CN101777121A - Extracting method for micro-image cellula target of acerous red tide algae - Google Patents

Abstract

The invention discloses a extracting method for micro-image cellula target of acerous red tide algae, comprising the following procedures that: a, the original image of the acerous red tide algae is converted into a grayscale image; b, image binaryzation, the grayscale image is in automatic threshold value division based on a strengthened OSTU; c, the binary image is in repeated morphology closing operation; d, the maximum outline of the binary image is sought to be filled; e, a filing image is in logic study and is calculated with the original image for getting a cellula target image. After the maximum outline of the binary image is extracted to be filled, maximum outline is in logic study and is calculated with the original image for getting the target cellula part of the original image. The invention is capable of exactly extracting the target cellula from the micro-image of acerous red tide algae with sediment, wreckage and such interferent, thus greatly lowering the technical requirements for the automatic classification and distinguishing work of red tide algae, and improving the efficiency; the invention also provides effective help for the red-tide monitoring staff working on the first line and researcher of red tide.

Description

A kind of micro-image cellula target of acerous red tide algae extracting method

Technical field

The present invention relates to a kind of phytoplankton cell target extraction method technical field, particularly a kind of extracting method of micro-image cellula target of acerous red tide algae.

Background technology

Red tide is some small phytoplankton, protozoan or a bacterium in the water body, breeds abruptly under certain environmental baseline and assembles, and causes in the certain limit water body metachromatism in a period of time.Usually the water body color is red, yellow, green and brown etc. because of quantity, the kind of red tide plankton.Aggravation along with marine environmental pollution and seawater eutrophication degree, the red tide disaster is more and more frequent, red tide was found 96 times altogether in China marine site in 2004, and wherein the Bohai Sea is 12 times, the Huanghai Sea 13 times, the East Sea 53 times, the South Sea 18 times, about 26630 square kilometres of cumulative area is surplus the red tide 20 that poisonous red tide plankton causes time, about 7000 square kilometres of area, direct economic loss reach 6.5 ten thousand yuan (Chinese aquatic products in 2006).

But, to the monitoring of red tide plankton, at home and abroad there is no very good monitoring technology and instrument at present.The qualitative, quantitative of traditional red tide plankton mainly is to utilize microscope that water sample is observed, and seeks red tide plankton wherein, then according to its feature to its count, kind identifies.This is consuming time a, effort, the demanding work of professional standards.Therefore, seek a kind of method for quickly identifying, realization with environmental change, particularly to the real-time detection of red tide generation, development, extinction process, is the target of the common pursuit of colleague both at home and abroad to phytoplankton.

All there is the other property of interspecific difference in red tide plankton at aspects such as cell shape, structure, pigment composition, protein composition and dna sequence dnas.Utilize these differences can realize identification to red tide plankton.This wherein image recognition be the most basic, classic methods, but utilizing image knowledge to discern in the process of red tide plankton, it is again a most key step that target is extracted, the quality that target is extracted has crucial effects to follow-up work.Therefore, propose a kind of effective target extraction method, can improve the recognition accuracy of red tide plankton greatly.

Summary of the invention

Technical matters to be solved by this invention is, a kind of micro-image cellula target of acerous red tide algae extracting method is provided, robotization evaluation as red tide plankton population classification provides a kind of means, for work such as follow-up feature extraction, classification and counting are laid a solid foundation.

For solving the problems of the technologies described above, the invention provides a kind of micro-image cellula target of acerous red tide algae extracting method, described method comprises following steps:

A. acerous hairs red tide algae original image is converted to gray level image;

B. image binaryzation carries out cutting apart based on the automatic threshold that strengthens big Tianjin method to gray level image;

C carries out the morphology closed operation to bianry image;

D. seek the largest contours and the filling of bianry image;

E. blank map picture and original image are done logic and operation, obtain the cell target image.

Among the described step b, strengthen big Tianjin method and preferably before the method for the big Tianjin of utilization, do a linear stretch, to solve image subject part and background gray scale difference problem of smaller.

The principle of big Tianjin method foundation is to utilize the classification variance as criterion among the described step b, can choose make the maximum and class internal variance minimum of inter-class variance gradation of image as optimal threshold.

Described micro-image cellula target of acerous red tide algae extracting method can be done 2～8 morphology closed operations in step c, form elongated curved mouthful and the little hole of packing ratio structural element so that breach narrow in the bianry image is coupled together.

Described micro-image cellula target of acerous red tide algae extracting method, largest contours can be meant that the pixel count that the profile that searches out comprises is maximum in steps d.

Described micro-image cellula target of acerous red tide algae extracting method can be that the largest contours inside that will search out is filled to white in the step of filling described in the steps d.

Described micro-image cellula target of acerous red tide algae extracting method in step e, can be done logic and operation with image and original image after filling, and the edge of extraction cell image also keeps cytologic characteristic such as inner vein.

Among the described step b,, gray level image carried out cutting apart preferably based on the automatic threshold that strengthens big Tianjin method be meant image binaryzation:

Did a linear stretch before the method for the big Tianjin of utilization, be used to solve image subject part and background gray scale difference problem of smaller, concrete steps are as follows:

If the gray level of original image is X, the image gray levels after expectation is handled is Y, and the distribution range extreme value of the gray level of original image and desired image is respectively X _Max, X _MinAnd Y _Max, Y _Min, the picture contrast retention wire sexual intercourse before and after the expectation conversion, promptly satisfy following formula:

$\frac{Y-Y_{\min }}{Y_{\max }-Y_{\min }}=\frac{X-X_{\min }}{X_{\max }-X_{\min }}$

Simple mathematical expression formula through the arrangement linear stretch is: Y=aX+b

Wherein $a=\frac{Y_{\max }-Y_{\min }}{X_{\max }-X_{\min }},$ $b=\frac{{X_{\max }{Y}_{\min }-Y}_{\max }-X_{\min }}{X_{\max }-X_{\min }}$

When a＞1, Y _Max-Y _Min＞X _Max-X _Min, then the contrast of image increases after the conversion, and visual response is that bright place is brighter, and the dark place is darker; And, can make the average of entire image gray level change corresponding b value by the b value is set; Make Y _Max=255, Y _Min=0;

The gray level of original-gray image is that the pixel number of i is n for the L gray level _i, all pixel is N, normalization histogram:

Threshold value t is divided into two classes: C with gray level ₀=(0,1 ..., t) and C ₁=(t+1, t+2 ... L-1)

The probability of this two class is respectively:

${\mathrm{\ω}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{P}_i=\mathrm{\ω}\left(t\right),$ ${\mathrm{\ω}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{P}_i=1-\mathrm{\ω}\left(t\right)$

Average is:

${\mathrm{\μ}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_0}=\frac{\mathrm{\μ}\left(t\right)}{\mathrm{\ω}\left(t\right)},$ ${\mathrm{\μ}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_1}=\frac{{\mathrm{\μ}}_T\left(t\right)-\mathrm{\μ}\left(t\right)}{1-\mathrm{\ω}\left(t\right)}$

In the following formula $\mathrm{\μ}\left(t\right)=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i{P}_i,$ ${\mathrm{\μ}}_T\left(t\right)=\underset{i=0}{\overset{L-1}{\mathrm{\Σ}}}i{P}_i$

Variance:

${\mathrm{\σ}}_0^2=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_0)}^2\frac{P_i}{{\mathrm{\ω}}_0},$ ${\mathrm{\σ}}_1^2=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_1)}^2\frac{P_i}{{\mathrm{\ω}}_1}$

The class internal variance is: ${\mathrm{\σ}}_{\mathrm{\ω}}^2={\mathrm{\ω}}_0{\mathrm{\σ}}_0^2+{\mathrm{\ω}}_1{\mathrm{\σ}}_1^2$

Inter-class variance is:

${\mathrm{\σ}}_B^2={\mathrm{\ω}}_0{({\mathrm{\μ}}_0-{\mathrm{\μ}}_T)}^2+{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_T)}^2={\mathrm{\ω}}_0{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_0)}^2$

Population variance is: ${\mathrm{\σ}}_T^2={\mathrm{\σ}}_B^2+{\mathrm{\σ}}_{\mathrm{\ω}}^2$

Change the value of t, the t value when making inter-class variance obtain maximal value is optimal threshold, with the optimal threshold of trying to achieve gray level image is carried out binaryzation.

Among the described step c, the concrete steps of bianry image being carried out repeatedly morphology closed operation are preferably:

The closed operation of utilization structure element B pair set A is expressed as AB, is defined as follows:

$A\·B=(A\⊕B)\mathrm{\ΘB}$

This formula shows that the closed operation of utilization structure element B pair set A is expanded to A with B exactly, then with B the result is corroded; The definition of wherein expanding and corroding is respectively:

This formula is to carry out displacement based on what obtain B with respect to the map of it self initial point and by the z map over;

$\mathrm{A\ΘB}=\left\{z\right|{\left(B\right)}_z\⊆A\}$

It is the set z translation that is contained in the some z among the A among all B that this formula explanation uses B that A is corroded;

The structural element that uses is 5 * 5 oval element, carries out 5 morphology closed operations.

The present invention can extract target cell accurately from the acerous hairs red tide algae micro-image that has chaff interferences such as silt, remains, reduce the technical requirement to the automatic Classification and Identification work of red tide algae significantly, raises the efficiency; Also can provide guidance and help effectively for the vast first line red tide monitoring personnel, red tide researcher.

Description of drawings

Fig. 1 is the process flow diagram of micro-image cellula target of acerous red tide algae extracting method of the present invention;

The original image of Fig. 2 for choosing in the specific embodiment;

Fig. 3 is through the gray level image after the conversion in the specific embodiment;

Fig. 4 is through the bianry image after the binaryzation in the specific embodiment;

Fig. 5 is for being result after the morphology closed operation to bianry image in the specific embodiment;

Fig. 6 is the image after the largest contours of extracting being filled in the specific embodiment;

Fig. 7 does the cell target image that obtains behind the logic and operation for blank map picture in the specific embodiment and original image.

Embodiment

Micro-image cellula target of acerous red tide algae extracting method of the present invention, acerous hairs red tide algae micro-image is carried out with strengthening big Tianjin method it being carried out the automatic threshold binaryzation after the greyscale transformation, then bianry image is done the morphology closed operation and form elongated curved mouthful and the little hole of packing ratio structural element so that breach narrow in the bianry image is coupled together, extract the largest contours and the filling back of bianry image and do logic and operation, obtain the target cell part in the original image with original image.

The present invention is further illustrated below in conjunction with the drawings and specific embodiments:

As shown in Figure 1, be micro-image cellula target of acerous red tide algae extracting method of the present invention, described method comprises following steps: (1) is converted to gray level image with acerous hairs red tide algae original image; (2) image binaryzation: gray level image is carried out cutting apart based on the automatic threshold that strengthens big Tianjin method; (3) bianry image is carried out the morphology closed operation; (4) seek the largest contours of bianry image and filling: described largest contours is meant that the pixel count that the profile of searching comprises is maximum; (5) blank map picture and original image are done logic and operation, obtain the cell target image.

After obtaining original image, enter step (1), original image is converted to gray level image, because microorganism difference on color is little, gray level image can significantly reduce the operand of Flame Image Process and more help image is carried out Feature Extraction etc. simultaneously.Fig. 2 is an original image, and Fig. 3 is through the gray level image after the conversion.

Enter step (2) then, gray level image is carried out cutting apart based on the automatic threshold that strengthens big Tianjin method, strengthening big Tianjin method is to do a linear stretch to solve image subject part and background gray scale difference problem of smaller before the method for the big Tianjin of utilization, and concrete principle is as described below:

If the gray level of original image is X, the image gray levels after expectation is handled is Y, and the distribution range extreme value of the gray level of original image and desired image is respectively X _Max, X _MinAnd Y _Max, Y _Min, we expect the picture contrast retention wire sexual intercourse before and after the conversion, promptly satisfy following formula:

$\frac{Y-Y_{\min }}{Y_{\max }-Y_{\min }}=\frac{X-X_{\min }}{X_{\max }-X_{\min }}$

Simple mathematical expression formula through the arrangement linear stretch is: Y=aX+b

Wherein $a=\frac{Y_{\max }-Y_{\min }}{X_{\max }-X_{\min }},$ $b=\frac{{X_{\max }{Y}_{\min }-Y}_{\max }-X_{\min }}{X_{\max }-X_{\min }}$

When a＞1, Y _Max-Y _Min＞X _Max-X _Min, then the contrast of image increases after the conversion, and visual response is that bright place is brighter, and the dark place is darker; And, can make the average of entire image gray level change corresponding b value by the b value is set.Make Y among the present invention _Max=255, Y _Min=0.

The principle of big Tianjin method foundation is to utilize the classification variance as criterion, choose make the maximum and class internal variance minimum of inter-class variance the gradation of image value as optimal threshold.Big Tianjin method can be done following understanding: because of variance is the inhomogeneity a kind of tolerance of intensity profile, variance yields is big more, two parts difference that composing images is described is big more, be divided into target and all can cause two parts difference to diminish when part target mistake is divided into background or part background mistake, therefore make to mean the misclassification probability minimum cutting apart of inter-class variance maximum.

The gray level of original-gray image is that the pixel number of i is n for the L gray level _i, all pixel is N, normalization histogram:

Threshold value t is divided into two classes: C with gray level ₀=(0,1 ..., t) and C ₁=(t+1, t+2 ... L-1)

The probability of this two class is respectively:

${\mathrm{\ω}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{P}_i=\mathrm{\ω}\left(t\right),$ ${\mathrm{\ω}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{P}_i=1-\mathrm{\ω}\left(t\right)$

Average is:

${\mathrm{\μ}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_0}=\frac{\mathrm{\μ}\left(t\right)}{\mathrm{\ω}\left(t\right)},$ ${\mathrm{\μ}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_1}=\frac{{\mathrm{\μ}}_T\left(t\right)-\mathrm{\μ}\left(t\right)}{1-\mathrm{\ω}\left(t\right)}$

In the following formula $\mathrm{\μ}\left(t\right)=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i{P}_i,$ ${\mathrm{\μ}}_T\left(t\right)=\underset{i=0}{\overset{L-1}{\mathrm{\Σ}}}i{P}_i$

Variance: ${\mathrm{\σ}}_0^2=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_0)}^2\frac{P_i}{{\mathrm{\ω}}_0},$ ${\mathrm{\σ}}_1^2=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_1)}^2\frac{P_i}{{\mathrm{\ω}}_1}$

The class internal variance is: ${\mathrm{\σ}}_{\mathrm{\ω}}^2={\mathrm{\ω}}_0{\mathrm{\σ}}_0^2+{\mathrm{\ω}}_1{\mathrm{\σ}}_1^2$

Inter-class variance is:

${\mathrm{\σ}}_B^2={\mathrm{\ω}}_0{({\mathrm{\μ}}_0-{\mathrm{\μ}}_T)}^2+{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_T)}^2={\mathrm{\ω}}_0{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_0)}^2$

Population variance is: ${\mathrm{\σ}}_T^2={\mathrm{\σ}}_B^2+{\mathrm{\σ}}_{\mathrm{\ω}}^2$

Change the value of t, the t value when making inter-class variance obtain maximal value is optimal threshold.With the optimal threshold of trying to achieve gray level image is carried out binaryzation.

Fig. 4 is the result that the threshold value of utilizing the method in the step (2) to choose is cut apart gray level image.As can be seen from Figure 4 the effect of binaryzation is fine, the also rare fracture part in the edge of red tide frustule.

After obtaining bianry image, enter step (3), bianry image is done the morphology closed operation.The closed operation of utilization structure element B pair set A is expressed as AB, is defined as follows:

$A\·B=(A\⊕B)\mathrm{\ΘB}$

This formula shows that the closed operation of utilization structure element B pair set A is expanded to A with B exactly, then with B the result is corroded.The definition of wherein expanding and corroding is respectively: This formula is to carry out displacement based on what obtain B with respect to the map of it self initial point and by the z map over.

It is the set z translation that is contained in the some z among the A among all B that this formula explanation uses B that A is corroded.

The morphology closed operation is intended to contours of objects is become smooth, and the narrow interruption that diminishes and long thin wide gap are eliminated little hole, and filled up the fracture in the outline line.2～8 morphology closed operations be can do, elongated curved mouthful and the little hole of packing ratio structural element formed so that breach narrow in the bianry image is coupled together.The structural element that uses in this step is 5 * 5 oval element, carries out 5 morphology closed operations.Fig. 5 is the result who carries out after the closed operation, as seen from the figure, has eliminated the hole littler than structural element, and it is more smooth that profile becomes.

Enter step (4) afterwards, seek the largest contours of the bianry image after the morphology closed operation is handled.The largest contours of saying in this step is meant the maximum profile of pixel number that is comprised, and after finding largest contours largest contours inside is filled to white.The largest contours of Fig. 6 for being obtained by step (4) also can be removed noise through this step.

Enter step (5) then, image and original image that step (4) obtains are done logic and operation, extract the edge of acerous hairs red tide algae microimage cells and kept cell characteristics such as inner vein, obtain the cell target image.The cell target image of Fig. 7 for finally obtaining.

All are above-mentioned to be the primary implementation system of this intellecture property, does not set restriction and implements this new system with other forms.Those skilled in the art will utilize this important information, foregoing be revised, to realize similar implementation status.But all are based on modification of the present invention or transform new method, belong to the right of reservation.

The above only is preferred embodiment of the present invention, is not to be the restriction of the present invention being made other form, and any those skilled in the art may utilize the technology contents of above-mentioned announcement to be changed or be modified as the equivalent embodiment of equivalent variations.But every technical solution of the present invention content that do not break away from according to any simple modification, equivalent variations and the remodeling that technical spirit of the present invention is done above example, still belongs to the protection domain of technical solution of the present invention.

Claims (9)

1. a micro-image cellula target of acerous red tide algae extracting method is characterized in that, described method comprises following steps:

A. acerous hairs red tide algae original image is converted to gray level image;

B. image binaryzation carries out cutting apart based on the automatic threshold that strengthens big Tianjin method to gray level image;

C. bianry image is carried out repeatedly morphology closed operation;

D. seek the largest contours and the filling of bianry image;

E. blank map picture and original image are done logic and operation, obtain the cell target image.

2. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that, in step b, strengthen big Tianjin method and be meant, before the method for the big Tianjin of utilization, do a linear stretch, to solve image subject part and background gray scale difference problem of smaller.

3. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that, big Tianjin method is to utilize the classification variance as criterion in step b, choose make the maximum and class internal variance minimum of inter-class variance gradation of image as optimal threshold.

4. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that, in step c, do 2～8 morphology closed operations, so that breach narrow in the bianry image is coupled together, form elongated curved mouthful, and the little hole of packing ratio structural element.

5. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that largest contours is meant described in the steps d: the pixel count that the profile that searches out comprises is maximum.

6. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that, be meant: the largest contours inside that searches out is filled to white in the step of filling described in the steps d.

7. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that image and original image after will filling are done logic and operation in step e, extract the edge of cell image, and keep the inner vein of cell.

8. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that, among the described step b,, gray level image carried out cutting apart based on the automatic threshold that strengthens big Tianjin method be meant image binaryzation:

Did a linear stretch before the method for the big Tianjin of utilization, be used to solve image subject part and background gray scale difference problem of smaller, concrete steps are as follows:

If the gray level of original image is X, the image gray levels after expectation is handled is Y, and the distribution range extreme value of the gray level of original image and desired image is respectively X _Max, X _MinAnd Y _Max, Y _Min, the picture contrast retention wire sexual intercourse before and after the expectation conversion, promptly satisfy following formula:

$\frac{Y-Y_{\min }}{Y_{\max }-Y_{\min }}=\frac{X-X_{\min }}{X_{\max }-X_{\min }}$

Simple mathematical expression formula through the arrangement linear stretch is: Y=aX+b

Wherein $a=\frac{Y_{\max }-Y_{\min }}{X_{\max }-X_{\min }},$ $b=\frac{X_{\max }{Y}_{\min }-Y_{\max }{X}_{\min }}{X_{\max }-X_{\min }}$

When a＞1, Y _Max-Y _Min＞X _Max-X _Min, then the contrast of image increases after the conversion, and visual response is that bright place is brighter, and the dark place is darker; And, can make the average of entire image gray level change corresponding b value by the b value is set; Make Y _Max=255, Y _Min=0;

The gray level of original-gray image is that the pixel number of i is n for the L gray level _i, all pixel is N, normalization histogram: $P_i=\frac{n_i}{N},$ $\underset{i=0}{\overset{L-1}{\mathrm{\Σ}}}{P}_i=1$

Threshold value t is divided into two classes: C with gray level ₀=(0,1 ..., t) and C ₁=(t+1, t+2 ... L-1)

The probability of this two class is respectively:

${\mathrm{\ω}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{P}_i=\mathrm{\ω}\left(t\right),$ ${\mathrm{\ω}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{P}_i=1-\mathrm{\ω}\left(t\right)$

Average is:

${\mathrm{\μ}}_0=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_0}=\frac{\mathrm{\μ}\left(t\right)}{\mathrm{\ω}\left(t\right)},$ ${\mathrm{\μ}}_1=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}i\frac{P_i}{{\mathrm{\ω}}_1}=\frac{{\mathrm{\μ}}_T\left(t\right)-\mathrm{\μ}\left(t\right)}{1-\mathrm{\ω}\left(t\right)}$

In the following formula $\mathrm{\μ}\left(t\right)=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}i{P}_i,$ ${\mathrm{\μ}}_T\left(t\right)=\underset{i=0}{\overset{L-1}{\mathrm{\Σ}}}i{P}_i$

Variance:

${\mathrm{\σ}}_0^2=\underset{i=0}{\overset{t}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_0)}^2\frac{P_i}{{\mathrm{\ω}}_0},$ ${\mathrm{\σ}}_1^2=\underset{i=t+1}{\overset{L-1}{\mathrm{\Σ}}}{(i-{\mathrm{\μ}}_1)}^2\frac{P_i}{{\mathrm{\ω}}_1}$

The class internal variance is: ${\mathrm{\σ}}_{\mathrm{\ω}}^2={\mathrm{\ω}}_0{\mathrm{\σ}}_0^2+{\mathrm{\ω}}_1{\mathrm{\σ}}_1^2$

Inter-class variance is:

${\mathrm{\σ}}_B^2={\mathrm{\ω}}_0{({\mathrm{\μ}}_0-{\mathrm{\μ}}_T)}^2+{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_T)}^2={\mathrm{\ω}}_0{\mathrm{\ω}}_1{({\mathrm{\μ}}_1-{\mathrm{\μ}}_0)}^2$

Population variance is: ${\mathrm{\σ}}_T^2={\mathrm{\σ}}_B^2+{\mathrm{\σ}}_{\mathrm{\ω}}^2$

Change the value of t, the t value when making inter-class variance obtain maximal value is optimal threshold, with the optimal threshold of trying to achieve gray level image is carried out binaryzation.

9. according to the described micro-image cellula target of acerous red tide algae extracting method of claim 1, it is characterized in that among the described step c, the concrete steps of bianry image being carried out repeatedly morphology closed operation are:

The closed operation of utilization structure element B pair set A is expressed as AB, is defined as follows:

$A\·B=(A\⊕B)\mathrm{\ΘB}$

This formula shows that the closed operation of utilization structure element B pair set A is expanded to A with B exactly, then with B the result is corroded; The definition of wherein expanding and corroding is respectively:

This formula is to carry out displacement based on what obtain B with respect to the map of it self initial point and by the z map over;

$\mathrm{A\ΘB}=\left\{z\right|{\left(B\right)}_z\⊆A\}$

It is the set z translation that is contained in the some z among the A among all B that this formula explanation uses B that A is corroded;

The structural element that uses is 5 * 5 oval element, carries out 5 morphology closed operations.

Images