JPH0360775A - Color detection type device for discriminating kind of leaf tobacco - Google Patents

Abstract

PURPOSE:To allow automatic discrimination by providing a color measuring means which outputs the coordinate information on the color space of a color specification system, a means for storing the kinds of leaf tobacco and an input means. CONSTITUTION:A coordinate converting means 23 makes the coordinate conversion of the numerical data from a color space value reading means 22 to form coordinate data Z1, Z2, Z3 when the leaf taking position data are stored in a storage means Z1. A classifying deciding means 24 discriminates the segments of the measuring points Z1, Z2, Z3 in the discrimination space by reading the data on the leaf taking position of the storage means 21, determining the angle within the plane of the coordinate data Z1, Z2 and comparing the angle range of the segment of the middle leaf system stored in the storage means 21 and the angle determined by an arithmetic means 25. A ranking means 27 reads-out the attributes with the respective sections stored by an attribute discriminating means 26 and determines a ranking decision value. The decision is automatically executed in this way.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a leaf tobacco sorting device suitable for use in grading the quality of harvested and dried leaf tobacco.

[Conventional technology]

Traditionally, the quality of leaf tobacco has been determined by the leaf position, ripeness,
It is evaluated based on the quality factors of color, texture, and mesophyll, and is classified by the naked eye into skin surface 1.

Prices are then set corresponding to each purchasing category (categories marked with "○").

(Hereinafter, blank) Leaf tobacco purchasing classification table Table 1 Among the purchasing classifications in the table above, P-type leaf tobacco with discoloration is called rapid-drying leaf tobacco, and it is caused by dehydration after yellowing during the post-harvest drying process. However, the natural browning of leaf tobacco has not been completed sufficiently and a yellowish tinge remains. In addition, among the poorly ripened middle leaves (Kinshu, middle leaves, and lower leaves), blurred leaves with a dull whitish hue and no luster in appearance occur together with rapidly drying leaves, so blurred leaves are also P type. It is rated as such. These P-type leaf tobaccos have problems such as a bad tobacco taste and the fact that their harmful effects are not fully exerted during the tobacco manufacturing process, so they are different from regular tobacco types in terms of price. For this reason, special attention is paid to the P type rating.

However, since the P-type leaf tobacco described above is similar in hue to the ordinary A-type leaf tobacco, there is a problem in that it is difficult to grade even an expert using the conventional visual grading method.

An object of the present invention is to enable automatic discrimination of the type of leaf tobacco based on the color and leaf position of the specimen.

[Means for Solving the Problems] The color detection type leaf tobacco type device of the present invention, which has been made to solve the above problems, detects the color of a specimen and represents it with a brightness index of 1 and a perceived color index of 2. a color measurement means that outputs coordinate information in a color space of a color system to be used; and a characteristic boundary within a distribution area of the leaf tobacco in the color space for a plurality of leaf tobaccos that have been classified in advance based on a plurality of types and leaf-bearing positions. a storage means for storing information indicative of the type of leaf tobacco and the leaf-bearing position, an input means for inputting information showing the leaf-bearing position of the sample leaf tobacco, and a leaf-bearing position input by the input means; calculation means for calculating the distance between the measurement point of the leaf tobacco and the characteristic boundary in the color space based on the information indicating the characteristic boundary corresponding to the color space and the coordinate information from the color measurement means; and the distance obtained by the calculation means. and a determination means for determining a difference between the types of leaf tobacco distributed within the characteristic boundary and the type of leaf tobacco to be measured based on a preset determination criterion, and the determination means determines the difference between the types of leaf tobacco distributed within the characteristic boundary and the type of leaf tobacco to be measured, and the color obtained by the determination means regarding the leaf tobacco measured by the color measuring means. The present invention is characterized in that the type of leaf tobacco is determined for each leaf-bearing position based on the determination result and information indicating the leaf-bearing position selected by the selection input means.

[For production]

In the color detection type leaf tobacco sorting device of the present invention, information indicating the characteristic boundaries of the leaf tobacco distribution area is stored in the storage means, and when information indicating the leaf-bearing position of the sample leaf tobacco is inputted by the input means, the input Based on the information indicating the characteristic boundary corresponding to the leaf-bearing position and the coordinate information from the color measurement means, the calculation means calculates the distance between the measurement point of the leaf tobacco and the characteristic boundary in the color space. Then, the determining means determines the difference between the type of leaf tobacco distributed within the characteristic boundary and the type of leaf tobacco to be measured based on the determined distance and a preset determination criterion.

The color of leaf tobacco is distributed on a certain curve in a color space such as the L''a''b'' color system, and P type leaf tobacco is mainly distributed on the outer peripheral side of this distribution area.

Therefore, for example, if the boundary between the distribution areas of regular leaf tobacco and 2541 leaf tobacco is set as a characteristic boundary, 2541 leaf tobacco can be discriminated based on the distance between this characteristic boundary and the measurement point.

In addition, even in the same distribution area, P
There are two types: P-type and non-P-type, but by selecting characteristic boundaries according to the leaf-bearing position of the specimen, it is possible to separate and distinguish P-type.

〔Example〕

Hereinafter, the present invention will be explained in detail using a type of leaf tobacco as an example.

Figure 10 is a diagram showing the color distribution of leaf tobacco in the color space of the L''a''b'' color system, and Figure 11 is a diagram showing the color distribution of leaf tobacco in the color space of the L''a''b'' color system.
FIG. 3 is a diagram showing cross section A, and the distribution of leaf tobacco shows a constant color change path within the color space corresponding to the leaf setting position shown in Table 1 above. Ordinary tea leaf tobacco includes lower leaf, middle leaf, kinju,
They are distributed along a curved transition path in the order of tree leaves, upper leaves, and top leaves, and 2541 leaf tobacco is concentrated in the outer region of ordinary tea leaf tobacco, and is particularly distributed in large numbers between the golden leaves and the tree leaves. Furthermore, as shown in Figure 11, the area of 2541 leaf tobacco that is woody (tree leaves, upper leaves, and top leaves) is medium-leaf (
It partially overlaps with the lower leaf, middle leaf, and common tea leaf tobacco regions (ff1).

The present invention relates to the data of the lightness index L* and the perceived chromaticity index a 11 , bO in the color space of the L"a"b1 color system (hereinafter referred to as color space values) regarding the color of leaf tobacco.

), and based on the distance (color difference) between the measurement point in the color space corresponding to this color space value and the distribution area corresponding to the measured leaf position (wooden leaf type and intermediate leaf type) of leaf tobacco, 2541
Leaf tobacco can now be identified.

Next, the determination method in the embodiment will be explained.

(Discrimination method) First, l, *a11b9 explained in FIG. 10 above.
For the color space of the color system, Zl tZZ , z= obtained by the coordinate transformation shown in the following equations (1) and (2)
Two types of three-dimensional discriminant spaces are set. Then, by the coordinate transformation of equations (1) and (2), the distribution areas of woody-leaved and medium-leaved tobacco in the above color space are respectively assumed in each discriminant space, and the distribution areas in each discriminant space are described later. It is set in advance by the feature boundary of the ellipse to be explained. In addition, as will be explained later, the color space values from the color sensor that detects the color of leaf tobacco are also coordinate-transformed using equation (1) or (2) depending on the leaf position of the specimen (woody-leafed or meso-leafed).
Each of 2541 leaf tobaccos is discriminated within the discrimination space corresponding to the leaf arrival position.

When the distribution of multi-leaf tobacco (woody-leaf type and medium-leaf type tobacco) in the color space is transformed into the two types of discriminant spaces as described above, the center line of the distribution area of regular tea leaf tobacco becomes as shown in Figure 3 in the case of tree-leaf type tobacco. As shown, it can be approximated by an arc and a straight line, and
In the case of mesophyllosis, it can be approximated by an arc in the discriminant space as shown in FIG. Then, the center line of the distribution area of the tree-leaf type becomes a circular arc shown by the following equation (3) and a straight line, and the center line of the distribution area of the meso-leaf type becomes a circular arc shown by the following equation (4). In addition, in FIG. 3 and FIG. 4, the coordinate axis Z3 is the coordinate axis zl, z.

The direction is perpendicular to

(Tree-leaf type) Z 2 = OZ 3 = 0 However, O≦z+ <7.3 ...... (3) (Medium-leaf type) zIz+ zt! = 10”, zs=0, while
The distribution area of leaf tobacco is around each center line as shown in FIG. In the case of mesophyllosis, as shown in Figure 4, the center line is divided into four sections (■ to ■) within the Z and Zz planes, and criteria for judgment are set for each of these divided sections. .

In the case of mesophyllosis, if we divide it by angles counterclockwise around the origin with the positive direction of the 21st axis as the reference in Figure 4, we get the following:
The distribution of leaf tobacco is as shown in skin surface 2.

・・・・・・(4) Table 2 As shown in Table 2 above, 2541 leaf tobacco is classified into categories ■～■
Therefore, in the determination process, first, it is determined to which category the measurement point in the discriminant space corresponding to the measured color space value belongs to the z and ZzT planes, and if it belongs to the categories Make a determination. Note that the coordinates (Z+tZz ?Z3) of the measurement point in the discriminant space are obtained by the coordinate transformation described above, and the angle α indicating the division in the Z, Z2 plane is α-tan-'('')...・・・
(5) Obtained by 1. Then, the classification is determined by comparing this angle α with the angle ranges corresponding to the classifications (■) to (■), respectively.

As a standard for each classification of 1511 leaf tobacco in categories ■ to ■, a ZaZ3 coordinate system perpendicular to this center line is set along the center line of categories ■ to ■, and the boundary of the distribution area of ordinary leaf tobacco is The equation of the ellipse representing the feature is set in the 242ff coordinate system. Note that the origin of this Za23 coordinate system is on the center line, and the z4 coordinate axis is on the Z,23 coordinate system of the discriminant space.
Within the three planes, the z3 coordinate is the same as the 23rd coordinate in the discriminant space.

The following equation shows the equation of the ellipse in sections 1 to 2, and its graphs are shown in FIGS. 6(a) to 6(C). Note that θ in the following equation is the inclination of the major axis of the ellipse, and 2. The angle is rotated counterclockwise around the origin with the positive direction of the axis as the reference.

Discrimination between regular leaf tobacco and 1511 leaf tobacco is performed based on the distance (color difference) from this characteristic boundary to the measurement point, using the ellipse for each category set as described above as a characteristic boundary in the discrimination space.

Note that the above distance X is determined as follows.

First, the coordinates of the measurement point (ZltZ2z,) in the discriminant space are transformed using the following equation (6), and the coordinates (ZapZx) of the measurement point on the Z and Z3 planes are determined.

Z3 =Zs t Za ”Z+” +z,,
R・”・”(6) However, R is the radius of the center line (R
=10) Then, the distance X as shown in the following equation (7) is determined by the length of the perpendicular line hanging from this point (z4 tzs) to the feature boundary. Note that the value of distance X is negative inside the feature boundary and positive outside the feature boundary.

Now, the equation of the ellipse of the feature boundary is as follows: The measurement point is (Z=D, Z311), and the intersection of the ellipse and the perpendicular line hanging from the measurement point to the ellipse is (Zar - Zsp).
Then, the distance '4x can be calculated using the following equation.

X = 24P 240') + (Lp
Z+n However, 'lao' = Z, 4D CO
5θ-Z, D sinθZ3D' = Ln sin
θ+Z+n CoSθ In addition, Zar is calculated from the following quartic equation using the well-known Ferrari formula, etc., a-(Zip)'+b-(Lr)"+c・(Lp)"+
d・(Lp) +e=・・・・・・(7) Also, 3F is determined by the following formula.

23F = “’57-Author I A.

Next, in the case of leaf tobacco, there are 1511 leaf tobaccos only in the positive direction of the Z axis in FIG.

Also, 2. in the discriminant space. Since the distribution area of leaf tobacco around the axis is small, the determination process for regular leaf tobacco and 1511 leaf tobacco uses Z, Z, and an ellipse on the plane in the discrimination space as a feature boundary, as shown in Figure 5 and the following equation. The measurement is performed based on the distance (color difference) from this feature boundary to the measurement point.

Note that the above distance X is determined as follows.

That is, the distance MX as shown in the following equation (8) is determined by the length of the perpendicular line hanging from the measurement point (ZIsZ2) in the discrimination section to the feature boundary.

Now, the equation of the ellipse of the feature boundary is: The measurement point is (2+□Z0), the intersection of the perpendicular line hanging from the measurement point to the ellipse and the ellipse is (ZIp, Zgp), and the distance X can be found using the following formula. .

x= ZIP Zll+) +(Z2P
Z2D Note that ZIF is ri which is known from the following quartic equation.
Find it using the formula etc.

a-(ZIp)'+b・(Ztp)"+c・(Lp)"
+d-(ZIp) +e=0...(8) erra Furthermore, 22F is determined by the following formula.

Zip =-! L-40ZIF e As described above, calculate the distance
41 Identification of leaf tobacco.

By the way, some leaf tobacco, even leaf tobacco,
There may be different types depending on the base, center, and tip of the leaf, and there are two types of leaf tobacco, one leaf tobacco or a bunch of leaf tobacco (a handful of leaf tobacco sampled for discrimination). There may be a mixture of P type parts. For this reason, when a bunch of leaf tobacco has uneven color, the current grading by graders is to grade each part of the leaf tobacco, as shown in skin table 3, and judge each part comprehensively. We are doing the grading.

Table 3 Furthermore, for each part, as shown in skin table 4, for example, the degree of "normal type-like" and "P-type-like" is evaluated for each part, and based on each evaluation result, the entire East The normal type is rated as to whether it is P type or not. In addition, in the skin surface and the following description, "N", "Light Nj", "Light P", "Medium PJ"
and "Severe P", "N" is a normal type, "Light N" is a normal type that is closer to the P type, "Light P" is a mild P type, and "Medium P".
represents each attribute indicating the degree of "P-type-likeness", such as "severe P type" and "severe P type" respectively.

Table 4 Therefore, in this example, as shown in FIG. 7, for the case parts of the base, center, and tip of the leaf tobacco, the distance X from the characteristic boundary is set as N as a variable.

A discriminant function indicating the degree of each attribute of light N, light P, medium p, and ip is set, and from this discriminant function, the probability that the measurement site has each attribute (hereinafter referred to as attribute probability) is calculated. I have to.

The discriminant functions for the tree-leaf type and meso-leaf type are shown below, and their graphs are shown in Figure 8 for the tree-leaf type and Figures 9 (a) to (C) for the meso-leaf type.
Shown below.

(Discriminant function of tree leaf system) Discriminant function of light N: P, (x) P zz (x) −L P ! ! (X)
-3,20≦x<-1,00Pzz(x) = 0.403・(-1,48) ■,00≦X〈1.48 (Mesophyte discriminant function) Ku category ■〉 Ku category ■〉 Ku Category ■〉 Once the attribute probability is determined using the above discriminant function, the attribute of the measurement part (N) that has a large meat amount with the attribute probability is determined.

One of the five categories: light N, light P, medium P, 9 heavy P).

For example, as shown in Table 5 below, distance X is distance section CM
3, M,), the attribute with the greater of the probability P8 of light P and the probability P4.4 of medium P is set as the attribute of the measurement part.

Table 5 Then, depending on the combination of the attributes of each measurement site, the grading in Table 6 below is based on the rules, and the preset grading judgment values (P,
75, 50, 25. Find N).

(Hereafter, margin) Table 6 however, Judgment value of the above rating (hereinafter referred to as Rating judgment It's called value.

] indicates the percentage of appraisers who graded the leaf tobacco as P type when a large number of appraisers graded a bunch of leaf tobacco for each combination of each part and its attributes, and shows the following contents.

P: A combination of leaf tobacco in bundles that all appraisers rate as P type.A combination of leaf tobacco in bundles that 757,100 appraisers rate as P type.A combination that 757,100 appraisers rate as P type. Leaf tobacco in a bundle size 50: Leaf tobacco in a bundle size that 50 out of 100 appraisers would rate as P type 25: Leaf tobacco in a bundle size that 25 people out of 100 appraisers would rate as P type N : A bunch of leaf tobacco that all the appraisers rate as normal. Grading judgment value (P, 75, 50.25) as above.
, N) is determined, the rating judgment value is compared with the judgment standard to determine the P type. In this example,
If the rating judgment value is P or 75, it is determined as P type,
If it is either N, 25 or 50, it is determined to be normal.

Next, the configuration of the device of the embodiment will be explained.

(Configuration of Apparatus) FIG. 1 is a block diagram of an embodiment of the present invention, in which ordinary leaf tobacco and 1541 leaf tobacco are determined based on the above-described determination method.

In the figure, l is a color sensor that irradiates the object to be measured (leaf tobacco) with illumination light and outputs a colorimetric value as digital data based on the reflected light. Data (color space values) of chromaticity indices a1, b" are output. As this color sensor, for example, "Color Difference Meter CR-110J" manufactured by Minolta can be used.

Reference numeral 2 denotes a determination control means composed of a microcomputer or the like, and the functions obtained based on a control program stored in a memory (not shown) are shown in a functional block diagram.

The determination control means 2 takes in the color space values from the color sensor 1 via the interface 3, performs various calculations, and displays the determination results on the display means 4. In addition, data indicating the leaf position of the leaf tobacco to be measured (hereinafter referred to as leaf position data), data indicating the measurement site (hereinafter referred to as measurement site data), and data indicating the judgment criteria are input to an input means 5 such as a keyboard. Input from Note that these data can be obtained by, for example, displaying the leaf formation position and the measurement site in a menu format on the display means 4, operating a predetermined key using a keyboard on the input means 5, and identifying the code of the operated key. It can be entered by

In the determination control means 2, the storage means 21 is configured in the memory of the microcomputer, and is
1) Equation 9 (2), data on the angular range indicating each category ■ to Z
Equation (6) to obtain the coordinate values of the Z4 Z3 plane from Z t Zl ), Equations (7) and (8) to obtain the distance nx from the measurement point to the feature boundary, and the discriminant function to obtain the attribute probability, shown in Table 6 above. The shown ratings are stored in programs such as data expressing rules in a table format. Further, the storage means 21 stores leaf landing position data and measurement site data inputted from the input means 5.

Color space value reading means 22, coordinate conversion means 23, category discrimination means 24, distance calculation means 25, attribute judgment means 26, rating means 27, output means 28 and control means 29 are stored in advance in a memory of a microcomputer or the like. The control means 29 associates the functions of each means based on a determination flow described later.

When the color space value reading means 22 detects that the measurement value has been determined by the color sensor 1 based on the interrupt signal from the color sensor 1, the color space value reading means 22 reads L", a*, 1 output from the color sensor 1.
．． * signals are taken in through the interface 3, and the L", a", and b(I signals are output as numerical data.

When the leaf arrival position data is stored in the storage means 21, the coordinate conversion means 23 converts the color space value reading means 22 into the color space value reading means 22 based on the above-mentioned equation (1) or equation (2) corresponding to the leaf arrival position indicated by this data. Coordinate transformation is applied to the numerical data from Z + yZz 9
23 is generated.

The classification determining means 24 reads the leaf arrival position data in the storage means 21, and in the case of mesophyll type, it determines z based on the above-mentioned 2(5).
, the angle in the Zz plane is determined, and the angle range of the mesophyletic division stored in the storage means 21 is compared with the angle determined by the calculation means 24 to determine the measurement point (Zl +
22 * 23) classification. Note that when the measurement point corresponds to category (2), the attribute probability of N is set to °'1.Also, when 21 is negative in the case of tree leaves, the attribute probability of N is set to °'1.

The distance calculating means 25 calculates the above equation (6) in the case of mesophyllis.
Based on the coordinate data 24 on the z and z planes.

2, and when it is determined by the classification determining means 25 to be any of the classifications ■ to ■, the feature boundary of the determined classification is selected from the storage means 21 and the distance MX is determined from this selected characteristic boundary and 24s23. . In addition, in the case of tree leaves, storage means 2
The distance X is calculated from the characteristic boundary of true leaf tea stored in 1 and z1z2 obtained by the coordinate conversion means.

The attribute determination means 26 uses the distance X calculated by the distance calculation means 25.
The attribute probability is determined from the discriminant function stored in the storage means 21, and the attribute showing the maximum attribute probability for one measurement site is determined and temporarily stored in the storage means 21.

The grading means 27 reads the attributes of each part stored by the attribute discriminating means 26, and based on the combination of the attributes, the grading stored in the storage means 21 refers to the rule data and determines the grading judgment value. The determination criteria stored in the storage means 21 are compared with the rating determination value, and the P type determination result is output to the output means.

The output means 28 outputs display data indicating the determination result to the display means 4, and the determination result is displayed on the display means 4.

FIG. 2 shows that the determination control means 2
This is a flowchart showing the determination process performed in step S1), in which when the control program is started, it is monitored that the leaf arrival position data is input from the input means 5 (step S1), and when the leaf arrival position data is input, this input is performed. The leaf landing position data thus obtained is stored in the storage output 21 (step S).

When the color space value reading means 22 detects that the measured value of the color sensor 1 has been determined based on the interrupt signal from the color sensor 1, the color space value reading means 22 reads Llj, a1 output from the color sensor 1.
'', bl signals are taken in through the interface 3, and the L'', a'', and b signals are temporarily stored as numerical data (Step S,), and the input of measurement site data from the input means 5 is monitored. (Step S4), and when the measurement site data is input, the numerical data is associated with the measurement site data and stored in the storage means 21 (Step S,
).

Next, determine whether the tree is leafy or mesophyllous (step S).
, control is performed as follows depending on each case.

(In the case of tree-leaf system) The coordinate transformation means 23 transforms the numerical data stored in the storage means 21 using equation (1), and converts the coordinate data ZI+2, Zff in the discriminant space into step St), Zl.
Determine whether the value of is negative (step Sa)
. When zl is negative, the attribute probability that the attribute of the part corresponding to this measurement point is N is set to "1" (step S9); when Zl is not negative, the distance calculation means 25
Calculate the distance X from the feature boundary (step S
1°).

(In case of intermediate lobe system) The coordinate transformation means 23 transforms the numerical data stored in the storage means 21 using equation (2) to generate coordinate data Z+yztZx in the discriminant space (Stenbu S1.).

Next, the classification determining means 25 calculates the angle α in the z, Zz plane from Zl and Z2 using equation (5), and further calculates the coordinate data Z4 on the z, z4 plane based on equation (6).
, Zff are determined (step S Ig). Then, the angle range of the division stored in the storage means 21 is compared with the obtained angle α, and the point (Zl, Z2 t Zi
) is determined (step 5I3).

As a result of classification, if the measurement point belongs to the classification (65
〈α〉315) means that the attribute probability that the attribute of the part corresponding to this measurement point is N is set to "loo".
, when the measurement point belongs to any of the categories ■ to ■, the distance calculation means 25 calculates the distance NX from the feature boundary corresponding to the category to which it belongs (step S Is p S 1
6 s S l).

In both cases of tree-leaf type and meso-leaf type, when the distance 1fiff x is calculated (step S I 11 y S I S w
S l 69 S I j ), attribute determination means 26
Accordingly, the attribute probability of the measurement part is calculated from the predetermined discriminant function corresponding to each classification of tree-leaf type and meso-leaf type stored in the storage means 21 (step 518).

Setting the attribute probability of N+11 I+ (step S).

,S,) or calculation of the above attribute probability (step 5Il
When step 1) is completed, the attribute indicating the maximum attribute probability is temporarily stored in the storage means 21 in association with the data indicating the measurement site (step S4).

Then, the above flow is repeated while determining whether the attributes have been determined for all parts (base, center, and leaf tip) (step 5ho), and when the attributes of each part are stored in the storage means 21, the grading means 27, the stored attributes of each part are read out, and based on the combination of the attributes, the rating stored in the storage means 21 is determined by referring to the rule data to determine the rating judgment value (step St), and Means 2
Compare the judgment criteria stored in 1 and the rating judgment value and
The type determination result is output to the output means (step 52
2). Then, the determination result is displayed on the display means 4 by the output means 28.

In the above embodiment, the grading judgment value for the combination of attributes of each part is calculated according to the rules, but the grading judgment value shown in Table 6 above is "N" → "25" → "
50"→"75"→"P" may be expressed as a continuous value.

For example, a determination expression as shown in the following equation (9) is set.

D=α・Σ(P,)+β・Σ(P□)+γ・Σ(P,i
i) +δ・Σ(Pat) +ε・Σ(P, Mu)...
...(9) T: 1 company F's number of village 0 = υ, Jl Then, as in the above embodiment, N for each part.

Find the attribute probabilities of light N, light P, medium P and double P, and add the attribute probabilities of each part for each same attribute (each summation term of the discriminant),
A determination value (D) is calculated by assigning a weighting coefficient to each.

In addition, as a criterion for determining regular tea leaf tobacco and 2741 leaf tobacco, a threshold value Ds, such as the boundary between "75" and rN in the above example, is set in advance, and when D<Ds, it is determined as regular tea leaf tobacco. and 27 when Ds≦D
41 It is determined that it is leaf tobacco.

As described above, by measuring the color of leaf tobacco with a color sensor, it is possible to identify 2741 leaf tobacco, and furthermore, by inputting the data on the leaf position of leaf tobacco, it is possible to identify the color of leaf tobacco, which has a similar hue to that of medium-leaf regular brown leaf tobacco. Konoha type 27
41 leaf tobacco can also be identified.

〔Effect of the invention〕

As explained above, according to the color detection leaf tobacco sorting device of the present invention, information on feature boundaries indicating the distribution area of leaf tobacco in a color space such as the L$ a1″b” color system is applied to the leaf position of leaf tobacco. The measured point in the color space is identified by the color space value of the leaf tobacco measured by a color sensor, etc., and the leaf formation position is selected, and the distance (color difference) between the memorized characteristic boundary and the measured point is ), it is possible to easily distinguish between regular tea leaf tobacco and 2741 leaf tobacco, which have similar colors. It is possible to separate and distinguish between 2741 leaf tobacco and ordinary tea leaf tobacco.

[Brief explanation of drawings]

Fig. 1 is a block diagram of an embodiment of the present invention, Fig. 2 is a flowchart related to the embodiment, Fig. 3 is a diagram showing the center line of the distribution area in the discriminant space of tree leaves in the embodiment, and Fig. 4 is an implementation example. Figure 5 is a diagram showing an example of the ellipse of the characteristic boundary of the mesophyll family in the example. Figure 6 is the characteristic boundary of the mesophyll family in the example. FIG. 7 is a diagram explaining the discriminant function in the example. FIG. 8 is a diagram showing a graph of the discriminant function for the tree-leaf type in the example. FIG. 9 is a diagram for explaining the discriminant function in the example. FIG. 10 is a diagram showing a graph of a discriminant function, FIG. 1O is a diagram showing a distribution state of leaf tobacco in a color space according to the present invention, and FIG. 11 is a diagram showing a cross section of the distribution area of FIG. 10. 1... Color sensor, 2... Judgment control means, 3...
Input means, 4... display means. 3 Figure 1 Figure 1 Figure special 4. Earka/Lanoni Tsutomu Figure 4 3 2-1 Figure (0) (bl (C) Figure True Leaf P Tights Figure 11

Claims (1)

[Scope of Claims] Color measurement means for detecting the color of a specimen and outputting coordinate information in a color space of a color system expressed by a brightness index of 1 and a perceptual color index of 2; a storage means for storing information indicating characteristic boundaries within the distribution area of the leaf tobacco in the color space for a plurality of leaf tobaccos classified in advance based on the leaf position, in correspondence with the type of the leaf tobacco and the leaf setting position; an input means for inputting information indicating the leaf-bearing position of the leaf tobacco, information indicating a feature boundary corresponding to the leaf-bearing position inputted by the input means, and coordinate information from the color measuring means; A calculation means for calculating the distance between a measurement point of leaf tobacco in space and a characteristic boundary, and a calculation means for calculating the distance between a measurement point of leaf tobacco and a characteristic boundary in space, and a calculation method for determining the types of leaf tobacco distributed within the characteristic boundary and the measured leaf tobacco based on the distance obtained by the calculation means and a preset criterion. and a determination means for determining the difference between the types of leaf tobacco. A color detection type leaf tobacco type device, characterized in that the type of leaf tobacco is determined by position.