CN117058670B - Electronic tobacco tar flexibility evaluation method - Google Patents
Electronic tobacco tar flexibility evaluation method Download PDFInfo
- Publication number
- CN117058670B CN117058670B CN202311314865.0A CN202311314865A CN117058670B CN 117058670 B CN117058670 B CN 117058670B CN 202311314865 A CN202311314865 A CN 202311314865A CN 117058670 B CN117058670 B CN 117058670B
- Authority
- CN
- China
- Prior art keywords
- smoke
- cluster
- clusters
- pixel points
- flexibility
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 34
- 241000208125 Nicotiana Species 0.000 title claims abstract description 18
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 18
- 239000000779 smoke Substances 0.000 claims abstract description 224
- 239000003571 electronic cigarette Substances 0.000 claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 15
- 238000009792 diffusion process Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 239000000306 component Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- SNICXCGAKADSCV-JTQLQIEISA-N (-)-Nicotine Chemical compound CN1CCC[C@H]1C1=CC=CN=C1 SNICXCGAKADSCV-JTQLQIEISA-N 0.000 description 1
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 208000021063 Respiratory fume inhalation disease Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 229960002715 nicotine Drugs 0.000 description 1
- SNICXCGAKADSCV-UHFFFAOYSA-N nicotine Natural products CN1CCCC1C1=CC=CN=C1 SNICXCGAKADSCV-UHFFFAOYSA-N 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an electronic cigarette oil flexibility evaluation method, which comprises the following steps: obtaining a plurality of clusters according to the gray distribution histogram corresponding to the smoke image of any frame, obtaining smoke characteristics of the smoke image according to gray values and numbers of pixel points in the clusters, obtaining similarity among the clusters according to gray values among the clusters and differences among the pixel points in the smoke image of continuous frames, obtaining flexibility evaluation indexes corresponding to the electronic tobacco tar of the smoke image of continuous frames according to the smoke characteristics of the smoke image of continuous frames and the similarity among the clusters, and completing the flexibility evaluation of the electronic tobacco tar. According to the invention, the flexibility of the electronic cigarette oil is evaluated by a machine vision method, the diffusion change along with the smoke is obtained according to the change of the cluster in the smoke image of different frames, the difference caused by manual evaluation can be overcome, and the evaluation result is more objective and comprehensive and has more reference value.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an electronic cigarette oil flexibility evaluation method.
Background
The electronic cigarette generates vapor by heating the electronic cigarette oil, and a user obtains enjoyment of nicotine or other taste substances by inhaling the vapor.
The electronic tobacco tar is a core component of the electronic tobacco, the quality and the characteristics of the electronic tobacco tar are vital to the user experience, compared with the burning tobacco, the smoke of the electronic tobacco is generally more flexible, however, different tobacco tar flexibility is different, some tobacco tar inlets are dry and firewood, and some tobacco tar inlets are flexible and mellow, clean and long, and very fine, and the effect is related to the blending technology of the tobacco tar, and the softener is added into the electronic tobacco tar generally when the electronic tobacco tar is produced, so that the taste of the electronic tobacco tar is changed.
In order to evaluate the flexibility of the electronic cigarette oil, the flexibility of the electronic cigarette oil is usually evaluated manually in the existing method, but subjective differences exist, so that the evaluation result is inaccurate and objective.
Disclosure of Invention
The invention provides an electronic cigarette oil softness evaluation method for solving the existing problems.
The invention relates to an electronic cigarette oil flexibility evaluation method which adopts the following technical scheme:
the invention provides a method for evaluating flexibility of electronic cigarette oil, which comprises the following steps:
acquiring continuous frame smoke images corresponding to the electronic tobacco tar;
obtaining the reference degree of the maximum value according to the horizontal coordinate difference of the maximum value and the number of pixel points in the smoke image in the gray level distribution histogram of the smoke image of any frame; according to the reference degree, obtaining pixel points corresponding to partial maxima in the gray distribution histogram in the smoke image, marking the pixel points as reference pixel points, clustering all the reference pixel points of the smoke image of any frame to obtain a plurality of clusters, obtaining smoke factors according to gray value differences of the pixel points in the clusters, and adjusting the smoke factors by utilizing the gray value differences of the whole clusters to obtain smoke characteristics of the smoke image;
in the smoke image of any adjacent frame, according to the gray value difference of the whole cluster and the quantity difference of pixel points contained in the cluster, the similarity between any two clusters in the smoke image of the adjacent frame is obtained, and according to the size of the similarity, the matching cluster corresponding to any cluster is obtained;
the method comprises the steps of obtaining tangential slopes of edge pixel points of an area formed by any cluster in any smoke image, adjusting differences of tangential slopes of all edge pixel points in the cluster and the corresponding matched cluster by utilizing similarity between the any cluster and the corresponding matched cluster to obtain a flexibility factor, and adjusting the flexibility factor by utilizing differences between smoke features of smoke images of adjacent frames to obtain a flexibility evaluation index of the electronic cigarette oil.
Further, the obtaining the reference degree of the maximum value according to the horizontal coordinate difference of the maximum value and the number of the pixel points in the smoke image in the gray level distribution histogram of the smoke image of any frame comprises the following specific steps:
firstly, acquiring the abscissa of all maximum values in a gray level distribution histogram of a smoke image of any frame; acquiring the number of corresponding pixel points of any maximum value in the gray distribution histogram in the smoke image;
then, any maximum value is marked as a target maximum value, and the difference value between the right side of the target maximum value and the adjacent maximum value and the target maximum value in the gray distribution histogram is marked as a first numerical value; the ratio of the number of the corresponding pixel points of the target maximum value in the smoke image to the number of the pixel points in the smoke image is recorded as a second numerical value;
and finally, obtaining the product result of the first numerical value and the second numerical value, normalizing all the product results by utilizing linear normalization, and marking the normalized result as the reference degree of the maximum value.
Further, according to the reference degree, the pixel point corresponding to the partial maximum value in the gray distribution histogram in the smoke image is obtained and recorded as the reference pixel point, and the specific steps are as follows:
and acquiring a maximum value of which the reference degree is larger than a preset reference degree threshold value, marking the maximum value as a reference maximum value, and marking a pixel point corresponding to the reference maximum value in the smoke image as a reference pixel point.
Further, the step of clustering all the reference pixel points of the smoke image of any frame to obtain a plurality of clusters, and obtaining the smoke factor according to the gray value difference of the pixel points in the clusters comprises the following specific steps:
wherein,indicate->The>Gray values of the individual pixels; />Indicate->The>Neighborhood gray level total difference of each pixel point; />Indicate->The number of pixels in each cluster, +.>Representing the number of clusters in the smoke image, +.>Indicate->The gray value of the pixel point with the largest gray value in each cluster; />An exponential function based on a natural constant; />A logarithmic function with a base of 10 is shown.
Further, the specific method for obtaining the neighborhood gray level total difference is as follows:
and recording the absolute value of the difference value of the gray values between any pixel point and the pixel points in the four adjacent domains in any cluster as the neighborhood gray level difference of the corresponding pixel point, wherein the any pixel point shares a plurality of neighborhood gray level differences, and recording the sum value of all the neighborhood gray level differences of the any pixel point as the neighborhood gray level total difference of the pixel point.
Further, the method for adjusting the smoke factor by using the gray value difference of the whole cluster to obtain the smoke characteristic of the smoke image comprises the following specific steps:
firstly, obtaining average gray values of all pixel points in each cluster, marking the average gray values as cluster gray values, and obtaining the maximum cluster gray value and the minimum cluster gray value in a smoke image;
and then, marking the product result of the difference value of the maximum cluster gray value and the minimum cluster gray value and the smoke factor as the smoke characteristic of the smoke image.
Further, in the smoke image of any adjacent frame, according to the gray value difference of the whole cluster and the number difference of pixel points contained in the cluster, the similarity between any two clusters in the smoke image of the adjacent frame is obtained, and according to the size of the similarity, the matching cluster corresponding to any cluster is obtained, which comprises the following specific steps:
firstly, the specific calculation method of the similarity between the clusters is as follows:
wherein,indicate->First->Cluster and->First->Similarity of the individual clusters; />Indicate->First->Cluster gray values of individual clusters, +.>Indicate->First->Cluster gray values of the individual clusters; />Indicate->First->The clusters contain the number of pixels, < >>Indicate->First->The cluster clusters contain the number of pixels; />An exponential function based on a natural constant;
then, in the smoke image of the adjacent frame, the firstFirst->Cluster and->The cluster corresponding to the maximum similarity in the frame smoke image is marked as +.>First->Matching clusters corresponding to the clusters.
Further, the method for obtaining the tangential slope of the edge pixel points of the area formed by any cluster in any smoke image, and adjusting the difference of the tangential slope of all the edge pixel points in the cluster and the corresponding matched cluster by using the similarity between any cluster and the corresponding matched cluster to obtain the flexibility factor comprises the following specific steps:
firstly, acquiring edge pixel points of an area corresponding to any cluster in a smoke image by using a Canny operator, and acquiring tangential slope of the edge pixel points;
then, the specific calculation method of the flexibility factor is as follows:
wherein,first->First->A flexibility factor between each cluster and the corresponding matched cluster; />Indicate->First->Similarity between each cluster and the corresponding matched cluster; />Indicate->Cluster formation region->Tangential slope of each edge pixel point, +.>Indicate->The first clustering cluster corresponds to the matching clustering cluster forming area>Tangential slope of each edge pixel point, +.>Representation->The number of edge pixels of the cluster forming area, +.>Indicate->Corresponding matches of clusterThe number of edge pixel points of the clustering cluster forming area is matched; />An exponential function based on a natural constant is represented.
Further, the method for adjusting the flexibility factor by utilizing the difference between smoke characteristics of smoke images of adjacent frames to obtain a flexibility evaluation index of the electronic cigarette oil comprises the following specific steps:
taking the difference between smoke characteristics of smoke images of adjacent frames as input of an exponential decay function, and recording an output result as a first characteristic;
the average value of the flexibility factors between all the clusters in any smoke image and the corresponding matched clusters is recorded as a second characteristic;
and recording the product result of the first characteristic and the second characteristic as characteristic parameters of the corresponding smoke images, and taking the average value of the characteristic parameters of all the smoke images in the smoke images of the continuous frames as a flexibility evaluation index of the corresponding electronic cigarette oil of the smoke images of the continuous frames.
Further, the specific method for obtaining the first feature is as follows:
acquiring the smoke characteristics of any frame of smoke image and the smoke characteristics of the next frame of smoke image, respectively recording asAndrespectively represent->Frame and->Smoke features of the frame smoke image; will->And->And inputting the ratio of the first characteristic to the exponential decay function to obtain the first characteristic.
The technical scheme of the invention has the beneficial effects that: the flexibility of the electronic cigarette oil is evaluated by a machine vision method, the individual difference caused by manual evaluation can be overcome, and the evaluation result is more objective and comprehensive and has more reference value. When the flexibility of the electronic cigarette oil is evaluated, an experiment device is arranged to obtain a smoke image of the electronic cigarette, and then smoke evaluation indexes of the electronic cigarette added with different softeners are obtained according to the change of smoke in the image, so that comparison is formed, and objective evaluation is performed.
When the evaluation index is obtained, the characteristic clustering is carried out according to the distribution of the smoke, then the variation along with the diffusion of the smoke is obtained according to the variation of the clustering clusters in the smoke images of different frames, and the flexibility degree of the electronic cigarette oil added with the softener with different concentrations can be obtained.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for evaluating flexibility of electronic cigarette oil according to the invention;
FIG. 2 is a schematic diagram of an experimental platform;
FIG. 3 is a smoke image;
fig. 4 is a schematic diagram of a constructed histogram.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of the method for evaluating the flexibility of the electronic cigarette oil according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for evaluating the flexibility of the electronic cigarette oil provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a method for evaluating flexibility of electronic cigarette oil according to an embodiment of the present invention is shown, where the method includes the following steps:
step S001, acquiring successive frame smoke images by using the high-speed camera.
When the flexibility of the electronic cigarette is evaluated by a machine vision method, firstly, smoke generated by electronic cigarette oil added with different softeners is required to be collected, and the smoke can be generated after the electronic cigarette is inhaled generally, so that the invention collects a smoke image of the electronic cigarette by arranging an experimental device as shown in fig. 2, wherein A represents an experimental platform, B represents a high-speed camera, C represents a smoke inhalation device, D represents an electronic cigarette nozzle, and fig. 3 is a smoke image;
in addition, in order to embody the morphological change of the smoke, when the smoke image is acquired, the smoke images of a plurality of continuous frames corresponding to the electronic cigarette oil with the same softener content need to be shot.
It should be noted that, when the continuous frame smoke image is acquired, the method should be performed in a windless environment, so as to avoid that the air flow interferes with the smoke diffusion to affect the experimental result.
So far, continuous frame smoke images corresponding to the electronic cigarette oil with any softener concentration are obtained.
Step S002, obtaining a plurality of clusters according to the corresponding gray distribution histogram of the smoke image of any frame, and obtaining the smoke characteristics of the smoke image according to the gray values and the numbers of the pixel points in the clusters.
In order to contrast, in this embodiment, when images are acquired, smoke images generated by electronic cigarette products to which different types and contents of softeners are added are acquired, and when images are acquired, continuous frame smoke images of each type of electronic cigarette oil are shot, and smoke feature evaluation values of the electronic cigarette oil to which different contents of softeners are added are obtained by analyzing the distribution of smoke in the image of the sheet Zhang Yanwu and the change of the smoke images of the continuous frames, so that evaluation indexes of the flexibility of the electronic cigarette oil are evaluated by comparing the smoke feature evaluation values of the different contents of softener electronic cigarette oil.
Therefore, firstly, a single frame of smoke image needs to be analyzed to obtain the distribution characteristics of the smoke, although the smoke is diffused with certain randomness, the smoke diffusion forms with different flexibilities are different, and the smoke of the electronic cigarette with higher flexibility is more continuous when being diffused, and is in continuous flocculence; when the smoke of the electronic cigarette with low flexibility is diffused, the smoke can be intermittent, and the diffusion of the smoke is more random and does not move in a certain direction.
Because the smoke with different concentrations in the smoke image can show different gray scales, the gray scale distribution characteristics of the smoke image are judged according to the distribution of the pixel points in the gray scale distribution histogram.
Step (1), acquiring a gray distribution histogram of a smoke image, wherein the acquired histogram is shown in fig. 4, performing curve fitting on the acquired histogram to obtain a corresponding curve, and acquiring maximum points on the curve, namely, obtaining a plurality of maximum values in the gray distribution histogram; the curve fitting and the maximum point obtaining methods are all the prior art, and are not repeated here. Obtaining the reference degree of the maximum value according to the maximum value, wherein the reference degree comprises the following specific steps: firstly, acquiring the abscissa of all maximum values in a gray level distribution histogram of a smoke image of any frame; acquiring the number of corresponding pixel points of any maximum value in the gray distribution histogram in the smoke image; then, any maximum value is marked as a target maximum value, and the difference between the next maximum value of the target maximum value and the target maximum value in the gray distribution histogram is marked as a first numerical value; the ratio of the number of the corresponding pixel points of the target maximum value in the smoke image to the number of the pixel points in the smoke image is recorded as a second numerical value;
and finally, obtaining the product result of the first numerical value and the second numerical value, normalizing all the product results by utilizing linear normalization, and marking the normalized result as the reference degree of the maximum value. It should be noted that: the next maximum of the target maximum is the next maximum adjacent to the target maximum, i.e. the maximum adjacent to the target maximum to the right.
The calculation formula of the reference degree is as follows:
wherein,indicate->Reference degree of the individual maxima, +.>Representing the +.>The number of corresponding pixels of the maximum value in the smoke image, < >>Representing the number of pixels in the smoke image, < >>Representing the +.>The abscissa of the individual maxima, +.>Representing the +.>The abscissa of the individual maxima,representing a linear normalization function.
In the smoke image, different smoke states are caused by the content of the softener, so that the regions are divided according to the distribution of the pixel points, when the number of the pixel points is more and the gray level distribution of the smoke image is more scattered, the pixel points corresponding to the maximum value with larger reference degree can divide the image into different regions, and the distribution number of the pixel points corresponding to the maximum value with larger reference degree in the smoke image is more, so that the corresponding regions can be reflected;
and acquiring a maximum value of which the reference degree is larger than a preset reference degree threshold value, marking the maximum value as a reference maximum value, and marking a pixel point corresponding to the reference maximum value as a reference pixel point.
It should be noted that the reference level threshold is preset to 0.63 according to experience, and may be adjusted according to actual situations, and the embodiment is not limited specifically.
Step (3), firstly, presetting a clustering radius and a minimum clustering number of a DBSCAN density clustering algorithm, and clustering all reference pixel points in a smoke image by combining the DBSCAN density clustering algorithm, wherein the preset gray scale range is as followsAnd then clustering the reference pixel points meeting the threshold range to obtain clusters in a plurality of gray scale ranges. And then analyzing each cluster to obtain the distribution characteristic value of the electronic cigarette smoke.
It should be noted that, the DBSCAN density clustering algorithm is an existing algorithm, and in this embodiment, too much description is omitted, the cluster radius and the cluster number of the DBSCAN density clustering algorithm are empirically preset values, the cluster radius is 2 according to the empirically preset values, the minimum cluster number is 4, and the method can be adjusted according to actual situations, and the embodiment is not specifically limited.
And analyzing the obtained cluster, and judging the distribution characteristics of the cluster. The density of the smoke in the air produced by different softeners may vary, and may be manifested as some may produce a fluffy cloud and some may produce a more uniform and smooth smoke shape.
Then, the average gray value of all pixel points in each cluster is obtained and marked as the cluster gray value, and the maximum cluster gray value and the minimum cluster gray value in the smoke image are obtained and respectively marked asAnd->The method comprises the steps of carrying out a first treatment on the surface of the The absolute value of the difference value of the gray values between any pixel point and the pixel points in the four adjacent domains in any cluster is recorded as the neighborhood gray level difference of the corresponding pixel point, the number of the neighborhood gray level differences is 4 in the total of any pixel point, the sum value of all the neighborhood gray level differences of any pixel point is recorded as the neighborhood gray level total difference of the pixel point>；
According to the distribution of different clusters, the characteristic value of the smoke generated by the electronic cigarette oil added with the softener with different concentrations is obtained and is recorded as the smoke characteristic, and the smoke characteristic of any smoke image is obtained, and the specific calculation method comprises the following steps:
wherein,smoke compliance characteristic value representing a smoke image, < +.>Represents the gray value of the largest cluster,representing the minimum cluster gray value, +.>Indicate->The>Gray values of the individual pixels; />Represent the firstThe>Neighborhood gray level total difference of each pixel point; />Indicate->The number of pixels in each cluster, +.>Representing the number of clusters in the smoke image, +.>Indicate->The gray value of the pixel point with the largest gray value in each cluster; />An exponential function based on a natural constant; />A logarithmic function with a base of 10 is shown.
Representing the size of the gray value distribution range of the smoke image because the greater the softness, the smoke densityThe greater the degree, the more likely it is that aggregation will occur, and the less the gray value of the more aggregated region, the greater the difference in gray distribution will be. The total difference of the neighborhood gray scale represents the gray scale distribution of the neighborhood pixel points, and the smoke with larger flexibility is more uniform and smooth, so the difference of the gray scale of the neighborhood pixel points is smaller, and the change degree is smaller.
The entropy value of a cluster in a smoke image is represented, the disorder degree of the gray level of pixel points in the same cluster is reflected, the larger the entropy value is, the disorder of smoke is indicated, the smaller the effect of a softener is, and the smaller the compliance of electronic cigarette oil is indicated;
smoke factorThe gray level discrete degree of the pixel points in the cluster and the difference between the adjacent pixel points in the smoke image are reflected, the gray level smoothness degree of smoke in the smoke image is reflected, and the larger the smoke factor is, the smoother the gray level change of the smoke is.
To this end, the smoke characteristics of any smoke image are obtained.
Step S003, obtaining the similarity between clusters according to the gray value and the difference of the pixel number among clusters in the smoke images of the continuous frames.
According to the smoke characteristics formed by the electronic cigarettes in the single-frame smoke image, and then analyzing the continuous frame images, because the smoke change is a continuous process, the smoke generated by the electronic cigarette oil with high flexibility contains more sticky components, and the components enable the smoke not to be dispersed in the air easily and rapidly. In contrast, smoke with low flexibility can be spread to a larger range in a shorter time because of less viscous components, so that the flexibility of the electronic cigarette oil is further obtained according to the change of different areas in continuous frame images.
Because the concentration of the smoke changes to cause the gray scale of different areas to change when the smoke drifts, the corresponding relation of different areas in adjacent frame images is utilized, and the dispersion degree of the smoke is obtained by combining the change of each area, so that a clustering cluster of each frame of smoke image is obtained by utilizing the method of the step S002;
according to the difference of the gray values of clusters in smoke images of adjacent frames and the difference of the number of the contained pixel points, the similarity of the clusters is obtained, and the concrete calculation method comprises the following steps:
wherein,indicate->First->Cluster and->First->Similarity of the individual clusters; />Indicate->First->Cluster gray values of individual clusters, +.>Indicate->First->Individual clusteringCluster gray values of clusters; />Indicate->First->The clusters contain the number of pixels, < >>Indicate->First->The cluster clusters contain the number of pixels; />An exponential function based on a natural constant is represented.
In the smoke image of the continuous frame, the smaller the gray level change of the cluster is, and the larger the similarity between two clusters with similar range sizes is.
So far, the similarity between clusters in the smoke images of the continuous frames is obtained.
Step S004, according to the smoke characteristics of the continuous frame smoke images and the similarity among the clusters, the flexibility evaluation index of the continuous frame smoke images corresponding to the electronic cigarette oil is obtained, and the electronic cigarette oil flexibility evaluation is completed.
First, in the smoke image of the adjacent frame, the firstFirst->Cluster and->The cluster corresponding to the maximum similarity in the frame smoke image is marked as +.>First->Matching cluster corresponding to the clusters, and the first->First->The similarity between the clusters and the corresponding matched clusters is noted +.>。
Then, utilizing a Canny operator to obtain edge pixel points of an area corresponding to any cluster in the smoke image, and obtaining tangential slope of any edge pixel points;
the flexibility evaluation index of the electronic cigarette oil is obtained according to the change of the same cluster, and the specific calculation method comprises the following steps:
wherein,indicating the flexibility evaluation index of the electronic cigarette oil, < ->Indicate->Smoke characteristics of the frame smoke image,indicate->Smoke characteristics of a frame smoke image, +.>Frame number representing smoke image of consecutive frames, +.>Indicate->Number of clusters of frame smoke images, +.>Indicate->First->Similarity between each cluster and the corresponding matched cluster; />Indicate->Cluster formation region->Tangential slope of each edge pixel point, +.>Indicate->The first clustering cluster corresponds to the matching clustering cluster forming area>Tangential slope of each edge pixel point, +.>Representation->The number of edge pixels of the cluster forming area, +.>Indicate->The number of edge pixel points of the cluster forming area is correspondingly matched with the cluster clusters; />Representing natural constant->An exponential function based on a natural constant is represented.
、/>The sum of the slopes of the edge pixel points is reflected in the shape change of the same cluster area in the smoke images of the continuous frames, and the smoke drifts are regular, so that the slower the shape change of the cluster is, the slower the smoke diffusion is, and the better the flexibility of the smoke is.
Softness factorThe degree of similarity between the clusters in the smoke images of the adjacent frames and the corresponding matched clusters in the aspects of edge morphology and gray level distribution is reflected, and the greater the flexibility factor is, the smaller the degree of diffusion between the matched clusters in the smoke images of the adjacent frames is reflected, the greater the corresponding flexibility is.
The two clusters with greater similarity account for the smaller changes in gray features and range features and therefore the smaller the degree of change in smoke images of adjacent frames.
The smaller the degree of variation in smoke characteristics in a single frame smoke image,i.e.The smaller the first feature->The greater the compliance, the greater;
flexibility evaluation indexThe larger the continuous frame smoke image is, the larger the flexibility of the electronic cigarette oil corresponding to the continuous frame smoke image is.
And using the flexibility evaluation index for evaluating the flexibility of the electronic cigarette oil, using the electronic cigarette oil with the flexibility evaluation index larger than a preset flexibility threshold as qualified electronic cigarette oil, and using the electronic cigarette oil with the flexibility evaluation index smaller than the preset flexibility threshold as unqualified electronic cigarette oil, so as to complete the flexibility evaluation of the electronic cigarette oil.
It should be noted that, the softness threshold value is preset to be 0.6 according to experience, and may be adjusted according to practical situations, and the embodiment is not limited specifically.
The following examples were usedThe model is used only to represent the negative correlation and the result of the constraint model output is at +.>In the section, other models with the same purpose can be replaced in the implementation, and the embodiment only uses +.>The model is described as an example, without specific limitation, wherein +.>Refers to the input of the model.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The method for evaluating the flexibility of the electronic cigarette oil is characterized by comprising the following steps of:
acquiring continuous frame smoke images corresponding to the electronic tobacco tar;
obtaining the reference degree of the maximum value according to the horizontal coordinate difference of the maximum value and the number of pixel points in the smoke image in the gray level distribution histogram of the smoke image of any frame; according to the reference degree, obtaining pixel points corresponding to partial maxima in the gray distribution histogram in the smoke image, marking the pixel points as reference pixel points, clustering all the reference pixel points of the smoke image of any frame to obtain a plurality of clusters, obtaining smoke factors according to gray value differences of the pixel points in the clusters, and adjusting the smoke factors by utilizing the gray value differences of the whole clusters to obtain smoke characteristics of the smoke image;
in the smoke image of any adjacent frame, according to the gray value difference of the whole cluster and the quantity difference of pixel points contained in the cluster, the similarity between any two clusters in the smoke image of the adjacent frame is obtained, and according to the size of the similarity, the matching cluster corresponding to any cluster is obtained;
obtaining tangential slope of edge pixel points of an area formed by any cluster in any smoke image, adjusting the difference of tangential slope of all edge pixel points in the cluster and the corresponding matched cluster by utilizing the similarity between any cluster and the corresponding matched cluster to obtain a flexibility factor, and adjusting the flexibility factor by utilizing the difference between smoke characteristics of smoke images of adjacent frames to obtain a flexibility evaluation index of electronic cigarette oil;
the method comprises the specific steps of obtaining the tangential slope of edge pixel points of an area formed by any cluster in any smoke image, adjusting the difference of the tangential slope of all edge pixel points in the cluster and the corresponding matched cluster by utilizing the similarity between the any cluster and the corresponding matched cluster, and obtaining a flexibility factor, wherein the specific steps are as follows:
firstly, acquiring edge pixel points of an area corresponding to any cluster in a smoke image by using a Canny operator, and acquiring tangential slope of the edge pixel points;
then, the specific calculation method of the flexibility factor is as follows:
wherein,first->First->A flexibility factor between each cluster and the corresponding matched cluster; />Indicate->First->Similarity between each cluster and the corresponding matched cluster; />Indicate->Cluster formation region->Tangential slope of each edge pixel point, +.>Indicate->The first clustering cluster corresponds to the matching clustering cluster forming area>Tangential slope of each edge pixel point, +.>Representation->The number of edge pixels of the cluster forming area, +.>Indicate->The number of edge pixel points of the cluster forming area is correspondingly matched with the cluster clusters; />An exponential function based on a natural constant is represented.
2. The method for evaluating the flexibility of the electronic cigarette oil according to claim 1, wherein the step of obtaining the reference degree of the maximum value according to the horizontal coordinate difference of the maximum value in the gray level distribution histogram of the smoke image of any frame and the number of the pixel points in the smoke image comprises the following specific steps:
firstly, acquiring the abscissa of all maximum values in a gray level distribution histogram of a smoke image of any frame; acquiring the number of corresponding pixel points of any maximum value in the gray distribution histogram in the smoke image;
then, marking any maximum value as a target maximum value, and marking a difference value between a right side of the target maximum value in the gray distribution histogram and an adjacent maximum value and the target maximum value as a first numerical value; the ratio of the number of the corresponding pixel points of the target maximum value in the smoke image to the number of the pixel points in the smoke image is recorded as a second numerical value;
and finally, obtaining the product result of the first numerical value and the second numerical value, normalizing all the product results by utilizing linear normalization, and marking the normalized result as the reference degree of the maximum value.
3. The method for evaluating the flexibility of the electronic cigarette oil according to claim 1, wherein the step of obtaining the pixel point corresponding to the partial maximum value in the gray distribution histogram in the smoke image according to the reference degree, and marking the pixel point as the reference pixel point comprises the following specific steps:
and acquiring a maximum value of which the reference degree is larger than a preset reference degree threshold value, marking the maximum value as a reference maximum value, and marking a pixel point corresponding to the reference maximum value in the smoke image as a reference pixel point.
4. The method for evaluating the flexibility of the electronic cigarette oil according to claim 1, wherein the step of adjusting the smoke factor by using the gray value difference of the cluster group to obtain the smoke characteristics of the smoke image comprises the following specific steps:
firstly, obtaining average gray values of all pixel points in each cluster, marking the average gray values as cluster gray values, and obtaining the maximum cluster gray value and the minimum cluster gray value in a smoke image;
and then, marking the product result of the difference value of the maximum cluster gray value and the minimum cluster gray value and the smoke factor as the smoke characteristic of the smoke image.
5. The method for evaluating the flexibility of the electronic cigarette oil according to claim 4, wherein in the smoke image of any adjacent frame, the similarity between any two clusters in the smoke image of the adjacent frame is obtained according to the gray value difference of the whole cluster and the number difference of the pixel points contained in the cluster, and the matching cluster corresponding to any cluster is obtained according to the size of the similarity, comprising the following specific steps:
firstly, the specific calculation method of the similarity between the clusters is as follows:
wherein,indicate->First->Cluster and->First->Similarity of the individual clusters; />Indicate->First->Cluster gray values of individual clusters, +.>Represent the firstFirst->Individual clusteringCluster gray values of clusters; />Indicate->First->The clusters contain the number of pixels, < >>Indicate->First->The cluster clusters contain the number of pixels;an exponential function based on a natural constant;
then, in the smoke image of the adjacent frame, the firstFirst->Cluster and->The cluster corresponding to the maximum similarity in the frame smoke image is marked as +.>First->Corresponding to the cluster groupAnd matching the cluster clusters.
6. The method for evaluating the flexibility of the electronic cigarette oil according to claim 1, wherein the step of adjusting the flexibility factor by utilizing the difference between the smoke characteristics of the smoke images of the adjacent frames to obtain the flexibility evaluation index of the electronic cigarette oil comprises the following specific steps:
taking the difference between smoke characteristics of smoke images of adjacent frames as input of an exponential decay function, and recording an output result as a first characteristic;
the average value of the flexibility factors between all the clusters in any smoke image and the corresponding matched clusters is recorded as a second characteristic;
and recording the product result of the first characteristic and the second characteristic as characteristic parameters of the corresponding smoke images, and taking the average value of the characteristic parameters of all the smoke images in the smoke images of the continuous frames as a flexibility evaluation index of the corresponding electronic cigarette oil of the smoke images of the continuous frames.
7. The method for evaluating flexibility of electronic cigarette oil according to claim 6, wherein the specific method for acquiring the first feature is as follows:
acquiring the smoke characteristics of any frame of smoke image and the smoke characteristics of the next frame of smoke image, respectively recording asAnd->Respectively represent->Frame and->Smoke features of the frame smoke image; will->And->And inputting the ratio of the first characteristic to the exponential decay function to obtain the first characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311314865.0A CN117058670B (en) | 2023-10-12 | 2023-10-12 | Electronic tobacco tar flexibility evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311314865.0A CN117058670B (en) | 2023-10-12 | 2023-10-12 | Electronic tobacco tar flexibility evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117058670A CN117058670A (en) | 2023-11-14 |
| CN117058670B true CN117058670B (en) | 2024-01-02 |
Family
ID=88663051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311314865.0A Active CN117058670B (en) | 2023-10-12 | 2023-10-12 | Electronic tobacco tar flexibility evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058670B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117453447B (en) * | 2023-12-21 | 2024-03-22 | 临沂大学 | Simulation test method for automobile electric drive system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108208915A (en) * | 2017-12-29 | 2018-06-29 | 深圳睿思奇科技开发有限公司 | A kind of preparation method of tobacco tar drop thorn softener and the tobacco tar drop thorn softener prepared with this method |
| CN208160034U (en) * | 2017-12-18 | 2018-11-30 | 深圳市傲斯唯博科技有限公司 | integrated electronic cigarette |
| CN110222644A (en) * | 2019-06-10 | 2019-09-10 | 哈尔滨理工大学 | Forest fire smoke detection method based on image segmentation |
| CN115115624A (en) * | 2022-08-25 | 2022-09-27 | 江苏濠玥电子科技有限公司 | Rolling damage detection method for anti-corrosion coating of cable bridge |
| CN115272820A (en) * | 2022-07-19 | 2022-11-01 | 深圳市莱达四维信息科技有限公司 | Flame smoke recognition model training method and device, application method and device of flame smoke recognition model training method and device, and storage medium |
| CN115330800A (en) * | 2022-10-14 | 2022-11-11 | 深圳市亿康医疗技术有限公司 | Automatic segmentation method for radiotherapy target area based on image processing |
| CN115345845A (en) * | 2022-08-10 | 2022-11-15 | 重庆大学 | Feature fusion smoke screen interference efficiency evaluation and processing method based on direction gradient histogram and electronic equipment |
| CN115690025A (en) * | 2022-10-24 | 2023-02-03 | 深圳市大道四九科技有限公司 | Electronic cigarette defect identification method |
| CN116259005A (en) * | 2023-02-04 | 2023-06-13 | 国网浙江省电力有限公司嘉兴供电公司 | Intelligent monitoring system based on roof photovoltaic fire control |
| CN116310360A (en) * | 2023-05-18 | 2023-06-23 | 实德电气集团有限公司 | Reactor surface defect detection method |
| CN116596936A (en) * | 2023-07-18 | 2023-08-15 | 深圳市魔方卫星科技有限公司 | Solar wing sailboard quality detection method based on image data |
| CN117058161A (en) * | 2023-10-12 | 2023-11-14 | 深圳市五轮科技股份有限公司 | Electronic cigarette atomized smoke image segmentation method based on image processing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009143651A1 (en) * | 2008-05-29 | 2009-12-03 | Carestream Health, Inc. | Fast image segmentation using region merging with a k-nearest neighbor graph |
-
2023
- 2023-10-12 CN CN202311314865.0A patent/CN117058670B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN208160034U (en) * | 2017-12-18 | 2018-11-30 | 深圳市傲斯唯博科技有限公司 | integrated electronic cigarette |
| CN108208915A (en) * | 2017-12-29 | 2018-06-29 | 深圳睿思奇科技开发有限公司 | A kind of preparation method of tobacco tar drop thorn softener and the tobacco tar drop thorn softener prepared with this method |
| CN110222644A (en) * | 2019-06-10 | 2019-09-10 | 哈尔滨理工大学 | Forest fire smoke detection method based on image segmentation |
| CN115272820A (en) * | 2022-07-19 | 2022-11-01 | 深圳市莱达四维信息科技有限公司 | Flame smoke recognition model training method and device, application method and device of flame smoke recognition model training method and device, and storage medium |
| CN115345845A (en) * | 2022-08-10 | 2022-11-15 | 重庆大学 | Feature fusion smoke screen interference efficiency evaluation and processing method based on direction gradient histogram and electronic equipment |
| CN115115624A (en) * | 2022-08-25 | 2022-09-27 | 江苏濠玥电子科技有限公司 | Rolling damage detection method for anti-corrosion coating of cable bridge |
| CN115330800A (en) * | 2022-10-14 | 2022-11-11 | 深圳市亿康医疗技术有限公司 | Automatic segmentation method for radiotherapy target area based on image processing |
| CN115690025A (en) * | 2022-10-24 | 2023-02-03 | 深圳市大道四九科技有限公司 | Electronic cigarette defect identification method |
| CN116259005A (en) * | 2023-02-04 | 2023-06-13 | 国网浙江省电力有限公司嘉兴供电公司 | Intelligent monitoring system based on roof photovoltaic fire control |
| CN116310360A (en) * | 2023-05-18 | 2023-06-23 | 实德电气集团有限公司 | Reactor surface defect detection method |
| CN116596936A (en) * | 2023-07-18 | 2023-08-15 | 深圳市魔方卫星科技有限公司 | Solar wing sailboard quality detection method based on image data |
| CN117058161A (en) * | 2023-10-12 | 2023-11-14 | 深圳市五轮科技股份有限公司 | Electronic cigarette atomized smoke image segmentation method based on image processing |
Non-Patent Citations (1)
| Title |
|---|
| 一种零照度环境下的主动红外视频烟雾识别方法;罗丹妮;国外电子测量技术(第11期);第42-46页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117058670A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117058670B (en) | Electronic tobacco tar flexibility evaluation method | |
| Datta et al. | Algorithmic inferencing of aesthetics and emotion in natural images: An exposition | |
| US9639769B2 (en) | Liveness detection | |
| WO2019000777A1 (en) | Internet-based face beautification system | |
| CN111274860A (en) | Machine vision-based online automatic tobacco leaf grade sorting identification method | |
| CN103488714B (en) | Book recommendation method and system based on social networking | |
| WO2022042135A1 (en) | Face image selection method and apparatus, device, and storage medium | |
| CN106529006A (en) | Depth image-based broiler growth model fitting method and apparatus | |
| CN116152231B (en) | Method for detecting impurities in lubricating oil based on image processing | |
| CN109376982A (en) | A kind of choosing method and equipment of target employee | |
| CN107341762A (en) | Take pictures processing method, device and terminal device | |
| CN111476296A (en) | Sample generation method, classification model training method, identification method and corresponding devices | |
| CN111553880A (en) | Model generation method, label labeling method, iris image quality evaluation method and device | |
| CN108132964A (en) | A kind of collaborative filtering method to be scored based on user item class | |
| WO2022148378A1 (en) | Rule-violating user processing method and apparatus, and electronic device | |
| CN110245687A (en) | User classification method and device | |
| CN110990782B (en) | Cigarette sensory quality evaluation method based on weighted hesitation fuzzy power aggregation operator | |
| CN117635507B (en) | Plastic particle online visual detection method and system | |
| CN106485266A (en) | A kind of ancient wall classifying identification method based on extraction color characteristic | |
| CN116993717B (en) | Visual detection method for production quality of heating wire of electronic cigarette | |
| Amirshahi et al. | Judging aesthetic quality in paintings based on artistic inspired color features | |
| CN116773520A (en) | Feed liquid atomization condition detection method based on image segmentation algorithm | |
| CN117372362A (en) | Image quality evaluation method and device | |
| Venkatesh et al. | A preliminary study of tongue prints for biometric authentication | |
| CN105674891A (en) | Thread-like cut stem form detection method and evaluation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |