An automatic tobacco leaf baking analysis and control system

Abstract

The present invention discloses an automatic tobacco leaf baking analysis and control system, which includes: an analysis module for analyzing the variety of the tobacco leaves to be baked and selecting a baking type according to the variety; an identification module for identifying the baking stage of the tobacco leaves to be baked; a judgment module for judging the baking mode of the tobacco leaves to be baked based on the baking stage and the baking type; and a baking module for baking the tobacco leaves to be baked according to the baking mode. By adopting the present invention, it is possible to perform differential baking on tobacco leaves of different varieties. The tobacco leaves at a certain baking stage do not need to repeat the previous baking process, saving time and energy, and the quality of the tobacco leaves is also better.

Description

Technical Field

[0001] The present invention relates to the field of tobacco leaf baking, and in particular to an automatic tobacco leaf baking analysis and control system. Background Art

[0002] Tobacco leaf baking is one of the important processes in modern cigarette processing. It is known that different tobacco leaf varieties have different baking processes. The existing baking methods cannot achieve differential baking for different varieties of tobacco leaves. It can be seen that adopting different temperature and humidity combinations for baking different varieties of tobacco leaves is beneficial to obtaining higher-quality tobacco leaves. In addition, it often happens that tobacco leaves baked to a certain stage are placed for a period of time and then re-baked. At this time, the existing technology usually re-bakes the tobacco leaves baked to a certain stage from the beginning, and at this time, the phenomenon of tobacco leaf damage is likely to occur. Therefore, the present invention provides an automatic tobacco leaf baking analysis and control system to solve the above problems. Summary of the Invention

[0003] In order to solve the above problems, the object of the present invention is to provide an automatic tobacco leaf baking analysis and control system, which can achieve differential baking for different varieties of tobacco leaves. The tobacco leaves baked to a certain stage do not need to repeat the previous baking process, saving time and energy, and the quality of the tobacco leaves is also better.

[0004] Based on this, the present invention provides an automatic tobacco leaf baking analysis and control system, and the system includes:

[0005] An analysis module, which is used to analyze the variety of the tobacco leaves to be baked and select a baking type according to the variety;

[0006] An identification module, which is used to identify the baking stage of the tobacco leaves to be baked;

[0007] A judgment module, which is used to judge the baking mode of the tobacco leaves to be baked according to the baking stage and the baking type;

[0008] A baking module, which is used to bake the tobacco leaves to be baked according to the baking mode.

[0009] Wherein, the analysis of the variety of the tobacco leaves to be baked includes:

[0010] Obtain a target feature map of a number of target detection points including the tobacco leaves to be baked;

[0011] Compare the target feature map with the standard point maps of the preset number of tobacco leaf varieties one by one to obtain a comparison result;

[0012] When the comparison result is successful, the tobacco leaf variety to which the standard point map belongs is the tobacco leaf variety to which the tobacco leaves to be baked belong.

[0013] Among them, obtaining the target feature map of a number of detection points including the tobacco leaves to be baked includes:

[0014] Randomly select a preset first quantity of tobacco leaves to be baked, and obtain the feature maps of the first quantity;

[0015] The process of obtaining the feature maps includes:

[0016] Extract the contour of the tobacco leaves to be baked to obtain the contour of the tobacco leaves to be baked;

[0017] Extract the contour corner points of each of the tobacco leaf contours to obtain a preset quantity of contour corner points, and select a preset second quantity of contour points between adjacent contour corner points to obtain the feature map of the tobacco leaves to be baked including feature points, where the feature points include: contour corner points and contour points;

[0018] Place the feature maps of the first quantity on the same plane, and divide the plane into a preset third quantity of regions;

[0019] Obtain the edge feature points in each region, and obtain the first centroid of the figure enclosed by each edge feature point as the target detection point, so as to obtain the target feature map including the third quantity of target detection points.

[0020] Among them, comparing the target feature map with the standard point maps of the preset number of tobacco leaf varieties, and obtaining the comparison result includes:

[0021] Place the target feature map and the standard point map on the same plane;

[0022] Compare the target feature map with the standard point map to obtain the comparison result, and the number of comparison times between the target feature map and the standard point map is the number of tobacco leaf varieties;

[0023] When the comparison result is successful, the variety of the tobacco leaves to be baked is the tobacco leaf variety to which the target standard point map belongs

[0024] Among them, placing the target feature map and the standard point map on the same plane includes:

[0025] Obtain the second centroid of the figure enclosed by the detection points in the target feature map as the positioning point;

[0026] Locate the standard point map according to the positioning point, and the third centroid of the standard point map coincides with the positioning point, and the third centroid is determined by the centroid of the figure enclosed by the standard points.

[0027] Among them, comparing the target feature map with the standard point map to obtain the comparison result includes:

[0028] The comparison process between the target feature map and the standard point map includes:

[0029] Sequentially number the detection points in the target feature map. The standard points in the standard point map have been sequentially numbered in advance. The number of detection points is the same as that of the standard points and the numbers correspond one by one;

[0030] Obtain the absolute values of the distances between the third quantity of the detection points and the corresponding standard points, and calculate the sum of the absolute values;

[0031] Compare the target feature map and the standard point map one by one to obtain the sum of the absolute values for the preset number of tobacco leaf varieties;

[0032] Judge whether the sum of the absolute values exceeds a preset threshold;

[0033] If it exceeds, the comparison result is unsuccessful;

[0034] If it does not exceed, the comparison result is successful, and obtain the standard point map corresponding to the minimum sum of the absolute values as the target standard point map.

[0035] Among them, the selection of the baking type according to the variety includes:

[0036] The variety and the baking type are in a one-to-one correspondence relationship. The baking type is determined in advance. The baking type includes: the baking processes at each baking stage when baking tobacco leaves;

[0037] Select the corresponding baking type according to the variety.

[0038] Among them, identifying the baking stage of the tobacco leaves to be baked includes:

[0039] Collect an image sample of the tobacco leaves to be baked obtained by random sampling;

[0040] Input the image sample into the baking stage recognition model, and the baking stage recognition model identifies the baking stage of the tobacco leaves to be baked.

[0041] Among them, determining the baking mode of the tobacco leaves to be baked based on the baking stage and the baking type includes:

[0042] The baking type includes: the baking processes at each baking stage when baking tobacco leaves, and there is a sequence among each of the required baking stages;

[0043] Obtain the baking process of the subsequent required baking stage after the baking stage;

[0044] The baking mode includes: the baking process of the required baking stage.

[0045] Among them, baking the to-be-baked tobacco leaves according to the baking mode includes:

[0046] The baking mode includes: the baking process in the to-be-baked stage;

[0047] Bake the to-be-baked tobacco leaves according to the baking process in the to-be-baked stage.

[0048] In the present invention, the analysis module is used to analyze the variety of the to-be-baked tobacco leaves, and select the baking type according to the variety. The analysis process of the analysis module for the to-be-baked tobacco leaves is a major innovation point of the present invention. It creatively adopts the method of comparing the target feature map of the to-be-baked tobacco leaves with the standard point maps of the preset number of tobacco leaf varieties one by one to obtain the comparison result, so as to analyze the variety of the to-be-baked tobacco leaves, and determine the baking type based on the variety. The baking type here is not unique, each variety corresponds to one baking type, and one baking type can correspond to multiple varieties. Differentiated baking of tobacco leaves of different varieties can improve the quality of tobacco leaves. The identification module is used to identify the baking stage of the to-be-baked tobacco leaves. The judgment module is used to judge the baking mode of the to-be-baked tobacco leaves according to the baking stage and the baking type. The setting of the judgment module is to enable the tobacco leaves baked to a certain stage not to repeat the previous baking process, saving time and energy. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a schematic diagram of the automatic baking analysis control system for tobacco leaves provided by the embodiment of the present invention;

[0051] Figure 2 It is a flowchart of analyzing the variety of the to-be-baked tobacco leaves provided by the embodiment of the present invention. Detailed Embodiments

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0053] Figure 1It is a schematic diagram of the automatic tobacco leaf baking analysis and control system provided by an embodiment of the present invention. The system includes:

[0054] An analysis module 101, which is used to analyze the variety of the tobacco leaves to be baked and select a baking type according to the variety.

[0055] Figure 2 It is a flow chart for analyzing the variety of the tobacco leaves to be baked provided by an embodiment of the present invention. Analyzing the variety of the tobacco leaves to be baked includes:

[0056] S201. Obtain a target feature map including a number of target detection points of the tobacco leaves to be baked.

[0057] Among them, obtaining the target feature map including a number of detection points of the tobacco leaves to be baked includes:

[0058] Randomly select a preset first number of tobacco leaves to be baked and obtain the feature maps of the first number; the first number can be set independently.

[0059] The process of obtaining the feature maps includes:

[0060] Extract the contour of the tobacco leaves to be baked to obtain the contour of the tobacco leaves to be baked; the method of contour extraction is the prior art.

[0061] Extract the contour corner points of each contour of the tobacco leaves to be baked, obtain a preset number of contour corner points, and select a preset second number of contour points between adjacent contour corner points to obtain the feature map of the tobacco leaves to be baked including feature points, where the feature points include: contour corner points and contour points.

[0062] Selecting a preset second number of contour points between adjacent contour corner points, the selection of contour points can be determined by the following method:

[0063] Connect adjacent contour corner points with a straight line and obtain the distance of the straight line.

[0064] Divide the distance into several parts according to a preset length, and the division points are used as logical points.

[0065] If the distance is less than the preset length, there are no logical points.

[0066] Place the feature maps of the first number on the same plane and divide the plane into a preset third number of regions.

[0067] Obtain the edge feature points in each region, and obtain the first centroid of the figure enclosed by each edge feature point as the target detection point to obtain the target feature map including the third number of target detection points.

[0068] S202. Compare the target feature map with the standard dot maps of the preset number of tobacco leaf varieties one by one to obtain the comparison result;

[0069] Among them, comparing the target feature map with the standard dot maps of the preset number of tobacco leaf varieties one by one to obtain the comparison result includes:

[0070] Place the target feature map and the standard dot map on the same plane;

[0071] Compare the target feature map with the standard dot map to obtain the comparison result, and the number of comparisons between the target feature map and the standard dot map is the number of tobacco leaf varieties;

[0072] When the comparison result is successful, the variety of the tobacco leaves to be baked is the tobacco leaf variety to which the target standard dot map belongs

[0073] Among them, placing the target feature map and the standard dot map on the same plane includes:

[0074] Obtain the second centroid of the figure enclosed by the detection points in the target feature map as the positioning point;

[0075] Locate the standard dot map according to the positioning point, and the third centroid of the standard dot map coincides with the positioning point, and the third centroid is determined by the centroid of the figure enclosed by the standard dots.

[0076] Among them, comparing the target feature map with the standard dot map to obtain the comparison result includes:

[0077] The comparison process between the target feature map and the standard dot map includes:

[0078] Number the detection points in the target feature map in sequence. The standard points in the standard dot map have been numbered in sequence in advance. The number of detection points is the same as that of the standard points and the numbers correspond one by one;

[0079] Obtain the absolute value of the distance between the third number of the detection points and the corresponding standard points, and calculate the sum of the absolute values;

[0080] Compare the target feature map with the standard dot map one by one to obtain the sum of the absolute values of the preset number of tobacco leaf varieties;

[0081] Judge whether the sum of the absolute values exceeds the preset threshold;

[0082] If it exceeds, the comparison result is unsuccessful;

[0083] If it does not exceed, the comparison result is successful, and obtain the standard dot map corresponding to the minimum sum of the absolute values as the target standard dot map.

[0084] S203. When the comparison result is successful, the tobacco leaf variety to which the standard dot map belongs is the tobacco leaf variety to which the tobacco leaves to be baked belong.

[0085] Among them, the selection of the baking type according to the variety includes:

[0086] The variety and the baking type are in a one-to-one correspondence relationship, and the baking type is determined in advance. The baking type includes: the baking process of each baking stage when baking tobacco leaves.

[0087] Select the corresponding baking type according to the variety.

[0088] Among them, the determination of the baking mode of the tobacco leaves to be baked based on the baking stage and the baking type includes:

[0089] The baking type includes: the baking process of each baking stage when baking tobacco leaves, and there is a sequence among the baking stages.

[0090] Obtain the baking process of the baking stage after the current baking stage.

[0091] The baking mode includes: the baking process of the baking stage.

[0092] It should be particularly noted that the baking processes of different varieties of tobacco leaves are preset and are prior art.

[0093] The recognition module 102, and the recognition and judgment module is used to recognize the baking stage of the tobacco leaves to be baked.

[0094] Among them, the recognition of the baking stage of the tobacco leaves to be baked includes:

[0095] Collect image samples of the tobacco leaves to be baked obtained by random sampling.

[0096] Input the image samples into the baking stage recognition model, and the baking stage recognition model recognizes the baking stage of the tobacco leaves to be baked.

[0097] The recognition module 102 is prior art. The baking stage can be divided into unbaked, early yellowing stage, mid-yellowing stage, late yellowing stage, early color-fixing stage, mid-color-fixing stage, late color-fixing stage, early stem-drying stage, mid-stem-drying stage, and late stem-drying stage.

[0098] The judgment module 103, and the judgment module is used to judge the baking mode of the tobacco leaves to be baked according to the baking stage and the baking type.

[0099] For example, if the baking stage of the tobacco leaves to be baked is the early color-fixing stage, then the baking mode of the tobacco leaves to be baked is the mid-color-fixing stage, late color-fixing stage, early stem-drying stage, mid-stem-drying stage, and late stem-drying stage of this variety.

[0100] A baking module 104, which is used to bake the tobacco leaves to be baked according to the baking mode.

[0101] Wherein, baking the tobacco leaves to be baked according to the baking mode includes:

[0102] The baking mode includes: the baking process in the baking stage to be carried out;

[0103] Bake the tobacco leaves to be baked according to the baking process in the baking stage to be carried out.

[0104] In the present invention, the analysis module is used to analyze the variety of the tobacco leaves to be baked and select the baking type according to the variety. The analysis process of the analysis module for the tobacco leaves to be baked is a major innovation point of the present invention. It creatively adopts the method of comparing the target feature map of the tobacco leaves to be baked with the standard dot maps of the preset number of tobacco leaf varieties one by one to obtain the comparison result, so as to analyze the variety of the tobacco leaves to be baked, and determine the baking type based on the variety. The baking type here is not unique, each variety corresponds to a baking type, and one baking type can correspond to multiple varieties. Differentiated baking of tobacco leaves of different varieties can improve the quality of tobacco leaves. The identification module is used to identify the baking stage of the tobacco leaves to be baked. The judgment module is used to judge the baking mode of the tobacco leaves to be baked according to the baking stage and the baking type. The setting of the judgment module is to avoid the necessity of repeating the previous baking process for the tobacco leaves baked to a certain stage, saving time and energy.

[0105] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and substitutions can be made, and these improvements and substitutions should also be regarded as the protection scope of the present invention.

Claims

1. An automatic tobacco leaf baking analysis and control system, characterized in that, Including: An analysis module, which is used to analyze the variety of the tobacco leaves to be baked and select a baking type according to the variety; An identification module, which is used to identify the baking stage of the tobacco leaves to be baked; A judgment module, which is used to judge the baking mode of the tobacco leaves to be baked according to the baking stage and the baking type; A baking module, which is used to bake the tobacco leaves to be baked according to the baking mode; In the analysis module, the analysis of the variety of the tobacco leaves to be baked includes: obtaining a target feature map including a plurality of detection points of the tobacco leaves to be baked; comparing the target feature map with standard point maps of a preset number of tobacco leaf varieties one by one to obtain a comparison result; when the comparison result is successful, the tobacco leaf variety to which the standard point map belongs is the tobacco leaf variety to which the tobacco leaves to be baked belong; The obtaining of the target feature map including a plurality of detection points of the tobacco leaves to be baked includes: randomly extracting a preset first number of the tobacco leaves to be baked and obtaining feature maps of the first number; the process of obtaining the feature maps includes: extracting the contour of the tobacco leaves to be baked to obtain the contour of the tobacco leaves to be baked; extracting contour corner points from each contour of the tobacco leaves to be baked to obtain a preset number of contour corner points, and selecting a preset second number of contour points between adjacent contour corner points to obtain a feature map of the tobacco leaves to be baked including feature points, where the feature points include: contour corner points and contour points; placing the feature maps of the first number in the same plane and dividing the plane into a preset third number of regions; obtaining edge feature points in each region and obtaining the first centroid of the figure enclosed by the edge feature points as a detection point to obtain a target feature map including a third number of detection points; Comparing the target feature map with standard point maps of a preset number of tobacco leaf varieties one by one to obtain a comparison result includes: placing the target feature map and the standard point maps in the same plane; comparing the target feature map with the standard point maps to obtain a comparison result, and the number of comparisons between the target feature map and the standard point maps is the number of tobacco leaf varieties; when the comparison result is successful, the variety of the tobacco leaves to be baked is the tobacco leaf variety to which the target standard point map belongs; Comparing the target feature map with the standard point maps to obtain a comparison result includes: the comparison process between the target feature map and the standard point maps includes: sequentially numbering the detection points in the target feature map, and the standard points in the standard point maps have been sequentially numbered in advance, and the number of the detection points is the same as that of the standard points and the numbers correspond one by one; obtaining the absolute values of the distances between the third number of the detection points and the corresponding standard points and calculating the sum of the absolute values; comparing the target feature map with the standard point maps one by one to obtain the sum of the absolute values of the preset number of tobacco leaf varieties; judging whether the sum of the absolute values exceeds a preset threshold; if it exceeds, the comparison result is unsuccessful; if it does not exceed, the comparison result is successful, and obtaining the standard point map corresponding to the minimum sum of the absolute values as the tobacco leaf variety to which the tobacco leaves to be baked belong.

2. The automatic tobacco leaf baking analysis control system according to claim 1, characterized in that, Placing the target feature map and the standard point map on the same plane includes: obtaining the second centroid of the figure enclosed by the detection points in the target feature map as the positioning point; positioning the standard point map according to the positioning point, where the third centroid of the standard point map coincides with the positioning point, and the third centroid is determined by the centroid of the figure enclosed by the standard points.

3. The automatic tobacco leaf baking analysis and control system according to claim 1, characterized in that Selecting the baking type according to the variety includes: there is a one-to-one correspondence between the variety and the baking type, the baking type is determined in advance, and the baking type includes: the baking processes for each baking stage during tobacco leaf baking; selecting the corresponding baking type according to the variety.

4. The automatic tobacco leaf baking analysis and control system according to claim 1, wherein Identifying the baking stage of the tobacco leaves to be baked includes: collecting an image sample of the tobacco leaves to be baked obtained by random sampling; inputting the image sample into a baking stage identification model, and the baking stage identification model identifies the baking stage of the tobacco leaves to be baked.

5. The automatic tobacco leaf baking analysis and control system according to claim 1, characterized in that, Judging the baking mode of the tobacco leaves to be baked according to the baking stage and the baking type includes: the baking type includes: the baking processes for each baking stage during tobacco leaf baking, and there is a sequence among the baking stages; obtaining the baking process of the subsequent baking stage after the baking stage; the baking mode includes: the baking process of the baking stage.

6. The automatic tobacco leaf baking analysis and control system according to claim 1, characterized in that, Baking the tobacco leaves to be baked according to the baking mode includes: the baking mode includes: the baking process of the baking stage; baking the tobacco leaves to be baked according to the baking process of the baking stage.

Images