CN104751167A - Method and device for classifying urine visible components - Google Patents

Abstract

The invention provides a method and a device for classifying urine visible components. The method comprises the following steps: using the difference between the average pixel value in a peripheral region of the visible components inside a visible component block and the average pixel value in a central region as characteristics in a characteristic set of a classifier; and using the classifier to classify the urine visible components. An embodiment of the invention aims at increasing the precision of classifying the urine visible components.

Description

Urinary formed element sorting technique and device

Technical field

The present invention relates to biological detection, particularly relate to a kind of urinary formed element sorting technique and device.

Background technology

In common urine sediment analysis technology, microscopic system is first utilized to take urine specimen image.Then, the particulate block in edge detecting technology segmentation urine specimen image is utilized.From these particulate blocks, remove contaminant particles block, leave visible component (as red blood cell, leucocyte, crystallization) block.Then, these visible components are classified, such as, divide erythroblast, leucocyte, crystallization etc.

Assorting process usually uses the sorter based on training pattern.Such as, some can be utilized for the helpful feature of all kinds of visible component of differentiation, and such as area, circularity, range of extension, gradient etc., composition characteristic collection carrys out training classifier, as neural network.Sorter utilizes existing a large amount of visible component block samples, is trained by the feature (such as area, circularity, range of extension, gradient etc.) calculating them.Like this, when after the visible component block that input is new, the sorter trained, according to the feature of this block of measuring and calculating, is classified to it.

Common sorting technique utilizes the composition characteristic collection such as shape facility and texure feature.Effective not during the classification of the different visible component of feature differentiation in traditional feature set, nicety of grading is not high enough.

Summary of the invention

One embodiment of the present of invention are intended to the precision improving urinary formed element classification.

According to one embodiment of present invention, provide a kind of urinary formed element sorting technique, comprising: the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block is used as the feature in the feature set of sorter; With described sorter, urinary formed element is classified.

In a kind of specific implementation, the step difference of the average pixel value of visible component outer region and the average pixel value of central area being used as the feature in the feature set of sorter comprises: remove surround lighting and noise out of focus to the impact of the pixel value in visible component; Calculate the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area; Described difference is used as the feature in described feature set.

In a kind of specific implementation, removal surround lighting and the step of noise out of focus on the impact of the pixel value in visible component comprise: for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively,

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$

Max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of this pixel;

The step calculating the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area comprises: the NT calculating each pixel of visible component outer region _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.

In a kind of specific implementation, removal surround lighting and the step of noise out of focus on the impact of the pixel value in visible component comprise: for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel,

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$

Max (T _gray) represent the grey coefficients maximal value of pixel in visible component, NT _grayrepresent the grey coefficients normalized value of this pixel;

The step calculating the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area comprises: the NT calculating each pixel of visible component outer region _graymean value and the NT of each pixel of central area _graythe difference of mean value.

In a kind of specific implementation, described method also comprises: the gray level co-occurrence matrixes obtaining visible component, and by the feature in the one or more feature sets being used as sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, wherein the contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

In a kind of specific implementation, described method also comprises: the difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block is used as the feature in the feature set of sorter.

In a kind of specific implementation, described method also comprises 7 the Hu distance I will gone out according to following process computation ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more be used as sorter feature sets in feature:

Convert visible component to gray level image, f (x, y) represents the gray scale of pixel (x, y) in gray level image, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

m _pq=∫∫x ^py ^qf(x,y)dxdy p,q=0,1,2,…

(p+q) rank centre distance is defined as:

μ _pq=∫∫(x-x ₀) ^p(y-y ₀) ^qf(x,y)dxdy

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}$

Reference center distance is

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+y ₀₂

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$

I ₃=(y ₃₀+3y) ²+(3y ₂₁-y ₀₃) ²

I ₄=(y ₃₀+y ₁₂) ²+(y ₂₁+y ₀₃) ²

I ₅=(y ₃₀-y ₁₂)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

I ₆=(y ₂₀-y ₀₂)[(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]+

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+y ₀₃)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]+

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]。

In a kind of specific implementation, described method also comprises the average gray level of the visible component calculated according to the following formula the standard deviation sigma of gray level _g, the gradient κ of RGB look, feature in one or more feature sets being used as sorter in entropy and energy:

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$

Wherein, probability density function gray scale be divided in L grey level, h (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component,

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$

In a kind of specific implementation, described visible component comprises red blood cell, leucocyte, crystallization.

According to one embodiment of present invention, provide a kind of urinary formed element sorter, comprise: characterization unit, be configured to the feature difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block be used as in the feature set of sorter; Taxon, is configured to classify to urinary formed element with described sorter.

In a kind of specific implementation, described characterization unit is configured to remove surround lighting and noise out of focus to the impact of the pixel value in visible component further, calculate the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area, described difference is used as the feature in described feature set.

In a kind of specific implementation, described characterization unit is configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively,

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$

Max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of this pixel;

Calculate the NT of each pixel of visible component outer region _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.

In a kind of specific implementation, described characterization unit is configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel,

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$

Max (T _gray) represent the grey coefficients maximal value of pixel in described visible component, NT _grayrepresent the grey coefficients normalized value of this pixel;

Calculate the NT of each pixel of visible component outer region _graymean value and the NT of each pixel of central area _graythe difference of mean value.

In a kind of specific implementation, described characterization unit is also configured to: the gray level co-occurrence matrixes obtaining visible component, and by the feature in the one or more feature sets being used as sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, wherein the contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

In a kind of specific implementation, described characterization unit is also configured to:

The difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block is used as the feature in the feature set of sorter.

In a kind of specific implementation, described characterization unit is also configured to 7 the Hu distance I will gone out according to following process computation ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more be used as sorter feature sets in feature:

Convert visible component to gray level image, f (x, y) represents the gray scale of pixel (x, y) in gray level image, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

m _pq=∫∫x ^py ^qf(x,y)dxdy p,q=0,1,2,…

(p+q) rank centre distance is defined as:

μ _pq=∫∫(x-x ₀) ^p(y-y ₀) ^qf(x,y)dxdy

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}$

Reference center distance is

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+y ₀₂

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$

I ₃=(y ₃₀+3y) ²+(3y ₂₁-y ₀₃) ²

I ₄=(y ₃₀+y ₁₂) ²+(y ₂₁+y ₀₃) ²

I ₅=(y ₃₀-y ₁₂)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

I ₆=(y ₂₀-y ₀₂)[(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]+

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+y ₀₃)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]+

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]。

In a kind of specific implementation, described characterization unit is also configured to the average gray level of the visible component calculated according to the following formula the standard deviation sigma of gray level _g, the gradient κ of RGB look, feature in one or more feature sets being used as sorter in entropy and energy:

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$

Wherein, probability density function gray scale be divided in L grey level, h (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component,

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$

In a kind of specific implementation, described visible component comprises red blood cell, leucocyte, crystallization.

Inventor observes discovery, under microscopical white light, some visible components (as red blood cell) except the dark district of centre, the green glow that periphery has a circle generous.Therefore, based on the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block, some visible components can be effectively distinguished, especially red blood cell, leucocyte, crystallization can be effectively distinguished.The difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block is used as the feature in the feature set of sorter by one embodiment of the present of invention, effectively distinguish some visible components, improve the precision of urinary formed element classification.

Inventor also found some other, the feature that do not find to be used for urinary formed element classification in prior art, as the feature based on gray level co-occurrence matrixes, the feature based on visible component luminance difference, based on the feature of Hu distance, the feature etc. based on histogram tolerance.The feature in the one or more feature sets being used as sorter in these features, more effectively can distinguish visible component, thus improve the precision of urinary formed element classification.

Accompanying drawing explanation

These and other feature and advantage of the present invention will be by becoming more apparent below in conjunction with the detailed description of accompanying drawing.

Fig. 1 shows the process flow diagram of urinary formed element sorting technique according to an embodiment of the invention.

Fig. 2 shows the detail flowchart of the feature in the feature set difference of the average pixel value of visible component outer region and the average pixel value of central area being used as sorter according to an embodiment of the invention.

Fig. 3 shows the block diagram of urinary formed element sorter according to an embodiment of the invention.

Fig. 4 shows the structural drawing of urinary formed element sorting device according to an embodiment of the invention.

Embodiment

Below, each embodiment of the present invention will be described by reference to the accompanying drawings in detail.

feature based on green glow circle characteristic is used as the feature in feature set

As shown in Figure 1, urinary formed element sorting technique 1 according to an embodiment of the invention, comprise: in step S1, by the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block, as the feature in the feature set of sorter; In step S2, with described sorter, urinary formed element is classified.

Wherein, outer region and central area are determined by range conversion (Distance Transform) method.The profile of visible component can be obtained in such as edge detection process.By the inwardly single-frame indentation of the profile of visible component, the size of the size of every lattice and a pixel is suitable.When after profile indentation n lattice, this profile cannot inwardly indentation.Cannot inwardly indentation standard such as: if any point on the outline line after indentation n lattice and along inside indentation direction, the size distance between millet cake being less than or equal to 2 lattice on outline line after indentation n lattice, then thinking cannot inwardly indentation ".When this profile cannot inwardly indentation time, the part that inside for the profile of the visible component indentation n × 2/3 lattice hour circle is lived is defined as central area, and the part beyond the central area of visible component is defined as outer region.

In another embodiment, the part that inside for the profile of the visible component indentation n × 1/2 lattice hour circle is lived is defined as central area, and the part beyond the central area of visible component is defined as outer region.

As previously mentioned, under microscopical white light, some visible components (as red blood cell) except the dark district of centre, the green glow that periphery has a circle generous.The difference of the average pixel value of visible component outer region and the average pixel value of central area just embodies this characteristic.Therefore, the difference of the average pixel value of the average pixel value of visible component outer region and central area is used as the feature in feature set, contributes to the classification of visible component.

As shown in Figure 2, in one embodiment, step S1 can be subdivided into following steps again: in step S11, and removal surround lighting and noise out of focus are on the impact of the pixel value in visible component; In step S12, calculate the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area; In step S13, described difference is used as the feature in described feature set.

It will be appreciated by those skilled in the art that step S11 also can omit.Because removal surround lighting and noise out of focus just make the calculating of described difference more accurate on the impact of the pixel value in visible component, still can calculate the difference of the average pixel value of outer region and the average pixel value of central area when not removing the affecting of surround lighting and noise out of focus, its result of calculation also can embody the evaluation to above-mentioned green glow circle characteristic to a certain extent.

About the calculating of the difference of the average pixel value of outer region and the average pixel value of central area, following present two embodiments.

In one embodiment, for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$ Formula 1

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively.

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$ Formula 2

Wherein max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in described visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of this pixel.

By formula 1 and 2 above, for pixel each in visible component, the green trichromatic coefficient normalized value NT of this pixel can be calculated _green.Then, the NT of each pixel of visible component outer region is calculated _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.The average pixel value of outer region calculated with green trichromatic coefficient normalized value and the difference of the average pixel value of central area more can reflect above-mentioned green glow circle characteristic.

In another embodiment, inventor finds, the average pixel value of outer region calculated with the grey coefficients normalized value based on gray scale and the difference of the average pixel value of central area also can reflect above-mentioned green glow circle characteristic to a certain extent.

In this embodiment, for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$ Formula 3

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, I _graythe gray-scale pixel values of described pixel, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel.

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$ Formula 4

Max (T _gray) represent the grey coefficients maximal value of pixel in described visible component, NT _grayrepresent the grey coefficients normalized value of this pixel.

By formula 3 and 4 above, for pixel each in visible component, the grey coefficients normalized value NT of this pixel can be calculated _gray.Then, the NT of each pixel of visible component outer region is calculated _graymean value and the NT of each pixel of central area _graythe difference of mean value.

Those skilled in the art are to be understood that, except the difference of the difference of the average pixel value of outer region that calculates with green trichromatic coefficient normalized value and the average pixel value of central area, the average pixel value of outer region calculated with grey coefficients normalized value and the average pixel value of central area, by the difference of the average pixel value of outer region red, blue coefficient normalized value calculates and the average pixel value of central area, also there is certain help for differentiation visible component.Therefore, the calculating of the difference of the average pixel value of outer region and the average pixel value of central area is not limited to above-mentioned two kinds of embodiments.

Those skilled in the art are to be understood that, although be defined as part inside and outside for this profile after inside for the profile of visible component indentation n × 1/2 lattice or n × 2/3 lattice in central area and outer region, other the ratio except 2/3 and 1/2 also can be specified above.Such as central area and outer region are defined as part inside and outside for this profile after the lattice of inside for the profile of visible component indentation n × 3/4.

Those skilled in the art are to be understood that, central area and outer region can be defined according to by part inside and outside for this profile after the lattice of inside for the profile of visible component indentation n × 2/3, and calculate the first poor of the average pixel value of outer region and the average pixel value of central area accordingly.Define central area and outer region according to by part inside and outside for this profile after the lattice of inside for the profile of visible component indentation n × 1/2 again, and calculate the second poor of the average pixel value of outer region and the average pixel value of central area accordingly.First difference and second are differed from all as the feature of two in feature set.In addition, when not only with green trichromatic coefficient normalized value but also when calculating the difference of the average pixel value of outer region and the average pixel value of central area with grey coefficients normalized value, in feature set, four features had just been added.

feature based on gray level co-occurrence matrixes is used as the feature in feature set

The present inventor finds, utilizes some features based on gray level co-occurrence matrixes, also can effectively distinguish some visible components, especially distinguish red blood cell, leucocyte, crystallization.

According to one embodiment of present invention, the gray level co-occurrence matrixes of visible component is obtained.For specific visible component, its gray level co-occurrence matrixes can be measured by prior art.Then, by the feature in the one or more feature sets being used as sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy.The contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

formula 5

formula 6

formula 7

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

Feature in one or more feature sets being used as sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, can improve the validity distinguishing visible component, improve nicety of grading.

the feature of the contrast based on visible component block is used as the feature in feature set

Inventor finds, for some visible components, its block prospect part under the microscope (visible component itself) and background parts difference in brightness are very large, and this point also can help to distinguish some visible components.Therefore, according to one embodiment of present invention, the difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block is used as the feature in the feature set of sorter.This also can improve the validity distinguishing visible component (especially red blood cell, leucocyte, crystallization), improves nicety of grading.

feature based on Hu distance is used as the feature in feature set

Inventor finds, for some visible components, its Hu is apart from also very large with other visible component difference.Therefore, 7 the Hu distance I will gone out according to following process computation ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more as feature be used as sorter feature sets in feature, also can improve distinguish visible component (especially red blood cell, leucocyte, crystallization) validity, improve nicety of grading.

First, convert visible component to gray level image, f (x, y) represents the gray scale of pixel (x, y) in gray level image, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

M _pq=∫ ∫ x ^py ^qf (x, y) dxdy p, q=0,1,2 ... formula 8

(p+q) rank centre distance is defined as:

μ _pq=∫ ∫ (x-x ₀) ^p(y-y ₀) ^qf (x, y) dxdy formula 9

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}.$

Reference center distance is formula 10

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+ y ₀₂formula 11

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$ Formula 12

I ₃=(y ₃₀+ 3y) ²+ (3y ₂₁-y ₀₃) ²formula 13

I ₄=(y ₃₀+ y ₁₂) ²+ (y ₂₁+ y ₀₃) ²formula 14

I ₅=(y ₃₀-y ₁₂)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

Formula 15

I ₆=(y ₂₀-y ₀₂) [(y ₃₀+ y ₁₂) ²-(y ₂₁+ y ₀₃) ²]+formula 16

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+ y ₀₃) (y ₃₀+ y ₁₂) [(y ₃₀+ y ₁₂) ²-3 (y ₂₁+ y ₀₃) ²]+formula 17.

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

the feature of measuring based on histogram is used as the feature in feature set

Inventor finds, for some visible components, its some histograms tolerance is also very large with other visible component difference.Therefore, the histogram of the visible component calculated according to the following formula tolerance (is comprised average gray level the standard deviation sigma of gray level _g, the gradient κ of RGB look, entropy and energy) in one or more feature sets being used as sorter as feature in feature, also can improve the validity distinguishing visible component (especially red blood cell, leucocyte, crystallization), improve nicety of grading.

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$ Formula 18

Wherein, probability density function gray scale is divided in L grey level.Such as, the gray scale in a certain tonal range is divided in a grey level.L can determine as required based on experience value or by the experiment of limited number of time and emulation, and usual L can not be too little.H (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component.

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$ Formula 19

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$ Formula 20

formula 21

formula 22.

an apparatus in accordance with one embodiment of the invention

As shown in Figure 3, urinary formed element sorter 2 according to an embodiment of the invention, comprises characterization unit 201 and taxon 202.Characterization unit 201 is configured to the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block, as the feature in the feature set of sorter.Taxon 202 is configured to classify to urinary formed element with described sorter.Device shown in Fig. 3 can utilize the mode of software, hardware (such as integrated circuit, FPGA etc.) or software and hardware combining to realize.

In one embodiment, described characterization unit 201 can be configured to remove surround lighting and noise out of focus to the impact of the pixel value in visible component further, calculate the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area, described difference is used as the feature in described feature set.

In one embodiment, described characterization unit 201 can be configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$ Formula 1

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively,

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$ Formula 2

Wherein, max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in described visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of this pixel;

Calculate the NT of each pixel of visible component outer region _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.

In one embodiment, described characterization unit 201 can be configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$ Formula 3

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, I _graythe gray-scale pixel values of described pixel, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel,

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$ Formula 4

Max (T _gray) represent the grey coefficients maximal value of pixel in described visible component, NT _grayrepresent the grey coefficients normalized value of this pixel;

Calculate the NT of each pixel of visible component outer region _graymean value and the NT of each pixel of central area _graythe difference of mean value.

In one embodiment, described characterization unit 201 is also configured to:

Obtain the gray level co-occurrence matrixes of visible component, and by the feature in the one or more feature sets being used as sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, wherein the contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

formula 5

formula 6

formula 7

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

In one embodiment, described characterization unit 201 also can be configured to the difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block to do as the feature in the feature set of sorter.

In one embodiment, described characterization unit 201 also can be configured to will go out according to following process computation 7 recklessly apart from I ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more as feature be used as sorter feature sets in feature:

Convert visible component to gray level image, f (x, _y) represent pixel in gray level image (x, _y) gray scale, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

M _pq=∫ ∫ x ^py ^qf (x, y) dxdy p, q=0,1,2 ... formula 8

(p+q) rank centre distance is defined as:

μ _pq=∫ ∫ (x-x ₀) ^p(y-y ₀) ^qf (x, y) dxdy formula 9

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}$

Reference center distance is formula 10

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+ y ₀₂formula 11

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$ Formula 12

I ₃=(y ₃₀+ 3y) ²+ (3y ₂₁-y ₀₃) ²formula 13

I ₄=(y ₃₀+ y ₁₂) ²+ (y ₂₁+ y ₀₃) ²formula 14

I ₅=(y ₃₀-y ₁₂) (y ₃₀+ y ₁₂) [(y ₃₀+ y ₁₂) ²-3 (y ₂₁+ y ₀₃) ²] formula 15

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

I ₆=(y ₂₀-y ₀₂) [(y ₃₀+ y ₁₂) ²-(y ₂₁+ y ₀₃) ²]+formula 16

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+ y ₀₃) (y ₃₀+ y ₁₂) [(y ₃₀+ y ₁₂) ²-3 (y ₂₁+ y ₀₃) ²]+formula 17

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

In one embodiment, described characterization unit 201 also can be configured to the average gray level of the visible component calculated according to the following formula the standard deviation sigma of gray level _g, the gradient κ of RGB look, feature in one or more feature sets being used as sorter in entropy and energy

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$ Formula 18

Wherein, probability density function gray scale is divided in L grey level.Such as, the gray scale in a certain tonal range is divided in a grey level.L can determine as required, but L can not be too little.H (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component.

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$ Formula 19

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$ Formula 20

formula 21

formula 22

In one embodiment, described visible component comprises red blood cell, leucocyte, crystallization.

Fig. 4 shows urinary formed element sorting device 3 according to an embodiment of the invention.This equipment can comprise storer 301 and processor 302.Storer 301 is for stores executable instructions.The executable instruction of processor 302 for storing according to described storer, the operation that in actuating unit 2, unit performs.

In addition, one embodiment of the present of invention also provide a kind of machine readable media, and it stores executable instruction, when this executable instruction is performed, make the operation of machine execution performed by processor 302.

It will be appreciated by those skilled in the art that each embodiment above can make various changes and modifications when not departing from invention essence, therefore, protection scope of the present invention should be limited by appending claims.

Claims (20)

1. a urinary formed element sorting technique (1), comprising:

By the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block, as the feature (S1) in the feature set of sorter;

With described sorter to urinary formed element classification (S2).

2. urinary formed element sorting technique (1) according to claim 1, the step (S1) wherein the difference of the average pixel value of visible component outer region and the average pixel value of central area being used as the feature in the feature set of sorter comprising:

Removal surround lighting and noise out of focus are on the impact (S11) of the pixel value in visible component;

Calculate the difference (S12) of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area;

Described difference is used as the feature (S13) in described feature set.

3. urinary formed element sorting technique (1) according to claim 2, wherein

Removal surround lighting and the step (S11) of noise out of focus on the impact of the pixel value in visible component comprising: for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively,

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$

Max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of described pixel;

The step (S12) calculating the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area comprising: the NT calculating each pixel of visible component outer region _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.

4. urinary formed element sorting technique (1) according to claim 2, wherein

Removal surround lighting and the step (S11) of noise out of focus on the impact of the pixel value in visible component comprising: for the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel,

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$

Max (T _gray) represent the grey coefficients maximal value of pixel in visible component, NT _grayrepresent the grey coefficients normalized value of this pixel;

The step (S12) calculating the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area comprising: the NT calculating each pixel of visible component outer region _graymean value and the NT of each pixel of central area _graythe difference of mean value.

5. urinary formed element sorting technique (1) according to claim 1, described method also comprises:

Obtain the gray level co-occurrence matrixes of visible component, and one or more as the feature in the feature set of sorter using in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, wherein the contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

6. urinary formed element sorting technique (1) according to claim 1, described method also comprises:

The difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block is used as the feature in the feature set of sorter.

7. urinary formed element sorting technique (1) according to claim 1, described method also comprises 7 the Hu distance I will gone out according to following process computation ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more be used as sorter feature sets in feature:

Convert visible component to gray level image, f (x, y) represents the gray scale of pixel (x, y) in gray level image, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

m _pq=∫∫x ^py ^qf(x,y)dxdy p,q=0,1,2,…

(p+q) rank centre distance is defined as:

μ _pq=∫∫(x-x ₀) ^p(y-y ₀) ^qf(x,y)dxdy

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}$

Reference center distance is

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+y ₀₂

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$

I ₃=(y ₃₀+3y) ²+(3y ₂₁-y ₀₃) ²

I ₄=(y ₃₀+y ₁₂) ²+(y ₂₁+y ₀₃) ²

I ₅=(y ₃₀-y ₁₂)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

I ₆=(y ₂₀-y ₀₂)[(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]+

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+y ₀₃)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]+

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]。

8. urinary formed element sorting technique (1) according to claim 1, described method also comprises the average gray level of the visible component calculated according to the following formula the standard deviation sigma of gray level _g, the gradient κ of RGB look, feature in one or more feature sets being used as sorter in entropy and energy:

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$

Wherein, probability density function gray scale be divided in L grey level, h (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component,

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$

9. urinary formed element sorting technique (1) according to claim 1, wherein said visible component comprises red blood cell, leucocyte, crystallization.

10. a urinary formed element sorter (2), comprising:

Characterization unit (201), is configured to the difference of the average pixel value of visible component outer region and the average pixel value of central area in visible component block, as the feature in the feature set of sorter;

Taxon (202), is configured to classify to urinary formed element with described sorter.

11. urinary formed element sorters (2) according to claim 10, wherein said characterization unit (201) is configured to remove surround lighting and noise out of focus to the impact of the pixel value in visible component further, calculate the difference of the average pixel value of outer region after the impact of removing surround lighting and noise out of focus and the average pixel value of central area, described difference is used as the feature of described feature set.

12. urinary formed element sorters (2) according to claim 11, wherein said characterization unit (201) is configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively,

${\mathrm{NT}}_{\mathrm{green}}=\frac{T_{\mathrm{green}}}{\max (\max \left(T_{\mathrm{red}}\right),\max \left(T_{\mathrm{green}}\right),\max \left(T_{\mathrm{blue}}\right))}$

Max (T _red), max (T _green), max (T _blue) represent the trichromatic coefficient maximal value of the redness of pixel in visible component, green trichromatic coefficient maximal value, blue trichromatic coefficient maximal value, NT _greenrepresent the green trichromatic coefficient normalized value of described pixel;

Calculate the NT of each pixel of visible component outer region _greenmean value and the NT of each pixel of central area _greenthe difference of mean value.

13. urinary formed element sorters (2) according to claim 11, wherein said characterization unit (201) is configured to further:

For the pixel in visible component, calculate

$T_{\mathrm{red}}=\frac{I_{\mathrm{red}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{green}}=\frac{I_{\mathrm{green}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

$T_{\mathrm{blue}}=\frac{I_{\mathrm{blue}}}{I_{\mathrm{red}}+I_{\mathrm{green}}+I_{\mathrm{blue}}}$

T _gray=0.2989T _red+0.5870T _green+0.1140T _blue

Wherein I _red, I _green, I _bluerepresent the pixel value of described pixel at red color layer, green layer, cyan coloring layer respectively, T _red, T _green, T _bluerepresent the redness of described pixel, green, blue trichromatic coefficient respectively, T _grayrepresent the grey coefficients of described pixel,

${\mathrm{NT}}_{\mathrm{gray}}=\frac{T_{\mathrm{gray}}}{\max \left(T_{\mathrm{gray}}\right)}$

Max (T _gray) represent the grey coefficients maximal value of pixel in visible component, NT _grayrepresent the grey coefficients normalized value of this pixel;

Calculate the NT of each pixel of visible component outer region _graymean value and the NT of each pixel of central area _graythe difference of mean value.

14. urinary formed element sorters (2) according to claim 10, wherein said characterization unit (201) is also configured to:

Obtain the gray level co-occurrence matrixes of visible component, and by the feature in the one or more feature sets being used as described sorter in the contrast of the gray level co-occurrence matrixes of visible component, homogeney, energy, wherein the contrast of gray level co-occurrence matrixes, homogeney, energy calculate as follows:

Wherein P(i, j) represent gray scale to be i and gray scale be the probability that the value of j occurs simultaneously.

15. urinary formed element sorters (2) according to claim 10, wherein said characterization unit (201) is also configured to:

The difference of the average luminance of pixels of background parts in the average luminance of pixels of prospect part in visible component block and visible component block is used as the feature in the feature set of described sorter.

16. urinary formed element sorters (2) according to claim 10, wherein said characterization unit (201) is also configured to 7 the Hu distance I will gone out according to following process computation ₁, I ₂, I ₃, I ₄, I ₅, I ₆, I ₇in one or more be used as described sorter feature sets in feature:

Convert visible component to gray level image, f (x, y) represents the gray scale of pixel (x, y) in gray level image, f (x, y)=0.2989I _red+ 0.5870I _green+ 0.1140I _blue, wherein I _red, I _green, I _bluerepresent the pixel value of described pixel (x, y) at red color layer, green layer, cyan coloring layer respectively, its (p+q) rank are apart from being defined as:

m _pq=∫∫x ^py ^qf(x,y)dxdy p,q=0,1,2,…

(p+q) rank centre distance is defined as:

μ _pq=∫∫(x-x ₀) ^p(y-y ₀) ^qf(x,y)dxdy

Wherein $x_0=\frac{m_{10}}{m_{00}},y_0=\frac{m_{01}}{m_{00}}$

Reference center distance is

Wherein $r+\frac{p+q+2}{2}$

Thus, 7 Hus are apart from being defined as:

I ₁=y ₂₀+y ₀₂

$I_2={(y_{20}+y_{02})}^2+{4y}_{11}^2$

I ₃=(y ₃₀+3y) ²+(3y ₂₁-y ₀₃) ²

I ₄=(y ₃₀+y ₁₂) ²+(y ₂₁+y ₀₃) ²

I ₅=(y ₃₀-y ₁₂)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]

+(3y ₂₁-y ₀₃)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]

I ₆=(y ₂₀-y ₀₂)[(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]+

4y ₁₁(y ₃₀+y ₁₂)(y ₂₁+y ₀₃)

I ₇=(3y ₂₁+y ₀₃)(y ₃₀+y ₁₂)[(y ₃₀+y ₁₂) ²-3(y ₂₁+y ₀₃) ²]+

(y ₃₀-3y ₁₂)(y ₂₁+y ₃₀)[3(y ₃₀+y ₁₂) ²-(y ₂₁+y ₀₃) ²]。

17. urinary formed element sorters (2) according to claim 10, wherein said characterization unit (201) is also configured to the average gray level of the visible component calculated according to the following formula the standard deviation sigma of gray level _g, the gradient κ of RGB look, feature in one or more feature sets being used as described sorter in entropy and energy:

$\stackrel{\‾}{g}=\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}P\left(g\right)\·g$

Wherein, probability density function gray scale be divided in L grey level, h (g) is the pixel count being in grey level g in visible component, and M is the sum of all pixels in visible component,

${\mathrm{\σ}}_g=\sqrt{\underset{g-0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^2\·P\left(g\right)}$

$\mathrm{\κ}=\frac{1}{{\mathrm{\σ}}_g^3}\underset{g=0}{\overset{L-1}{\mathrm{\Σ}}}{(g-\stackrel{\‾}{g})}^3\·P\left(g\right)$

18. urinary formed element sorters (2) according to claim 10, wherein said visible component comprises red blood cell, leucocyte, crystallization.

19. 1 kinds of urinary formed element sorting devices (3), comprising:

Storer (301), for stores executable instructions;

Processor (302), for the executable instruction stored according to described storer, enforcement of rights requires the operation performed by any one claim in 1-9.

20. 1 kinds of machine readable medias, it stores executable instruction, when described executable instruction is performed, makes the operation performed by any one claim in machine enforcement of rights requirement 1-9.