WO2019041842A1 - 一种图像处理方法及装置、存储介质和计算机设备 - Google Patents

一种图像处理方法及装置、存储介质和计算机设备 Download PDF

Info

Publication number
WO2019041842A1
WO2019041842A1 PCT/CN2018/084215 CN2018084215W WO2019041842A1 WO 2019041842 A1 WO2019041842 A1 WO 2019041842A1 CN 2018084215 W CN2018084215 W CN 2018084215W WO 2019041842 A1 WO2019041842 A1 WO 2019041842A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
pixel
original
value
standard deviation
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.)
Ceased
Application number
PCT/CN2018/084215
Other languages
English (en)
French (fr)
Chinese (zh)
Inventor
郭俊
邵喜斌
周呈祺
陈明
栗首
王洁琼
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BOE Technology Group Co Ltd
Beijing BOE Display Technology Co Ltd
Original Assignee
BOE Technology Group Co Ltd
Beijing BOE Display Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BOE Technology Group Co Ltd, Beijing BOE Display Technology Co Ltd filed Critical BOE Technology Group Co Ltd
Priority to JP2018560136A priority Critical patent/JP7175197B2/ja
Priority to US16/300,971 priority patent/US11210765B2/en
Priority to EP18789754.1A priority patent/EP3690801A4/en
Publication of WO2019041842A1 publication Critical patent/WO2019041842A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing

Definitions

  • the present disclosure relates to the field of image processing technologies, and in particular, to an image processing method and apparatus, a storage medium, and a computer device.
  • Histogram equalization is an image processing method.
  • the gray histogram of the original image is changed from a certain gray interval in the comparison set to a uniform distribution in the entire gray range, and the image can be enhanced by histogram equalization of the image.
  • the contrast makes the image clearer.
  • the pseudo-flat portion is caused by the video image being compressed during processing and transmission.
  • the pseudo-flat part refers to the area where the pseudo-flat state exists in the image. Although the area of the pseudo-flat state seems to be the same gray level, it is actually composed of similar gray levels, for example, the scene such as the sky in the video image is compressed. A block region of adjacent gray scales is formed.
  • the difference between the gray levels of the pseudo-flat portion may be enlarged, which may cause the pseudo-flat portion to have an irregular block visible to the naked eye, resulting in an image.
  • the image quality of the flat and flat portion is degraded, which seriously degrades the image quality.
  • the embodiments of the present disclosure provide an image processing method and apparatus, a storage medium, and a computer device, which solve the problem that the image quality of the pseudo-flat portion is deteriorated and the image quality is reduced when performing histogram equalization in the prior art.
  • the technical solution is as follows:
  • At least one embodiment of the present disclosure provides an image processing method, where the image processing method includes:
  • the decision factor profile including a first mark region and a second mark region, wherein the first mark region includes pixel positions adjacent to the original image and the standard deviation is less than An area where the pixel of the set value is located, and the second mark area is an area other than the first mark area in the decision factor distribution map;
  • the gradation value is a gradation value of a corresponding pixel in the equalized gradation map, and a gradation value of a pixel corresponding to the first marker region in the final grayscale image is a corresponding value in the original grayscale image
  • the processed image is restored according to the final grayscale image.
  • the generating a decision factor distribution map according to the original grayscale image includes:
  • the distribution map includes a standard deviation of each pixel in the original grayscale image
  • each of the original grayscale images is calculated according to a gray value of a pixel in a certain area centered on each pixel in the original grayscale image.
  • the standard deviation of the pixels, the standard deviation profile is obtained, including:
  • the square value of each pixel of the difference image is square rooted to obtain the standard deviation profile.
  • the performing average filtering on the original grayscale image includes:
  • the original grayscale image is average filtered by using a filtering template of size m ⁇ m, and the value of m ranges from 10 to 20;
  • Performing mean filtering on the gray squared map including:
  • the gray squared map is averaged by using the filtering template of size m ⁇ m.
  • m is 15.
  • the image processing method further includes:
  • the second mark region includes pixels of the original image whose pixel positions are adjacent and whose standard deviation is greater than or equal to the set value And an area, and an area of the original image in which the pixel positions are adjacent and the standard deviation is smaller than the set value, and the number of pixels in the area is smaller than a threshold.
  • the threshold is 8%-15% of the number of pixels of the original image.
  • the threshold is 10% of the number of pixels of the original image.
  • the set value ranges from 1-5.
  • the set value is 1.
  • At least one embodiment of the present disclosure further provides an image processing apparatus, where the image processing apparatus includes:
  • a histogram equalization circuit configured to perform histogram equalization processing on the original grayscale image to obtain a balanced grayscale image
  • a first processing circuit configured to generate a decision factor profile according to the original grayscale image, the decision factor profile includes a first mark region and a second mark region, the first mark region including pixels in the original image An area where pixels adjacent in position and whose standard deviation is smaller than a set value, wherein the second mark area is an area other than the first mark area in the decision factor distribution map;
  • a second processing circuit configured to obtain a final grayscale image according to the original grayscale image, the equalized grayscale image, and the decision factor distribution map, wherein the final grayscale image and the second grayscale image
  • the gray value of the pixel corresponding to the mark area is the gray value of the corresponding pixel in the equalized gray image
  • the gray value of the pixel corresponding to the first mark area in the final gray image is the The gray value of the corresponding pixel in the original grayscale image
  • a third processing circuit configured to recover the processed image according to the final grayscale image.
  • the first processing circuit is configured to calculate the original value according to a gray value of a pixel in a certain area centered on each pixel in the original grayscale image. a standard deviation profile of each pixel in the grayscale image, resulting in a standard deviation profile comprising a standard deviation of each pixel in the original grayscale image;
  • the first processing circuit includes:
  • a first calculating sub-circuit configured to calculate a square value of a gray value of each pixel of the original grayscale image to form a gray squared map
  • Mean filtering sub-circuit configured to perform mean filtering on the original grayscale image to generate a first desired image, and perform mean filtering on the grayscale squared image to generate a second desired image;
  • a second calculating sub-circuit configured to calculate a square value of a gray value of each pixel of the first desired image to obtain a third expected image
  • a third calculation sub-circuit configured to calculate a difference value of gray values of pixels corresponding to positions in the second desired image and the third desired image to obtain a difference image
  • a fourth calculating sub-circuit configured to square the gray value of each pixel of the difference image to obtain the standard deviation distribution map.
  • the mean filtering sub-circuit is configured to: average filter the original grayscale image and the grayscale square image by using a filtering template of size m ⁇ m
  • the value of m ranges from 10 to 20.
  • m is 15.
  • the first processing circuit is further configured to update the decision factor distribution map after the generating the decision factor profile according to the original grayscale image
  • the second mark region includes an area of the original image in which pixel positions are adjacent and the standard deviation is greater than or equal to the set value, and in the original image An area in which the number of pixels in the area where the pixel position is adjacent and the standard deviation is smaller than the set value is smaller than the threshold.
  • the threshold is 8%-15% of the number of pixels of the original image.
  • the threshold is 10% of the number of pixels of the original image.
  • the set value ranges from 1-5.
  • the set value is 1.
  • At least one embodiment of the present disclosure also provides a storage medium having at least one instruction stored therein, the instructions being loaded and executed by a processor to implement execution in any of the image processing methods as described above Operation.
  • At least one embodiment of the present disclosure also provides a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor configured to execute the computer
  • the program performs the operations performed in the image processing method as described above.
  • the original grayscale image and the equalized grayscale image are first generated according to the original image, and then the decision factor distribution map is generated according to the original grayscale image.
  • the first marked region includes the original In the region where the pixels in the image are adjacent to each other and the standard deviation is smaller than the set value, since the gradation difference of the pseudo-flat portion is small, the standard deviation of the pixels of the pseudo-flat portion is also small, so the first mark region corresponds to The area in the original image is a pseudo-flat area, the pseudo-flat area is not enhanced, that is, the histogram equalization processing is not performed, and the pixel gray value in the original gray image is used, and the second mark area is subjected to histogram equalization.
  • the grayscale value representation of the pixel in the processed grayscale image that is, the grayscale value representation of the pixel in the equalized grayscale image; since the above processing method does not enhance the pseudo-flat portion, the pseudo-flat portion is not enlarged
  • the gap between the gray levels avoids the deterioration of the image quality of the pseudo-flat parts in the image and ensures the image quality of the image.
  • FIG. 1 is a flowchart of an image processing method according to an embodiment of the present disclosure
  • FIG. 2 is a flowchart of a process of generating a decision factor profile according to an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic structural diagram of a first processing circuit according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • FIG. 1 is a flowchart of an image processing method according to an embodiment of the present disclosure.
  • the image processing method includes:
  • Step 101 Generate an original grayscale image of the original image.
  • the original image may be an image obtained in various ways, such as an image obtained by photographing, or a video image. Among them, the original image is a red (R, R) green (Green, G) blue (Blue, B) format image.
  • generating the original grayscale image of the original image may include: acquiring the original image; processing the original image to obtain an original grayscale image.
  • processing the original image includes, but is not limited to, converting the original image into a format such as YUV, thereby generating an original grayscale image.
  • YUV format Y represents luminance
  • U and V represent chrominance, so if there is only a Y component and no U and V components, then the obtained image is a grayscale image, and step 101 can perform image conversion based on this to generate original grayscale.
  • Step 102 Perform histogram equalization processing on the original grayscale image to obtain a balanced grayscale image.
  • performing histogram equalization processing on the original grayscale image may be implemented as follows:
  • Count the number of pixels n i , i 0, 1, ..., L-1 of each gray level in the original gray scale, where L is the total number of gray levels of the original gray scale, and the original gray scale
  • n is the total number of pixels of the original grayscale image
  • r i is the i-th gray scale
  • n i is the number of pixels of the i-th gray scale
  • each gray scale is sequentially calculated by the formula
  • the probability density of the level, the original image histogram can be obtained.
  • the horizontal axis of the original image histogram is the gray level
  • the vertical axis is the probability density
  • the original image histogram includes the probability density of each gray level.
  • r k is the kth gray level
  • the cumulative distribution function of the kth gray level is the sum of the probability densities of the 0th to kth gray levels.
  • the gray level in the grayscale image after equalization is gk. In this way, the gray level after equalization of each pixel in the original grayscale image can be calculated.
  • the grayscale level of the original grayscale image is modified to obtain a balanced grayscale image.
  • the gray level of each pixel in the original grayscale image is changed from k to gk, so that the gray level of each pixel is modified to the grayscale image after equalization, and the obtained grayscale image is the equalized grayscale image.
  • Step 103 Generate a decision factor profile according to the original grayscale map, where the decision factor profile includes a first mark area and a second mark area, where the first mark area includes pixel positions adjacent to the original image and The area where the standard deviation is smaller than the set value of the pixel, and the second mark area is an area other than the first mark area in the decision factor distribution map.
  • the standard deviation refers to the difference image obtained by filtering the squared value image of the gray value of each pixel in the original grayscale image, and subtracting the filtered image obtained by filtering and squared the original grayscale image.
  • the gray value of each pixel is squared.
  • the filtering refers to calculating the mean value of the gray value within a certain range from the pixel as the gray value of the pixel.
  • the standard deviation can reflect the difference in gamma between each pixel and the surrounding pixels in the original grayscale image.
  • FIG. 2 is a flowchart of step 103 provided by an embodiment of the present disclosure.
  • step 103 may include:
  • the standard deviation profile includes the standard deviation of each pixel in the original grayscale image.
  • step 103a may include: calculating a square value of a gray value of each pixel of the original grayscale image to form a grayscale squared map; respectively performing the original grayscale image and the grayscale squared image Mean filtering to respectively generate a first expected image and a second expected image, that is, performing mean filtering on the original grayscale image, generating a first desired image, performing mean filtering on the grayscale squared image, and generating a second desired image Calculating a square value of a gray value of each pixel of the first desired image to obtain a third desired image; calculating a gray value of a pixel of a corresponding position in the second desired image and the third desired image The difference value is obtained as a difference image; the square value of each pixel of the difference image is square rooted to obtain the standard deviation distribution map.
  • the standard deviation profile obtained by this method can reflect the gradation difference between each pixel and the surrounding pixels, so that the pseudo-flat region can be divided into the first marker region when the region division is performed subsequently.
  • the performing the mean filtering on the original grayscale image and the grayscale squared image respectively may include: respectively, using the filtering template of size m ⁇ m, respectively, the original grayscale image and the grayscale squared image.
  • Perform mean filtering refers to the pixel to be processed (x, y), and a filtering template is selected.
  • the filtering template is composed of a plurality of pixels adjacent to the pixel to be processed, and the gray mean value of all pixels in the filtering template is obtained, and the gray mean value is given to
  • the pixel (x, y) is processed as the gradation of the image (x, y) in the mean filtered image.
  • the filter template is used to define the number of pixels that calculate the grayscale mean.
  • the pixel to be processed is located at the center of the pixel selected by the filter template (eg, in the center or adjacent to the pixel in the center).
  • the value of m can range from 10-20.
  • the m of the value range is used to ensure that the standard deviation profile can better indicate the pseudo-flat area in the original image, thereby ensuring that the pseudo-flat area is not enhanced, thereby avoiding image quality degradation.
  • the value of m is 15, and the value of 15 as m can maximize the pseudo-flat areas in the original image.
  • the number of rows and columns of the second desired image and the third desired image are the same, and the pixels of the corresponding position refer to the pixels of the same row and column in the second desired image and the third desired image.
  • the standard deviation distribution map of the original grayscale image is first calculated, and the first marked region is divided according to the relationship between the standard deviation of each pixel and the set value in the standard deviation distribution map, due to the pseudo
  • the gradation difference of the flat portion is small, so the standard deviation of the pixels of the pseudo-flat portion is also small, so the portion where the standard deviation is smaller than the set value in the standard deviation profile is judged as a pseudo-flat region (ie, the first marker region).
  • the remaining area is judged as the second marked area.
  • the binarization may be implemented.
  • the process of dividing the first mark area and the second mark area is as follows: standard in the standard deviation profile
  • the pixel whose difference is smaller than the set value is set to 0 in the decision factor distribution map, and the pixel value corresponding to the standard deviation of the standard deviation distribution map is greater than or equal to the set value in the decision factor distribution map. Therefore, the pixel whose pixel value is 0 in the decision factor distribution map belongs to the first mark area, and the pixel whose pixel value is 1 belongs to the second mark area.
  • the binarization method After the area is divided by the binarization method, it is only necessary to determine whether the pixel corresponds to the first mark area or the second mark area according to the pixel value in the decision factor distribution map in the subsequent processing, which is simple and convenient.
  • the set value may range from 1-5.
  • the set value of the value range is used to ensure that the decision factor distribution map can better indicate the pseudo-flat area in the original image, thereby ensuring that the pseudo-flat area is not enhanced, thereby avoiding image quality degradation.
  • the set value has a value of 1, and the use of 1 as the set value maximizes the pseudo-flat area in the original image.
  • the image processing method further includes:
  • the second mark region includes pixels of the original image whose pixel positions are adjacent and whose standard deviation is greater than or equal to the set value And an area, and an area of the original image in which the pixel positions are adjacent and the standard deviation is smaller than the set value, and the number of pixels in the area is smaller than a threshold.
  • the hole filling algorithm is actually used, and the area in the original image in which the pixel position is adjacent and the standard deviation is smaller than the set value is smaller than the threshold, and the area is smaller than the threshold.
  • the area during processing, performs the same processing on the pixels of the hole and its periphery, thereby avoiding the enhancement of only the periphery or the center of the area (hole) of a certain area, resulting in a sudden change in the contrast between the center and the periphery of the area in the processed image. .
  • the threshold may be 8%-15% of the number of pixels of the original image.
  • the threshold of the value range is used, so that the hole filling algorithm is processed only when the pixel in the center of the area is sufficiently small, so that the hole filling algorithm is not processed in a region where the number of pixels is greater than or equal to the threshold, and the image quality of the pseudo-flat region cannot be optimized.
  • the value of the threshold is 10%.
  • the hole filling algorithm can be avoided for the area where the number of pixels is greater than or equal to the threshold, so that the image quality of the pseudo-flat area cannot be optimized, and only the enhancement can be avoided.
  • the periphery of a certain area or the center of the area causes a sudden change in the contrast between the center of the area and the periphery of the image after processing.
  • Step 104 Obtain a final grayscale image according to the original grayscale image, the equalized grayscale image, and the decision factor distribution map, where the final grayscale image corresponds to the second labeled region.
  • the gray value of the pixel is a gray value of the corresponding pixel in the equalized gray image
  • the gray value of the pixel corresponding to the first mark region in the final gray image is the original gray image.
  • step 104 the final grayscale image can be calculated according to the following formula:
  • I(i,j) G(i,j)*H(i,j)+(1-G(i,j))*A(i,j) (4)
  • I is the final grayscale image
  • G is the decision factor distribution map (where the pixel of the first marked area is 0, the pixel of the second marked area is 1)
  • H is the equalized grayscale image
  • A is Original grayscale image.
  • I(i,j) is the pixel of the i-th row and the j-th column in the final grayscale image
  • G(i,j) is the pixel of the i-th row and the j-th column in the decision factor distribution map
  • H(i,j) To equalize the pixels of the i-th row and the j-th column in the grayscale image
  • A(i,j) is the pixel of the i-th row and the j-th column in the original grayscale image.
  • the gray value of the pixel corresponding to the second mark area in I is the gray value of the corresponding pixel in H
  • the gray value of the pixel corresponding to the first mark area in I is The gray value of the corresponding pixel in A.
  • Step 105 Restore the processed image according to the final grayscale image.
  • the final grayscale image is restored to an R (red) G (green) B (blue) image to obtain a processed original image. It is also possible to restore the YUV format image to an RGB format image.
  • the original grayscale image and the equalized grayscale image are first generated according to the original image, and then the decision factor distribution map is generated according to the original grayscale image.
  • the first marked region includes the original In the region where the pixels in the image are adjacent to each other and the standard deviation is smaller than the set value, since the gradation difference of the pseudo-flat portion is small, the standard deviation of the pixels of the pseudo-flat portion is also small, so the first mark region corresponds to The area in the original image is a pseudo-flat area, the pseudo-flat area is not enhanced, that is, the histogram equalization processing is not performed, and the pixel gray value in the original gray image is used, and the second mark area is subjected to histogram equalization.
  • the grayscale value representation of the pixel in the processed grayscale image that is, the grayscale value representation of the pixel in the equalized grayscale image; since the above processing method does not enhance the pseudo-flat portion, the pseudo-flat portion is not enlarged
  • the gap between the gray levels avoids the deterioration of the image quality of the pseudo-flat parts in the image and ensures the image quality of the image.
  • the image processing apparatus includes: a generating circuit 201, a histogram equalization circuit 202, a first processing circuit 203, and a second processing circuit. 204 and third processing circuit 205.
  • the generating circuit 201 is configured to generate an original grayscale image of the original image.
  • the histogram equalization circuit 202 is configured to perform histogram equalization processing on the original grayscale image to obtain a balanced grayscale image.
  • a first processing circuit 203 configured to generate a decision factor profile according to the original grayscale image, where the decision factor profile includes a first mark area and a second mark area, where the first mark area includes the original image An area in which a pixel position is adjacent and a standard deviation is smaller than a set value, and the second mark area is an area other than the first mark area in the decision factor distribution map.
  • a second processing circuit 204 configured to obtain a final grayscale image according to the original grayscale image, the equalized grayscale image, and the decision factor profile, wherein the final grayscale image and the first grayscale image
  • the gray value of the pixel corresponding to the two mark regions is the gray value of the corresponding pixel in the equalized gray map
  • the gray value of the pixel corresponding to the first mark region in the final gray map is The gray value of the corresponding pixel in the original grayscale image.
  • the third processing circuit 205 is configured to recover the processed image according to the final grayscale image.
  • the generating circuit 201, the histogram equalization circuit 202, the first processing circuit 203, the second processing circuit 204, and the third processing circuit 205 can each be implemented by a separate circuit, wherein the circuit can be a chip or An integrated circuit, such as a central processing unit (CPU), a graphics processing unit (GPU), or the like; any of the generation circuit 201, the histogram equalization circuit 202, the first processing circuit 203, the second processing circuit 204, and the third processing circuit 205 Two or more of them may also be implemented by the same circuit.
  • the generating circuit 201, the histogram equalizing circuit 202, the first processing circuit 203, the second processing circuit 204, and the third processing circuit 205 are implemented by the same graphics processor.
  • the original grayscale image and the equalized grayscale image are first generated according to the original image, and then the decision factor distribution map is generated according to the original grayscale image.
  • the first marked region includes the original In the region where the pixels in the image are adjacent to each other and the standard deviation is smaller than the set value, since the gradation difference of the pseudo-flat portion is small, the standard deviation of the pixels of the pseudo-flat portion is also small, so the first mark region corresponds to The area in the original image is a pseudo-flat area, the pseudo-flat area is not enhanced, that is, the histogram equalization processing is not performed, and the pixel gray value in the original gray image is used, and the second mark area is subjected to histogram equalization.
  • the grayscale value representation of the pixel in the processed grayscale image that is, the grayscale value representation of the pixel in the equalized grayscale image; since the above processing method does not enhance the pseudo-flat portion, the pseudo-flat portion is not enlarged
  • the gap between the gray levels avoids the deterioration of the image quality of the pseudo-flat parts in the image and ensures the image quality of the image.
  • the first processing circuit 203 is configured to calculate, according to the gray value of a pixel in a certain area centered on each pixel in the original grayscale image, in the original grayscale image. a standard deviation of each pixel, a standard deviation profile is obtained, the standard deviation profile includes a standard deviation of each pixel in the original grayscale image; and a pixel whose standard deviation is less than a set value in the standard deviation distribution map Dividing into the first marking area, and dividing an area other than the first marking area in the standard deviation distribution map into the second marking area to obtain the determination factor distribution map.
  • the first processing circuit 203 first calculates the standard deviation distribution map of the original grayscale image, and divides the first according to the relationship between the standard deviation of each pixel and the set value in the standard deviation distribution map.
  • the marking area since the gradation difference of the pseudo-flat portion is small, the standard deviation of the pixels of the pseudo-flat portion is also small, so that the portion of the standard deviation distribution map whose standard deviation is smaller than the set value is judged as a pseudo-flat area (ie, First marked area).
  • the first processing circuit 203 may be implemented by using a binarization method when dividing the first mark area and the second mark area, and the specific process is as follows: the standard deviation of the standard deviation distribution chart is smaller than the set value of the pixel The corresponding pixel value in the decision factor distribution map is set to 0, and the pixel corresponding to the standard deviation in the standard deviation distribution map is greater than or equal to the set value, and the corresponding pixel value in the decision factor distribution map is set to 1, so the pixel in the decision factor distribution map is determined. A pixel having a value of 0 belongs to the first marked area, and a pixel having a pixel value of 1 belongs to the second marked area.
  • the binarization method After the area is divided by the binarization method, it is only necessary to determine whether the pixel corresponds to the first mark area or the second mark area according to the pixel value in the decision factor distribution map in the subsequent processing, which is simple and convenient.
  • the first processing circuit 203 includes: a first computing sub-circuit 231, an average filtering sub-circuit 232, and a second computing sub-circuit 233.
  • the third calculation sub-circuit 234 and the fourth calculation sub-circuit 235 are the third calculation sub-circuit 234 and the fourth calculation sub-circuit 235.
  • the first calculating sub-circuit 231 is configured to calculate a square value of the gray value of each pixel of the original grayscale image to form a grayscale squared image; an average filtering sub-circuit 232 for the original grayscale The image is subjected to mean filtering to generate a first desired image, and the gray squared image is subjected to mean filtering to generate a second desired image; and the second calculating sub-circuit 233 is configured to calculate a gray value of each pixel of the first desired image a squared value, the third expected image is obtained; the third calculating sub-circuit 234 is configured to calculate a difference between the gray values of the pixels of the corresponding positions in the second desired image and the third desired image to obtain a difference image And a fourth calculating sub-circuit 235, configured to square the gray value of each pixel of the difference image to obtain the standard deviation distribution map.
  • the standard deviation profile obtained by this method can reflect the gradation difference between each pixel and the surrounding pixels, so that the pseudo-flat region can be divided
  • the mean filtering sub-circuit 232 is configured to perform average filtering on the original grayscale image and the grayscale square image by using a filtering template of size m ⁇ m, where the value range of m is It is 10-20.
  • the m of the value range is used to ensure that the standard deviation profile can better indicate the pseudo-flat area in the original image, thereby ensuring that the pseudo-flat area is not enhanced, thereby avoiding image quality degradation.
  • the value of m is 15, and the value of 15 as m can maximize the pseudo-flat areas in the original image.
  • the first processing circuit 203 is further configured to: after the generating the decision factor profile according to the original grayscale image, update the decision factor profile to make the updated location
  • the second mark region includes a region of the original image in which pixel positions are adjacent and a standard deviation is greater than or equal to the set value, and pixel positions in the original image are adjacent to each other An area in which the number of pixels in the area where the standard deviation is smaller than the set value is smaller than the threshold.
  • the hole filling algorithm is actually used, and the area in the original image in which the pixel position is adjacent and the standard deviation is smaller than the set value is smaller than the threshold, and the area is smaller than the threshold.
  • the area during processing, performs the same processing on the pixels of the hole and its periphery, thereby avoiding the enhancement of only the periphery or the center of the area (hole) of a certain area, resulting in a sudden change in the contrast between the center and the periphery of the area in the processed image. .
  • the threshold is 8%-15% of the number of pixels of the original image.
  • the threshold of the value range is used, so that the hole filling algorithm is processed only when the pixel in the center of the area is sufficiently small, so that the hole filling algorithm is not processed in a region where the number of pixels is greater than or equal to the threshold, and the image quality of the pseudo-flat region cannot be optimized.
  • the value of the threshold is 10%.
  • the hole filling algorithm can be avoided for the area where the number of pixels is greater than or equal to the threshold, so that the image quality of the pseudo-flat area cannot be optimized, and only the enhancement can be avoided.
  • the periphery of a certain area or the center of the area causes a sudden change in the contrast between the center of the area and the periphery of the image after processing.
  • the set value ranges from 1-5.
  • the set value of the value range is used to ensure that the decision factor distribution map can better indicate the pseudo-flat area in the original image, thereby ensuring that the pseudo-flat area is not enhanced, thereby avoiding image quality degradation.
  • the set value has a value of 1, and the use of 1 as the set value maximizes the pseudo-flat area in the original image.
  • I is the final grayscale image
  • G is the decision factor distribution map (where the pixel of the first marked area is 0, the pixel of the second marked area is 1)
  • H is the equalized grayscale image
  • A is the original grayscale image.
  • I(i,j) is the pixel of the i-th row and the j-th column in the final grayscale image
  • G(i,j) is the pixel of the i-th row and the j-th column in the decision factor distribution map
  • H(i,j) To equalize the pixels of the i-th row and the j-th column in the grayscale image
  • A(i,j) is the pixel of the i-th row and the j-th column in the original grayscale image.
  • the gray value of the pixel corresponding to the second mark area in I is the gray value of the corresponding pixel in H
  • the gray value of the pixel corresponding to the first mark area in I is The gray value of the corresponding pixel in A.
  • the image processing apparatus provided in the foregoing embodiment is only illustrated by the division of each functional module in the image processing. In actual applications, the function allocation may be completed by different functional modules as needed. The internal structure of the device is divided into different functional modules to perform all or part of the functions described above.
  • the image processing apparatus and the image processing method embodiment provided in the above embodiments are in the same concept, and the specific implementation process is described in detail in the method embodiment, and details are not described herein again.
  • FIG. 5 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure.
  • the image processing device may be a device such as a computer.
  • the computer 300 includes a central processing unit (CPU) 301, a system memory 304 including a random access memory (RAM) 302 and a read only memory (ROM) 303, and a system bus 305 that connects the system memory 304 and the central processing unit 301.
  • Computer 300 also includes a basic input/output system (I/O system) 306 that facilitates the transfer of information between various devices within the computer.
  • I/O system basic input/output system
  • the basic input/output system 306 includes a display 308 for displaying information and an input device 309 such as a mouse, keyboard for inputting information by the user. Both display 308 and input device 309 are coupled to central processing unit 301 via an input and output controller 310 coupled to system bus 305.
  • the basic input/output system 306 can also include an input and output controller 310 for receiving and processing input from a plurality of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input-output controller 310 also provides output to a display screen, printer, or other type of output device.
  • Computer readable media may comprise computer storage media and communication media.
  • Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.
  • Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid state storage technologies, CD-ROM, DVD or other optical storage, tape cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices.
  • RAM random access memory
  • ROM read only memory
  • EPROM Erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • the computer 300 may also be operated by a remote computer connected to the network through a network such as the Internet. That is, the computer 300 can be connected to the network 312 through a network interface unit 311 connected to the system bus 305, or can be connected to other types of networks or remote computer systems (not shown) using the network interface unit 311.
  • the above memory also includes one or more programs, one or more programs being stored in the memory and configured to be executed by the CPU.
  • the CPU executes a program in memory, the method shown in any of Figures 1 - 2 can be implemented.
  • a computer readable storage medium comprising instructions, such as a memory including instructions, which may be loaded and executed by central processing unit 301 of computer 300 to perform any of Figures 1-2 The method shown in the picture.
  • the computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • a person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium.
  • the storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Facsimile Image Signal Circuits (AREA)
PCT/CN2018/084215 2017-08-28 2018-04-24 一种图像处理方法及装置、存储介质和计算机设备 Ceased WO2019041842A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2018560136A JP7175197B2 (ja) 2017-08-28 2018-04-24 画像処理方法および装置、記憶媒体、コンピュータ装置
US16/300,971 US11210765B2 (en) 2017-08-28 2018-04-24 Image processing method and device, storage medium and computer device
EP18789754.1A EP3690801A4 (en) 2017-08-28 2018-04-24 IMAGE PROCESSING PROCESS AND DEVICE, STORAGE MEDIA AND COMPUTER DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710762836.9A CN109427047B (zh) 2017-08-28 2017-08-28 一种图像处理方法及装置
CN201710762836.9 2017-08-28

Publications (1)

Publication Number Publication Date
WO2019041842A1 true WO2019041842A1 (zh) 2019-03-07

Family

ID=65504047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/084215 Ceased WO2019041842A1 (zh) 2017-08-28 2018-04-24 一种图像处理方法及装置、存储介质和计算机设备

Country Status (5)

Country Link
US (1) US11210765B2 (https=)
EP (1) EP3690801A4 (https=)
JP (1) JP7175197B2 (https=)
CN (1) CN109427047B (https=)
WO (1) WO2019041842A1 (https=)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111899146A (zh) * 2020-08-04 2020-11-06 西安科技大学 基于matlab发动机喷雾图像自动筛选方法
CN112862709A (zh) * 2021-01-27 2021-05-28 昂纳工业技术(深圳)有限公司 图像特征增强方法、装置及可读存储介质
CN112907684A (zh) * 2021-03-12 2021-06-04 珠海格力电器股份有限公司 一种湿度检测方法、装置、设备及介质
CN113822818A (zh) * 2021-09-28 2021-12-21 北京的卢深视科技有限公司 散斑提取方法、装置、电子设备及存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10580122B2 (en) * 2015-04-14 2020-03-03 Chongqing University Of Ports And Telecommunications Method and system for image enhancement
TWI659227B (zh) 2017-06-20 2019-05-11 Academia Sinica 以影像導引之顯微照射的顯微鏡系統及方法
CN111626949A (zh) * 2020-05-15 2020-09-04 上海幕革科技有限公司 一种提升图像画质的方法
CN113592937B (zh) * 2021-08-05 2024-05-07 上海天岳半导体材料有限公司 半导体衬底的原子台阶宽度计算装置、方法、设备及介质
CN113721859B (zh) * 2021-09-08 2023-07-21 欧亚高科数字技术有限公司 一种基于人工智能的图像重复数据删除方法
CN114742892B (zh) * 2022-04-01 2023-10-27 南通博纳纺织品有限公司 基于图像处理的纺织混棉机控制方法
CN114937019B (zh) * 2022-05-30 2022-12-23 杭州健培科技有限公司 基于自适应局部灰度均衡的关键点检测方法、装置及应用
TW202419918A (zh) * 2022-07-18 2024-05-16 新析生物科技股份有限公司 標準化基於顯微鏡的系統中之圖像像素值的方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007012986A1 (en) * 2005-07-29 2007-02-01 Nokia Corporation Binarization of an image
CN105139366A (zh) * 2015-09-23 2015-12-09 成都融创智谷科技有限公司 一种基于空间域的图像增强方法
CN106504205A (zh) * 2016-10-20 2017-03-15 凌云光技术集团有限责任公司 一种图像去雾方法及终端

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5450502A (en) * 1993-10-07 1995-09-12 Xerox Corporation Image-dependent luminance enhancement
US6312385B1 (en) * 2000-05-01 2001-11-06 Ge Medical Systems Global Technology Company, Llc Method and apparatus for automatic detection and sizing of cystic objects
US7433535B2 (en) * 2003-09-30 2008-10-07 Hewlett-Packard Development Company, L.P. Enhancing text-like edges in digital images
US7835587B2 (en) 2006-12-18 2010-11-16 Intel Corporation Method and apparatus for local standard deviation based histogram equalization for adaptive contrast enhancement
CN100594516C (zh) 2007-01-22 2010-03-17 清华大学 一种x射线图像边缘和对比度综合增强方法
US8355595B2 (en) * 2007-05-15 2013-01-15 Xerox Corporation Contrast enhancement methods and apparatuses
CN101655974A (zh) * 2009-09-17 2010-02-24 广东中大讯通信息有限公司 一种改进的基于局部直方图均衡化方法的图像增强方法
CN101916370B (zh) * 2010-08-31 2012-04-25 上海交通大学 人脸检测中非特征区域图像处理的方法
CN102129673B (zh) 2011-04-19 2012-07-25 大连理工大学 一种随意光照下彩色数字图像增强和去噪方法
CN102332155A (zh) * 2011-10-19 2012-01-25 江苏技术师范学院 一种图像增强方法
CN103377468A (zh) 2012-04-26 2013-10-30 上海竞天科技股份有限公司 图像处理装置及图像处理方法
CN102722871B (zh) 2012-05-24 2015-02-11 中山大学 一种快速有效的图像增强方法
CN102999750B (zh) 2012-12-31 2015-08-12 清华大学 一种去除背景干扰的现场指纹增强方法
CN103067661B (zh) * 2013-01-07 2017-12-05 华为终端有限公司 图像处理方法、装置和拍摄终端
CN103295191B (zh) * 2013-04-19 2016-03-23 北京航科威视光电信息技术有限公司 多尺度视觉自适应图像增强方法及评价方法
CN103325102A (zh) 2013-06-03 2013-09-25 武汉理工大学 基于直方图均衡化的雾天退化图像处理方法
CN104574316B (zh) 2015-01-13 2018-09-14 南京佰能唯医疗科技有限公司 一种数字化x线成像系统
CN105654438A (zh) 2015-12-27 2016-06-08 西南技术物理研究所 基于局部直方图均衡的灰度图像拟合增强方法
CN106296600B (zh) 2016-08-01 2018-12-21 大连理工大学 一种基于小波变换图像分解的对比度增强方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007012986A1 (en) * 2005-07-29 2007-02-01 Nokia Corporation Binarization of an image
CN105139366A (zh) * 2015-09-23 2015-12-09 成都融创智谷科技有限公司 一种基于空间域的图像增强方法
CN106504205A (zh) * 2016-10-20 2017-03-15 凌云光技术集团有限责任公司 一种图像去雾方法及终端

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3690801A4 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111899146A (zh) * 2020-08-04 2020-11-06 西安科技大学 基于matlab发动机喷雾图像自动筛选方法
CN112862709A (zh) * 2021-01-27 2021-05-28 昂纳工业技术(深圳)有限公司 图像特征增强方法、装置及可读存储介质
CN112862709B (zh) * 2021-01-27 2024-05-03 昂视智能(深圳)有限公司 图像特征增强方法、装置及可读存储介质
CN112907684A (zh) * 2021-03-12 2021-06-04 珠海格力电器股份有限公司 一种湿度检测方法、装置、设备及介质
CN113822818A (zh) * 2021-09-28 2021-12-21 北京的卢深视科技有限公司 散斑提取方法、装置、电子设备及存储介质
CN113822818B (zh) * 2021-09-28 2022-08-12 合肥的卢深视科技有限公司 散斑提取方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
JP7175197B2 (ja) 2022-11-18
US11210765B2 (en) 2021-12-28
JP2020531931A (ja) 2020-11-05
CN109427047A (zh) 2019-03-05
EP3690801A1 (en) 2020-08-05
CN109427047B (zh) 2021-01-26
US20210224954A1 (en) 2021-07-22
EP3690801A4 (en) 2021-08-11

Similar Documents

Publication Publication Date Title
WO2019041842A1 (zh) 一种图像处理方法及装置、存储介质和计算机设备
JP2020531931A5 (https=)
CN104821147B (zh) 一种子像素渲染方法
CN113596573B (zh) 图像处理方法、装置、电子设备和计算机可读存储介质
JP6615917B2 (ja) 実時間ビデオエンハンスメント方法、端末及び非一時的コンピュータ可読記憶媒体
WO2018040463A1 (zh) DeMura表的数据压缩、解压缩方法及Mura补偿方法
US20150187051A1 (en) Method and apparatus for estimating image noise
CN112967207A (zh) 一种图像处理方法、装置、电子设备及存储介质
CN112927147B (zh) 显示模组的显示数据修正方法及装置、计算机设备及介质
CN112700456A (zh) 图像区域对比度优化方法、装置、设备及存储介质
JP2017085570A (ja) 画像補正方法及び画像補正装置
CN115239653A (zh) 支持多分屏的黑屏检测方法、装置、电子设备及可读存储介质
JP5278243B2 (ja) 画像処理装置及び画像処理プログラム
US9594955B2 (en) Modified wallis filter for improving the local contrast of GIS related images
CN115100081B (zh) Lcd显示屏灰阶图像增强方法、装置、设备及存储介质
CN116485645B (zh) 图像拼接方法、装置、设备及存储介质
CN119671914A (zh) 暗图像增强方法及其装置、电子设备、存储介质
CN107154233B (zh) 图像处理方法及装置和显示控制卡
CN114841906B (zh) 一种图像合成方法、装置、电子设备和存储介质
CN117935726B (zh) Mini-LED显示屏色彩均化方法及装置
CN105468312B (zh) 一种图像显示方法及装置
CN116957983B (zh) 图像增强方法、装置、设备及存储介质
CN102456229A (zh) 电子系统和疤痕影像修补方法
CN113762016A (zh) 关键帧选取方法和装置
KR102940495B1 (ko) 이미지에 포함된 실제 노이즈의 노이즈 레벨을 증감시키는 이미지 전처리 장치 및 방법

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018560136

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18789754

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018789754

Country of ref document: EP

Effective date: 20200330