CN108827904B - Substance identification method, device and equipment based on terahertz spectrum and storage medium - Google Patents
Substance identification method, device and equipment based on terahertz spectrum and storage medium Download PDFInfo
- Publication number
- CN108827904B CN108827904B CN201810628198.6A CN201810628198A CN108827904B CN 108827904 B CN108827904 B CN 108827904B CN 201810628198 A CN201810628198 A CN 201810628198A CN 108827904 B CN108827904 B CN 108827904B
- Authority
- CN
- China
- Prior art keywords
- substance
- absorption peak
- characteristic absorption
- detected
- standard
- 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
- 239000000126 substance Substances 0.000 title claims abstract description 203
- 238000001228 spectrum Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000010521 absorption reaction Methods 0.000 claims abstract description 185
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 34
- 230000005484 gravity Effects 0.000 claims abstract description 25
- 230000003595 spectral effect Effects 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004611 spectroscopical analysis Methods 0.000 claims description 5
- 238000000418 atomic force spectrum Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- MHAJPDPJQMAIIY-UHFFFAOYSA-N Hydrogen peroxide Chemical compound OO MHAJPDPJQMAIIY-UHFFFAOYSA-N 0.000 description 5
- 230000003247 decreasing effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000004566 IR spectroscopy Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009878 intermolecular interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 description 1
- 238000002834 transmittance 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
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
- G01N21/3586—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation by Terahertz time domain spectroscopy [THz-TDS]
Abstract
The application discloses a method, a device, equipment and a storage medium for identifying substances based on terahertz spectrum, which comprises the following steps: extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time; repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set; acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing a substance to be detected from a spectral database; matching the characteristic absorption peak data set and the standard characteristic absorption peak data set through an inverse gravitation algorithm, and calculating the similarity of the two substances; and comparing the similarity with a set similarity threshold value to identify the substance to be detected. According to the method and the device, the characteristic absorption peak is extracted through the gravity algorithm, the confidence coefficient is calculated, and the characteristic absorption peak is identified by utilizing the matching of the absorption peak data set, so that the influence of amplitude fluctuation on characteristic extraction is effectively avoided, and the identification rate is improved.
Description
Technical Field
The invention relates to the field of substance identification, in particular to a substance identification method, a substance identification device, substance identification equipment and a storage medium based on terahertz spectrum.
Background
In recent years, problems such as terrorist threat, food safety and the like are increasingly exposed and serious, and a method for rapidly and effectively identifying and detecting substances such as explosives, foods, medicines and the like is urgently needed.
The terahertz wave has the properties of strong penetrability, low energy, fingerprint spectrum and the like, and has important application prospects in the aspects of safety inspection and nondestructive testing. Molecular vibration and intermolecular interaction of a plurality of organic matters can absorb terahertz waves with specific frequency, so that corresponding absorption peaks are generated, and infrared spectra can only detect rotation and stretching vibration of chemical bonds in molecules; by utilizing the terahertz time-domain spectroscopy technology, intermolecular framework vibration can be effectively obtained in a larger wavelength range, and information obtained by infrared spectroscopy can be effectively supplemented. Due to the fact that the composition groups of each substance are different, the terahertz spectrum obtained by irradiation of terahertz waves with different frequencies is large in difference, and the difference of the frequency of a characteristic absorption peak on a spectral curve of each substance is mainly large. After the features of the terahertz spectrum of each substance are extracted, the substances can be distinguished by the features.
At present, the commonly used terahertz feature extraction methods include a partial least square method and a principal component analysis method, and after the features are extracted by the methods, a support vector machine or other machine learning methods are used for identifying substances; or directly calculating the relation of the distance, the included angle and the like of the two spectral curves to judge whether the two spectral curves belong to the same substance. However, the actual terahertz spectrum measurement experiment proves that under the conditions of different concentrations (thicknesses), irradiation positions, environmental conditions, uniformity and the like, the spectrum amplitude obtained by the same substance still has large fluctuation, and only the characteristic absorption peak frequency of each substance changes slightly. The above methods directly extract the features of the frequency and amplitude of the feature absorption peak, and the extracted features are greatly influenced by the amplitude, so that the recognition rate of recognizing the substances measured under different conditions is low.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a storage medium for identifying a substance based on terahertz spectroscopy, which can improve the identification rate of substance identification. The specific scheme is as follows:
a substance identification method based on terahertz spectrum comprises the following steps:
extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time;
repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing the substance to be detected from a spectral database;
matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity of the substance to be detected and the standard substance;
and comparing the calculated similarity with a set similarity threshold, and identifying the substance to be detected according to the comparison result.
Preferably, in the method for identifying a substance based on a terahertz spectrum provided in an embodiment of the present invention, the extracting an absorption peak from a terahertz spectrum curve obtained by measuring a substance to be detected at a single time specifically includes:
preprocessing a terahertz spectrum curve measured by a substance to be measured at a single time, and finding the positions of a plurality of absorption peaks through monotonicity;
and circularly expanding the interval of each absorption peak through a peak interval expansion algorithm, calculating the confidence coefficient of each absorption peak, and reserving the absorption peak corresponding to the confidence coefficient which is greater than a set confidence coefficient threshold value.
Preferably, in the method for identifying a substance based on a terahertz spectrum according to an embodiment of the present invention, after finding the positions of the plurality of absorption peaks by monotonicity, before cyclically extending the interval of each absorption peak by a peak interval extension algorithm, the method further includes:
removing the interference part with dense wave peak points and wave valley points in the terahertz spectrum curve by using a window sliding method;
by intercepting valley points around a peak point as a fitting interval, fitting and judging whether the slope of the peak point exceeds a slope threshold value;
if so, removing the peak point; if not, the peak point is reserved.
Preferably, in the method for identifying a substance based on a terahertz spectrum according to an embodiment of the present invention, the extracting an absorption peak common to multiple measurements as a characteristic absorption peak of the substance to be detected by using a gravity algorithm specifically includes:
in a one-dimensional coordinate system space only with gravitation, each absorption peak is regarded as an object, the position of the absorption peak on a one-dimensional coordinate axis is the frequency of the absorption peak, and the mass is the confidence coefficient of the absorption peak;
respectively placing absorption peaks with fixed frequency and confidence at each point of a one-dimensional coordinate axis, and calculating the resultant force of the absorption peaks to obtain a resultant force curve of the attraction;
and extracting a proper maximum value point on the gravitational resultant curve to serve as a characteristic absorption peak of the substance to be detected.
Preferably, in the method for identifying a substance based on a terahertz spectrum according to an embodiment of the present invention, before acquiring a standard characteristic absorption peak data set of at least one standard substance that may include the substance to be detected from a spectrum database, the method further includes:
extracting absorption peaks of terahertz spectrum curves obtained by measuring a plurality of standard substances at a single time;
repeating the multiple measurements, extracting the common absorption peak in the multiple measurements as the standard characteristic absorption peak of the plurality of standard substances through a gravity algorithm, calculating the confidence coefficient of each standard characteristic absorption peak, obtaining the data set of the standard characteristic absorption peaks of the plurality of standard substances, and storing the data set into a spectrum database.
The embodiment of the invention also provides a substance identification device based on the terahertz spectrum, which comprises:
the absorption peak extraction module is used for extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time;
the confidence coefficient calculation module is used for repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
a data set acquisition module for acquiring a data set of standard characteristic absorption peaks of at least one standard substance possibly containing the substance to be detected from a spectral database;
the data set matching module is used for matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm and calculating the similarity of the substance to be detected and the standard substance;
and the substance identification module is used for comparing the calculated similarity with a set similarity threshold value and identifying the substance to be detected according to the comparison result.
The embodiment of the invention also provides a substance identification device based on the terahertz spectrum, which comprises a processor and a memory, wherein the processor executes a computer program stored in the memory to realize the substance identification method based on the terahertz spectrum.
Embodiments of the present invention further provide a computer-readable storage medium for storing a computer program, where the computer program is executed by a processor to implement the method for identifying a substance based on terahertz spectroscopy as provided in an embodiment of the present invention.
The invention provides a substance identification method, a device, equipment and a storage medium based on a terahertz spectrum, wherein the method comprises the following steps: extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time; repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set; acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing a substance to be detected from a spectral database; matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity between the substance to be detected and the standard substance; and comparing the calculated similarity with a set similarity threshold, and identifying the substance to be detected according to the comparison result.
The method provided by the invention has the advantages that the measurement is repeated for many times, the characteristic absorption peak is extracted through the gravity algorithm, the confidence coefficient is calculated, the characteristic absorption peak and the confidence coefficient are combined into the characteristic absorption peak data set, the identification is completed by utilizing the matching of the characteristic absorption peak data set, only the amplitude is used for calculating auxiliary parameters such as the confidence coefficient in the whole process, the influence of amplitude fluctuation on the characteristic extraction can be effectively avoided, the terahertz spectrum identification technology can be effectively applied to various environmental conditions and physical parameters of substances, and the identification rate of the terahertz spectrum substance identification is improved.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a substance identification method based on terahertz spectroscopy according to an embodiment of the present invention;
fig. 2 is a terahertz spectrum graph of 5 times hydrogen peroxide solution measured according to the embodiment of the present invention;
FIG. 3 is a graph of hydrogen peroxide attraction provided by an embodiment of the present invention;
FIG. 4 is a diagram of a matching situation between a characteristic absorption peak and a source spectral curve provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a substance identification device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a substance identification method based on terahertz spectrum, as shown in figure 1, comprising the following steps:
s101, extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time;
s102, repeating multiple measurements, extracting an absorption peak shared in the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
s103, acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing the substance to be detected from a spectrum database;
s104, matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity between the substance to be detected and the standard substance;
and S105, comparing the calculated similarity with a set similarity threshold, and identifying the substance to be detected according to the comparison result.
It should be noted that the hardware system used can be a terahertz spectrometer of type TAS7500, and can measure terahertz spectrum from 0.1THz to 5THz, and frequency resolution fr0.0019THz, it can provide various material parameters such as amplitude, phase, transmittance, reflectance, refractive index, and dielectric constant. Preferably, the substance to be detected and the standard substance may be both pure substances.
Further, in specific implementation, the step S101 of extracting an absorption peak of the terahertz spectrum curve obtained by measuring the substance to be measured at a single time may specifically include:
firstly, preprocessing a terahertz spectrum curve measured by a substance to be detected at a single time, and finding the positions of a plurality of absorption peaks through monotonicity;
specifically, a background curve obtained by measurement when a substance to be measured is not put is subtracted from a terahertz spectrum curve obtained by measurement after the substance to be measured is put to obtain a substance spectrum curve with a filtered background, and then wavelet denoising and interference filtering are carried out on the substance spectrum curve to obtain a smooth terahertz spectrum curve with less oscillation. All spectral curve points (f, y) form a point set G with a spectral curve frequency resolution of fr0.0019 THz. For each spectral curve point (f)i,yi) The following judgments were performed in order:
yi＞yi+1and y isi＞yi-1 (1)
yi＜yi+1And y isi＜yi-1 (2)
All the points satisfying the condition (1) are peak points, and all the peak points (f)P,yP) Forming a point set P, wherein the points satisfying the condition (2) are valley points, and all the valley points (f)V,yV) Forming a set of points V.
Next, after finding the positions of a plurality of absorption peaks (i.e. peaks) by monotonicity in step one, the method may further include:
removing interference parts with intensive wave peak points and wave valley points in the terahertz spectrum curve by using a window sliding method;
specifically, each peak point (f) in the point set PPi,yPi) At each peak point frequency f in turnPiIs a midpoint, and the frequency range is fixed to be fT(e.g. f)T0.025THz), the amplitude range size is fixed at ymax-yminEstablishing a two-dimensional window, wherein ymaxIs the y maximum value of each element in the point set G, yminIs the minimum value of y for each element in the set of points G. The two-dimensional window formed by the ith peak point is recorded as WiThen there is
Determine each two-dimensional window WiWhether the following conditions are satisfied:
wherein WiN is P is window WiSet of inner peak points, WiN is V is window WiThe set of valley points in (A), the function number (A) being defined as the number of elements in the set A, ρT(e.g.,. rho.)T5) is the set peak to valley density threshold. Removing the peak point (f) corresponding to the two-dimensional window which does not satisfy the above condition from the set PPi,yPi)；
Thirdly, fitting and judging whether the slope of the peak point exceeds a slope threshold value or not by intercepting the valley points around the peak point as a fitting interval; if yes, removing the peak point; if not, keeping the peak point;
specifically, each peak point (f) in the point set PPi,yPi) Find two points (f)vleft,yvleft)、(fvright,yvright) The following conditions are satisfied:
min|fvleft-fPii and (f)vleft,yvleft)∈V，fPi＞fvleft
min|fvright-fPiI and (f)vright,yvright)∈V，fPi＜fvright
When the point (f) of the above condition is satisfiedvleft,yvleft) [ or (f)vright,yvright)]Taking the left end point (f) of the spectral curve in the absencemin,y1) [ or the right end point (f)max,y2)]I.e., (f)vleft,yvleft)＝(fmin,y1) [ or (f)vright,yvright)＝(fmax,y2)]。
Set of points Q1＝{(x,y)|x∈[fvleft,fvright](x, y) belongs to G, and for a two-dimensional point set Q1All points in (2) make a minimum of twoMultiply the regression fit to fit the following function:
y＝C1·(f-fPi)+yPi
judging whether the fitted function meets the following conditions:
C1≤Ta
wherein T isa(e.g. T)a-300) is the set parabolic slope threshold. The peak point not satisfying the above condition is a pseudo peak, and the peak point not satisfying the above condition is removed from the set P (f)Pi,yPi)。
After the step three is carried out and the integral waveform fitting is carried out to judge whether the peak point meets the basic condition, the next step is carried out:
circularly expanding the interval of each absorption peak through a peak interval expansion algorithm, calculating the confidence coefficient of each absorption peak, and reserving the absorption peak corresponding to the confidence coefficient which is greater than a set confidence coefficient threshold;
specifically, each peak point (f) in the point set PPi,yPi) Set of set points Q2＝{(x,y)|x∈[fPi-f0,fPi+f0](x, y) e G, where f0(e.g. f)00.0038) is the set frequency difference constant. The following operations are cyclically carried out:
Q2k＝{(x,y)|x∈[fPi-f0-k·fr,fPi+f0+k·f],(x,y)∈G,k∈N}
point set Q2kIs subjected to a least squares regression, fitting the following function:
y＝C1·(f-fPi)+C2 (3)
the determined coefficient obtained by fitting is set as
Until the expansion coefficient is a local maximum value, that is, the following conditions are satisfied:
and taking 1,2,3 and … in turn during the circulation process. Let the result of the expansion at the end of the cycle be
Q3＝{(x,y)|x∈[f′left,f′right],(x,y)∈G}
Then, similar to the above steps, the interval is expanded left and right respectively, namely, the expansion is circularly carried out respectively
Q3k＝{(x,y)|x∈[f′left-k·fr,f′right],(x,y)∈G,k∈N}
Q3k＝{(x,y)|x∈[f′left,f′right+k·fr],(x,y)∈G,k∈N}
Up to the coefficient of expansion
And reaching the local maximum to finish the cycle of expansion at the left and right sides.
Let the final expanded result Qend＝{(x,y)|x∈[fleft,fright](x, y) is belonged to G }, and the confirmation coefficient obtained by fitting in the interval is
The peak amplitude after fitting is C2endCoefficient of parabolic quadratic term of C1endThe left and right endpoints are respectively (f)left,yleft)、(fright,yright). According to the formula of curvature calculation
The curvature of the parabola at the peak point is calculated by substituting equation (3) of the parabola into the equation
k＝|2*C1end|
From this, the basic parameters of the absorption peak such as wave width, wave height, confidence level, etc. can be calculated as follows:
wherein C is1(e.g. C)1＝300)、C2(e.g. C)2＝1)、C3(e.g. C)31) are all undetermined constants.
Performing S-shaped function mapping on the confidence degree to obtain the final confidence degree beta (beta is more than or equal to 0 and less than or equal to 100 percent), namely
β＝fS(β0)*100％
Wherein f iss(. cndot.) is a given sigmoidal function having
Removing confidence coefficient beta < beta in point set PTCorresponding peak point of wave, whereinT(e.g.. beta.) ofT20%) is a given confidence threshold. The points in the point set P are all characteristic absorption peaks.
Next, in practical application, the step S102 repeats the multiple measurements and extracts an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected by using a gravity algorithm, and calculates a confidence of each characteristic absorption peak to obtain a characteristic absorption peak data set, which may specifically include the following steps:
in specific implementation, the substance to be measured is repeatedly subjected to the steps from one to four (n is 5) times to obtain absorption peaks extracted from n measurement results, 5 spectral curves are uniformly drawn as shown in fig. 2, the horizontal axis is the terahertz frequency (THz), the vertical axis is the amplitude (dB), that is, the two-dimensional set obtained by the extraction at the ith time is PiThen P isi＝{(f1,β1),(f2,β2),...,(fm,βm) In which fmIs the m-th absorption peak, β, extractedmIs the confidence corresponding to the mth absorption peak. Let PWP is the set of all the absorption peaks extracted from the substance to be measuredW＝P1+P2+P3...+Pn。
It is assumed that in a one-dimensional coordinate system space where only gravity exists, each absorption peak is an object, the position of the absorption peak on the one-dimensional coordinate axis is the frequency f thereof, and the mass is the confidence degree β thereof. The calculation formula of the magnitude of the gravity is set as
Wherein F is the size of gravity, F1、f2Respectively the frequency of the two absorption peaks, r the frequency distance between the two absorption peaks, and y (r) is a given function of the frequency distance r, monotonically decreasing.
Specifically, first, one frequency is set as a standard frequency f0Is respectively placed at each point of one-dimensional coordinate axis (resolution is f)r0.0019THz), calculating the resultant force received by the sensor to obtain a resultant force curve F of the attraction forceG＝fG(f) (ii) a Then, normalization processing is carried out on the resultant force of the gravitation in the gravitation curve, and interference is removed through wavelet denoising and filtering; then, all the wave peak points and wave valley points of the gravitational resultant force curve are found out in a traversing way, and then whether each wave peak point meets the condition or not is judged by utilizing the integral waveform fitting method in the step three, and the condition is not met and discarded.
Let the obtained characteristic absorption peak set be PZ，PZ＝{f1,f2...,fmIn which fmIs the mth characteristic absorption peak obtained by the method, and the final fitting interval in the third step is [ fleft,fright]，ym、yleft、yrightThe amplitudes of the corresponding points are respectively, and the gravity of the absorption peak at the normalized gravity curve is Fm. The hydrogen peroxide attraction curve is shown in fig. 3, the horizontal axis is the terahertz wave frequency (THz), the vertical axis is the normalized attraction magnitude, and the peak marked by the circle is the characteristic absorption peak. Confidence degree beta of mth characteristic absorption peakmThe calculation is as follows:
βm＝Fm·g(min(ym-yleft,ym-yright))
where g (-) is a given attenuation coefficient function, monotonically decreasing, βmConfidence of the m characteristic absorption peak, FmTo absorb the magnitude of the peak's gravitational force at the normalized gravitational curve, ym、yleft、yrightRespectively, the amplitudes of the corresponding points in the fitting interval. Finally obtaining a characteristic absorption peak data set P of the substance to be detectedfinal：
Pfinal＝{(f1,β1),(f2,β2),...,(fm,βm)}
The extracted characteristic absorption peaks are then plotted on the original spectral curve, as shown in fig. 4, and it can be seen that the method can effectively extract a common absorption peak (i.e., a common absorption peak) in a plurality of spectral curves.
Further, before the step S103 of obtaining the standard characteristic absorption peak data set of at least one standard substance possibly containing the substance to be tested from the spectrum database, the method may further include: extracting absorption peaks of terahertz spectrum curves obtained by measuring a plurality of standard substances at a single time; repeating the multiple measurements, extracting the common absorption peak in the multiple measurements as the standard characteristic absorption peak of the plurality of standard substances through a gravity algorithm, calculating the confidence coefficient of each standard characteristic absorption peak, obtaining the data set of the standard characteristic absorption peaks of the plurality of standard substances, and storing the data set into a spectrum database.
It should be noted that the process of obtaining the standard characteristic absorption peak data set in the spectrum database is substantially the same as that of steps S101 to S102, that is, terahertz spectrum curve data of a plurality of standard substances can be measured in advance by the feature extraction method of steps S101 to S102 of the present invention, and the standard characteristic absorption peak data thereof is extracted and stored in the spectrum database, and the specific process is not described herein again.
In specific implementation, h standard substances possibly containing the substances to be detected can be selected from a spectrum database according to physical properties, and characteristic absorption peak data sets of the standard substances are obtained and respectively recorded as
Further, in step S104, the feature absorption peak data set of the substance to be detected and the standard feature absorption peak data set of the standard substance are matched through an inverse gravity algorithm, and the similarity between the substance to be detected and the standard substance is calculated, which may specifically include the following steps:
matching a standard characteristic absorption peak data set of a possible standard substance with a characteristic absorption peak of a substance to be detected by using an inverse gravitation algorithm; the specific algorithm for the inverse gravity is described as follows:
data set of standard characteristic absorption peak
Each absorption peak in (1)
Sequentially at each absorption peak frequency
Is a midpoint, and the frequency range is fixed
(e.g. using
) The amplitude range is fixed to be 0,100%]Establishing a two-dimensional window, and recording the two-dimensional window formed by the jth standard characteristic absorption peak as
Then there is
In addition, the set of absorption peaks of the substance to be measured in the two-dimensional window can be
Note WjEach element (f) ofj,βj) Let us mean the variance s2The calculation formula is as follows:
where D (x) is the variance of all data in x, and y (r) is a given function with respect to the frequency distance r, monotonically decreasing, as with y (r) in step S102. s2The attenuation coefficient α is obtained by functional mapping, i.e.
α＝t(s2)
Wherein t(s)2) Is about s2A given function that monotonically increases.
Then at WjFind such an element within:
matching coefficient C of jth characteristic absorption peakMjThe calculation is as follows:
where z (r) is similar to y (r), and is also monotonically decreasing given a function of frequency distance r.
And (3) weighted averaging of the matching coefficients of all the characteristic absorption peaks to obtain the similarity between the substance and the substance to be detected:
where k is the number of characteristic absorption peaks for the standard.
Finally, repeating the steps until all possible standard substances are compared, and recording the similarity of the ith possible substance as similarityiJudging whether the following inequality is true:
similaritymax＝max(similarity1,similarity2,...,similarityi)＞Tsim
wherein, Tsim(e.g. T)sim60% or more) is set as the similarity threshold. When the inequality is satisfied, among the possible standard substances, there is a substance suspected of being a substance to be measured, and the substance to be measured is considered to be the substance responsible for similarityi＝similaritymaxA substance that is established; if the inequality is not true, the possible standard substances are considered to be free of the substance to be detected. That is, if the maximum value among the calculated plurality of similarities is greater than or equal to the set similarity threshold TsimIf so, the standard substance contains the substance of the substance to be detected; if the maximum value of the calculated multiple similarity is less than the set similarity threshold value TsimAnd if the standard substance is not the substance to be detected.
Based on the same inventive concept, embodiments of the present invention further provide a substance identification device, and as the principle of solving the problem of the substance identification device is similar to that of the aforementioned substance identification method based on the terahertz spectrum, the implementation of the substance identification device can refer to the implementation of the substance identification method based on the terahertz spectrum, and repeated details are omitted.
In specific implementation, the substance identification device provided in the embodiment of the present invention, as shown in fig. 5, specifically includes:
the absorption peak extraction module 11 is used for extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time;
the confidence coefficient calculation module 12 is used for repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
a data set acquisition module 13, configured to acquire a standard characteristic absorption peak data set of at least one standard substance that may include a substance to be detected from a spectrum database;
the data set matching module 14 is used for matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity between the substance to be detected and the standard substance;
and the substance identification module 15 is used for comparing the calculated similarity with a set similarity threshold value and identifying the substance to be detected according to the comparison result.
In the substance identification device provided by the embodiment of the invention, through the interaction of the five modules, the influence of amplitude fluctuation on feature extraction can be effectively avoided, the terahertz spectrum identification technology can be effectively applied to various environmental conditions and physical parameters of substances, and the identification rate of terahertz spectrum substance identification is improved.
For more specific working processes of the modules, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Correspondingly, the embodiment of the invention also discloses a substance identification device, which comprises a processor and a memory; wherein the processor implements the terahertz spectrum based substance identification method disclosed in the foregoing embodiments when executing the computer program stored in the memory.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Further, the present invention also discloses a computer readable storage medium for storing a computer program; the computer program is executed by a processor to realize the terahertz spectrum-based substance identification method disclosed in the foregoing.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device, the equipment and the storage medium disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The embodiment of the invention provides a substance identification method, a substance identification device, substance identification equipment and a storage medium based on terahertz spectrum, wherein the method comprises the following steps: extracting an absorption peak of a terahertz spectrum curve measured by a substance to be detected at a single time; repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set; acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing a substance to be detected from a spectral database; matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity between the substance to be detected and the standard substance; and comparing the calculated similarity with a set similarity threshold, and identifying the substance to be detected according to the comparison result. The terahertz spectrum identification method has the advantages that multiple times of measurement are repeated, the characteristic absorption peak is extracted through the gravity algorithm, the confidence coefficient is calculated, the characteristic absorption peak and the confidence coefficient are combined into the characteristic absorption peak data set, identification is completed through matching of the characteristic absorption peak data set, only the amplitude is used for calculating auxiliary parameters such as the confidence coefficient in the whole process, the influence of amplitude fluctuation on characteristic extraction can be effectively avoided, the terahertz spectrum identification technology can be effectively applied to various environmental conditions and physical parameters of substances, and the identification rate of terahertz spectrum substance identification is improved.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The method, the device, the apparatus and the storage medium for identifying a substance based on terahertz spectrum provided by the present invention are described in detail above, and a specific example is applied in the present document to illustrate the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (6)
1. A substance identification method based on terahertz spectrum is characterized by comprising the following steps:
preprocessing a terahertz spectrum curve measured by a substance to be measured at a single time, and finding the positions of a plurality of absorption peaks through monotonicity;
removing the interference part with dense wave peak points and wave valley points in the terahertz spectrum curve by using a window sliding method;
by intercepting valley points around a peak point as a fitting interval, fitting and judging whether the slope of the peak point exceeds a slope threshold value;
if so, removing the peak point; if not, the peak point is reserved;
circularly expanding the interval of each absorption peak through a peak interval expansion algorithm, calculating the confidence coefficient of each absorption peak, and reserving the absorption peak corresponding to the confidence coefficient which is greater than a set confidence coefficient threshold;
repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing the substance to be detected from a spectral database;
matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm, and calculating the similarity of the substance to be detected and the standard substance;
and comparing the calculated similarity with a set similarity threshold, and identifying the substance to be detected according to the comparison result.
2. The terahertz spectrum-based substance identification method as claimed in claim 1, wherein an absorption peak common to a plurality of measurements is extracted as a characteristic absorption peak of the substance to be detected by a gravity algorithm, and specifically comprises:
in a one-dimensional coordinate system space only with gravitation, each absorption peak is regarded as an object, the position of the absorption peak on a one-dimensional coordinate axis is the frequency of the absorption peak, and the mass is the confidence coefficient of the absorption peak;
respectively placing absorption peaks with fixed frequency and confidence at each point of a one-dimensional coordinate axis, and calculating the resultant force of the absorption peaks to obtain a resultant force curve of the attraction;
and extracting a proper maximum value point on the gravitational resultant curve to serve as a characteristic absorption peak of the substance to be detected.
3. The method for identifying a substance based on terahertz spectrum according to claim 1, further comprising, before acquiring a standard characteristic absorption peak data set of at least one standard substance possibly containing the substance to be detected from a spectrum database, the following steps:
extracting absorption peaks of terahertz spectrum curves obtained by measuring a plurality of standard substances at a single time;
repeating the multiple measurements, extracting the common absorption peak in the multiple measurements as the standard characteristic absorption peak of the plurality of standard substances through a gravity algorithm, calculating the confidence coefficient of each standard characteristic absorption peak, obtaining the data set of the standard characteristic absorption peaks of the plurality of standard substances, and storing the data set into a spectrum database.
4. A substance identification device based on terahertz spectroscopy, comprising:
the absorption peak extraction module is used for preprocessing a terahertz spectrum curve measured by a substance to be detected at a single time and finding the positions of a plurality of absorption peaks through monotonicity; removing the interference part with dense wave peak points and wave valley points in the terahertz spectrum curve by using a window sliding method; by intercepting valley points around a peak point as a fitting interval, fitting and judging whether the slope of the peak point exceeds a slope threshold value; if so, removing the peak point; if not, the peak point is reserved; circularly expanding the interval of each absorption peak through a peak interval expansion algorithm, calculating the confidence coefficient of each absorption peak, and reserving the absorption peak corresponding to the confidence coefficient which is greater than a set confidence coefficient threshold;
the confidence coefficient calculation module is used for repeating multiple measurements, extracting an absorption peak common to the multiple measurements as a characteristic absorption peak of the substance to be detected through a gravity algorithm, and calculating the confidence coefficient of each characteristic absorption peak to obtain a characteristic absorption peak data set;
a data set acquisition module for acquiring a data set of standard characteristic absorption peaks of at least one standard substance possibly containing the substance to be detected from a spectral database;
the data set matching module is used for matching the characteristic absorption peak data set of the substance to be detected and the standard characteristic absorption peak data set of the standard substance through an inverse gravitation algorithm and calculating the similarity of the substance to be detected and the standard substance;
and the substance identification module is used for comparing the calculated similarity with a set similarity threshold value and identifying the substance to be detected according to the comparison result.
5. A terahertz spectrum-based substance identification apparatus comprising a processor and a memory, wherein the processor implements the terahertz spectrum-based substance identification method according to any one of claims 1 to 3 when executing a computer program stored in the memory.
6. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the method for substance identification based on terahertz spectroscopy of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810628198.6A CN108827904B (en) | 2018-06-19 | 2018-06-19 | Substance identification method, device and equipment based on terahertz spectrum and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810628198.6A CN108827904B (en) | 2018-06-19 | 2018-06-19 | Substance identification method, device and equipment based on terahertz spectrum and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108827904A CN108827904A (en) | 2018-11-16 |
| CN108827904B true CN108827904B (en) | 2021-01-26 |
Family
ID=64142712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810628198.6A Active CN108827904B (en) | 2018-06-19 | 2018-06-19 | Substance identification method, device and equipment based on terahertz spectrum and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108827904B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110068544B (en) * | 2019-05-08 | 2021-09-17 | 广东工业大学 | Substance identification network model training method and terahertz spectrum substance identification method |
| CN110532308B (en) * | 2019-07-11 | 2024-01-02 | 北京嘉元文博科技有限公司 | Cultural relic substance identification method and device and computer readable storage medium |
| CN113607680B (en) * | 2021-08-11 | 2023-05-26 | 江门市华讯方舟科技有限公司 | Method for detecting methionine content |
| CN113670848B (en) * | 2021-08-23 | 2022-08-02 | 中国人民解放军军事科学院国防科技创新研究院 | High-resolution broadband terahertz detector based on pixelized structure and detection method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128035A (en) * | 2007-11-20 | 2009-06-11 | Nippon Telegr & Teleph Corp <Ntt> | Spectrum analysis method and program |
| CN103020959A (en) * | 2012-11-24 | 2013-04-03 | 中国科学院地理科学与资源研究所 | Gravity model-based oceanic front information extraction method |
| CN104266993A (en) * | 2014-08-28 | 2015-01-07 | 北京环境特性研究所 | Article characteristic extraction method and device based on terahertz frequency band |
| CN104713845A (en) * | 2015-03-25 | 2015-06-17 | 西安应用光学研究所 | Mixture component identification method based on terahertz absorption spectrum processing |
| CN105279379A (en) * | 2015-10-28 | 2016-01-27 | 昆明理工大学 | Terahertz spectroscopy feature extraction method based on convex combination kernel function principal component analysis |
| CN105303585A (en) * | 2015-09-29 | 2016-02-03 | 燕山大学 | Rapid target tracking method and device |
| CN105512675A (en) * | 2015-11-27 | 2016-04-20 | 中国石油大学(华东) | Memory multi-point crossover gravitational search-based feature selection method |
| CN106645014A (en) * | 2016-09-23 | 2017-05-10 | 上海理工大学 | Terahertz spectroscopy based material recognition method |
| CN106952315A (en) * | 2017-03-22 | 2017-07-14 | 广东工业大学 | A kind of method that image quick reconfiguration is carried out to Terahertz complex-valued data based on BFGS |
-
2018
- 2018-06-19 CN CN201810628198.6A patent/CN108827904B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128035A (en) * | 2007-11-20 | 2009-06-11 | Nippon Telegr & Teleph Corp <Ntt> | Spectrum analysis method and program |
| CN103020959A (en) * | 2012-11-24 | 2013-04-03 | 中国科学院地理科学与资源研究所 | Gravity model-based oceanic front information extraction method |
| CN104266993A (en) * | 2014-08-28 | 2015-01-07 | 北京环境特性研究所 | Article characteristic extraction method and device based on terahertz frequency band |
| CN104713845A (en) * | 2015-03-25 | 2015-06-17 | 西安应用光学研究所 | Mixture component identification method based on terahertz absorption spectrum processing |
| CN105303585A (en) * | 2015-09-29 | 2016-02-03 | 燕山大学 | Rapid target tracking method and device |
| CN105279379A (en) * | 2015-10-28 | 2016-01-27 | 昆明理工大学 | Terahertz spectroscopy feature extraction method based on convex combination kernel function principal component analysis |
| CN105512675A (en) * | 2015-11-27 | 2016-04-20 | 中国石油大学(华东) | Memory multi-point crossover gravitational search-based feature selection method |
| CN106645014A (en) * | 2016-09-23 | 2017-05-10 | 上海理工大学 | Terahertz spectroscopy based material recognition method |
| CN106952315A (en) * | 2017-03-22 | 2017-07-14 | 广东工业大学 | A kind of method that image quick reconfiguration is carried out to Terahertz complex-valued data based on BFGS |
Non-Patent Citations (8)
| Title |
|---|
| Identification and quantitative analysis of chemical compounds based on multiscale linear fitting of terahertz spectra;Lingbo Qiao et al.;《Optical Engineering》;20140731;第53卷(第07期);第074102-1-074102-8页 * |
| Terahertz Image Segmentation Based on K-Harmonic-Means Clustering and Statistical Feature Extraction Modeling;Mohamed Walid Ayech;《21st International Conference on Pattern Recognition》;20121115;第222-225页 * |
| Terahertz reflective spectroscopy;Liangliang Zhang;《Proc. of SPIE》;20111231;第8195卷;第819502-1-819502-8页 * |
| 一种基于置信度的动态特征提取算法;温涛;《电力自动化设备》;20010331;第21卷(第03期);第23-26页 * |
| 基于几何代数的太赫兹时域光谱信号分析及物质识别方法研究;李静;《万方学位论文》;20120929;全文 * |
| 基于深层信念网络的太赫兹光谱识别;马 帅;《光谱学与光谱分析》;20151231;第35卷(第12期);第3325-3329页 * |
| 太赫兹频段微动特征边缘检测及提取方法;田坤;《电子科技大学学报》;20180131;第47卷(第01期);第19-36页 * |
| 核优化相关向量机太赫兹频谱特征提取方法;钟毅伟;《光谱学与光谱分析》;20161231;第36卷(第12期);第3857-3862页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108827904A (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108827904B (en) | Substance identification method, device and equipment based on terahertz spectrum and storage medium | |
| US11493447B2 (en) | Method for removing background from spectrogram, method of identifying substances through Raman spectrogram, and electronic apparatus | |
| CN107818298B (en) | General Raman spectrum feature extraction method for machine learning substance identification algorithm | |
| CN107219188B (en) | A method of based on the near-infrared spectrum analysis textile cotton content for improving DBN | |
| CN110068544B (en) | Substance identification network model training method and terahertz spectrum substance identification method | |
| CN107179310B (en) | Raman spectrum characteristic peak recognition methods based on robust noise variance evaluation | |
| JP5623061B2 (en) | Inspection apparatus and inspection method | |
| CN113139610A (en) | Abnormity detection method and device for transformer monitoring data | |
| CN109709062B (en) | Substance identification method and device and computer readable storage medium | |
| CN109374568B (en) | Sample identification method using terahertz time-domain spectroscopy | |
| Kuzmiakova et al. | An automated baseline correction protocol for infrared spectra of atmospheric aerosols collected on polytetrafluoroethylene (Teflon) filters | |
| US8954286B2 (en) | Method and device for measuring electromagnetic wave | |
| CN110599425A (en) | Wavelet parameter selection method suitable for ACFM signal wavelet denoising | |
| CN108195817B (en) | Raman spectrum detection method for removing solvent interference | |
| Zhuang et al. | Rapid determination of green tea origins by near-infrared spectroscopy and multi-wavelength statistical discriminant analysis | |
| CN107239768A (en) | A kind of high spectrum image object detection method based on tensor principal component analysis dimensionality reduction | |
| CN102542284B (en) | Method for identifying spectrum | |
| CN106970042B (en) | Method for detecting impurity and moisture content of carrageenin | |
| CN109670531A (en) | A kind of denoising method of the near infrared light spectrum signal based on Hodrick-Prescott filter | |
| CN108241846B (en) | Method for identifying Raman spectrogram | |
| CN113252641B (en) | Substance identification method based on residual analysis under Raman spectrum | |
| CN115015120A (en) | Fourier infrared spectrometer and temperature drift online correction method thereof | |
| Yiming et al. | Research on iris recognition algorithm based on hough transform | |
| CN111222455B (en) | Wavelength selection method and device, computing equipment and computer storage medium | |
| CN116796262A (en) | Vine tea grade discriminating method, device and equipment based on near infrared spectrum data |
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 |