CN105277663A - Facial identification method for cigarette flavor characteristics - Google Patents

Abstract

The invention discloses a face recognition method for cigarette flavor characteristics. Step 1: Acquire sensory evaluation data; Step 2: Read cigarette sensory evaluation data into Matlab software and perform normalization transformation; Step 3: Normalize preprocessing The final data draws the cigarette sample facial graph; Step 4, classify the samples according to the similarity between the cigarette sample facial graphs; the advantage of the present invention is: the facial graph is vivid and intuitive, and can very vividly visualize the flavor characteristics of the cigarette flavor type For facial features, use the psychological characteristics of human beings who are sensitive to subtle changes in facial features to intuitively identify the similarity of flavor/flavor features of cigarette products, so as to meet the needs of comparative analysis of cigarette products and category construction.

Description

A Face Recognition Method Based on the Characteristics of Cigarette Flavor

technical field

The invention belongs to the technical field of cigarette sensory evaluation, and in particular relates to a face recognition method for cigarette flavor characteristics.

Background technique

Cigarettes are a special product for human consumption. Since the final form of consumption of cigarette products is smoking, the style, characteristics and flavor quality of cigarettes must be burned to provide consumers with feelings. Therefore, the most direct, timely and most representative of consumers' will is the sensory analysis and evaluation of cigarettes. . The overall task and purpose of cigarette sensory analysis and evaluation is to determine and describe the level of flavor quality and style characteristics, and to provide effective and reliable information for product developers and marketing personnel to make correct product and market decisions. Due to market demand and product development, analysis and evaluation of cigarettes has become an important research field and technical work in the tobacco industry.

For the evaluation of cigarette style characteristics, the tobacco industry has established a corresponding evaluation standard YC/T497-2014 "Sensory Evaluation Method for Cigarette Chinese Style Cigarette Style". Applying the method stipulated in this standard can carry out quantitative evaluation of 15 flavor types of cigarettes, and can also The radar chart is used to obtain the corresponding evaluation result chart, but it is difficult to intuitively analyze the similarity of the fragrance characteristics of different products based on the quantitative results and the radar chart.

In view of the above problems, how to use the data visualization method to intuitively analyze the similarity and dissimilarity of the flavor characteristics of cigarette products, so as to meet the needs of comparative analysis of cigarette products and category construction, is a technical problem to be solved in this field .

Contents of the invention

The purpose of the present invention is to address the deficiencies of the prior art and provide a method for visualizing cigarette flavor characteristics, thereby vividly displaying the sensory evaluation results of cigarettes in the form of facial patterns, and visually judging the quality of each cigarette sample according to the shape of the facial patterns. Whether the fragrance characteristics are similar or not, what aspects are the similarities, and what are the differences.

The purpose of the present invention is achieved through the following technical solutions:

1. Obtain sensory evaluation data

The evaluators for the sensory evaluation of cigarettes use YC/T497-2014 "Methods for Sensory Evaluation of Cigarette Chinese Style Cigarette Style" to evaluate the 15 flavor characteristics of N cigarette samples;

2. Read the cigarette sensory evaluation data of 15 flavor characteristics of N cigarette samples into the Matlab software according to the sequence in Table 1 to obtain data X;

$\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\left(\begin{array}{cccc}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 11</span>}}& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 12</span>}}& <span\; class="notranslate">\; ...</span>& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}\mathrm{<span\; class="notranslate">\; p</span>}}\\ {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; twenty\; one</span>}}& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; twenty\; two</span>}}& <span\; class="notranslate">\; ...</span>& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; p</span>}}\\ <span\; class="notranslate">\; \&CenterDot;</span>& <span\; class="notranslate">\; \&CenterDot;</span>& & <span\; class="notranslate">\; \&CenterDot;</span>\\ <span\; class="notranslate">\; \&Center\; Dot;</span>& <span\; class="notranslate">\; \&CenterDot;</span>& & <span\; class="notranslate">\; \&CenterDot;</span>\\ <span\; class="notranslate">\; \&CenterDot;</span>& <span\; class="notranslate">\; \&CenterDot;</span>& & <span\; class="notranslate">\; \&CenterDot;</span>\\ {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; N</span>}\mathrm{<span\; class="notranslate">\; 1</span>}}& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; N</span>}\mathrm{<span\; class="notranslate">\; 2</span>}}& <span\; class="notranslate">\; ...</span>& {\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; N</span>}\mathrm{<span\; class="notranslate">\; p</span>}}\end{array}\right)<span\; class="notranslate">\; ,</span>$

In formula 1: X11 represents the evaluation score of flue-cured tobacco aroma of the first cigarette sample, X12 represents the evaluation score of air-cured tobacco aroma of the first evaluation sample, and the rest are deduced according to the order of the aroma type indicators in Table (2); XN1 Represents the flue-cured tobacco flavor evaluation score of the Nth cigarette sample, and the rest are deduced in accordance with the order of the flavor index in Table (2);

The data X is preprocessed with the following normalization transformation:

${x^{*}}_{ik}=\frac{x_{ik}-x_{\min ,k}}{x_{\max ,k}-x_{\min ,k}}(b-a)+a,i=1,...,N,k=1,...,p,$ In the formula, x _ik is the original data of the k-th comfort characteristic index of the i-th sample, x ^* _ik represents the transformed data, x _max,k ＝max _1≤i≤N x _ik ,x _min,k ＝min _{1≤ i≤N} x _ik , a=0.05, b=0.95;

3. Call the Matlab function glyphplot on the preprocessed data X ^* to draw the cigarette sample face, and the input parameter 'standardize' of glyphplot takes the value 'off';

4. Classify the samples according to the similarity between the cigarette sample faces, and call the Matlab function glyphplot to draw the classified sample faces;

5. Compare and observe the face pictures, and analyze the prominent features of various types of faces.

The beneficial effects of the present invention are: the facial makeup is vivid and intuitive, can convert the characteristics of cigarette flavor into facial features very vividly, utilize the psychological characteristics of human beings who are sensitive to subtle changes in facial features, and make use of the similarity of the flavor characteristics of cigarette products Intuitively identify similarities and dissimilarities to meet the needs of comparative analysis of cigarette products.

Description of drawings

Fig. 1 is 8 cigarette sample facial figures of the face recognition method of a kind of cigarette fragrance type feature of the present invention;

Fig. 2 is the 8 cigarette sample face graphs that the classification of the face recognition method of a kind of cigarette fragrance type feature of the present invention shows;

Fig. 3 is a schematic diagram of the operation flow of the facial recognition method for cigarette flavor characteristics.

detailed description

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

Referring to Fig. 3, the method of the present invention selects 8 cigarette samples as an example, and the specific steps are consistent with those described in the summary of the invention.

1. The sensory evaluation experts are to N=8 cigarette samples, the evaluation data of p=15 flavor characteristics, namely table 1, read into Matlab software, according to the cigarette flavor characteristics and facial features mapping table (table 1) The order of the scent type features is adjusted to the original feature order to obtain the data variable X.

$\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\left[\begin{array}{cccccccccc}\mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}\\ \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}\\ \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 5.0</span>}\\ \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.5</span>}\\ \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}\\ \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}\\ \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}\\ \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}\\ \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.4</span>}& \mathrm{<span\; class="notranslate">\; 4.6</span>}& \mathrm{<span\; class="notranslate">\; 7.9</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}\\ \mathrm{<span\; class="notranslate">\; 8.3</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.8</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.8</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}\\ \mathrm{<span\; class="notranslate">\; 6.4</span>}& \mathrm{<span\; class="notranslate">\; 7.2</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.7</span>}& \mathrm{<span\; class="notranslate">\; 5.4</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}\\ \mathrm{<span\; class="notranslate">\; 9.5</span>}& \mathrm{<span\; class="notranslate">\; 8.7</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.8</span>}& \mathrm{<span\; class="notranslate">\; 8.8</span>}& \mathrm{<span\; class="notranslate">\; 8.6</span>}& \mathrm{<span\; class="notranslate">\; 9.3</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.7</span>}& \mathrm{<span\; class="notranslate">\; 9.0</span>}\\ \mathrm{<span\; class="notranslate">\; 6.9</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 6.0</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.2</span>}& \mathrm{<span\; class="notranslate">\; 5.5</span>}& \mathrm{<span\; class="notranslate">\; 6.9</span>}& \mathrm{<span\; class="notranslate">\; 5.0</span>}& \mathrm{<span\; class="notranslate">\; 8.3</span>}& \mathrm{<span\; class="notranslate">\; 6.5</span>}\\ \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 7.6</span>}& \mathrm{<span\; class="notranslate">\; 7.8</span>}& \mathrm{<span\; class="notranslate">\; 7.7</span>}& \mathrm{<span\; class="notranslate">\; 7.7</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.8</span>}& \mathrm{<span\; class="notranslate">\; 7.3</span>}& \mathrm{<span\; class="notranslate">\; 7.5</span>}& \mathrm{<span\; class="notranslate">\; 7.4</span>}\\ \mathrm{<span\; class="notranslate">\; 9.2</span>}& \mathrm{<span\; class="notranslate">\; 8.0</span>}& \mathrm{<span\; class="notranslate">\; 8.3</span>}& \mathrm{<span\; class="notranslate">\; 8.4</span>}& \mathrm{<span\; class="notranslate">\; 8.7</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.5</span>}& \mathrm{<span\; class="notranslate">\; 8.4</span>}& \mathrm{<span\; class="notranslate">\; 9.2</span>}& \mathrm{<span\; class="notranslate">\; 7.0</span>}\end{array}\right]$

The data X is preprocessed with the following normalization transformation:

${{\mathrm{<span\; class="notranslate">\; x</span>}}^{<span\; class="notranslate">\; *</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; k</span>}}}{{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; k</span>}}}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; b</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; p</span>}<span\; class="notranslate">\; ,</span>$

In the formula, x _ik is the original data of the k-th comfort characteristic index of the i-th sample, x ^* _ik represents the transformed data, x _max,k ＝max _1≤i≤N x _ik ,x _min,k ＝min _{1≤ i≤N} x _ik , a=0.05, b=0.95.

2. Execute the following Matlab command on the preprocessed data X ^* :

n = {'sample1', 'sample2', ..., 'sampleN'};

glyphplot(X ^* ,'standardize','off','ObsLabels',n,'glyph','face')

The input parameter 'standardize' of glyphplot takes the value 'off', the input parameter 'ObsLabels' will add the specific name n of the sample under each face map, and the input parameter 'glyph' takes the value 'face' to draw the face map, and the figure can be obtained 1.

Observing Figure 1, we can see that the face, eyes, nose and mouth of sample 3 and sample 2 are relatively similar. In contrast, the faces of sample 5, sample 6, and sample 8 are actually relatively similar to these two samples, but each part The ratio is smaller, so these 5 samples can be classified into one category (category 1); because the face patterns of each facebook and sample 7 are quite different, so sample 7 is a separate category (category 2); sample 1, sample 4 The face shape, eyes, nose, and mouth of the two samples are similar, and these two samples can be divided into one category (category 3).

3. Classify the samples according to the similarity between the cigarette sample faces, and call the Matlab function glyphplot to draw the classified sample faces, as shown in Figure 2.

It can be seen from Fig. 1 that face pictures can be divided into l=3 categories. Note that X _j ^* is the data of the jth sample, and n _j is the name of the jth sample;

Execute the Matlab command:

forj=1:l

figure(j);

glyphplot(X _j ^* ,'standardize','off','ObsLabels',n _j ,'glyph','face');

end

The input parameter 'standardize' of glyphplot takes the value 'off'.

4. Compare and observe various types of facial makeup, analyze the prominent features of various types of facial makeup, and determine the main flavor characteristics of various samples according to the cigarette flavor type characteristics and facial feature mapping table (see Table 1).

Observing Figure 2, it can be seen that in general, the face size, the width of the eyes and the vertical position of the mouth of the samples in category 1 are relatively prominent relative to other parts. According to the mapping table of fragrance characteristics and facial characteristics (see Table 1), it can be seen that These 5 samples are mainly flue-cured tobacco aroma, light aroma and sweet aroma. The face of class 2 sample 7 has a certain size, and the face shape is different. The upper half of the face is larger than the lower half of the face, and the distance between the two eyes is wider. According to Table 1, it is known that it is mainly scented with flue-cured tobacco, flowers, and herbs. Fragrance type. Each part of the two samples of category 3 has some characteristics, but there are no particularly prominent characteristics. According to Table 1 and combined with Table 1, it can be seen that they are mainly flue-cured tobacco aroma, supplemented by certain spicy, fruity, and bean aromas , milky, baked and sweet.

Table 2: Raw data

The beneficial effects of the present invention are: the facial makeup is vivid and intuitive, can convert the characteristics of cigarette flavor into facial features very vividly, utilize the psychological characteristics of human beings who are sensitive to subtle changes in facial features, and make use of the similarity of the flavor characteristics of cigarette products Intuitively identify similarities and dissimilarities to meet the needs of comparative analysis of cigarette products.

The above is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto, and any changes or replacements that are not thought of through creative work should be covered by the protection scope of the present utility model.

Claims (3)

1. a face recognition method for flavor type of cigarette feature, is characterized in that, comprise the following steps:

Step one, acquisition sensory evaluation data: the valuation officer of cigarette sensory evaluation adopts YC/T497-2014 " cigarette Chinese-style cigarette style sensory evaluation method " to evaluate the odor type feature of N number of cigarette sample;

Step 2, cigarette sensory evaluation data is read in Matlab software, the comfort characteristic index sequencing according to flavor type of cigarette feature and facial feature map table adjusts former characteristic sequence, line number of going forward side by side Data preprocess;

Step 3, cigarette sample face graph is drawn to pretreated data call Matlab function glyphplot;

Step 4, according to the similarity between cigarette sample face graph to sample classification, and call Matlab function glyphplot and draw sub-category sample face graph;

Step 5, comparative observation face graph, analyze the prominent feature of all kinds of types of facial makeup in Beijing operas, and according to flavor type of cigarette feature and facial feature map table, determine the main body odor type feature of all kinds of sample;

The method, by 15 of Chinese-style cigarette odor type/note features and face features, comprises the size of face, the position of the length of nose and face, eyes, eyebrow etc. maps one by one.

2. the face recognition method of flavor type of cigarette feature as claimed in claim 1, it is characterized in that, the data preprocessing method of described step 2 is:

Following normalization is adopted to convert to the sensory evaluation data of N number of sample p odor type feature: ${x^{*}}_{ik}=\frac{x_{ik}-x_{\min ,k}}{x_{\max ,k}-x_{\min ,k}}(b-a)+a,i=1,\mathrm{...},N,k=1,\mathrm{...},p,$ X in formula _ikbe the raw data of the kth odor type feature of the i-th sample, x ^* _ikrepresent the data after conversion, x _{max, k}=max _1≤i≤Nx _ik, x _{min, k}=min _1≤i≤Nx _ik, a=0.05, b=0.95.

3. the face recognition method of flavor type of cigarette feature as claimed in claim 1 or 2, it is characterized in that, the flavor type of cigarette feature of described step 2 and step 5 and facial feature map table are in table 1:

Table 1: flavor type of cigarette feature and facial feature map table

Comfort characteristic index due to Chinese-style cigarette is 15, and the face feature of mapping in Matlab is 17, does not have 2 corresponding face features automatically to get default value when Matlab draws face graph.