds, which seriously affects the efficiency of the auditing side.
Disclosure of Invention
In view of this, embodiments of the present invention provide an image processing method, an image processing apparatus, an image processing device, and an image processing medium, so as to greatly reduce the time required for manually adjusting an image illumination link in the prior art, and improve the image processing efficiency.
In a first aspect, an embodiment of the present invention provides an image processing method, including: when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image; determining mapping interval information according to the pixel quantile information; and carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
In a second aspect, an embodiment of the present invention further provides an image processing apparatus, including:
the pixel quantile determining module is used for determining pixel quantile information according to the pixel information of the target image when the read target image needs illumination adjustment;
the mapping interval information determining module is used for determining mapping interval information according to the pixel quantile information;
and the self-adaptive adjusting module is used for carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
In a third aspect, an embodiment of the present invention further provides an image processing apparatus, including: a processor and a memory; the memory has stored therein at least one instruction that, when executed by the processor, causes the image processing apparatus to perform the image processing method according to the first aspect.
In a fourth aspect, the present invention also provides a computer-readable storage medium, where instructions of the computer-readable storage medium, when executed by a processor of a computer device, enable the computer device to execute the image processing method according to the first aspect.
According to the embodiment of the invention, when the read target image needs illumination adjustment, the pixel quantile information is determined according to the pixel information of the target image, the mapping interval information is determined according to the pixel quantile information, and the target image is subjected to self-adaptive illumination adjustment according to the mapping interval information, so that the aim of dynamically adjusting illumination is fulfilled, the image can have a good visual effect on a complex changing scene, the time required for manually adjusting an illumination link in the prior art is greatly reduced, the problem of low efficiency of an auditing side caused by the fact that an auditor needs to manually adjust the brightness and contrast of the image in the prior art is solved, the image auditing efficiency is improved, and the image processing efficiency is further improved.
Drawings
FIG. 1 is a flow chart illustrating steps of an image processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating the steps of an image processing method in an alternative embodiment of the invention;
FIG. 3 is a schematic diagram of image screening requiring adjusted illumination in accordance with an example of the present invention;
fig. 4 is a block diagram illustrating an image processing apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures or components relevant to the present invention are shown in the drawings, not all of them.
Fig. 1 is a schematic flowchart illustrating steps of an image processing method according to an embodiment of the present invention. The embodiment is applicable to an image processing situation, for example, to a situation of image illumination adjustment, and the image processing method may specifically include the following steps:
and 110, when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image.
The target image may refer to a currently read image, and specifically may include an image read by an image demander; the image demander may include various terminals that need to perform business processing by using images, such as a client terminal and a server terminal that can use an Application program (App), which is not limited in this embodiment.
Specifically, when an image is read, the currently read image can be used as a target image, and whether the target image needs illumination adjustment or not can be judged according to the image quality, so that the image quality is improved. If the target image needs to be subjected to illumination adjustment, pixel quantile information can be determined according to the pixel information of the target image, so that a brightness mapping interval corresponding to the target image can be determined according to the pixel quantile information in the following process.
For example, after the target image is read, a quality evaluation result of the target image may be generated by detecting the illumination intensity of the image, so as to determine whether the target image needs illumination adjustment according to the quality evaluation result. Optionally, the image processing method provided in the embodiment of the present invention may further include: reading a target image; judging whether the target image needs illumination adjustment or not according to the quality evaluation result of the target image; if the target image does not need to be subjected to illumination adjustment, the target image can be displayed, for example, the target image can be displayed according to the brightness information of the target image. If the target image needs illumination adjustment, the pixel quantile information can be determined according to the pixel information of the target image. The pixel information of the target image may specifically include a pixel value of the target image, such as a read pixel value of the original image; the pixel quantile information may include quantiles determined according to pixels of the image, and for example, may include a maximum quantile and a minimum quantile determined according to pixel values of the original image, and may be specifically used to determine a target interval in which the pixels of the image are located after being mapped, so as to avoid interference of some extreme points in the original image with the image.
And 120, determining mapping interval information according to the pixel quantile information.
The mapping interval information may indicate a target interval in which the pixel is mapped, and the mapping interval information may include a minimum value and a maximum value of the target interval, and in a case where the mapping interval information indicates the target interval in which the image brightness after the pixel of the image is located, the mapping interval information may include a maximum brightness value and a minimum brightness value after the image mapping, so that adaptive illumination adjustment may be performed subsequently according to the maximum brightness value and the minimum brightness value after the mapping.
And step 130, performing adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
The self-adaptive illumination adjustment is to adjust the brightness of the image according to the brightness of the image, so that the image which cannot be seen clearly due to illumination can be automatically converted into an image which can be observed clearly by naked eyes. Specifically, after the mapping interval information is determined, the embodiment of the present invention may perform adaptive illumination adjustment on the target image according to the mapping interval information to dynamically adjust illumination, so that a difference between a light part and a dark part in the adjusted target image is reduced, so that the adjusted target image is converted into an image that is easy to be clearly observed by naked eyes, thereby achieving an objective of performing adaptive illumination intensity processing on the image, and may generate a corresponding illumination adjustment result based on the brightness information after the target image is adjusted, so that corresponding business processing may be performed subsequently according to the illumination adjustment result, for example, the target image may be displayed according to the illumination adjustment result, which is not particularly limited in this embodiment.
Therefore, when the read target image needs illumination adjustment, the embodiment of the invention determines the pixel quantile information according to the pixel information of the target image, determines the mapping interval information according to the pixel quantile information, and performs self-adaptive illumination adjustment on the target image according to the mapping interval information to achieve the aim of dynamically adjusting illumination, so that the image has a good visual effect on a complex changing scene, the time required by manually adjusting an illumination link in the prior art is greatly reduced, the problem of low efficiency of an auditing side caused by manually adjusting the image brightness and contrast by an auditor in the prior art is solved, the image auditing efficiency is improved, and the image processing efficiency is further improved.
In the actual processing, after the target image is judged to need illumination adjustment, that is, after the target image needing illumination adjustment is screened out, the pixel quantile information can be determined based on the pixel information of the target image and the preset interference coefficient information, so that the target interval where the image pixel is mapped can be determined based on the pixel quantile information, interference of some extreme points in the original image on the image self-adaptive illumination adjustment is avoided, and the self-adaptive illumination adjustment effect is ensured.
Optionally, on the basis of the above embodiment, the determining pixel quantile information according to the pixel information of the target image in the embodiment of the present invention may specifically include: determining pixel information of the target image; and determining pixel quantile information of the target image based on the pixel information and preset interference coefficient information, wherein the pixel quantile information comprises a first pixel quantile and a second pixel quantile, and the first pixel quantile is greater than the second pixel quantile. The first pixel quantile can be the maximum quantile determined according to the image pixels and can be specifically used for determining the maximum value of the target interval after pixel mapping; the second pixel quantile may refer to a minimum quantile determined according to the image pixel, and may be specifically used to determine a minimum value of the target interval after the pixel mapping.
Furthermore, after the illumination adjustment result of the target image is obtained, the target image can be displayed according to the illumination adjustment result, so that a better visual effect is achieved. Optionally, the image processing method provided in the embodiment of the present invention further includes: and displaying the target image according to the illumination adjustment result.
Referring to fig. 2, a flowchart illustrating steps of an image processing method in an alternative embodiment of the present invention is shown. As shown in fig. 2, the image processing method in the embodiment of the present invention may specifically include the following steps:
Specifically, after the target image is read, the quality evaluation result of the target image can be determined based on the image illumination intensity, for example, the quality evaluation result can be generated by detecting the illumination intensity of the target image, so that whether the target image needs to be adjusted can be judged based on the quality evaluation result; if the target image needs to be adjusted, for example, when the illumination intensity of the target image is the illumination intensity in a relatively dark scene, and the quality evaluation result of the target image is the image brightness dim result, the step 240 may be skipped to perform, so that the pixel quantile information may be determined according to the pixel information of the target image in the following step for adaptive illumination adjustment; if the target image does not need to be adjusted, for example, if the illumination intensity of the target image is the illumination intensity in a relatively bright scene and the brightness of the target image exceeds a certain threshold, the target image can be directly displayed, i.e., step 230 is performed.
In the actual processing, the embodiment of the invention can process the target image by using the pre-trained image quality evaluation model to detect the illumination intensity of the target image to obtain the image dimming probability corresponding to the target image, and further can generate the quality evaluation result of the target image based on the image dimming probability. Further, before determining whether the target image needs to be subjected to illumination adjustment, the image processing method provided in the embodiment of the present invention may further include: evaluating the target image through a preset image quality evaluation model to obtain the image darkness probability; and generating a quality evaluation result of the target image based on the image dimming probability. The image dimming probability may refer to a dimming probability of the image, and a higher image dimming probability may indicate a higher possibility of image dimming.
In a specific implementation, the embodiment of the present invention may use an image quality evaluation model based on depth learning to perform image brightness detection, and may screen out a target image to be processed in a card threshold manner, as shown in fig. 3, the depth model serving as the image quality evaluation model may be used to predict an image dimming probability, so that a target image with an image dimming probability greater than a preset probability threshold may be determined as an image whose illumination needs to be adjusted. Further, the generating of the quality evaluation result of the target image based on the image dimming probability in the embodiment of the present invention may specifically include: judging whether the image dimming probability is greater than a preset probability threshold value or not; if the image dimming probability is larger than a preset probability threshold, generating an image brightness dimming result; and if the image dimming probability is smaller than a preset probability threshold, generating a normal image brightness result. The preset probability threshold may be set according to the image brightness adjustment requirement, for example, may be set to 0.8 or 0.7, and this is not specifically set in the embodiment of the present invention.
Optionally, the determining, according to the quality evaluation result of the target image, whether the target image needs to be subjected to illumination adjustment may specifically include: when the quality evaluation result is an image brightness normal result, judging whether brightness information of the target image meets a preset illumination regulation condition; if the brightness information of the target image meets a preset illumination adjustment condition, judging that the target image needs illumination adjustment; otherwise, judging that the target image does not need illumination adjustment. The brightness information may be image brightness, such as HSV brightness. It should be noted that hsv (hue Saturation value) is a color space created according to the intuitive characteristics of color, and is also called a hexagonal cone Model (Hexcone Model), and the parameters of the color in this Model are hue, Saturation and lightness, respectively.
In this embodiment, the detection of the image brightness may be mainly used to distinguish whether the image needs additional illumination adjustment processing. When the quality evaluation result of the target image is the normal image brightness result, the target image can be screened again according to the HSV brightness of the target image, namely whether the brightness information of the target image meets the preset illumination regulation condition or not is judged, so that the target image can be judged to need illumination regulation when the brightness information of the target image meets the preset illumination regulation condition, and the target image does not need illumination regulation when the brightness information of the target image does not meet the preset illumination regulation condition.
Of course, in the embodiment of the present invention, when the quality evaluation result of the target image is the image brightness dim result, it may also be determined that the target image does not need to be subjected to illumination adjustment. Further, the determining whether the target image needs to be subjected to illumination adjustment according to the quality evaluation result of the target image may further include: and when the quality evaluation result is an image brightness dim result, judging that the target image does not need illumination adjustment.
As an example of the present invention, after reading an image into a memory, an image demander may determine the image as a target image, and then may determine whether the target image needs to be adjusted through brightness detection and image screening, i.e., detecting the illumination intensity of the image and determining whether illumination processing is required to determine whether the target image needs to be adjusted, as shown in figure 3, the read target image may be input into a depth model as an image quality evaluation model, therefore, the quality evaluation result of the target image can be generated based on the image dimming probability output by the depth model, and when the quality evaluation result of the target image is the image brightness dimming result, when the image dimming probability output by the depth model is greater than the preset probability threshold, determining that the target image needs illumination self-adaptive adjustment, and then skipping to the step 240 for execution; and when the quality evaluation result of the target image is the normal image brightness result, namely when the image dimming probability output by the depth model is not greater than the preset probability threshold, whether the brightness information of the target image meets the preset illumination adjustment condition can be determined by judging whether the HSV brightness of the target image is smaller than the brightness threshold. If the HSV brightness of the target image is smaller than the brightness threshold, determining that the brightness information of the target image is in accordance with a preset illumination adjustment condition, and determining that the target image is an image needing illumination adjustment, namely determining that the target image needs illumination self-adaptive adjustment, and then skipping to the step 240 for execution; if the HSV brightness of the target image is not less than the brightness threshold, for example, if the HSV brightness of the target image is greater than or equal to the brightness threshold, it may be determined that the brightness information of the target image does not comply with the preset illumination adjustment condition, so that it may be determined that the target image does not require illumination adjustment, and then step 230 is performed. The brightness threshold may be a brightness index set according to the illumination adjustment of the image, and may be specifically used to determine whether the image needs illumination adjustment, for example, the brightness threshold may be set to 75 or 80, and the present example is not limited in this embodiment.
It can be seen that, in this embodiment, after the images that need additional illumination adjustment processing are screened out by the depth model, that is, after the images with illumination problems are screened out by the depth model, the lightness index in the image HSV space can be used as the evaluation standard, the remaining images that are considered by the depth model to have no illumination problems are screened out again, that is, for the remaining images that are considered by the depth model to have no illumination problems, the lightness index in the image HSV space is used as the evaluation standard, and then, when the lightness threshold is set to 75, the images whose mean lightness is less than 75 in HSV can be considered as the images whose illumination needs to be adjusted, so that all the images whose brightness needs to be adjusted are screened out, and then, the image processing step 240 is executed.
Of course, the embodiment of the present invention may also screen out a target image that needs to be subjected to illumination adjustment by using other manners, for example, screening by using a gray histogram, which is not particularly limited in this embodiment of the present invention.
Step 230, if the target image does not need to be illuminated, displaying the target image according to the brightness information of the target image.
Step 240, if the target image needs illumination adjustment, determining pixel information of the target image.
And 250, determining pixel quantile information of the target image based on the pixel information and preset interference coefficient information.
The pixel quantile information comprises a first pixel quantile and a second pixel quantile, and the first pixel quantile is larger than the second pixel quantile. The interference coefficient information may include a coefficient set in advance for the image interference, such as may be set to 1%, 2%, and the like, which is not specifically limited in this embodiment of the present invention.
For example, when the preset interference coefficient information is 1%, after the pixel information of the target image is determined, that is, after the pixel value of the original image is determined, the first 1% of the large pixel values of the original image may be referred to as a maximum quantile (maxpercent), and the maximum quantile is set as a first pixel quantile, so that all the pixel values larger than the maximum quantile in the target image may be set as the maximum quantile, and the first 1% of the small pixel values of the original image may be referred to as a minimum quantile (minpercent), so that the maximum quantile is set as the first pixel quantile, and thus all the pixel values smaller than the minimum quantile in the target image may be set as the minimum quantile, and further, the interference of some extreme value points in the original image on the image may be avoided, and the purpose of adaptive histogram equalization may be achieved.
Note that adaptive histogram equalization refers to: after the target image is divided into a plurality of blocks, each block can be arranged from small to large according to the pixel value of the block, and the block can be flattened into a more balanced mode. For each point's pixel value img (i, j), the transformation formula may be: imgequalizatin(i, j) ═ cumsum (img (i, j)). 255; wherein, cumsum (x) may represent a frequency at which a histogram gray level in the block is less than or equal to x; img (i, j) may represent a pixel value corresponding to the coordinate (i, j). The local histogram equalization makes the pixel distribution in each small block as uniform as possible, thereby improving the local contrast. Compared with global histogram equalization, adaptive histogram equalization performs equalization locally, has a low probability of image distortion, and particularly for scenes in which excessive brightness and excessive darkness appear simultaneously in the same image: global histogram equalization is prone to distortion; the local histogram equalization is processed locally, so that no distortion effect occurs; meanwhile, the brightness of the dark part in the original image can be properly improved.
Specifically, after determining the pixel sub-bit information, the embodiment of the present invention may determine the mapping interval information based on the pixel sub-bit information and by combining the mapping coefficient of the target image, so that adaptive histogram normalization may be performed subsequently based on the mapping interval information. Optionally, the image processing method provided in the embodiment of the present invention further includes: determining an average brightness of the target image; subtracting the average brightness by adopting a preset image brightness threshold value to obtain a brightness difference coefficient; determining a mapping coefficient of the target image based on the brightness difference coefficient. The average brightness of the target image can be determined according to the average light intensity in the original image of the target image; the preset image brightness threshold may be set according to image mapping requirements, for example, may be set to 87.5, and this is not particularly limited in the embodiment of the present invention.
As an example of the present invention, after calculating the average brightness of the target image as light according to the average light intensity in the original image, the average brightness light may be subtracted from a preset image brightness threshold 87.5 to obtain a brightness difference coefficient, and then the brightness difference coefficient may be used to perform calculation, for example, according to a mapping coefficient calculation formula, to obtain a mapped coefficient ratio, and the coefficient ratio may be determined as the mapping coefficient of the target image. Wherein, the calculation formula of the mapping coefficient is as follows:
after the mapping coefficient of the target image is determined, the mapping coefficient can be respectively calculated with the first pixel quantile and the second pixel quantile in the pixel quantile information to obtain a first brightness threshold and a second brightness threshold, and the first brightness threshold and the second brightness threshold can be used as mapping interval information, so that the gray level of the target image can be linearly mapped to a specified interval based on the first brightness threshold and the second brightness threshold in the following process, and the purpose of self-adaptive histogram normalization is achieved. It should be noted that the mapping coefficient can be used to measure the scale of the image that needs to be scaled; if the average brightness value of the image is smaller, the value needing radiation is larger; meanwhile, the mapped upper and lower boundaries are also related to the upper quantile and the lower quantile of the image, namely the maximum value and the minimum value of the brightness of the mapped image are respectively related to the maximum quantile and the minimum quantile of the image.
Further, the mapping interval information in the embodiment of the present invention may include a first luminance threshold and a second luminance threshold, and the determining the mapping interval information according to the pixel quantile information specifically includes the following sub-steps:
substep 2601, determining a first luminance threshold value according to the first pixel quantile and the mapping coefficient of the target image;
sub-step 2602, determining a second luminance threshold value depending on said second quantile of pixels and said mapping coefficient.
In the actual processing, the first brightness threshold determined according to the first pixel quantile can be used as the maximum brightness value after image mapping, and the second brightness threshold determined according to the second pixel quantile can be used as the minimum brightness value after image mapping, so that the target image can be adjusted to the proper brightness and contrast range according to the first brightness threshold and the second brightness threshold, and the purpose of self-adaptive illumination intensity processing is achieved.
Further, in the embodiment of the present invention, the first luminance threshold is greater than the second luminance threshold, and the mapping coefficient is a coefficient determined according to an average luminance of the target image.
Optionally, in the embodiment of the present invention, determining the first luminance threshold according to the first pixel quantile and the mapping coefficient of the target image may specifically include: determining a product of the first pixel quantile and the mapping coefficient as a target product, and comparing the target product with a preset mapping target threshold to determine a first brightness threshold based on the comparison result. The preset mapping target threshold may be set according to the image mapping requirement, for example, a first mapping target threshold and/or a second mapping target threshold may be set, which is not specifically limited in this embodiment. It should be noted that the first mapping target threshold may represent a maximum threshold of the mapped maximum brightness, and the second mapping target threshold may represent a minimum threshold of the mapped maximum brightness.
Further, in a case that the preset mapping target threshold includes a first mapping target threshold and a second mapping target threshold, the embodiment of the present invention compares the target product with the preset mapping target threshold to determine the first brightness threshold based on the comparison result, which may specifically include: determining the target product as a first brightness threshold when the target product is less than the first mapping target threshold and greater than the second mapping target threshold; determining the first mapping target threshold as a first brightness threshold when the target product is greater than or equal to the first mapping target threshold; determining the second mapping target threshold as a first brightness threshold when the target product is less than or equal to the second mapping target threshold.
For example, in a case where the first mapping target threshold is set to 240 and the second mapping target threshold is set to 100, after the first pixel quantile maxpercent is determined, the product of the first pixel quantile maxpercent and the mapping coefficient ratio may be determined as the target product maxpercen ratio, and the target product maxpercen ratio may be compared with the first mapping target threshold 240 and the second mapping target threshold 100, such as the target product maxpercen ratio may be compared with the first mapping target threshold 240 first to take out the minimum value min (maxpercen ratio, 240) therebetween to compare with the second mapping target threshold 100, so that the maximum value (100, min (maxpercen ratio, 240)) of min (maxpercen ratio, 240) and the second mapping target threshold 100 may be determined as the first luminance (100, 240) hi ghermax).
Of course, after the second pixel quantile and the mapping coefficient of the target image are determined, the second luminance threshold value may be determined by using the second pixel quantile and the mapping coefficient of the target image in the embodiment of the present invention. Optionally, in the embodiment of the present invention, determining the second luminance threshold according to the second pixel quantile and the mapping coefficient may specifically include: determining a product of the second pixel quantile and the mapping coefficient as a second luminance threshold. For example, after the second pixel quantile minpercent is determined, the product minpercent ratio of the second pixel quantile minpercent and the mapping coefficient ratio may be determined as the second luminance threshold value lower, that is, lower ratio. .
And 270, performing adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
Specifically, after the mapping interval information is determined, the embodiment of the present invention may perform adaptive illumination adjustment on the target image based on the first brightness threshold and the second brightness threshold in the mapping interval information, for example, after adaptive histogram equalization, the overall brightness of the target image is linearly mapped to the specified adaptive interval through adaptive histogram normalization, so as to generate an illumination adjustment result of the target image. The upper limit and the lower limit of the adaptive interval are related to the original brightness of the target image, so that the image illumination conditions can be classified more finely, for example, the image illumination conditions can be divided into an overexposed scene, a multi-light source scene, a half-overexposed and a half-underexposed scene, and the like, and then the images of different scenes can be processed more specifically, so as to achieve a better visual effect.
Specifically, after the illumination adjustment result is obtained, the target image can be displayed based on the good illumination adjustment result, that is, the image is displayed according to the adjusted brightness, so that the image can have a good visual effect on a complex changing scene.
As an application example of the present invention, after an image is read by an audit side of an APP, the image may be determined as a target image to detect the illumination intensity of the image and determine whether adjustment is needed; if the image does not need to be adjusted, the image can be directly displayed; if the image needs to be adjusted, the image processing method provided by the embodiment of the invention can be used for adaptively adjusting the illumination aiming at the image so as to display the image according to the adjustment result, namely, the image after the adaptive illumination adjustment is displayed, so that the image can have a good visual effect on a complex changing scene, the time required by manually adjusting an illumination link is greatly reduced, and the efficiency of an auditing side is further improved.
Of course, the image processing method provided in the embodiment of the present invention may be applied to other image processing scenarios besides the image review side, for example, a data enhancement direction may be applied, and the present embodiment is not limited to this specifically.
To sum up, after the target image is read, the embodiment of the present invention may determine whether the target image needs illumination adjustment according to the quality evaluation result of the target image and the brightness information of the target image, for example, use the image quality evaluation model based on deep learning to screen the target image that needs to be processed in a threshold value mode, and use the brightness index in the image hsv space as the evaluation standard to screen the target image that is considered to have no illumination problem by the image quality evaluation model again, that is, screen the image that needs illumination adjustment according to the illumination detection method based on the combination of deep learning and the conventional method, so as to avoid unnecessary processing of the image under normal illumination conditions, thereby improving the image processing efficiency.
In addition, after the target image needing to adjust illumination is screened out, the pixel quantile information is determined according to the pixel information of the target image and the preset interference coefficient information, so that image blocks with different brightness degrees of the image can be adjusted by using a self-adaptive histogram equalization method successively based on a first pixel quantile and a second pixel quantile in the pixel quantile information, the difference of the brightness parts in the same image is reduced, and mapping interval information can be determined according to the first pixel quantile and the second pixel quantile in the pixel quantile information and the mapping coefficient of the target image, so that self-adaptive illumination adjustment can be performed on the target image subsequently based on the average brightness, the highest brightness, the maximum brightness, the brightness and the like of the image, The minimum brightness is used for dynamically adjusting illumination, so that images of different scenes can be processed more specifically to achieve a better visual effect, for example, for scenes with strong illumination transformation such as live broadcast and short video, a simple illumination screening mechanism is designed by combining a deep learning technology and a traditional method, images needing to be adjusted are screened out, and illumination can be dynamically adjusted according to the average brightness, the maximum brightness and the minimum brightness of the images, so that the images can have a better visual effect for the scenes with complex transformation, the time required by manually adjusting an illumination link is greatly reduced, and the image processing efficiency is further improved.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention.
Referring to fig. 4, a schematic diagram of a structural block of an image processing apparatus in an embodiment of the present invention is shown, where the image processing apparatus may specifically include the following modules:
a pixel quantile determining module 410, configured to determine pixel quantile information according to pixel information of a read target image when the target image needs to be subjected to illumination adjustment;
a mapping interval information determining module 420, configured to determine mapping interval information according to the pixel quantile information;
the adaptive adjustment module 430 is configured to perform adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
On the basis of the foregoing embodiment, optionally, the image processing apparatus may further include the following sub-modules:
the image reading module is used for reading a target image;
the image judgment module is used for judging whether the target image needs illumination adjustment or not according to the quality evaluation result of the target image;
and the image display module is used for displaying the target image according to the brightness information of the target image when the target image does not need illumination adjustment.
In an alternative embodiment of the present invention, the image judgment module may include the following sub-modules:
the brightness judgment sub-module is used for judging whether brightness information of the target image meets a preset illumination regulation condition or not when the quality evaluation result is an image brightness normal result; if the brightness information of the target image meets a preset illumination adjustment condition, triggering a first judgment sub-module to judge that the target image needs illumination adjustment; if the brightness information of the target image does not accord with the preset illumination adjustment condition, triggering a second judgment submodule to judge that the target image does not need illumination adjustment;
the first judgment sub-module is used for judging that the target image needs illumination adjustment when the brightness information of the target image meets a preset illumination adjustment condition;
and the second judging submodule is used for judging that the target image does not need illumination adjustment when the brightness information of the target image does not accord with the preset illumination adjustment condition.
Optionally, on the basis of the foregoing embodiment, the first determining sub-module is further configured to determine that the target image does not need to be subjected to illumination adjustment when the quality evaluation result is an image brightness dim result.
Optionally, the image processing apparatus may further include the following sub-modules:
the image quality evaluation module is used for evaluating the target image through a preset image quality evaluation model to obtain the image darkness probability;
and the quality evaluation result module is used for generating a quality evaluation result of the target image based on the image dimming probability.
For example, before the image determination module determines whether the target image needs to be subjected to illumination adjustment, the image quality evaluation module performs evaluation processing on the target image through a preset image quality evaluation model to obtain an image dimming probability, so that the quality evaluation result module can generate a quality evaluation result of the target image based on the image dimming probability, and further, the image determination module can determine whether the target image needs to be subjected to illumination adjustment according to the quality evaluation result of the target image.
Optionally, the quality evaluation result module may include the following sub-modules:
the dimming probability judgment submodule is used for judging whether the image dimming probability is greater than a preset probability threshold value or not;
the dimming result generation submodule is used for generating an image brightness dimming result when the image dimming probability is greater than a preset probability threshold;
and the normal brightness result submodule is used for generating a normal image brightness result when the image dimming probability is smaller than a preset probability threshold.
Optionally, the pixel quantile determining module may include the following sub-modules:
a pixel determination sub-module for determining pixel information of the target image;
the quantile determining submodule is used for determining pixel quantile information of the target image based on the pixel information and preset interference coefficient information, the pixel quantile information comprises a first pixel quantile and a second pixel quantile, and the first pixel quantile is larger than the second pixel quantile.
In an optional embodiment of the present invention, the mapping section information includes a first brightness threshold and a second brightness threshold, and the mapping section information determining module may include the following sub-modules:
a first luminance threshold determination submodule for determining a first luminance threshold according to the first pixel quantile and the mapping coefficient of the target image;
and the second brightness threshold value determining submodule is used for determining a second brightness threshold value according to the second pixel quantile and the mapping coefficient.
Further, in the embodiment of the present invention, the first luminance threshold is greater than the second luminance threshold, and the mapping coefficient is a coefficient determined according to an average luminance of the target image. Optionally, the first luminance threshold determination sub-module is specifically configured to determine a product of the first pixel quantile and the mapping coefficient as a target product, and compare the target product with a preset mapping target threshold, so as to determine a first luminance threshold based on a comparison result; the second luminance threshold determination submodule is specifically configured to determine a product of the second pixel quantile and the mapping coefficient as a second luminance threshold.
Optionally, the mapping target threshold in the embodiment of the present invention includes a first mapping target threshold and a second mapping target threshold, and the first brightness threshold determining sub-module may include the following units:
a first determination unit for determining the target product as a first brightness threshold when the target product is less than the first mapping target threshold and greater than the second mapping target threshold;
a second determination unit for determining the first mapping target threshold as a first brightness threshold when the target product is greater than or equal to the first mapping target threshold;
a third determining unit for determining the second mapping target threshold as the first brightness threshold when the target product is less than or equal to the second mapping target threshold.
Optionally, the image processing apparatus in the embodiment of the present invention further includes the following modules:
the average brightness determining module is used for determining the average brightness of the target image;
the brightness difference coefficient determining module is used for subtracting the average brightness from a preset image brightness threshold value to obtain a brightness difference coefficient;
a mapping coefficient determining module for determining a mapping coefficient of the target image based on the brightness difference coefficient.
Further, the image display module in the embodiment of the present invention may be further configured to display the target image according to the illumination adjustment result.
It should be noted that the image processing apparatus provided above can execute the image processing method provided in any embodiment of the present invention, and has the corresponding functions and advantages of the execution method.
In a specific implementation, the image processing apparatus described above may be integrated in an image processing device. The image processing apparatus may be configured as two or more physical entities, or may be configured as one physical entity, for example, the electronic apparatus may be a Personal Computer (PC), a Computer, a server, a game console, or the like.
Further, an embodiment of the present invention further provides an image processing apparatus, including: a processor and a memory. At least one instruction is stored in the memory, and the instruction is executed by the processor, so that the image processing device executes the image processing method in the method embodiment. Specifically, the processor in the present embodiment may execute various functional applications and data processing of the image processing apparatus by running software programs, instructions, and modules stored in the memory, that is, implement the image processing method described above. For example, when the processor executes one or more programs stored in the memory, the following operations are implemented: when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image; determining mapping interval information according to the pixel quantile information; and carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
Embodiments of the present invention further provide a computer-readable storage medium, where instructions in the computer-readable storage medium, when executed by a processor of a computer device, enable the computer device to perform the image processing method according to the above method embodiment. Illustratively, the image processing method includes: when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image; determining mapping interval information according to the pixel quantile information; and carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
It should be noted that, as for the embodiments of the apparatus, the device, and the storage medium, since they are basically similar to the embodiments of the method, the description is relatively simple, and in relevant places, reference may be made to the partial description of the embodiments of the method.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by suitable instruction execution devices.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in more detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the claims.
Claims (15)
1. An image processing method, comprising:
when the read target image needs illumination adjustment, determining pixel quantile information according to the pixel information of the target image;
determining mapping interval information according to the pixel quantile information;
and carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
2. The image processing method according to claim 1, further comprising:
reading a target image;
judging whether the target image needs illumination adjustment or not according to the quality evaluation result of the target image;
and if the target image does not need illumination adjustment, displaying the target image according to the brightness information of the target image.
3. The image processing method according to claim 2, wherein the determining whether the target image needs illumination adjustment according to the quality evaluation result of the target image comprises:
when the quality evaluation result is an image brightness normal result, judging whether brightness information of the target image meets a preset illumination regulation condition;
if the brightness information of the target image meets a preset illumination adjustment condition, judging that the target image needs illumination adjustment; otherwise, judging that the target image does not need illumination adjustment.
4. The image processing method according to claim 3, wherein the determining whether the target image needs illumination adjustment according to the quality evaluation result of the target image further comprises:
and when the quality evaluation result is an image brightness dim result, judging that the target image does not need illumination adjustment.
5. The image processing method according to claim 3, wherein before determining whether the target image needs illumination adjustment, the method further comprises:
evaluating the target image through a preset image quality evaluation model to obtain the image darkness probability;
and generating a quality evaluation result of the target image based on the image dimming probability.
6. The image processing method according to claim 5, wherein the generating a quality evaluation result of the target image based on the image dimming probability comprises:
judging whether the image dimming probability is greater than a preset probability threshold value or not;
if the image dimming probability is larger than a preset probability threshold, generating an image brightness dimming result;
and if the image dimming probability is smaller than a preset probability threshold, generating a normal image brightness result.
7. The method according to claim 1, wherein said determining pixel quantile information from pixel information of the target image comprises:
determining pixel information of the target image;
and determining pixel quantile information of the target image based on the pixel information and preset interference coefficient information, wherein the pixel quantile information comprises a first pixel quantile and a second pixel quantile, and the first pixel quantile is greater than the second pixel quantile.
8. The method according to claim 7, wherein the mapping interval information includes a first luminance threshold and a second luminance threshold, and the determining mapping interval information according to the pixel quantile information includes:
determining a first brightness threshold value according to the first pixel quantile and the mapping coefficient of the target image;
determining a second luminance threshold value according to the second pixel quantile and the mapping coefficient.
9. The image processing method according to claim 8, wherein the first luminance threshold value is larger than the second luminance threshold value, and the mapping coefficient is a coefficient determined depending on an average luminance of the target image;
the determining a first luminance threshold according to the first pixel quantile and the mapping coefficient of the target image comprises: determining a product of the first pixel quantile and the mapping coefficient as a target product, and comparing the target product with a preset mapping target threshold to determine a first brightness threshold based on a comparison result;
the determining a second luminance threshold from the second pixel quantile and the mapping coefficient includes: determining a product of the second pixel quantile and the mapping coefficient as a second luminance threshold.
10. The method of claim 9, wherein the mapping target threshold comprises a first mapping target threshold and a second mapping target threshold, and the comparing the target product with a preset mapping target threshold to determine a first brightness threshold based on the comparison comprises:
determining the target product as a first brightness threshold when the target product is less than the first mapping target threshold and greater than the second mapping target threshold;
determining the first mapping target threshold as a first brightness threshold when the target product is greater than or equal to the first mapping target threshold;
determining the second mapping target threshold as a first brightness threshold when the target product is less than or equal to the second mapping target threshold.
11. The image processing method according to any one of claims 8 to 10, further comprising:
determining an average brightness of the target image;
subtracting the average brightness by adopting a preset image brightness threshold value to obtain a brightness difference coefficient;
determining a mapping coefficient of the target image based on the brightness difference coefficient.
12. The image processing method according to any one of claims 1 to 10, further comprising:
and displaying the target image according to the illumination adjustment result.
13. An image processing apparatus characterized by comprising:
the pixel quantile determining module is used for determining pixel quantile information according to the pixel information of the target image when the read target image needs illumination adjustment;
the mapping interval information determining module is used for determining mapping interval information according to the pixel quantile information;
and the self-adaptive adjusting module is used for carrying out self-adaptive illumination adjustment on the target image according to the mapping interval information to obtain an illumination adjustment result of the target image.
14. An image processing apparatus characterized by comprising: a processor and a memory;
the memory has stored therein at least one instruction that, when executed by the processor, causes the image processing apparatus to perform the image processing method of any of claims 1 to 12.
15. A computer-readable storage medium, wherein instructions in the readable storage medium, when executed by a processor of a computer device, enable the computer device to perform the image processing method of any of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011552981.2A CN112561906A (en) | 2020-12-24 | 2020-12-24 | Image processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011552981.2A CN112561906A (en) | 2020-12-24 | 2020-12-24 | Image processing method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561906A true CN112561906A (en) | 2021-03-26 |
Family
ID=75033675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011552981.2A Pending CN112561906A (en) | 2020-12-24 | 2020-12-24 | Image processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561906A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700422A (en) * | 2021-01-06 | 2021-04-23 | 百果园技术(新加坡)有限公司 | Overexposure point detection method and device, electronic equipment and storage medium |
| CN113470156A (en) * | 2021-06-23 | 2021-10-01 | 网易（杭州）网络有限公司 | Texture mapping hybrid processing method and device, electronic equipment and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050036033A1 (en) * | 2003-05-16 | 2005-02-17 | Toshie Imai | Brightness correction for image |
| CN103729854A (en) * | 2014-01-16 | 2014-04-16 | 重庆邮电大学 | Tensor-model-based infrared dim target detecting method |
| CN104156921A (en) * | 2014-08-08 | 2014-11-19 | 大连理工大学 | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method |
| US20150220789A1 (en) * | 2014-01-31 | 2015-08-06 | The Charles Stark Draper Technology, Inc. | Systems and methods for detecting and tracking objects in a video stream |
| CN106296612A (en) * | 2016-08-09 | 2017-01-04 | 南京工业大学 | The stagewise monitor video sharpening system and method that a kind of image quality evaluation and weather conditions guide |
| CN107230182A (en) * | 2017-08-03 | 2017-10-03 | 腾讯科技（深圳）有限公司 | A kind of processing method of image, device and storage medium |
| WO2017166886A1 (en) * | 2016-03-30 | 2017-10-05 | 努比亚技术有限公司 | Image processing system and method |
| CN107257452A (en) * | 2017-07-21 | 2017-10-17 | 浙江大华技术股份有限公司 | A kind of image processing method, device and computing device |
| CN107977941A (en) * | 2017-12-04 | 2018-05-01 | 国网山东省电力公司电力科学研究院 | A kind of bright areas color fidelity and the image defogging method of contrast enhancing |
| CN108259701A (en) * | 2018-01-17 | 2018-07-06 | 深圳市唯特视科技有限公司 | A kind of color reproduction method based on high dynamic range Color Gamut Mapping |
| CN108307125A (en) * | 2018-02-08 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image-pickup method, device and storage medium |
| CN109785251A (en) * | 2018-12-25 | 2019-05-21 | 北京中科慧眼科技有限公司 | A kind of picture quality method for improving, device and automated driving system |
| CN109905677A (en) * | 2019-03-21 | 2019-06-18 | 重庆工程职业技术学院 | A kind of mine supervision image enhancement processing method |
| CN110223244A (en) * | 2019-05-13 | 2019-09-10 | 浙江大华技术股份有限公司 | A kind of method, apparatus of image procossing, electronic equipment and storage medium |
| CN110807748A (en) * | 2019-11-06 | 2020-02-18 | 广州市皓品信息科技有限公司 | New tone mapping image enhancement method based on high dynamic range |
| CN111080577A (en) * | 2019-11-27 | 2020-04-28 | 北京至真互联网技术有限公司 | Method, system, device and storage medium for evaluating quality of fundus image |
| CN111200709A (en) * | 2019-01-08 | 2020-05-26 | 英属开曼群岛商麦迪创科技股份有限公司 | Method for setting light source of camera system, camera system and vehicle |
| CN111598862A (en) * | 2020-05-13 | 2020-08-28 | 北京推想科技有限公司 | Breast molybdenum target image segmentation method, device, terminal and storage medium |
| CN111860533A (en) * | 2019-04-30 | 2020-10-30 | 深圳数字生命研究院 | Image recognition method and device, storage medium and electronic device |
-
2020
- 2020-12-24 CN CN202011552981.2A patent/CN112561906A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050036033A1 (en) * | 2003-05-16 | 2005-02-17 | Toshie Imai | Brightness correction for image |
| CN103729854A (en) * | 2014-01-16 | 2014-04-16 | 重庆邮电大学 | Tensor-model-based infrared dim target detecting method |
| US20150220789A1 (en) * | 2014-01-31 | 2015-08-06 | The Charles Stark Draper Technology, Inc. | Systems and methods for detecting and tracking objects in a video stream |
| CN104156921A (en) * | 2014-08-08 | 2014-11-19 | 大连理工大学 | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method |
| WO2017166886A1 (en) * | 2016-03-30 | 2017-10-05 | 努比亚技术有限公司 | Image processing system and method |
| CN106296612A (en) * | 2016-08-09 | 2017-01-04 | 南京工业大学 | The stagewise monitor video sharpening system and method that a kind of image quality evaluation and weather conditions guide |
| CN107257452A (en) * | 2017-07-21 | 2017-10-17 | 浙江大华技术股份有限公司 | A kind of image processing method, device and computing device |
| CN107230182A (en) * | 2017-08-03 | 2017-10-03 | 腾讯科技（深圳）有限公司 | A kind of processing method of image, device and storage medium |
| CN107977941A (en) * | 2017-12-04 | 2018-05-01 | 国网山东省电力公司电力科学研究院 | A kind of bright areas color fidelity and the image defogging method of contrast enhancing |
| CN108259701A (en) * | 2018-01-17 | 2018-07-06 | 深圳市唯特视科技有限公司 | A kind of color reproduction method based on high dynamic range Color Gamut Mapping |
| CN108307125A (en) * | 2018-02-08 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of image-pickup method, device and storage medium |
| CN109785251A (en) * | 2018-12-25 | 2019-05-21 | 北京中科慧眼科技有限公司 | A kind of picture quality method for improving, device and automated driving system |
| CN111200709A (en) * | 2019-01-08 | 2020-05-26 | 英属开曼群岛商麦迪创科技股份有限公司 | Method for setting light source of camera system, camera system and vehicle |
| CN109905677A (en) * | 2019-03-21 | 2019-06-18 | 重庆工程职业技术学院 | A kind of mine supervision image enhancement processing method |
| CN111860533A (en) * | 2019-04-30 | 2020-10-30 | 深圳数字生命研究院 | Image recognition method and device, storage medium and electronic device |
| CN110223244A (en) * | 2019-05-13 | 2019-09-10 | 浙江大华技术股份有限公司 | A kind of method, apparatus of image procossing, electronic equipment and storage medium |
| CN110807748A (en) * | 2019-11-06 | 2020-02-18 | 广州市皓品信息科技有限公司 | New tone mapping image enhancement method based on high dynamic range |
| CN111080577A (en) * | 2019-11-27 | 2020-04-28 | 北京至真互联网技术有限公司 | Method, system, device and storage medium for evaluating quality of fundus image |
| CN111598862A (en) * | 2020-05-13 | 2020-08-28 | 北京推想科技有限公司 | Breast molybdenum target image segmentation method, device, terminal and storage medium |
Non-Patent Citations (7)
| Title |
|---|
| CHUNHE SHI等: "Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System", 《SYMMETRY》, vol. 12, no. 9, 20 September 2020 (2020-09-20), pages 1 - 18 * |
| MIGUEL A. MARTÍNEZ等: "Adaptive exposure estimation for high dynamic range imaging applied to natural scenes and daylight skies", 《APPLIED OPTICS》, vol. 54, no. 4, 31 December 2015 (2015-12-31), pages 1 - 11 * |
| WENCHENG WANG等: "Adaptive image enhancement method for correcting low-illumination images", 《INFORMATION SCIENCES》, vol. 496, 8 May 2019 (2019-05-08), pages 25 * |
| 仝清芬: "基于iCAM框架的彩色数字图像色差评价研究", 《中国优秀硕士学位论文全文数据库：信息科技辑》, no. 2014, 15 October 2014 (2014-10-15), pages 138 - 980 * |
| 寇杏子: "结合极化特征和图像特征的极化SAR图像分类研究", 《中国优秀硕士学位论文全文数据库：信息科技辑》, no. 2014, 15 November 2014 (2014-11-15), pages 136 - 805 * |
| 王晓红等: "不同亮度下无参考图像质量评价方法", 《光学技术》, no. 05, 15 September 2018 (2018-09-15), pages 569 - 575 * |
| 钱晟: "基于Retinex理论的图像增强算法的应用研究", 《中国优秀硕士学位论文全文数据库：信息科技辑》, no. 2016, 15 March 2016 (2016-03-15), pages 138 - 6834 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700422A (en) * | 2021-01-06 | 2021-04-23 | 百果园技术(新加坡)有限公司 | Overexposure point detection method and device, electronic equipment and storage medium |
| CN113470156A (en) * | 2021-06-23 | 2021-10-01 | 网易（杭州）网络有限公司 | Texture mapping hybrid processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Objective quality assessment for color-to-gray image conversion | |
| EP3300061A1 (en) | Image processing apparatus | |
| Cheng et al. | Efficient histogram modification using bilateral Bezier curve for the contrast enhancement | |
| US20210158488A1 (en) | Image edge processing method, electronic device, and computer readable storage medium | |
| US8577142B2 (en) | Image processing device, image processing method and program with improved image contrast | |
| US20140139561A1 (en) | Display Processing Method Display Processing Device and Display | |
| CN108876742B (en) | Image color enhancement method and device | |
| WO2021218603A1 (en) | Image processing method and projection system | |
| CN115115554B (en) | Image processing method and device based on enhanced image and computer equipment | |
| CN112561906A (en) | Image processing method, device, equipment and medium | |
| TWI390483B (en) | Apparatus and method for contrast control | |
| CN110751608A (en) | Night scene high dynamic range image fusion method and device and electronic equipment | |
| WO2021180173A1 (en) | Image processing method and apparatus, device and storage medium | |
| Ok et al. | HDR tone mapping algorithm based on difference compression with adaptive reference values | |
| Sun et al. | Dynamic backlight scaling considering ambient luminance for mobile videos on lcd displays | |
| US10445865B1 (en) | Method and apparatus for converting low dynamic range video to high dynamic range video | |
| CN108961209B (en) | Pedestrian image quality evaluation method, electronic device and computer readable medium | |
| TW201606732A (en) | Image adjusting method and related display | |
| Chubarau et al. | Perceptual image quality assessment for various viewing conditions and display systems | |
| CN117218039A (en) | Image processing method, device, computer equipment and storage medium | |
| An et al. | Perceptual brightness-based inverse tone mapping for high dynamic range imaging | |
| CN109982012B (en) | Image processing method and device, storage medium and terminal | |
| CN116959381A (en) | Image enhancement display method, display device and electronic device | |
| JP4978697B2 (en) | Image correction apparatus, image correction method, and image correction program | |
| CN114266803A (en) | Image processing method, image processing device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |