CN115112598A - Modeling method, model and detection method of automatic jade detection model - Google Patents
Modeling method, model and detection method of automatic jade detection model Download PDFInfo
- Publication number
- CN115112598A CN115112598A CN202211011721.3A CN202211011721A CN115112598A CN 115112598 A CN115112598 A CN 115112598A CN 202211011721 A CN202211011721 A CN 202211011721A CN 115112598 A CN115112598 A CN 115112598A
- Authority
- CN
- China
- Prior art keywords
- peak
- infrared
- peak position
- spectrum data
- interval
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 239000010977 jade Substances 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 30
- 229910052640 jadeite Inorganic materials 0.000 claims abstract description 96
- 238000001228 spectrum Methods 0.000 claims abstract description 45
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 27
- 238000004433 infrared transmission spectrum Methods 0.000 claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 241000579895 Chlorostilbon Species 0.000 claims description 13
- 239000010976 emerald Substances 0.000 claims description 13
- 229910052876 emerald Inorganic materials 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000000985 reflectance spectrum Methods 0.000 claims 3
- 230000006870 function Effects 0.000 description 8
- 230000003595 spectral effect Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 229910052500 inorganic mineral Inorganic materials 0.000 description 3
- 239000011707 mineral Substances 0.000 description 3
- 235000010755 mineral Nutrition 0.000 description 3
- 239000005416 organic matter Substances 0.000 description 3
- 229910052611 pyroxene Inorganic materials 0.000 description 3
- 235000015424 sodium Nutrition 0.000 description 3
- NWXHSRDXUJENGJ-UHFFFAOYSA-N calcium;magnesium;dioxido(oxo)silane Chemical compound [Mg+2].[Ca+2].[O-][Si]([O-])=O.[O-][Si]([O-])=O NWXHSRDXUJENGJ-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910052637 diopside Inorganic materials 0.000 description 2
- 125000000524 functional group Chemical group 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- 229910052612 amphibole Inorganic materials 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 239000011651 chromium Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000010433 feldspar Substances 0.000 description 1
- KWLMIXQRALPRBC-UHFFFAOYSA-L hectorite Chemical group [Li+].[OH-].[OH-].[Na+].[Mg+2].O1[Si]2([O-])O[Si]1([O-])O[Si]([O-])(O1)O[Si]1([O-])O2 KWLMIXQRALPRBC-UHFFFAOYSA-L 0.000 description 1
- 229910000271 hectorite Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000012766 organic filler Substances 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000000411 transmission spectrum Methods 0.000 description 1
- 238000002371 ultraviolet--visible spectrum Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/87—Investigating jewels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a modeling method, a model and a detection method for an automatic jade detection model, wherein the method comprises the following steps: obtaining a jadeite sample set for reflection and a jadeite sample set for transmission; acquiring an infrared reflection spectrum data set corresponding to a jadeite sample set for reflection, and acquiring an infrared transmission spectrum data set corresponding to a jadeite sample set for transmission; acquiring a designated peak position in each infrared reflection spectrum data, obtaining a peak position interval set corresponding to all designated peak positions by taking the corresponding designated peak position of the infrared reflection spectrum data in a first interval as a basis, and obtaining a first judgment basis by using the peak position interval set; acquiring a peak position related threshold value of the infrared transmission spectrum in a second set interval by taking the infrared transmission data set as a basis, and acquiring a second judgment basis by taking the peak position related threshold value as a basis; and storing the first judgment basis and the second judgment basis to obtain the automatic jade detection model. The invention solves the problem that the existing jadeite infrared spectrum identification software cannot meet the jadeite identification requirement.
Description
Technical Field
The invention relates to the field of jewelry detection, in particular to a modeling method, a model and a detection method of an automatic jade detection model.
Background
At present, no automatic jade detection equipment and no intelligent judgment software exist in the jewelry detection field. The jewelry detection laboratory mainly relies on qualitative analysis such as manual visual inspection and manual density test, ultraviolet-visible spectrum test, infrared spectrum and the like, a large number of jewelry experts are needed for inspection, the labor is relatively intensive, the automation degree is low, and the jade detection efficiency is influenced. Meanwhile, along with the expansion of the market scale of the jade trading, the market demand is greatly increased, the processing modes such as organic fillers and the like are changed, more unconventional production places and the jade with the unconventional mineral content proportion also fill the jade trading market, and new challenges appear in the identification of the jade. The conventional infrared matching software for emerald cannot meet the requirement for identifying emerald, and cannot realize intelligent identification of a map.
Disclosure of Invention
In view of the disadvantages of the prior art, the present invention provides a modeling method, a model and a detection method for automatically detecting a model of jadeite, so as to solve the problem that the existing jadeite recognition software cannot meet the jadeite identification requirement.
In order to achieve the above and other related objects, the present invention provides a method for modeling an automatic jade detection model, comprising:
obtaining a jadeite sample set for reflection and a jadeite sample set for transmission;
acquiring an infrared reflection spectrum data set corresponding to the jadeite sample set for reflection, wherein jadeite samples for reflection correspond to the infrared reflection spectrum data one by one, and acquiring an infrared transmission spectrum data set corresponding to the jadeite sample set for transmission, wherein the jadeite samples for transmission correspond to the infrared transmission spectrum data one by one;
acquiring a designated peak position in each infrared reflection spectrum data, obtaining a peak position interval set corresponding to all designated peak positions by taking the corresponding designated peak position of the infrared reflection spectrum data in a first interval as a basis, and obtaining a first judgment basis by using the peak position interval set;
acquiring a peak position related threshold value of the infrared transmission spectrum in a second set interval by taking the infrared transmission data set as a basis, and acquiring a second judgment basis by taking the peak position related threshold value as a basis;
and storing the first judgment basis and the second judgment basis to obtain the automatic jade detection model.
In an embodiment of the present invention, the method further includes the steps of: acquiring a verification sample set, acquiring a characteristic peak position set of an infrared spectrum interval corresponding to the verification sample set, and establishing a jadeite discrimination standard; and verifying the automatic jade detection model by utilizing the infrared spectrum interval characteristic peak position set to contrast with jade judgment standards.
In one embodiment of the present invention, the peak correlation threshold includes: a minimum peak height threshold, a minimum horizontal distance threshold between adjacent peaks, a minimum protrusion threshold for each peak value, and a difference between a maximum peak intensity of a peak position in the second set section and a 0.5-fold amplitude, the amplitude being a difference between a maximum value and a minimum value of the peak position intensity in a specified wave number range, the specified peak position being a peak position at a specified wave number.
In an embodiment of the present invention, the step of obtaining the designated peak position in each infrared reflection spectrum data, and based on the corresponding designated peak position of the infrared reflection spectrum data in the first interval, obtaining a peak position interval set corresponding to all designated peak positions includes: and searching all peak positions of the infrared reflection spectrum data set in a first set interval of wave numbers by adopting a differential peak searching method, wherein each peak position comprises intensity and a corresponding wave number.
In an embodiment of the present invention, the step of obtaining a set of peak intervals corresponding to all designated peak positions based on the corresponding designated peak positions of the infrared reflection spectrum data in the first interval includes: sorting each infrared reflection spectrum data in a descending order according to peak intensity, and taking the peak position N before the intensity ranking; sequencing the peak position sets corresponding to the infrared reflection spectrum data sets to obtain a sequence aiming at the same peak position, setting peak positions at two ends of the sequence as a maximum value and a minimum value, and determining the peak position interval by taking the minimum value and the maximum value as endpoints; repeating the steps until the sorting of the peak positions of N before the strength ranking is completed, and obtaining a peak position interval set corresponding to all the appointed peak positions.
In an embodiment of the present invention, the step of obtaining a peak position correlation threshold of the infrared transmission spectrum in a second set interval based on the infrared transmission data set, and obtaining a second determination based on the peak position correlation threshold includes: through iterative training, a peak searching function self-defines a minimum peak height threshold, a minimum horizontal distance threshold between adjacent peaks and a minimum projection threshold of each peak, whether a peak is searched is judged according to the self-defined minimum peak height threshold, the self-defined minimum horizontal distance threshold between adjacent peaks and the minimum projection threshold of each peak, and whether the peak is searched through the peak searching function and whether the specific peak intensity is smaller than the maximum peak intensity and the difference between 0.5 times of the amplitude is used as the second judgment basis.
In an embodiment of the present invention, the verification sample set includes a first sample set and a second sample set, where the samples in the first sample set are jadeite, the samples in the second sample set are non-jadeite, and the infrared spectrum data corresponding to the first sample includes infrared reflection spectrum data and infrared transmission spectrum data of the first sample; the infrared spectral data corresponding to the second sample only includes infrared reflectance spectral data of the second sample.
The invention also provides an automatic detection model of jade, which is obtained by the method.
The invention also provides an automatic detection method of emerald, which is realized by the model and comprises the following steps:
acquiring infrared spectrum data of a piece to be detected, wherein the infrared spectrum data at least comprises infrared reflection spectrum data;
and inputting the infrared reflection spectrum data of the piece to be detected into the model, comparing the infrared reflection spectrum data with the peak position interval set, and outputting a first detection result according to a first judgment basis.
In an embodiment of the present invention, after outputting the first detection result, the method further includes: and when the first detection result is jade, the infrared spectrum data of the to-be-detected piece further comprises infrared transmission spectrum data, the infrared spectrum data of the to-be-detected piece is input into the model, and a second detection result is output according to a second judgment basis.
In an embodiment of the present invention, the first detection result includes: jadeite, non-jadeite or multicomponent jadeite; the second detection result includes: treated jadeite or untreated jadeite.
The modeling method of the automatic jadeite detection model can quickly acquire the first judgment basis and the second judgment basis, and stores the first judgment basis and the second judgment basis to obtain the automatic jadeite detection model, wherein the accuracy of the model for identifying non-jadeite is up to 100%, the accuracy of identifying jadeite is 99.2%, and the accuracy of identifying organic matter filled with jadeite is 98.2%.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a modeling method of the present invention;
fig. 2 is a schematic structural diagram of an infrared reflection spectrum of a jadeite sample, wherein a is jadeite and b is hectorite;
fig. 3 is a schematic structural diagram of an infrared transmission spectrum of a jadeite sample.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. It is also to be understood that the terminology used in the examples is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention. Test methods in which specific conditions are not specified in the following examples are generally carried out under conventional conditions or under conditions recommended by the respective manufacturers.
It should be understood that the terms "upper", "lower", "left", "right", "middle" and "a" used herein are used for descriptive purposes only and are not intended to limit the scope of the present invention, and that the relative relationship between the terms and the terms should be construed as the scope of the present invention without substantial change in the technical spirit.
The jade in the invention is defined according to the national standard GB/T23885-2009 Jade Classification. Jadeite is a mineral aggregate mainly composed of jadeite or jadeite and other sodiums and sodiums calcareous pyroxene (sodiums chromium pyroxene, green pyroxene) and having a process value, and can contain a small amount of minerals such as amphibole, feldspar, chromite and the like. Mohs hardness of 6.5-7, density of 3.34 (+ 0.06, -0.09) g/cm 3 The refractive index is 1.666-1.680 (+ -0.008), and the point measurement is 1.65-1.67.
Referring to fig. 1, the present invention provides a method for modeling an automatic jade detection model, including the steps of:
and (5) setting up test conditions. Adopts a Thermo Fisher Nicolet iS50 infrared spectrometer and a reflection-transmission accessory, and adopts a resolution of 2-8 cm -1 And (5) scanning for 8-128 times, and deducting a background peak.
Distinguishing sample sets and verifying sample sets.
Acquiring a jadeite sample set for reflection and an infrared reflection spectrum data set thereof; the jadeite samples for reflection correspond to the infrared reflection spectrum data one by one, namely one jadeite sample for reflection corresponds to one infrared reflection spectrum data, and the identification standard is established. Polishing a jade sample for reflection, placing a reflection support under a normal temperature condition, deducting a background, placing the sample for reflection on a reflection support accessory, generating a discrete data file capable of being edited for storage, testing 3300 samples, wherein the number of the samples of the jade sample set for reflection can be 3000, obtaining 3000 infrared reflection spectrum data, each infrared reflection spectrum data at least comprises all peak positions in a first set interval, and the first set interval at least comprises the peak position characteristics of a jade fingerprint area. For example, the first setting interval is 400-1200 cm -1 。
And acquiring a jadeite sample set for transmission and an infrared transmission spectrum data set corresponding to the jadeite sample set for transmission, wherein the jadeite sample for transmission corresponds to the infrared transmission spectrum data one to one. Sample number of jadeite sample set for transmissionPolishing a jade sample, placing the sample for transmission into a transmission support under the normal temperature condition, deducting the background, placing the sample on the transmission support accessory, generating a discrete data file capable of being edited for storage, testing 2000 jade samples to obtain 2000 infrared transmission data, and setting a second set interval to be 3000-3200cm -1 。
Referring to fig. 2, a designated peak position in each infrared reflection spectrum data is obtained, a peak position interval set corresponding to all designated peak positions is determined by using the minimum value and the maximum value of the corresponding designated peak positions in the infrared reflection spectrum data set as end points, and a first judgment basis is obtained by using the peak position interval set, wherein the first judgment basis is used for judging whether a to-be-detected device is jadeite, non-jadeite or multi-component jadeite. The peak position refers to an X-axis wave number position corresponding to the peak position of the infrared reflection spectrum data. The designated peak position refers to an interval characteristic peak position meeting set conditions, and the designated peak position comprises at least two interval characteristic peak positions. The interval characteristic peak positions are some peak positions required for determining the type of jade, for example, the peak positions are specified as the top N peak positions in descending order of peak position intensity in the first set interval: respectively, a first peak position, a second peak position, a third peak position, … … and an Nth peak position, wherein N is a positive integer, for example, N is 10.
In this step, 3000 infrared reflection spectrum data need to be traversed according to the characteristic peak position property of the jadeite fingerprint region. According to the peak position intensity, all the peak positions of the infrared reflection spectrum data corresponding to each jadeite sample for reflection in the first set interval of the wave number are arranged in a descending order, then the characteristic peak positions (the first peak, the second peak, the third peak, … … and the Nth peak position) of N intervals before the intensity ranking are taken, and after the interference peak positions are removed, an interval characteristic peak position set is formed. Then, sorting (ascending or descending) corresponding interval characteristic peak positions in all infrared reflection spectrum data (namely all peak positions in the interval characteristic peak position set) in the jadeite sample set for reflection according to intensity to obtain a sequence, setting peak positions at two ends of the sequence as a maximum value and a minimum value, and determining a peak position interval by taking the minimum value and the maximum value as end points; repeating the steps until the sorting of the peak positions of N before the strength ranking is completed, and obtaining a peak position interval set corresponding to all the appointed peak positions. The corresponding interval characteristic peak position refers to: and peak positions with equal intensity ranking of the interval peak positions between different infrared reflection spectrum data, for example, the first peak position in the sample A and the first peak position in the sample B are corresponding interval characteristic peak positions. In the present embodiment, first, the first peak position of 3000 data items is sorted, and the sorted ends are the maximum value and the minimum value corresponding to the first peak position, respectively, so that the peak position section of the first peak position is determined by the end point of the sorted sequence, and the peak position section corresponding to the first peak position is named as the first peak position section.
And by analogy, a second peak position interval corresponding to the second peak position, a third peak position interval corresponding to the third peak position, a fourth peak position interval corresponding to the fourth peak position and a fifth peak position interval corresponding to the fifth peak position are obtained. The peak intervals corresponding to all the designated peak positions constitute a peak interval set, and in the present embodiment, the peak interval set includes a first peak interval, a second peak interval, a third peak interval, … …, and up to an nth peak interval. The peak position interval set is a standard for judging jadeite, namely a first judgment basis, and is used for judging whether the to-be-detected article is jadeite, non-jadeite or multi-component jadeite.
The specific criterion of the first criterion may be: when the corresponding designated peak position of the to-be-detected piece is totally in the corresponding peak position interval (2-10 peak position intervals according to the different peak position numbers of jadeite of different types), for example, the first peak position of the to-be-detected piece falls in the first peak position interval, the second peak position falls in the second peak position interval, the third peak position falls in the third peak position interval, the fourth peak position falls in the fourth peak position interval, … …, the Nth peak position falls in the Nth peak position interval, and the to-be-detected piece is jadeite. When the number of the corresponding designated peak positions of the to-be-detected product falling into the corresponding peak position interval meets the set condition, the to-be-detected product is multi-component jade, for example, the set condition is that the first peak position falls into the first peak position interval, the second peak position falls into the second peak position interval, and other peak positions do not fall into the corresponding peak position interval. It should be noted that the setting conditions in the present embodiment can be adjusted according to the current industry standard of jadeite industry. And when the corresponding designated peak position of the to-be-detected article does not meet any one of the two conditions, the to-be-detected article is non-jade.
And acquiring a peak searching function self-defined minimum peak height threshold value, a minimum horizontal distance threshold value between adjacent peaks and each peak value minimum projection threshold value of the infrared transmission spectrum in a second set interval by taking the infrared transmission data set as a basis, searching peaks through the peak searching function, and determining whether the intensity of the infrared transmission spectrum data of the to-be-detected piece at a specific peak position is smaller than the difference between the maximum intensity of the peak position in the second set interval and half of the wave amplitude. Wherein the amplitude is a difference between a maximum value and a minimum value of intensity of a peak position within a specified wave number range, and the specified peak position is a peak position at the specified wave number. And obtaining a second judgment basis according to whether the infrared spectrum transmission data of the to-be-detected article finds a peak in a second set interval and whether the intensity of the specific peak position is smaller than the difference between the maximum intensity and half of the amplitude, wherein the second judgment basis is used for judging whether the to-be-detected article is treated jade or untreated jade. The second set interval is the interval where the characteristic peak position of the functional group region of jadeite filled with organic substance is located, for example, 3000-3200cm -1 . The peak finding function is the self-carrying function in Python.
In one embodiment of the invention, the minimum peak height threshold is defined as at least the mean of the intensities plus 1 standard deviation of the intensities; a minimum horizontal distance threshold between adjacent peaks is defined as 50; the peak position protrusion degree threshold is the product of infrared intensity standard deviation multiple and infrared intensity standard deviation; and continuously iterating the infrared transmission spectrum data in the second interval to obtain an infrared intensity standard deviation multiple, and determining the minimum protrusion threshold value by multiplying the infrared intensity standard deviation multiple by the infrared intensity standard deviation in the second interval. The minimum protrusion threshold is the multiple of the infrared intensity standard deviation multiplied by the infrared intensity standard deviation in a second set interval. The infrared intensity standard deviation multiple is obtained by automatically and continuously observing the identification accuracy rate by using a computer, and a coefficient with higher identification rate is used as the standard deviation multiple. The judgment basis of whether the peak is found is as follows: and when the peak height of the infrared transmission spectrum data of the piece to be detected in the minimum horizontal distance threshold is smaller than the minimum peak height threshold and the projection degree of the peak position is smaller than the minimum projection degree threshold, judging that the peak is not found, otherwise, judging that the peak is found. By infrared transmission of the part to be measuredWhether the spectral data finds a peak in the second set interval and whether the specific peak position intensity is smaller than the difference between the maximum intensity and half (0.5 times of the amplitude) of the amplitude are used as second judgment basis, and the second judgment basis is used for judging whether the to-be-detected element is treated jade or untreated jade. And when the infrared transmission spectrum data of the to-be-detected piece is at the found peak or the specific peak position intensity is greater than or equal to the difference between the maximum intensity and half (0.5 times) of the amplitude, judging to be treated jade. And when the infrared spectrum data of the piece to be detected does not find a peak in the second set interval, or the peak is found but the specific peak position intensity is smaller than the difference between the maximum intensity and half (0.5 times) of the amplitude, judging that the piece to be detected is not processed. For example: searching peaks by using a difference method, traversing the peak position characteristics of a second interval of the original data of 2000 jadeite infrared transmission spectrum data, and selecting a calculation interval of 3000-3200cm according to the characteristic peak position characteristics of the jadeite functional group area filled with organic matters -1 Judging whether to find the peak according to the peak-finding function, considering that the intensity value is monotonously decreased, no peak exists, monotonously increased or changed, and the standard deviation of the peak position intensity in the second interval needs to be calculated, referring to the formula as follows, and calculating the characteristic peak (the peak with the significance of distinguishing processing from non-processing 3000-plus-3200 cm) -1 ) Calibrating the position;
in the formula
Represents each X (wave number cm) in the infrared spectrum -1 ) Y (intensity) axis numerical values corresponding to the coordinate points, namely infrared intensity values;
denotes X (wave number cm) within a specified interval -1 ) The average of the Y-axis (intensity) values corresponding to the coordinate points,
denotes X (wave number)cm -1 ) The number of coordinate points.
Finding out a fixed parameter (infrared intensity standard deviation multiple) with the highest identification accuracy by continuously iterating fixed infrared intensity standard deviation multiple of 2000 pieces of infrared transmission spectrum data, wherein the product of the fixed parameter and the standard deviation is used as a peak position minimum projection threshold value and belongs to the category of peak finding functions; and calculating the difference between the maximum value and the minimum value of the Y-axis numerical value as the amplitude, and adopting the difference between the specific peak position intensity which is less than the maximum intensity and half (0.5 times of the amplitude) of the amplitude together with whether a peak is found or not as a standard for judging whether to process or not. Referring to fig. 3, the second criterion may be: and when the peak is found in the second interval of the article to be detected and the specific peak position intensity is greater than or equal to the difference between the maximum intensity and half of the amplitude (0.5 times of the amplitude), judging to be treated jade, and when the peak is not found in the article to be detected or the specific peak position intensity is less than the difference between the maximum intensity and half of the amplitude (0.5 times of the amplitude), judging to be non-treated jade (natural jade). Wherein the X-axis of FIGS. 2-3 is in units of wavenumbers (cm) -1 ）。
And acquiring a verification sample set, acquiring an infrared spectrum data interval characteristic peak position set corresponding to the verification sample set, and enabling verification sample data to correspond to infrared spectrum data one to one. Establishing a jadeite reflection judgment standard; and verifying the automatic jade detection model by using the infrared spectrum interval characteristic peak position set according to the jade judgment standard. Respectively carrying out mathematical statistics on wave numbers of the first three peak positions of the characteristic peak position set of each spectrum interval in the data set according to different data sets of jadeite and emerald, determining the wave number ranges of the first three peak positions of jadeite and emerald by combining theoretical research, and comprehensively establishing jadeite judgment standards; the judgment is carried out according to different standards of jadeite and diopside simultaneously, jadeite is adopted as long as one standard of jadeite and diopside is met, and further processing judgment is carried out under special conditions. The verification sample set comprises a first sample set and a second sample set, samples in the first sample set are jadeite, samples in the second sample set are non-jadeite, and infrared spectrum data corresponding to the first samples comprise infrared reflection spectrum data and infrared transmission spectrum data of the first samples; the infrared spectral data corresponding to the second sample comprises infrared reflectance spectral data of the second sample. The first sample included 2000 jadeite samples, and the second sample included 300 non-jadeite samples.
And storing the first judgment basis and the second judgment basis to obtain the automatic jade detection model, wherein the computer language adopted for establishing the automatic jade detection model can be Python.
The invention also provides an automatic detection model of jade, which is obtained by the method. The computer language adopted by the automatic detection model of emerald can be Python.
The invention also provides an automatic detection method of emerald, which is realized by the model and comprises the following steps:
acquiring infrared spectrum data of a piece to be detected, wherein the infrared spectrum data at least comprises infrared reflection spectrum data;
and inputting the infrared reflection spectrum data of the piece to be detected into the model, comparing the infrared reflection spectrum data with the peak position interval set, and outputting a first detection result according to a corresponding judgment basis. When the corresponding designated peak position of the to-be-detected piece falls into the corresponding peak position interval, for example, the first peak position of the to-be-detected piece falls into the first peak position interval, the second peak position falls into the second peak position interval, the third peak position falls into the third peak position interval, the fourth peak position falls into the fifth peak position interval, and the to-be-detected piece is jade. When the corresponding designated peak position of the to-be-detected article falls into the corresponding peak position interval but the number of the to-be-detected article is different from the standard, the to-be-detected article is further inspected for the multicomponent jade, for example, the set condition is that the first peak position falls into the first peak position interval, the second peak position falls into the second peak position interval, and other peak positions do not fall into the corresponding peak position intervals, it needs to be explained that the set condition in the embodiment can be correspondingly adjusted according to the industry standard of the jade industry. And when the corresponding designated peak position of the to-be-detected article does not meet any one of the two conditions, the to-be-detected article is non-jade.
In an embodiment of the present invention, after outputting the first detection result, the method further includes: when the first detection result is jade, the infrared spectrum data of the to-be-detected piece further comprises infrared transmission spectrum data, the infrared spectrum data of the to-be-detected piece is input into the model and compared with the peak fluctuation reference value, and a second detection result is output according to corresponding judgment basis.
In an embodiment of the present invention, the first detection result includes: jadeite, non-jadeite or multicomponent jadeite; the second detection result includes: treated jadeite or untreated jadeite.
The modeling method of the automatic jadeite detection model can quickly acquire the first judgment basis and the second judgment basis, and stores the first judgment basis and the second judgment basis to obtain the automatic jadeite detection model, wherein the accuracy of the model for identifying non-jadeite is up to 100%, the accuracy of identifying jadeite is 99.2%, and the accuracy of identifying organic matter filled with jadeite is 98.2%. According to the invention, jadeite, non-jadeite, multi-component jadeite and organic matter filled jadeite can be automatically detected based on the infrared reflection-transmission spectrum. Through inputting the discrete original data of the infrared spectrum, the automatic identification of jadeite, non-jadeite, multi-component jadeite, jadeite (processed) and jadeite (unprocessed) can be realized.
Therefore, the invention effectively overcomes some practical problems in the prior art, thereby having high utilization value and use significance.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A method for modeling an automatic detection model of emerald, which is characterized by comprising the following steps:
obtaining a jadeite sample set for reflection and a jadeite sample set for transmission;
acquiring an infrared reflection spectrum data set corresponding to the jadeite sample set for reflection, wherein jadeite samples for reflection correspond to the infrared reflection spectrum data one by one, and acquiring an infrared transmission spectrum data set corresponding to the jadeite sample set for transmission, wherein the jadeite samples for transmission correspond to the infrared transmission spectrum data one by one;
acquiring a designated peak position in each infrared reflection spectrum data, obtaining a peak position interval set corresponding to all designated peak positions by taking the corresponding designated peak position of the infrared reflection spectrum data in a first interval as a basis, and obtaining a first judgment basis by using the peak position interval set;
acquiring a peak position related threshold value of the infrared transmission spectrum in a second set interval by taking the infrared transmission data set as a basis, and acquiring a second judgment basis by taking the peak position related threshold value as a basis;
and storing the first judgment basis and the second judgment basis to obtain the automatic jade detection model.
2. The method for modeling an automatic detection model of emerald according to claim 1, further comprising the steps of: acquiring a verification sample set, acquiring a characteristic peak position set of an infrared spectrum interval corresponding to the verification sample set, and establishing a jadeite discrimination standard; and verifying the automatic jade detection model by utilizing the infrared spectrum interval characteristic peak position set to contrast with jade judgment standards.
3. A modeling method for an automatic detection model of emerald according to claim 1, wherein the peak position correlation threshold comprises: a minimum peak height threshold, a minimum horizontal distance between adjacent peaks threshold, and a minimum prominence per peak threshold.
4. The method of claim 1, wherein the step of obtaining the designated peak position in each infrared reflectance spectrum data, and obtaining the peak position interval set corresponding to all designated peak positions based on the corresponding designated peak position of the infrared reflectance spectrum data in the first interval comprises: and searching all peak positions of the infrared reflection spectrum data set in a first set range of wave numbers by adopting a differential peak searching method, wherein each peak position comprises intensity and a corresponding wave number.
5. The method of claim 4, wherein the step of obtaining a set of peak intervals corresponding to all designated peak positions based on the corresponding designated peak positions of the infrared reflectance spectrum data in the first interval comprises: sorting each infrared reflection spectrum data in a descending order according to peak intensity, and taking the peak position N before the intensity ranking; sequencing the peak position sets corresponding to the infrared reflection spectrum data sets to obtain a sequence aiming at the same peak position, setting peak positions at two ends of the sequence as a maximum value and a minimum value, and determining the peak position interval by taking the minimum value and the maximum value as endpoints; repeating the steps until the sorting of the peak positions of N before the strength ranking is completed, and obtaining a peak position interval set corresponding to all the appointed peak positions.
6. The method of claim 1, wherein the step of obtaining a peak-related threshold of the infrared transmission spectrum in a second predetermined interval based on the infrared transmission data set, and obtaining a second determination based on the peak-related threshold comprises: through iterative training, a peak searching function self-defines a minimum peak height threshold, a minimum horizontal distance threshold between adjacent peaks and a minimum projection threshold of each peak, whether the peak is searched is judged according to the self-defined minimum peak height threshold, the minimum horizontal distance threshold between the adjacent peaks and the minimum projection threshold of each peak, the peak searching function is used for searching the peak of the infrared jade sample set wave number for transmission in a second set interval, whether the peak is searched in the second set interval is judged, and whether the specific peak position intensity is smaller than the difference between the maximum intensity value and 0.5 times of wave amplitude is used as the second judgment basis.
7. The method of claim 2, wherein the set of verification samples comprises a first set of samples and a second set of samples, the samples in the first set of samples are jadeite, and the samples in the second set of samples are jadeite.
8. An automatic detection model of emerald, characterized in that, the automatic detection model of emerald is obtained by the method of any one of claims 1 to 7.
9. An automatic detection method for emerald, which is implemented by the model of claim 8, and comprises the steps of:
acquiring infrared spectrum data of a piece to be detected, wherein the infrared spectrum data at least comprises infrared reflection spectrum data;
and inputting the infrared reflection spectrum data of the piece to be detected into the model, comparing the infrared reflection spectrum data with the peak position interval set, and outputting a first detection result according to a first judgment basis.
10. The method of claim 9, further comprising the step of, after outputting the first detection result: when the first detection result is jade, the infrared spectrum data of the to-be-detected piece further comprises infrared transmission spectrum data, the infrared spectrum data of the to-be-detected piece is input into the model, and a second detection result is output according to a second judgment basis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211011721.3A CN115112598B (en) | 2022-08-23 | 2022-08-23 | Modeling method, model and detection method of automatic jade detection model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211011721.3A CN115112598B (en) | 2022-08-23 | 2022-08-23 | Modeling method, model and detection method of automatic jade detection model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115112598A true CN115112598A (en) | 2022-09-27 |
| CN115112598B CN115112598B (en) | 2023-04-07 |
Family
ID=83335991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211011721.3A Active CN115112598B (en) | 2022-08-23 | 2022-08-23 | Modeling method, model and detection method of automatic jade detection model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115112598B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115905881A (en) * | 2022-09-30 | 2023-04-04 | 国家珠宝玉石首饰检验集团有限公司 | Method and device for classifying yellow pearls, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101788507A (en) * | 2010-02-03 | 2010-07-28 | 北京矿冶研究总院 | Spectral analysis method |
| CN101915746A (en) * | 2010-07-22 | 2010-12-15 | 中国人民解放军空军油料研究所 | Method for identifying aviation fuels and additives |
| CN103439266A (en) * | 2013-08-26 | 2013-12-11 | 广东省珠宝玉石及贵金属检测中心 | Identification and analysis system for jewelry jade and rock minerals |
| CN104749158A (en) * | 2013-12-27 | 2015-07-01 | 同方威视技术股份有限公司 | Jade jewelry appraisal method and device thereof |
| CN108398398A (en) * | 2018-02-12 | 2018-08-14 | 山西省交通科学研究院 | The method for identifying asphalt quality using decaying In situ ATR-FTIR standard spectrogram |
| CN111398208A (en) * | 2020-04-22 | 2020-07-10 | 谭贵平 | Method for rapidly identifying traditional art jadeite by utilizing near-infrared technology |
| CN111562265A (en) * | 2020-03-10 | 2020-08-21 | 自然资源部珠宝玉石首饰管理中心深圳珠宝研究所 | Method for quantitatively analyzing emerald spectral data |
| CN112098340A (en) * | 2020-08-04 | 2020-12-18 | 中南民族大学 | Turquoise identification method based on hyperspectral imaging technology and assembly line process |
| CN112782146A (en) * | 2019-11-11 | 2021-05-11 | 中国石油天然气股份有限公司 | Gasoline olefin content analysis method based on Raman spectrum |
| CN113049520A (en) * | 2021-03-18 | 2021-06-29 | 吉林化工学院 | Identification method for screening activities of different medicinal parts of Dictamnus dasycarpus |
| CN113640272A (en) * | 2021-07-13 | 2021-11-12 | 黄埔海关技术中心 | Spectral library establishing and detecting method based on portable Raman spectrometer and application |
-
2022
- 2022-08-23 CN CN202211011721.3A patent/CN115112598B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101788507A (en) * | 2010-02-03 | 2010-07-28 | 北京矿冶研究总院 | Spectral analysis method |
| CN101915746A (en) * | 2010-07-22 | 2010-12-15 | 中国人民解放军空军油料研究所 | Method for identifying aviation fuels and additives |
| CN103439266A (en) * | 2013-08-26 | 2013-12-11 | 广东省珠宝玉石及贵金属检测中心 | Identification and analysis system for jewelry jade and rock minerals |
| CN104749158A (en) * | 2013-12-27 | 2015-07-01 | 同方威视技术股份有限公司 | Jade jewelry appraisal method and device thereof |
| CN108398398A (en) * | 2018-02-12 | 2018-08-14 | 山西省交通科学研究院 | The method for identifying asphalt quality using decaying In situ ATR-FTIR standard spectrogram |
| CN112782146A (en) * | 2019-11-11 | 2021-05-11 | 中国石油天然气股份有限公司 | Gasoline olefin content analysis method based on Raman spectrum |
| CN111562265A (en) * | 2020-03-10 | 2020-08-21 | 自然资源部珠宝玉石首饰管理中心深圳珠宝研究所 | Method for quantitatively analyzing emerald spectral data |
| CN111398208A (en) * | 2020-04-22 | 2020-07-10 | 谭贵平 | Method for rapidly identifying traditional art jadeite by utilizing near-infrared technology |
| CN112098340A (en) * | 2020-08-04 | 2020-12-18 | 中南民族大学 | Turquoise identification method based on hyperspectral imaging technology and assembly line process |
| CN113049520A (en) * | 2021-03-18 | 2021-06-29 | 吉林化工学院 | Identification method for screening activities of different medicinal parts of Dictamnus dasycarpus |
| CN113640272A (en) * | 2021-07-13 | 2021-11-12 | 黄埔海关技术中心 | Spectral library establishing and detecting method based on portable Raman spectrometer and application |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115905881A (en) * | 2022-09-30 | 2023-04-04 | 国家珠宝玉石首饰检验集团有限公司 | Method and device for classifying yellow pearls, electronic equipment and storage medium |
| CN115905881B (en) * | 2022-09-30 | 2023-10-20 | 国家珠宝玉石首饰检验集团有限公司 | Yellow pearl classification method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115112598B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111337606A (en) | Overlapping peak processing method and device applied to chromatographic analysis | |
| CN105466884B (en) | It is a kind of by near infrared light spectrum discrimination crude oil species and its method for property | |
| CN102841070B (en) | Method for identifying types of crude oil by using two-dimensional correlation infrared synchronization spectrum | |
| CN115112598B (en) | Modeling method, model and detection method of automatic jade detection model | |
| CN112613536B (en) | Near infrared spectrum diesel fuel brand recognition method based on SMOTE and deep learning | |
| CN108844941B (en) | Method for identifying and classifying different-grade phosphate ores based on Raman spectrum and PCA-HCA | |
| CN107727592A (en) | A kind of coal-rock interface identification method based on coal petrography high spectrum reflection characteristic | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| CN105424641A (en) | Crude oil type near infrared spectrum identification method | |
| CN102841069B (en) | Method for rapidly identifying types of crude oil by using mid-infrared spectrum | |
| CN113720797B (en) | Online rapid quality measuring and liquor picking method for distilled liquor | |
| CN104502299A (en) | Method for identifying Wuchang rice-flower fragrance rice by virtue of near infrared spectrum technique | |
| CN104568815A (en) | Method for quickly and nondestructively detecting content of volatile basic nitrogen in fresh beef | |
| CN105823752A (en) | Method for fast identifying variety of edible oil through near-infrared spectroscopy method | |
| CN108693139A (en) | The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application | |
| CN112525879A (en) | In-situ identification and rapid quantification method for coal rock micro-components | |
| CN113607679A (en) | Discrete maximum value-based terahertz absorption peak position extraction method | |
| CN116881530A (en) | Device surface defect detection system based on deep learning | |
| CN105223140A (en) | The method for quickly identifying of homology material | |
| CN107966420B (en) | Method for predicting crude oil property by near infrared spectrum | |
| CN112362609A (en) | Method for identifying oil stain smoke pollution source based on infrared spectrum technology | |
| CN111398208B (en) | Method for rapidly identifying jadeite in traditional process by utilizing near infrared technology | |
| CN108197662A (en) | A kind of solid wooden floor board sorting technique | |
| CN117250169A (en) | Method for nondestructively and rapidly distinguishing wild cordyceps sinensis based on model transfer technology | |
| CN116952895A (en) | Method for rapidly determining mixing uniformity |
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 | ||
| CP02 | Change in the address of a patent holder |
Address after: Floor 15, Jewelry Testing Center Building, No. 4, Beili South Road, Luohu District, Shenzhen, Guangdong 518000 Patentee after: GUO JIAN CENTER SHENZHEN JEWELRY INSPECTION LABORATORY Co.,Ltd. Address before: 13th Floor, Jewelry Testing Center Building, No. 4 Bei Li South Road, Luohu District, Shenzhen, Guangdong 518000 Patentee before: GUO JIAN CENTER SHENZHEN JEWELRY INSPECTION LABORATORY Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |