CN1588429A - Automatic identifying method for skin micro imiage symptom - Google Patents

Abstract

The invention relates to an automatic recognition method for skin microscopic image symptoms. It is to input the preprocessed symptom segmentation image of the skin microscopic image into the microcomputer, extract the characteristic parameters of the symptom segmentation image and convert it into a feature vector reflecting the essence of symptom classification, and then carry out the recognition operation on the feature vector according to the recognition algorithm based on the support vector machine. Identify the attribute of the symptom, and then display the attribute of the symptom in text on the microcomputer display. The invention lays the foundation for the skin diagnosis system and can be used as the realization basis of the skin diagnosis system.

Description

Automatic recognition method of skin microscopic image symptoms

technical field

The invention relates to an image automatic recognition method, in particular to a skin microscopic image symptom automatic recognition method.

Background technique

The automatic recognition method of skin microscopic image symptoms includes two aspects: firstly, feature parameters are extracted from the symptom segmentation image of skin microscopic images, and then classified and identified according to the characteristic parameters, so as to obtain the attributes of skin symptoms.

In the prior art, the extraction of skin symptoms features includes: imitating the method of skin expert visual diagnosis, extracting the size of skin symptoms (represented by diameter or area, also available needle point, needle head, rice grain, mung bean, pea, peanut, longan, litchi , walnuts, eggs, fists, palms, etc.), shape (oval, hemispherical, pointed, flat, polygonal, arc, ring, irregular), color (red, yellow, brown, black, white, normal skin color, etc.), color (such as bright red, light red, dark red, etc.), surface (smooth or rough, papillary or cauliflower-shaped, pointed, with or without umbilical fossa in the center), edge (clear or fuzzy, neat or present Infiltrating, raised or depressed, etc.), texture (solid or soft, cystic, fluctuating), arrangement (different patterns formed by multiple lesions, linear, multi-ring, clustered, scattered, banded or umbrella). This method is more complex and difficult to accurately grasp the analysis.

There are many methods of image classification, such as statistical pattern classification, structural method, classification tree and neural network, etc., but for high-dimensional and massive classification recognition problems, and without prior knowledge, it is difficult to use these methods to obtain satisfaction. the result of. The artificial neural network method is more effective in small-scale classification, but the artificial neural network learning algorithm has its inherent shortcomings. For example, there is no reliable rule for determining the network structure, and it is easy to reach the local optimum. Therefore, for small-sample, multi-category training sets, the artificial neural network will have a serious overfitting problem, that is, the problem of good fitting results but poor forecasting results.

Contents of the invention

The purpose of the present invention is to provide an automatic recognition method for symptom features of skin microscopic images, which can automatically recognize the attributes of symptoms for the provided symptom segmentation images after preprocessing of skin microscopic images.

To achieve the above object, the present invention adopts the following technical solutions:

A method for automatic identification of skin microscopic image symptoms, characterized in that the symptom segmentation image after preprocessing of the skin microscopic image is input to a microcomputer, the feature parameters of the symptom segmentation image are extracted and converted into feature vectors reflecting the essence of symptom classification, and the feature vector The attribute of the symptom is recognized by the recognition operation based on the recognition algorithm of the support vector machine, and then the attribute of the symptom is displayed in text on the microcomputer display.

The specific steps for converting the feature parameters of the extracted symptom segmentation image into feature vectors reflecting the essence of symptom classification are as follows:

a. Extract geometric features of symptoms:

(a) Extract the area of symptoms: count the number of pixels with a value of 1 in the segmentation map of various symptoms, and this number is the area of symptoms;

(b) Extract the maximum and minimum diameters of the symptoms: Project the segmentation map of the symptoms in a direction that forms an angle θ with the horizontal direction to obtain a projection direction vector; count the number of elements in this vector that are 1, and record it as N(θ ); θ increases by 1° each time from 0° to 179°, and 180 N(θ) are obtained; the maximum value among these 180 N(θ) is used as the maximum diameter of the symptom, and the minimum value is used as the minimum diameter of the symptom;

b. Extract color features of symptoms:

(a) Color feature extraction inside the symptom: select the difference between the average color amount inside the symptom and the average color amount of the background skin as the feature of the color:

i. Calculate the characteristic value of the symptom hue, which is recorded as Hcha: Hcha=(averHzh-averHbei)*360; in the formula: the average hue value inside the symptom, which is recorded as averHzh; the average hue value of the background skin, which is recorded as averHbei;

ii. Calculate the symptom saturation (S) eigenvalue, denoted as Scha: Scha=averSzh-averSbei; In the formula: the average saturation value inside the symptom, denoted as averSzh; The average saturation value of the background skin, denoted as averSbei;

iii. calculate symptom intensity (I) eigenvalue, denoted as Icha: Icha=averIzh-averIbei; In the formula: the average intensity value inside the symptom, denoted as averIzh; The average intensity value of background skin, denoted as averIbei;

iv. Calculate the symptom gray scale (G) eigenvalue, be recorded as Gcha: Gcha=averGzh-averGbei; In the formula: the average gray value of symptom inside, be recorded as averGzh; The average gray value of background skin, be recorded as averGbei;

(b) Color Feature Extraction of Symptom Edge: In addition to the difference between the average color amount of the symptom edge and the average color amount of the background skin as the feature of the color, the difference between the average color amount of the symptom edge and the average color amount inside the symptom is also selected As a feature of color:

i. The difference between the average color volume of the symptom edge and the average color volume of the background skin

Calculate the hue difference between symptom edge and background skin, which is recorded as ebHcha: ebHcha=(averHedge-averHbei)*360; where: the average hue of symptom edge is recorded as averHedge; the average hue of background skin is recorded as averHbei;

●Calculate the saturation difference between the symptom edge and the background skin, denoted as ebScha, ebScha=averSedge-averSbei; where: the average saturation of the symptom edge, denoted as averSedge; the average saturation of the background skin, denoted as averSbei;

●Calculate the intensity difference between the symptom edge and the background skin, which is recorded as ebIcha, ebIcha=averIedge-averIbei; where: the average intensity of the symptom edge, which is recorded as averIedge: the average intensity of the background skin, which is recorded as averIbei;

●Calculate the gray level difference between the symptom edge and the background skin, which is recorded as ebGcha, ebGcha=averGedge-averGbei; where: the average gray value of the symptom edge is recorded as averGedge; the average gray value of the background skin is recorded as averGbei;

ii. The difference between the average amount of color at the edge of the symptom and the average amount of color inside the symptom

● Calculate the hue difference between the edge of the symptom and the interior of the symptom, and record it as ezHcha, ebHcha=(averHedge-averHbei)*360, where: the average hue of the edge of the symptom is recorded as averHedge; the average hue of the interior of the symptom is recorded as averHzh;

● Calculate the saturation difference between the edge of the symptom and the interior of the symptom, which is recorded as ezScha, ezScha=averSedge-averSzh, where: the average saturation of the edge of the symptom is recorded as averSedge; the average saturation of the interior of the symptom is recorded as averSzh;

● Calculate the intensity difference between the edge of the symptom and the inside of the symptom, which is recorded as ezIcha, ezIcha=averIedge-averIzh, where: the average intensity of the edge of the symptom is recorded as averIedge; the average intensity of the inside of the symptom is recorded as averIzh;

●Calculate the gray level difference between the edge of the symptom and the interior of the symptom, which is recorded as ezGcha, ezGcha=averGedge-averGzh, where: the average gray level of the symptom edge is recorded as averGedge; the average gray level of the symptom interior is recorded as averGzh;

(c) Extraction and conversion operation of shape features of symptoms: extract f(x, y) value, f(x, y) is the value of the image at the pixel (x, y), and (p+q) of the entire image The order moment m _pq is calculated according to the following formula:

${\mathrm{<span\; class="notranslate">\; m</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; q</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; p</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; q</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0,1,2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&Center\; Dot;</span><span\; class="notranslate">\; \&Center\; Dot;</span><span\; class="notranslate">\; \&Center\; Dot;</span>$

The central moment μ _pq of the image is calculated as follows:

${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; p</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; q</span>}}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>$

in $\stackrel{\&OverBar;}{x}=\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}\mathrm{xf}(x,\mathrm{the\; y})/\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}f(x,\mathrm{the\; y}),$ $\stackrel{\&OverBar;}{\mathrm{the\; y}}=\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}\mathrm{yf}(x,\mathrm{the\; y})/\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}f(x,\mathrm{the\; y})$

The normalized central moment η _pq is calculated according to the following formula:

${\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; /</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; 00</span>}}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}}$

In the formula, γ=(p+q+2)/2, p+q=2, 3,...

A set of invariant moments can be derived from the second and third moments:

φ ₁ =η ₂₀ +η ₀₂

${\mathrm{<span\; class="notranslate">\; \&phi;</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 20</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 02</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 4</span>}\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$

φ ₃ ＝(η ₃₀ -3η ₁₂ ) ² +(3η ₂₁ -η ₀₃ ) ²

φ ₄ ＝(η ₃₀ +η ₁₂ ) ² +(η ₂₁ +η ₀₃ ) ²

φ ₅ ＝(η ₃₀ -3η ₁₂ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+

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

φ ₆ ＝(η ₂₀ -η ₀₂ )[(η ₃₀ +η ₁₂ ) ² -(η ₂₁ +η ₀₃ ) ² ]+

4η ₁₁ (η ₃₀ +η ₁₂ )(η ₂₁ +η ₀₃ )

φ ₇ ＝(3η ₂₁ -η ₀₃ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+

(3η ₂₁ -η ₀₃ )(η ₂₁ +η ₀₃ )×[3(η ₀₃ +η ₁₂ ) ² -(η ₁₂ +η ₀₃ ) ² ]

The specific steps of the above recognition operation are as follows:

a. Select the kernel function: Using different inner product kernel functions will lead to different support vector machine algorithms. At present, three types of kernel functions are used more as follows:

i. Polynomial kernel function: k(x, y)=(x*y+1) ^d d=1, 2.....

ii. RBF (Radial Basis Function) kernel function: $K(x,\mathrm{the\; y})=\exp [-\frac{{\left|\right|x-\mathrm{the\; y}\left|\right|}^2}{{2\mathrm{\&sigma;}}^2}]$

iii.Sigmoid kernel function: K(x, y)=tanh[b(x*y)-c]

b. Training: For real samples and false samples, the ideal outputs are respectively 1 and -1, and the SVM training algorithm is used, that is, the above classification function formula is trained to convergence, and a classifier based on SVM is obtained at this time;

c. Identification: The sample to be identified is input into the classifier, and the output is a real value, and the category of the sample can be determined through the set threshold;

Steps a) to d) are for two-category classification problems. For skin microscopic image classification, we divide them into four categories,

Therefore, k(k-1)/2 classifiers can be designed, and each classifier is trained with two types of data;

d. Repeat b) for chloasma and blackhead samples to obtain classifier SVM1;

e. Repeat b) for the chloasma and acne samples to obtain classifier SVM2;

f. Repeat b) for chloasma and freckle samples to obtain classifier SVM3;

g. Repeat b) for freckles and blackhead samples to obtain classifier SVM4;

h. Repeat b) for freckles and acne samples to obtain classifier SVM5;

i. Repeat b) for blackhead and acne samples to obtain classifier SVM6;

j. When classifying, adopt a scoring strategy: For a certain sample to be classified, use the training process to obtain 6 classifiers for testing, that is, step c), each result is 1 point, and each category is accumulated Score;

k. Select the category corresponding to the highest scorer as the category of the test data;

l. Calculation of recognition rate;

m. Assuming that there are n initial samples, one sample is taken out for testing each time, and the remaining n-1 are used as training samples;

n. Repeat steps d) to i) for the n-1 training samples;

o. Test with another sample to get an accuracy, 0 or 100%;

p. This process is repeated n times, and as a result, each sample is used as a test sample once, so the final accuracy value is the average value of n times;

q.18) The method of selecting the kernel function is to select the kernel function with the highest recognition rate through steps m) to p).

Compared with the prior art, the present invention has the following obvious outstanding substantive features and significant advantages: in the present invention, the geometric features represented by the symptom area, maximum diameter and minimum diameter extracted from the symptom segmentation image of the skin microscopic image are represented by The color feature represented by the difference between the average color amount of the symptom and the average color amount of the background skin and the shape feature represented by a group of invariant moments obtained by the operation can more accurately reflect the essence of symptom classification; one extracted in the present invention The recognition method of skin microscopic image symptoms based on support vector machine (SVM) can better solve the problems that the skin microscopic image has strong nonlinearity, high dimensionality, and belongs to small sample learning. The calculation is simple, convenient, and has strong generalization ability, which is very suitable for real-time processing systems. The invention lays the foundation for the skin diagnosis system and can be used as the realization basis of the skin diagnosis system.

Description of drawings

Fig. 1 is a system block diagram for one embodiment of the present invention.

Fig. 2 is a microscopic image diagram of chloasma in the example of Fig. 1, wherein diagram (a) is a symptom segmentation diagram, diagram (b) is a symptom edge diagram, and diagram (c) is a color diagram of chloasma.

Figure 3 is a flow chart of the system in the example in Figure 1

Detailed ways

An embodiment of the present invention is aimed at four typical skin symptoms of melasma, freckles, blackheads and acne in skin microscopic images, and provides a method for automatically identifying the symptoms. Using the system shown in Figure 1, according to the system flow diagram shown in Figure 3, the extraction and identification of symptom features are performed:

1. Feature extraction

Taking melasma as an example, Fig. 2 shows the symptom segmentation map, symptom edge map and symptom color map of melasma. Specific steps:

1) Calculate the geometric features of symptoms

1.1 Extract the area of symptoms

The number of pixels with a value of 1 in the statistical graph 2(a) is 10765, and this number is the area of the symptom.

1.2 Extract the maximum and minimum diameters of symptoms

1.2.1 Figure 2(a) is projected in a direction forming an angle θ with the horizontal direction to obtain a projection direction vector;

1.2.2 Count the number of 1 elements in this vector, denoted as N(θ);

1.2.3θ increases by 1° each time from 0° to 179° to get 180 N(θ),

1.2.4 Take the maximum value among these 180 N(θ) as the maximum diameter of the symptom, and the minimum value as the minimum diameter of the symptom. Figure 2(a) has a maximum diameter of 151 and a minimum diameter of 105.

2) Symptom color characteristics

2.1 Color feature extraction inside the symptom in Figure 2

2.1.1 Calculation of symptom hue characteristic value Hcha=(averHzh-averHbei)*360=-220.071

2.1.2 Calculation of symptom saturation (S) eigenvalue Scha=averSzh-averSbei=0.248057

2.1.3 Calculation of symptom intensity (I) eigenvalue Icha=averIzh-averIbei=-12.7408;

2.1.4 Calculate symptom gray level (G) eigenvalue Gcha=averGzh-averGbei=-24.9796;

2.2 Color Feature Extraction of Symptom Edge in Figure 2

2.2.1 The difference between the average color volume of the symptom edge and the average color volume of the background skin

2.2.1.1 Calculate the hue difference between the symptom edge and the background skin ebHcha=averHedge-averHbei=-224.289

2.2.1.2 Calculate the saturation difference between the symptom edge and the background skin ebScha=averSedge-averSbei=0.125347

2.2.1.3 Calculation of intensity difference between symptom edge and background skin ebIcha=averIedge-averIbei=-8.3465

2.2.1.4 Calculation of gray difference between symptom edge and background skin ebGcha=averGedge-averGbei=-16.070

2.2.2 The difference between the average color volume at the edge of the symptom and the average color volume inside the symptom

2.2.1.1 Calculate the hue difference between the edge of the symptom and the interior of the symptom ebHcha=averHedge-averHbei=-4.2176

2.2.1.2 Calculate the saturation difference between the edge of the symptom and the interior of the symptom ezScha=averSedge-averSzh=0.122709

2.2.1.3 Calculation of intensity difference between symptom edge and symptom interior ezIcha=averIedge-averIzh=4.39426

2.2.1.4 Calculate the gray difference between the edge of the symptom and the interior of the symptom ezGcha=averGedge-averGzh=8.90916

3) Shape characteristics of symptoms in Figure 2

Compute the 7 invariant moments:

φ ₁ =η ₂₀ +η ₀₂ =0.73399

${\mathrm{<span\; class="notranslate">\; \&phi;</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 20</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 02</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; 4</span>}\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 2.6432</span>}$

φ ₃ =(η ₃₀ -3η ₁₂ ) ² +(3η ₂₁ -η ₀₃ ) ² =3.2293

φ ₄ =(η ₃₀ +η ₁₂ ) ² +(η ₂₁ +η ₀₃ ) ² =4.61191

φ ₅ ＝(η ₃₀ -3η ₁₂ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+

(3η ₂₁ -η ₀₃ )(η ₂₁ +η ₀₃ )×[3(η ₃₀ +η ₁₂ ) ² -(η ₂₁ +η ₀₃ ) ² ]＝7.87397

φ ₆ ＝(η ₂₀ -η ₀₂ )[(η ₃₀ +η ₁₂ ) ² -(η ₂₁ +η ₀₃ ) ² ]+

4η ₁₁ (η ₃₀ +η ₁₂ )(η ₂₁ +η ₀₃ )＝6.10877

φ ₇ ＝(3η ₂₁ -η ₀₃ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+

(3η ₂₁ -η ₀₃ )(η ₂₁ +η ₀₃ )×[3(η ₀₃ +η ₁₂ ) ² -(η ₁₂ +η ₀₃ ) ² ]＝7.78115

这样，黄褐斑图像就转换为22维特征向量，如[10765 151 105  -220.0710.248057  -12.7408  -24.9796  -224.289  0.125347  -8.34654  -16.0704-4.21761  -0.122709  4.39426  8.90916  0.73399  2.6432  3.2293  4.611917.87397  6.10877  7.78115]

2 Skin Microscopic Image Recognizer Based on Support Vector Machine (SVM)

We collected 289 skin microscopic images, under the guidance of relevant professionals, guided the classification of samples, randomly divided them into two groups, used as training and test samples (159 cases/130 cases), each sample calculated Its 22 eigenvalues. In this way, the training samples are converted into 159 22-dimensional vectors.

Construct 6 classifiers, and each classifier is trained with two types of data. During training, three types of kernel functions are tried: (1) linear kernel function (linear); (2) polynomial kernel function (polynomial); (3 ) through the radial basis to select the kernel function that obtains the best LOOCV (leave one out) accuracy. After experiments, this patent uses the first type of kernel function as the support vector machine algorithm, that is, k(x, y)=(x*y+1) ³ , which can make the classifier have the highest recognition rate. The results are shown in Table 1.

Table 1 The recognition rate of several different kernel functions under different parameters Kernel RBF linea Polyfunction r Paramete None None D＝1 D＝2 D＝3 D＝4 D＝5 D＝6、7 D＝8、9r Leave-one-out recognition rate 55.88 79.41 79.41 82.54 88.24 85.29 58.82 11.76 2.94/%

Table 2 shows the results of using the training data (159 cases) to train an SVM, and finally predicting and classifying the test samples (130 cases).

Table 2 Recognition rate of test samples by SVM classifier Sample Category Melasma Freckles Blackheads Acne Normal Skin (30) (23) (16) (32) (11) Classification accuracy/% 88.1 90.0 86.2 85.2 100.0

Claims (3)

1. a skin microscopic image symptom automatic recognition method, it is characterized in that to microcomputer input the symptom segmentation image after skin microscopic image preprocessing, extract the characteristic parameter of symptom segmentation image and convert into the feature vector reflecting symptom classification essence, the The eigenvector performs identification operation based on the identification algorithm of the support vector machine to identify the attribute of the symptom, and then displays the attribute of the symptom in text on the microcomputer display. 2. skin microscopic image symptom automatic identification method according to claim 1, it is characterized in that extracting symptom segmentation image feature parameter and transforming into the concrete steps that reflect the feature vector of symptom classification essence are: a. Extract geometric features of symptoms: (a) Extract the area of symptoms: count the number of pixels with a value of 1 in the segmentation map of various symptoms, and this number is the area of symptoms; (b) Extract the maximum and minimum diameters of the symptoms: Project the segmentation map of the symptoms in a direction that forms an angle θ with the horizontal direction to obtain a projection direction vector; count the number of elements in this vector that are 1, and record it as N(θ ); θ increases by 1° each time from 0° to 179°, and 180 N(θ) are obtained; the maximum value among these 180 N(θ) is used as the maximum diameter of the symptom, and the minimum value is used as the minimum diameter of the symptom; b. Extract color features of symptoms: (a) Color feature extraction inside the symptom: select the difference between the average color amount inside the symptom and the average color amount of the background skin as the feature of the color: i. Calculate the characteristic value of the symptom hue, which is recorded as Hcha: Hcha=(averHzh-averHbei)*360; in the formula: the average hue value inside the symptom, which is recorded as averHzh; the average hue value of the background skin, which is recorded as averHbei; ii. Calculate the symptom saturation (S) eigenvalue, denoted as Scha: Scha=averSzh-averSbei; In the formula: the average saturation value inside the symptom, denoted as averSzh; The average saturation value of the background skin, denoted as averSbei; iii. calculate symptom intensity (I) eigenvalue, denoted as Icha: Icha=averIzh-averIbei; In the formula: the average intensity value inside the symptom, denoted as averIzh; The average intensity value of background skin, denoted as averIbei; iv. Calculate the symptom gray scale (G) eigenvalue, be recorded as Gcha: Gcha=averGzh-averGbei; In the formula: the average gray value of symptom inside, be recorded as averGzh; The average gray value of background skin, be recorded as averGbei; (b) Color Feature Extraction of Symptom Edge: In addition to the difference between the average color amount of the symptom edge and the average color amount of the background skin as the feature of the color, the difference between the average color amount of the symptom edge and the average color amount inside the symptom is also selected As a feature of color: i. The difference between the average color volume of the symptom edge and the average color volume of the background skin Calculate the hue difference between symptom edge and background skin, which is recorded as ebHcha: ebHcha=(averHedge-averHbei)*360; where: the average hue of symptom edge is recorded as averHedge; the average hue of background skin is recorded as averHbei; ●Calculate the saturation difference between the symptom edge and the background skin, denoted as ebScha, ebScha=averSedge-averSbei; where: the average saturation of the symptom edge, denoted as averSedge; the average saturation of the background skin, denoted as averSbei; ●Calculate the intensity difference between the symptom edge and the background skin, which is recorded as ebIcha, ebIcha=averIedge-averIbei; where: the average intensity of the symptom edge, which is recorded as averIedge: the average intensity of the background skin, which is recorded as averIbei; ●Calculate the gray level difference between the symptom edge and the background skin, which is recorded as ebGcha, ebGcha=averGedge-averGbei; where: the average gray value of the symptom edge is recorded as averGedge; the average gray value of the background skin is recorded as averGbei; ii. The difference between the average amount of color at the edge of the symptom and the average amount of color inside the symptom ● Calculate the hue difference between the edge of the symptom and the interior of the symptom, and record it as ezHcha, ebHcha=(averHedge-averHbei)*360, where: the average hue of the edge of the symptom is recorded as averHedge; the average hue of the interior of the symptom is recorded as averHzh; ● Calculate the saturation difference between the edge of the symptom and the interior of the symptom, which is recorded as ezScha, ezScha=averSedge-averSzh, where: the average saturation of the edge of the symptom is recorded as averSedge; the average saturation of the interior of the symptom is recorded as averSzh; ● Calculate the intensity difference between the edge of the symptom and the inside of the symptom, which is recorded as ezIcha, ezIcha=averIedge-averIzh, where: the average intensity of the edge of the symptom is recorded as averIedge; the average intensity of the inside of the symptom is recorded as averIzh; ●Calculate the gray level difference between the edge of the symptom and the interior of the symptom, which is recorded as ezGcha, ezGcha=averGedge-averGzh, where: the average gray level of the symptom edge is recorded as averGedge; the average gray level of the symptom interior is recorded as averGzh; (c) Extraction and conversion operation of shape features of symptoms: extract f(x, y) value, f(x, y) is an image The value at the pixel (x, y), the (p+q) order moment m _pq of the entire image is calculated as follows: ${\mathrm{<span\; class="notranslate">\; m</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; x</span>}}^{\mathrm{<span\; class="notranslate">\; p</span>}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{\mathrm{<span\; class="notranslate">\; q</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; p</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; q</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 0,1,2</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; \&CenterDot;</span><span\; class="notranslate">\; \&CenterDot;</span><span\; class="notranslate">\; \&Center\; Dot;</span>$ The central moment μ _pq of the image is calculated as follows: ${\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; x</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\underset{\mathrm{<span\; class="notranslate">\; the\; y</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; p</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; q</span>}}\mathrm{<span\; class="notranslate">\; f</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span>$ in $\stackrel{\&OverBar;}{x}=\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}\mathrm{xf}(x,\mathrm{the\; y})/\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}f(x,\mathrm{the\; y})$ $\stackrel{\&OverBar;}{\mathrm{the\; y}}=\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}\mathrm{yf}(x,\mathrm{the\; y})/\underset{x}{\mathrm{\&Sigma;}}\underset{\mathrm{the\; y}}{\mathrm{\&Sigma;}}f(x,\mathrm{the\; y})$ The normalized central moment η _pq is calculated according to the following formula: ${\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; pq</span>}}<span\; class="notranslate">\; /</span>{\mathrm{<span\; class="notranslate">\; \&mu;</span>}}_{\mathrm{<span\; class="notranslate">\; 00</span>}}^{\mathrm{<span\; class="notranslate">\; \&gamma;</span>}}$ In the formula, γ=(p+q+2)/2, p+q=2, 3,... A set of invariant moments can be derived from the second and third moments: φ ₁ =η ₂₀ +η ₀₂ ${\mathrm{<span\; class="notranslate">\; \&phi;</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 20</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 02</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 4</span>}{\mathrm{<span\; class="notranslate">\; \&eta;</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$ φ ₃ ＝(η ₃₀ -3η ₁₂ ) ² +(3η ₂₁ -η ₀₃ ) ² φ ₄ ＝(η ₃₀ +η ₁₂ ) ² +(η ₂₁ +η ₀₃ ) ² φ ₅ ＝(η ₃₀ -3η ₁₂ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+ (3η ₂₁ -η ₀₃ )(η ₂₁ +η ₀₃ )×[3(η ₃₀ +η ₁₂ ) ² -(η ₂₁ +η ₀₃ ) ² ] φ ₆ ＝(η ₂₀ -η ₀₂ )[(η ₃₀ +η ₁₂ ) ² -(η ₂₁ +η ₀₃ ) ² ]+ 4η ₁₁ (η ₃₀ +η ₁₂ )(η ₂₁ +η ₀₃ ) φ ₇ ＝(3η ₂₁ -η ₀₃ )(η ₃₀ +η ₁₂ )×[(η ₃₀ +η ₁₂ ) ² -3(η ₂₁ +η ₀₃ ) ² ]+ (3η ₂₁ -η ₀₃ )(η ₂₁ +η ₀₃ )×[3(η ₀₃ +η ₁₂ ) ² -(η ₁₂ +η ₀₃ ) ² ] 3. the automatic recognition method of skin microscopic image symptom special disease according to claim 1, it is characterized in that the concrete steps of recognition operation are: a. Select the kernel function: Using different inner product kernel functions will lead to different support vector machine algorithms. At present, three types of kernel functions are used more as follows: i. Polynomial kernel function: k(x, y)=(x*y+1) ^d d=1, 2..... ii. RBF (Radial Basis Function) kernel function: $K(x,\mathrm{the\; y})=\exp [-\frac{{\left|\right|x-\mathrm{the\; y}\left|\right|}^2}{2{\mathrm{\&sigma;}}^2}]$ iii.Sigmoid kernel function: K(x, y)=tanh[b(x*y)-c] b. b. Training: For real samples and false samples, the ideal outputs are respectively 1 and -1, and the SVM training algorithm is used, that is, the above classification function formula is trained to convergence, and a classifier based on SVM is obtained at this time; c. Identification: The sample to be identified is input into the classifier, and the output is a real value, and the category of the sample can be determined through the set threshold; Steps a) to c) are for two types of classification problems, and for skin microscopic image classification, they are divided into four types. Therefore, k(k-1)/2 classifiers can be designed, and each classifier uses two types of data to train; d. Repeat b) for the chloasma and blackhead samples to obtain the classifier SVM1; e. Repeat b) for the chloasma and acne samples to obtain classifier SVM2; f. Repeat b) for chloasma and freckle samples to obtain classifier SVM3; g. Repeat b) for freckles and blackhead samples to obtain classifier SVM4; h. Repeat b) for freckles and acne samples to obtain classifier SVM5; i. Repeat b) for blackhead and acne samples to obtain classifier SVM6; j. When classifying, adopt a scoring strategy: For a certain sample to be classified, use the training process to obtain 6 classifiers for testing, that is, step c), each result is 1 point, and each category is accumulated Score; k. Select the category corresponding to the highest scorer as the category of the test data; l. Calculation of recognition rate; m. Assuming that there are n initial samples, one sample is taken out for testing each time, and the remaining n-1 are used as training samples; n. Repeat steps d) to i) for the n-1 training samples; o. Test with another sample to get an accuracy, 0 or 100%; p. This process is repeated n times, and as a result, each sample is used as a test sample once, so the final accuracy value is the average value of n times; q. The method of selecting the kernel function is to select the kernel function with the highest recognition rate through steps m) to p).

Images