CN111223110A - Microscopic image enhancement method and device and computer equipment - Google Patents
Microscopic image enhancement method and device and computer equipment Download PDFInfo
- Publication number
- CN111223110A CN111223110A CN202010009215.5A CN202010009215A CN111223110A CN 111223110 A CN111223110 A CN 111223110A CN 202010009215 A CN202010009215 A CN 202010009215A CN 111223110 A CN111223110 A CN 111223110A
- Authority
- CN
- China
- Prior art keywords
- microscopic image
- image
- color space
- value
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000012937 correction Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000001000 micrograph Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 2
- 210000004027 cell Anatomy 0.000 abstract description 8
- 210000003855 cell nucleus Anatomy 0.000 abstract description 6
- 210000001519 tissue Anatomy 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a microscopic image enhancement method, which comprises the steps of segmenting a microscopic image into an interested area and a background area by analyzing the characteristics of cells or tissue sections in the microscopic image, and then respectively carrying out image equalization processing on the interested area and the background area in the image by adopting a self-adaptive strategy, so that the characteristics of cell nucleuses, cell outlines and the like in the microscopic image are highlighted, and meanwhile, the background area noise is greatly inhibited. The microscopic image obtained by the method has transparent background and strong contrast, particularly has more clear cell outline and clearer and more distinguishable cell nucleus, and is more suitable for observation and judgment of pathologists.
Description
Technical Field
The invention relates to the technical field of medical microscopic image processing, in particular to a microscopic image enhancement method, a device and computer equipment.
Background
Medical microscopic images, for which the requirements for details in the microscopic image are strict, contain a large amount of data. However, in the imaging process, some degradation factors often exist, which cause the detail of the final microscopic image to be blurred and the quality to be reduced.
As a large class of basic medical microscopic image processing technologies, the medical microscopic image enhancement technology mainly solves the defects of image edge blurring, poor contrast and the like, processes the medical microscopic image, further improves the effectiveness and usability of the image, and provides richer and more accurate information for the diagnosis of doctors. The commonly used medical microscopic image enhancement methods mainly include: (1) and spatial domain methods such as contrast enhancement and sharpening enhancement. Each method has obvious defects, the contrast enhancement method cannot completely solve the problems existing in histogram equalization, and the sharpening method is only suitable for sharpening the detail blurred image with better contrast and is not obvious in enhancement effect when being used on the medical image alone. (2) Transform domain methods. Wavelet transform is the most common transform domain method. Transform domain methods typically require post-processing in the spatial domain. (3) Combined with statistical methods. The statistical learning method generally can obtain a better enhancement effect, but the processing speed of the statistical learning method cannot meet the real-time requirement. (4) An algorithm utilizing fuzzy theory and a combined optimization algorithm. The image is regarded as a fuzzy set, the image is read by using a fuzzy theory to be processed, and the aim of contrast enhancement is achieved by modifying pixels by means of a fuzzy contrast enhancement operator (INT).
In the prior art, for example, chinese patent CN107481206 proposes a microscope image background equalization processing algorithm, which converts an acquired RGB microscopic image into an HSV color space, processes a lightness component V of the HSV color space, determines whether the lightness component V contains salt and pepper noise, performs linear mapping transformation on the lightness component V, performs image equalization processing on the transformed image, and finally converts the image of the HSV color space into the RGB color space. The brightness component V is enhanced, the hue and the saturation of the image are not changed, the overall brightness of the image is improved, and the local detail and the contrast change difference of the image are not highlighted. For example, chinese patent CN106780379 proposes a color image enhancement method for a metrology microscope, which converts an acquired RGB microscopic image into an HSI color space, changes an original luminance component I and an original saturation component S using a Retinex algorithm, and finally converts an image of the HSI color space into an RGB color space, and performs gray stretching on the processed RGB image. The invention solves the problem of color distortion of the color image when the color image is enhanced, but the problem of unclear details of the obtained microscopic image is not improved greatly.
Disclosure of Invention
The invention provides a microscopic image enhancement method, a microscopic image enhancement device and computer equipment, which are used for overcoming the defects of insufficient definition of image details, image blurring, poor contrast and the like in the prior art and realizing transparent background and strong contrast of a microscopic image obtained by processing.
In order to achieve the above object, the present invention provides a method for enhancing a microscopic image, comprising:
s1: acquiring a color microscopic image;
s2: converting the microscopic image from RGB color space to HSV color space;
s3: firstly, obtaining a series of candidate interested regions based on saturation values of HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
s4: respectively carrying out image equalization processing on an interest region and a background region in the microscopic image by adopting a self-adaptive strategy;
s5: and converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
In order to achieve the above object, the present invention further provides a microscopic image enhancing apparatus, comprising:
the image acquisition module is used for acquiring a color microscopic image;
the image conversion module is used for converting the microscopic image from an RGB color space to an HSV color space;
the image processing module is used for obtaining a series of candidate interested areas based on the saturation value of the HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
the image enhancement module is used for respectively carrying out image equalization processing on an interest area and a background area in the microscopic image by adopting a self-adaptive strategy;
and the image output module is used for converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
To achieve the above object, the present invention further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
Compared with the prior art, the invention has the beneficial effects that:
the microscopic image enhancement method provided by the invention divides the microscopic image into the interested area and the background area by analyzing the cell or tissue slice characteristics in the microscopic image, and then respectively carries out image equalization processing on the interested area and the background area in the image by adopting a self-adaptive strategy, so that the characteristics of cell nucleuses, cell outlines and the like in the microscopic image are highlighted, and meanwhile, the background area noise is greatly inhibited. The microscopic image obtained by the method has transparent background and strong contrast, particularly has more clear cell outline and clearer and more distinguishable cell nucleus, and is more suitable for observation and judgment of pathologists.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a flow chart of a method for enhancing a microscopic image according to the present invention;
fig. 2 is a schematic view of a microscopic image.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical solutions in the embodiments of the present invention may be combined with each other, but it must be based on the realization of those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should not be considered to exist, and is not within the protection scope of the present invention.
The drugs/reagents used are all commercially available without specific mention.
The invention provides a microscopic image enhancement method, as shown in figure 1, comprising:
s1: acquiring a color microscopic image;
s2: converting the microscopic image from RGB color space to HSV color space;
s3: firstly, obtaining a series of candidate interested regions based on saturation values of HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
s4: respectively carrying out image equalization processing on an interest region and a background region in the microscopic image by adopting a self-adaptive strategy;
s5: and converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
In S1, the microscopic image refers to an image observed in a microscope, as shown in fig. 2.
The microscopic image includes a medical microscopic image, a biological microscopic image, and the like. The medical microscopic image is acquired by a medical microscope, and the biological microscopic image is acquired by a biological microscope.
In S2, the RGB color space is a common color representation, but the RGB color space is very different from the human eye in perception, and the spatial similarity thereof does not represent the similarity of the actual colors. Considering that the conversion of the RGB color space to the HSV color space is a simple and fast nonlinear transformation, the invention firstly converts the RGB original microscopic image collected by the microscope to the HSV color space which accords with the perception characteristic of human eyes.
The HSV color space is a color model which is more intuitive and more suitable for human eye observation, and the parameters of colors in the model are as follows: hue H, saturation S, lightness V. Hue H is a basic attribute of color, that is, the name of a commonly-known color, such as red, yellow, etc. The saturation S is the purity of the color, and the higher the saturation value is, the purer the color is, and the lower the saturation value is, the lighter the color is. The lightness V indicates the degree to which the color is bright.
Step S2 specifically includes:
s21: taking a point P (r, g, b) in an RGB color space of the microscopic image, and carrying out normalization processing on the point P to obtain a point P '(r', g ', b'); r, g and b respectively represent the red, green and blue color values of the P point in the RGB color space, and r ', g ' and b ' respectively represent the normalized values of the red, green and blue color values of the P point in the RGB color space;
the normalization process adopted in this embodiment is: dividing the three color values of the point P by 255, normalizing to a numerical range of 0-1 to obtain a point P '(r', g ', b'),
r'＝r/255g'＝g/255b'＝b/255 (8)；
s22: the maximum value C of the three color values in P '(r', g ', b') is obtained by calculationmaxAnd minimum value CmixAnd finding the maximum value CmaxAnd minimum value CmixA difference value Δ of;
Cmax＝max(r',g',b')Cmix＝mix(r',g',b') (9)；
Δ＝Cmax-Cmix(10)；
in the formula, max is a maximum calculation function; mix is the minimum calculation function.
S23: based on steps S21 and S22, the hue H, saturation S, and value V in the HSV color space corresponding to the P point are calculated, thereby completing the conversion of the microscopic image from the RGB color space to the HSV color space.
The formulas for calculating hue H, saturation S and lightness V are:
V＝Cmax(3)；
in the formula, Delta represents a maximum value CmaxAnd minimum value CmixA difference of (d); r ', g ' and b ' respectively represent the normalized values of the red, green and blue color values of the P point in the RGB color space; mod represents the remainder function. mod is an arithmetic operation, e.g., 3mod2 ═ 1.
In S3, by analyzing a plurality of microscopic images (for example, cell microscopic images), it was found that: the saturation of the object of interest (e.g. cell nucleus) in the microscopic image is much higher than that of the background region, so that the region of interest in the microscopic image can be segmented by the saturation value in the HSV color space of the image.
Step S3 specifically includes:
s31: in the HSV color space, subdividing a microscopic image into N sub-images, respectively setting different saturation thresholds for the sub-images, and extracting a target area with the saturation value higher than the saturation threshold in each sub-image to obtain a series of candidate interesting areas, wherein N is a positive integer; the calculation formula is as follows:
wherein, ROI represents a candidate region of interest; t ismA saturation threshold representing the mth sub-image; i ismRepresents the mth sub-image;
representing the coordinates in the mth sub-image as (x, y) image∪ represents the union of pixel points with saturation value larger than threshold in the mth sub-image, and the union constitutes a candidate interested region.
Several candidate regions of interest may be included in one sub-image.
S32: and combining the candidate interesting regions by calculating the characteristic value of each candidate interesting region so as to obtain the interesting region of the microscopic image, wherein other regions of the microscopic image are background regions.
In this embodiment, step S32 specifically includes:
s321: selecting the characteristic mean value and the characteristic variance of the candidate interesting region as the characteristic value of the candidate interesting region;
s322: judging whether the two adjacent candidate interesting regions are combined or not by judging whether the characteristic values of the two adjacent candidate interesting regions are similar, and if so, combining; if they are not similar, they are not combined;
s323: calculating the feature value of the new candidate region of interest formed after merging, and repeating the step S322;
s324: and repeating the step 323 until all the candidate interesting regions are processed to obtain the interesting region of the microscopic image, wherein other regions of the microscopic image are background regions.
In S321, the calculation formula of the feature mean and the feature variance is:
in the formula, Mean and Variance respectively represent a feature Mean and a feature Variance; q. q.si,j(H, S, V) represents values of hue H, lightness V, and saturation S of the pixel at the (i, j) position in the candidate region of interest; p and Q represent the number of rows and columns, respectively, of the microscope image.
In S322, the specific process of determining whether the feature values of two adjacent candidate regions of interest are similar is as follows:
for the t candidate interested region, calculating the characteristic Mean of the regiontAnd the Variance of the features, Variancet；
For the h candidate interested region, calculating the characteristic Mean of the regionhAnd the Variance of the features, Varianceh；
Calculating the similarity of the characteristic values of the t, h candidate interested areas as follows:
in the formula, DisthRepresenting the Euclidean distance, Sim, between two characteristic valuesthAnd representing the similarity between the two characteristic values, wherein the value range is 0-1.
When SimthWhen the number of the candidate interesting regions is more than or equal to T, combining the two candidate interesting regions;
when SimthIf T is less than T, no combination is carried out; t denotes a set similarity threshold.
In S4, enhancement of the microscopic image of the region of interest is implemented based on the human eye vision model, that is, Gamma Correction (Gamma Correction) is used to perform gray scale stretching, so that white pixel regions in the microscopic image are whiter, and black pixel regions in the microscopic image are blacker, so as to improve the contrast of the region of interest.
Gamma Correction (Gamma Correction) is a method of editing a Gamma curve of an image to perform nonlinear tone editing on the image, and detects a dark color portion and a light color portion in an image signal to increase a ratio of the dark color portion and the light color portion, thereby improving an effect of image contrast. The gamma correction has a remarkable image enhancement effect for the case where the contrast of an image is low and the overall brightness value is high. The transformation formula of gamma correction is to multiply each pixel value on the image.
The gamma correction expression is as follows:
f(I)＝cIγI∈[0,1](6)
wherein, f (I) represents the function value corresponding to the gamma curve under different gray values of the microscopic image; c represents a constant, gamma represents a gamma value, and I represents a gray value of the microscopic image;
in the gamma correction process, when the gamma value gamma is less than 1, the dynamic range in a low gray value area is enlarged, and the dynamic range change in a high gray value area is small, namely, the area with lower gray level in the image is stretched, and meanwhile, the part with higher gray level is compressed, so that the contrast of the image is enhanced, and meanwhile, the whole gray value of the image is enlarged; when the gamma value γ is greater than 1, the dynamic range in the low gray value region becomes smaller, and the dynamic range in the high gray value region becomes larger, that is, the contrast of the image in the low gray value region is reduced, the contrast of the image in the high gray value region is improved, and the gray value of the whole image becomes smaller. γ may be 1, and taking 1 is actually a linear transformation of input and output, but the gamma correction is a nonlinear transformation, so γ generally does not take 1.
Denoising a background region based on a non-local mean denoising method, specifically: for a given pixel Y, n (Y) is an image block with size m × m centered on Y, and n (Z) is an image block in the neighborhood of n (Y), the similarity between Y and Z is measured by using the gaussian weighted euclidean distance between image blocks n (Y) and n (Z), and the formula is as follows:
in the formula (I), the compound is shown in the specification,
representing the gray value of the pixel Y after noise reduction; y and Z respectively represent pixels; Ω represents a search neighborhood centered on pixel Y; ω (Y, Z) represents a weighted average and is a weight corresponding to the pixel Z; f (Z) represents the gray value of the pixel Z. Omega should theoretically be the entire image space, and in order to reduce the computational load of the algorithm, the present invention sets it to a larger search neighborhood centered on pixel Y.
The smaller the distance between n (Y) and n (Z), the more similar the pixels Z and Y, i.e. the larger the weight value corresponding to the pixel Z.
Non-Local-mean denoising (Non-Local-Means denoising) is an improvement on the traditional neighborhood filtering method, which makes full use of redundant information in an image and can furthest maintain the detail characteristics of the image while denoising.
In S5, the calculation method for converting HSV color space to RGB color space is as follows:
C＝V×S (13)；
D＝V-C (15)；
(r,g,b)＝((r'+D)×255,(g'+D)×255,(b'+D)×255) (17)；
c, X, D is an intermediate variable in the calculation process and has no special meaning; v represents lightness; s represents saturation; h represents a hue; mod represents a remainder function; r, g and b respectively represent the red, green and blue color values of the P point in the RGB color space, and r ', g ' and b ' respectively represent the normalized values of the red, green and blue color values of the P point in the RGB color space.
The microscopic image enhancement method provided in the embodiment divides a microscopic image into an interested area and a background area by using a saturation S value in a microscopic image HSV color space, and adopts different image equalization methods for different areas, namely, an image enhancement method based on a human eye visual model is adopted for the interested area (gamma curve correction is used for gray stretching, and then the contrast of the image is improved), and a method based on Non-Local-mean noise reduction (Non-Local-means noise) is adopted for the background area for denoising. The microscopic image processed by the method has the advantages of transparent background and strong contrast, and particularly, the cell outline is clearer, the cell nucleus is clearer and more distinguishable, so that the method is more suitable for observation and judgment of a pathologist.
The present embodiment also provides a microscopic image enhancing apparatus, including:
the image acquisition module is used for acquiring a color microscopic image;
the image conversion module is used for converting the microscopic image from an RGB color space to an HSV color space;
the image processing module is used for obtaining a series of candidate interested areas based on the saturation value of the HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
the image enhancement module is used for respectively carrying out image equalization processing on an interest area and a background area in the microscopic image by adopting a self-adaptive strategy;
and the image output module is used for converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
The present embodiment also provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method of enhancing a microscopic image, comprising:
s1: acquiring a color microscopic image;
s2: converting the microscopic image from RGB color space to HSV color space;
s3: firstly, obtaining a series of candidate interested regions based on saturation values of HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
s4: respectively carrying out image equalization processing on an interest region and a background region in the microscopic image by adopting a self-adaptive strategy;
s5: and converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
2. The microscopic image enhancement method according to claim 1, wherein the step S2 specifically is:
s21: taking a point P (r, g, b) in an RGB color space of the microscopic image, and carrying out normalization processing on the point P to obtain a point P '(r', g ', b'); r, g and b respectively represent the red, green and blue color values of the P point in the RGB color space, and r ', g ' and b ' respectively represent the normalized values of the red, green and blue color values of the P point in the RGB color space;
s22: the maximum value C of the three color values in P '(r', g ', b') is obtained by calculationmaxAnd minimum value CmixAnd finding the maximum value CmaxAnd minimum value CmixA difference value Δ of;
s23: based on steps S21 and S22, the hue H, saturation S, and value V in the HSV color space corresponding to the P point are calculated, thereby completing the conversion of the microscopic image from the RGB color space to the HSV color space.
3. The microscopic image enhancement method according to claim 2, wherein in the step S23, the calculation formulas of hue H, saturation S, and lightness V are:
V＝Cmax(3)；
in the formula, Delta represents a maximum value CmaxAnd minimum value CmixA difference of (d); r ', g ' and b ' respectively represent the normalized values of the red, green and blue color values of the P point in the RGB color space; mod represents the remainder function.
4. The microscopic image enhancement method according to claim 1, wherein the step S3 specifically is:
s31: in the HSV color space, subdividing a microscopic image into N sub-images, respectively setting different saturation thresholds for the sub-images, and extracting a target area with the saturation value higher than the saturation threshold in each sub-image to obtain a series of candidate interesting areas, wherein N is a positive integer;
s32: and combining the candidate interesting regions by calculating the characteristic value of each candidate interesting region so as to obtain the interesting region of the microscopic image, wherein other regions of the microscopic image are background regions.
5. The microscopic image enhancement method according to claim 4, wherein the step S32 is specifically:
s321: selecting the characteristic mean value and the characteristic variance of the candidate interesting region as the characteristic value of the candidate interesting region;
s322: judging whether the two adjacent candidate interesting regions are combined or not by judging whether the characteristic values of the two adjacent candidate interesting regions are similar, and if so, combining; if they are not similar, they are not combined;
s323: calculating the feature value of the new candidate region of interest formed after merging, and repeating the step S322;
s324: and repeating the step 323 until all the candidate interesting regions are processed to obtain the interesting region of the microscopic image, wherein other regions of the microscopic image are background regions.
6. The microscopic image enhancement method according to claim 5, wherein the calculation formula of the feature mean and the feature variance is:
in the formula, Mean and Variance respectively represent a feature Mean and a feature Variance; q. q.si,j(H, S, V) represents values of hue H, lightness V, and saturation S of the pixel at the (i, j) position in the candidate region of interest; p and Q represent the number of rows and columns, respectively, of the microscope image.
7. The microscopic image enhancement method according to claim 1, wherein in step S4, enhancement of the microscopic image of the region of interest is realized based on a human eye vision model; denoising the background region based on a non-local mean denoising method.
8. The microscopic image enhancement method according to claim 7, wherein the enhancement of the microscopic image of the region of interest based on the human eye vision model is specifically:
performing gray stretching by utilizing gamma correction to improve the contrast of the region of interest; the gamma correction expression is as follows:
f(I)＝cIγI∈[0,1](6)；
wherein, f (I) represents the function value corresponding to the gamma curve under different gray values of the microscopic image; c represents a constant, gamma represents a gamma value, and I represents a gray value of the microscopic image;
the denoising method for the background area based on the non-local mean value specifically comprises the following steps: for a given pixel Y, n (Y) is an image block with size m × m centered on Y, and n (Z) is an image block in the neighborhood of n (Y), the similarity between Y and Z is measured by using the gaussian weighted euclidean distance between image blocks n (Y) and n (Z), and the formula is as follows:
in the formula (I), the compound is shown in the specification,
representing the gray value of the pixel Y after noise reduction; y and Z are respectively shownShowing a pixel; Ω represents a search neighborhood centered on pixel Y; ω (Y, Z) represents a weighted average and is a weight corresponding to the pixel Z; f (Z) represents the gray value of the pixel Z.
9. A microscopic image enhancement apparatus, comprising:
the image acquisition module is used for acquiring a color microscopic image;
the image conversion module is used for converting the microscopic image from an RGB color space to an HSV color space;
the image processing module is used for obtaining a series of candidate interested areas based on the saturation value of the HSV color space; calculating the characteristic value of the candidate interested region based on the hue, brightness and saturation of the HSV color space, and obtaining the interested region of the microscopic image according to the similarity of the characteristic value;
the image enhancement module is used for respectively carrying out image equalization processing on an interest area and a background area in the microscopic image by adopting a self-adaptive strategy;
and the image output module is used for converting the processed microscopic image into an RGB color space to obtain an enhanced microscopic image.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010009215.5A CN111223110B (en) | 2020-01-06 | 2020-01-06 | Microscopic image enhancement method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010009215.5A CN111223110B (en) | 2020-01-06 | 2020-01-06 | Microscopic image enhancement method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111223110A true CN111223110A (en) | 2020-06-02 |
| CN111223110B CN111223110B (en) | 2023-07-18 |
Family
ID=70831243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010009215.5A Active CN111223110B (en) | 2020-01-06 | 2020-01-06 | Microscopic image enhancement method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223110B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639099A (en) * | 2020-12-15 | 2022-06-17 | 深圳市瑞图生物技术有限公司 | Method, device, equipment and medium for identifying and positioning target object in microscopic image |
| CN115100077A (en) * | 2022-07-25 | 2022-09-23 | 深圳市安科讯实业有限公司 | Novel image enhancement method and device |
| CN115797225A (en) * | 2023-01-06 | 2023-03-14 | 山东环宇地理信息工程有限公司 | Unmanned ship acquisition image enhancement method for underwater topography measurement |
| CN116934755A (en) * | 2023-09-18 | 2023-10-24 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image enhancement system based on histogram equalization |
| CN117372308A (en) * | 2023-12-04 | 2024-01-09 | 华侨大学 | Phase contrast cell microscopic image definition enhancement method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150146032A1 (en) * | 2013-11-22 | 2015-05-28 | Vidinoti Sa | Light field processing method |
| CN105205804A (en) * | 2015-08-18 | 2015-12-30 | 爱威科技股份有限公司 | Caryon-cytolymph separation method and apparatus of white blood cells in blood cell image, and classification method and apparatus of white blood cells in blood cell image |
| CN105913096A (en) * | 2016-06-29 | 2016-08-31 | 广西大学 | Extracting method for disordered image key frame |
| WO2017132858A1 (en) * | 2016-02-03 | 2017-08-10 | Chongqing University Of Posts And Telecommunications | Methods, systems, and media for image processing |
| CN107369145A (en) * | 2017-06-16 | 2017-11-21 | 广东欧珀移动通信有限公司 | image processing method, device and terminal device |
| CN107481206A (en) * | 2017-08-28 | 2017-12-15 | 湖南友哲科技有限公司 | MIcrosope image background equalization Processing Algorithm |
| CN107578383A (en) * | 2017-08-29 | 2018-01-12 | 北京华易明新科技有限公司 | A kind of low-light (level) image enhancement processing method |
| CN107609537A (en) * | 2017-10-09 | 2018-01-19 | 上海海事大学 | A kind of waterfront line detecting method based on HSV space Surface Picture feature |
| CN110189293A (en) * | 2019-04-15 | 2019-08-30 | 广州锟元方青医疗科技有限公司 | Cell image processing method, device, storage medium and computer equipment |
| CN110598560A (en) * | 2019-08-15 | 2019-12-20 | 重庆特斯联智慧科技股份有限公司 | Night monitoring and identifying method and system based on neural network enhancement |
-
2020
- 2020-01-06 CN CN202010009215.5A patent/CN111223110B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150146032A1 (en) * | 2013-11-22 | 2015-05-28 | Vidinoti Sa | Light field processing method |
| CN105205804A (en) * | 2015-08-18 | 2015-12-30 | 爱威科技股份有限公司 | Caryon-cytolymph separation method and apparatus of white blood cells in blood cell image, and classification method and apparatus of white blood cells in blood cell image |
| WO2017132858A1 (en) * | 2016-02-03 | 2017-08-10 | Chongqing University Of Posts And Telecommunications | Methods, systems, and media for image processing |
| CN105913096A (en) * | 2016-06-29 | 2016-08-31 | 广西大学 | Extracting method for disordered image key frame |
| CN107369145A (en) * | 2017-06-16 | 2017-11-21 | 广东欧珀移动通信有限公司 | image processing method, device and terminal device |
| CN107481206A (en) * | 2017-08-28 | 2017-12-15 | 湖南友哲科技有限公司 | MIcrosope image background equalization Processing Algorithm |
| CN107578383A (en) * | 2017-08-29 | 2018-01-12 | 北京华易明新科技有限公司 | A kind of low-light (level) image enhancement processing method |
| CN107609537A (en) * | 2017-10-09 | 2018-01-19 | 上海海事大学 | A kind of waterfront line detecting method based on HSV space Surface Picture feature |
| CN110189293A (en) * | 2019-04-15 | 2019-08-30 | 广州锟元方青医疗科技有限公司 | Cell image processing method, device, storage medium and computer equipment |
| CN110598560A (en) * | 2019-08-15 | 2019-12-20 | 重庆特斯联智慧科技股份有限公司 | Night monitoring and identifying method and system based on neural network enhancement |
Non-Patent Citations (3)
| Title |
|---|
| MARZIA HOQUE TANIA 等: "Advances in automated tongue diagnosis techniques" * |
| 毛本清 等: "自适应直方图均衡化算法在图像增强处理的应用" * |
| 魏德志 等: "基于改进的CLAHE显微细胞图像增强算法" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114639099A (en) * | 2020-12-15 | 2022-06-17 | 深圳市瑞图生物技术有限公司 | Method, device, equipment and medium for identifying and positioning target object in microscopic image |
| CN115100077A (en) * | 2022-07-25 | 2022-09-23 | 深圳市安科讯实业有限公司 | Novel image enhancement method and device |
| CN115100077B (en) * | 2022-07-25 | 2022-11-04 | 深圳市安科讯实业有限公司 | Image enhancement method and device |
| CN115797225A (en) * | 2023-01-06 | 2023-03-14 | 山东环宇地理信息工程有限公司 | Unmanned ship acquisition image enhancement method for underwater topography measurement |
| CN116934755A (en) * | 2023-09-18 | 2023-10-24 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image enhancement system based on histogram equalization |
| CN116934755B (en) * | 2023-09-18 | 2023-12-01 | 中国人民解放军总医院第八医学中心 | Pulmonary tuberculosis CT image enhancement system based on histogram equalization |
| CN117372308A (en) * | 2023-12-04 | 2024-01-09 | 华侨大学 | Phase contrast cell microscopic image definition enhancement method and system |
| CN117372308B (en) * | 2023-12-04 | 2024-03-12 | 华侨大学 | Phase contrast cell microscopic image definition enhancement method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111223110B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111223110B (en) | Microscopic image enhancement method and device and computer equipment | |
| Agrawal et al. | A novel joint histogram equalization based image contrast enhancement | |
| CN107833220B (en) | Fabric defect detection method based on deep convolutional neural network and visual saliency | |
| CN105654436B (en) | A kind of backlight image enhancing denoising method based on prospect background separation | |
| Du et al. | Union Laplacian pyramid with multiple features for medical image fusion | |
| CN111275696B (en) | Medical image processing method, image processing method and device | |
| CN109191390A (en) | A kind of algorithm for image enhancement based on the more algorithm fusions in different colours space | |
| CN104103082A (en) | Image saliency detection method based on region description and priori knowledge | |
| CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
| WO2020038312A1 (en) | Multi-channel tongue body edge detection device and method, and storage medium | |
| CN116843581B (en) | Image enhancement method, system, device and storage medium for multi-scene graph | |
| CN112330613A (en) | Method and system for evaluating quality of cytopathology digital image | |
| CN113298763B (en) | Image quality evaluation method based on significance window strategy | |
| CN112184696B (en) | Cell nucleus and organelle counting and area calculating method and system thereof | |
| CN112365517A (en) | Super-pixel segmentation method based on image color and density characteristics | |
| CN117197064A (en) | Automatic non-contact eye red degree analysis method | |
| CN112508024A (en) | Intelligent identification method for embossed seal font of electrical nameplate of transformer | |
| CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction | |
| CN114862706B (en) | Tone mapping method for keeping gradient direction of image | |
| CN107239761A (en) | Fruit tree branch pulling effect evaluation method based on skeleton Corner Detection | |
| CN110930358A (en) | Solar panel image processing method based on self-adaptive algorithm | |
| CN112070771B (en) | Adaptive threshold segmentation method and device based on HS channel and storage medium | |
| CN114022879B (en) | Squamous cell structure enhancement method based on optical fiber microscopy endoscope image | |
| PL | A study on various image processing techniques | |
| Tie-Rui et al. | The research of X-ray bone fracture image enhancement algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |