CN115905881B - Yellow pearl classification method and device, electronic equipment and storage medium - Google Patents
Yellow pearl classification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115905881B CN115905881B CN202211219593.1A CN202211219593A CN115905881B CN 115905881 B CN115905881 B CN 115905881B CN 202211219593 A CN202211219593 A CN 202211219593A CN 115905881 B CN115905881 B CN 115905881B
- Authority
- CN
- China
- Prior art keywords
- yellow
- data
- pearl
- nanyang
- pearls
- 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
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Abstract
The application discloses a yellow pearl classification method and device, electronic equipment and storage medium. The method comprises the steps of obtaining yellow pearl data to be processed; obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearls of south ocean and sample data of dyed yellow pearls of south ocean; and obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result. The application solves the technical problem of distinguishing and classifying whether the yellow pearl is natural or dyed. In addition, the application also provides a jewelry detection method.
Description
Technical Field
The application relates to the field of jewelry identification, in particular to a method and a device for classifying yellow pearls, electronic equipment and a storage medium.
Background
Yellow pearl of Nanyang: yellow seawater pearls, one of the south ocean pearls, are produced from white or gold lipshells (big pearl shell), the main production areas of both shells being in northern australia, indonesia, philippines, maine, japan and thailand sand Mei Dao and china.
Dyeing yellow pearl: the non-yellow, pale yellow pearl is colored by an organic dye to appear as a yellow pearl.
The research on the color of the yellow pearl in the related art is still in the characterization of the phenomenon, namely, whether the color of the yellow pearl is dyed or not is judged by comparing the test of the yellow pearl which is known to be undyed and dyed, and further summarizing the difference of the characterization.
Aiming at the problem of distinguishing and classifying whether the yellow pearl is natural or dyed in the related art, no effective solution is proposed at present.
Disclosure of Invention
The application mainly aims to provide a method and a device for classifying yellow pearls, electronic equipment and a storage medium, so as to solve the problem of distinguishing and classifying whether the yellow pearls are natural or dyed.
In order to achieve the above object, according to one aspect of the present application, there is provided a method of classifying yellow pearls.
The method for classifying the yellow pearls according to the present application comprises:
obtaining yellow pearl data to be treated;
obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearls of south ocean and sample data of dyed yellow pearls of south ocean;
And obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result.
In some embodiments, the sample data of the south ocean natural yellow pearl comprises at least uv-vis spectrum data of the south ocean natural yellow pearl, and the sample data of the south ocean colored yellow pearl comprises at least uv-vis spectrum data of the south ocean colored yellow pearl.
In some embodiments, the pre-trained discriminant model comprises:
the similarity calculation result of the ultraviolet-visible spectrum data, the difference traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls, and the correlation coefficient calculation result of the correlation between the patterns of the Nanyang natural yellow pearls and the standard patterns respectively;
and determining a calculation method corresponding to the weight with the highest recognition confidence according to the calculation result, and obtaining a criterion for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl.
In some embodiments, the pre-trained discriminant model further comprises:
obtaining a similarity calculation result of the ultraviolet-visible spectrum data by calculating the similarity between the Nanyang natural yellow pearl sample data and the Nanyang dyed yellow pearl sample data;
Obtaining a differential traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls by traversing the peak position characteristics of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls;
obtaining a correlation coefficient calculation result of the correlation between the pattern of the Nanyang natural yellow pearl and the pattern of the Nanyang dyed yellow pearl by calculating the correlation between the pattern of the Nanyang natural yellow pearl sample data and the pattern of the Nanyang dyed yellow pearl sample data and a preset standard pattern respectively;
and determining a standard for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl based on the similarity calculation result, the difference traversal calculation result and the correlation coefficient calculation result.
In some embodiments, the standard profile is obtained by:
the sample data of the Nanyang natural yellow pearls and the discrete data files of the sample data of the Nanyang dyed yellow pearls are selected in advance to be a typical map data as a unified standard;
and carrying out unified processing on the rest other sample data according to the unified standard.
In order to achieve the above object, according to another aspect of the present application, there is provided a jewelry inspection method.
The jewelry inspection method according to the present application comprises: obtaining the classification of the yellow pearls by adopting the yellow pearl classification method for unknown samples;
outputting classification results of any one of the yellow pearls to be further tested;
and jewelry detection is carried out according to the classification result.
In some embodiments, the method further comprises:
obtaining the classification of the yellow pearls by adopting the yellow pearl classification method to the sample of the yellow pearls which is unknown whether to be filled with organic matters;
outputting the classification result of any one of the yellow pearl which is treated by organic matters and non-organic matters and needs to be further tested;
and jewelry detection is carried out according to the classification result.
In order to achieve the above object, according to another aspect of the present application, there is provided a yellow pearl classifying device.
The yellow pearl classifying device according to the present application comprises:
the acquisition module is used for acquiring yellow pearl data to be processed;
the judging module is used for obtaining a judging result in the yellow pearl data to be processed through a pre-trained judging model, wherein the judging model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of Nanyang natural yellow pearls and sample data of Nanyang dyed yellow pearls;
And the classification module is used for obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result.
According to a further aspect of the application there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
In order to achieve the above object, according to a further aspect of the present application, there is also provided a storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
In the embodiment of the application, the discrimination result in the yellow pearl data to be processed is obtained by adopting a mode of obtaining the yellow pearl data to be processed through a discrimination model trained in advance, and the aim of obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result is fulfilled, so that the technical effect of automatically and accurately classifying the yellow pearls with different qualities is realized, and the technical problem of distinguishing and classifying whether the yellow pearls are natural or dyed is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application. In the drawings:
FIG. 1 is a flow chart of a method for sorting yellow pearls according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a yellow pearl classifying device according to an embodiment of the present application;
FIG. 3 is a schematic diagram of the measurement results using an ultraviolet-visible spectrometer in the method of classifying yellow pearls according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present application and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present application will be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, the terms "mounted," "configured," "provided," "connected," "coupled," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.
The inventors have found that some effort has been made to identify the colour of yellow pearls by the above-described non-destructive analysis means (Elen, 2003; saber et al 2008; chen Yo et al 2009; lanyan et al 2010; zhang Xiangjun et al 2010; hu Yang et al 2014; zhou Dan and Li Liping, 2014; guo Qian and Xu Zhi, 2015). Guo Qian and Xu Zhi (2015) adopt ultraviolet-visible spectrum to consider that the main absorption peak of the natural gold pearl is 350-360 nm, while the dyed gold pearl has obvious spectrum peak of 410-450 nm; the natural gold pearl can be obtained at 275cm by Raman spectrum method -1 The obvious characteristic peak, the spectral peak at 376nm is centered at 472nm, and the spectral peak at 436nm when the dyed pearl is excited by light at 372 nm. Zhou Dan and Li Liping (2014) test seawater yellow pearls before and after dyeing by adopting Raman spectrum, mainly show Raman peak positions of carbonate, and cannot distinguish dyed from non-dyed yellow pearls.
The former uses spectrum method to distinguish pearl from shell and divide gloss, and some harvest is achieved. Yan Jun in the patent CN104181120B, the method for identifying the pearl powder and the shell powder based on the infrared spectrum and whiteness test combined technology is based on the basis of the out-of-plane bending vibration v 2 characteristic absorption peak position of CO 32-ions of biogenic aragonite calcium carbonate and the difference of organic matter content in hyriopsis cumingii pearls and shells, mainly utilizes the difference spectral lines displayed by different molecular structures in the infrared spectrums of the fresh water pearls and the hyriopsis cumingii, can provide laboratory detection basis for identifying the true and false pearl powder, and has important practical significance for promoting sustainable healthy development of the economy of the pearl powder processing industry and normalizing benign competition of the pearl powder industry. Peng Jie et al (2019) disclose a method for detecting pearl luster based on visible light spectrum, comprising obtaining a pearl sample set; randomly measuring visible light spectrum data of the surface of each pearl in the pearl sample set to obtain visible light spectrum data sets of all pearls in the pearl sample set; and testing the test feature vector set by adopting a pearl level identification model to obtain the gloss level of the pearl sample corresponding to the test feature vector set.
At present, the field of yellow pearl color detection does not have automatic detection equipment or intelligent judging software. The detection laboratory mainly relies on the test and the like, a large number of jewelry specialists are required to carry out the detection, the identification parameters are difficult to quantify, the degree of automation is low, and the detection efficiency of the yellow pearl is affected. The method utilizes the computer language to make the Nanyang yellow pearl detection process into the computer language, not only provides scientific reference basis for intelligent identification of the yellow pearl, but also has important practical significance for reducing the error rate of manual detection and improving the circulation supervision capability of the yellow pearl.
The study on the color of yellow pearls is still in the characterization of the phenomenon, namely by comparing the test of known undyed, dyed yellow pearls, and further summarizing the judgment of whether the characterization difference gives a dyeing or not. And partial reasons which can influence the color change of the pearl are found out through amplification, spectroscopy, physics and chemistry methods, for example, the content of various metal elements in the pearl layer is related to the color of the pearl layer, for example, the coloring elements of yellow pearls tend to be related to Cu and Fe elements. The metal ions in the center of metalloporphyrin are different in size, so that the plane of the porphyrin ring structure is distorted, thereby causing various colors of pearls, and Cu, fe, mg, mn is a metal complex of a metalloporphyrin compound with common colors, and yellow pearls are related to copper porphyrin and zinc porphyrin. A great deal of researches show that the color dyeing treatment of the yellow gold pearls can lead to the deviation of absorption peak positions, and the adoption of optical spectral lines has certain feasibility for distinguishing the pearl colors and the freshwater pearls from the mother pearls.
But also found problems to be solved. The conventional amplified observation and identification method can intuitively reflect the appearance morphological characteristics of the gold pearls, but the characteristics of the dyed gold pearls are not displayed on each dyed gold pearl. Conventional infrared spectrum and Raman spectrum tests show that the method has no great effect on the identification of the dyed yellow pearl, and the reason is that the dye of the pearl does not enter the crystal lattice of the pearl and does not influence the crystal structure of the pearl, so that the identification of the dyed pearl cannot be carried out through infrared and Raman spectra. Ultraviolet-visible absorption spectrometry is often used as an identification means for distinguishing natural gold pearls from dyed gold pearls, but the absorption peak does not have a strict fixed peak position, but is characterized by a bulge with a strong half-width of an envelope line, and if the bulge is not compared with the bulge, the correct judgment is difficult to be given by direct artificial observation. Guo Qian and Xu Zhi (2015) consider that the test result of the ultraviolet-visible absorption spectrometry still has great identification significance, however, other factors should be considered when judging the spectrogram, and the intensity or the relative intensity of the natural pearl and the dyed pearl near 420nm can be quantitatively compared in the future to obtain more accurate judgment.
Based on the above shortcomings, the method in the embodiment of the application adopts ultraviolet-visible spectrum to analyze the yellow pearl in a specific place, reduces the research scope of the yellow pearl, provides more detailed implementation steps, and uses the method to language the computer by mathematical calculation, namely, the method is used as a computer readable storage medium or an electronic device.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
As shown in fig. 1, a method for classifying yellow pearls according to an embodiment of the present application includes the following steps S110 to S130:
step S110, obtaining the data of the yellow pearl to be processed.
It should be noted that here the detection step is performed instead of the training step. That is, in the actual detection, first, the yellow pearl data to be processed needs to be acquired. At this time, it is not known whether there is a natural yellow pearl of south ocean or a dyed yellow pearl of south ocean in the yellow pearl data to be treated, that is, it is necessary to classify the yellow pearl data to be treated.
Illustratively, the automatic identification of the natural yellow pearl in the south ocean and the dyed yellow pearl in the south ocean can be realized by inputting the discrete original data of the ultraviolet-visible spectrum.
Step S120, obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearl in south ocean and sample data of dyed yellow pearl in south ocean.
The discrimination results in the yellow pearl data to be processed are obtained through a discrimination model trained in advance, and it can be understood that the discrimination results are the classification of the yellow pearl data. The relevant standard obtained in the training stage is written into a computer program, and the judgment result can be directly output when the user uses the relevant standard.
Preferably, the sample data of the Nanyang natural yellow pearl at least comprises ultraviolet-visible spectrum data of the Nanyang natural yellow pearl, and the sample data of the Nanyang dyed yellow pearl at least comprises ultraviolet-visible spectrum data of the Nanyang dyed yellow pearl.
Further, the judging model is obtained through machine learning training by using multiple groups of data, and the judging model is obtained through supervised machine learning training according to a training set and a verification set. In training the model, each set of data in the plurality of sets of data includes: sample data of natural yellow pearl in south ocean and sample data of dyed yellow pearl in south ocean. That is, in the training phase, sample data of both the Nanyang natural yellow pearl and the Nanyang dyed yellow pearl are input into the model for training.
Illustratively, preparing a yellow pearl sample, cleaning the surface of the Nanyang yellow pearl sample, placing the Nanyang yellow pearl sample into an ultraviolet-visible spectrometer analysis bracket at normal temperature, randomly measuring data points of the sample as test signal data, collecting the sample signal data, and forming an editable discrete data file for storage. I.e. to the sample data.
The automatic detection of the color of the Nanyang yellow pearl belongs to the category of searching the similarity by using organic and inorganic spectrum data, and in an alternative implementation, a database spectrum similarity matching map can be established. Through many years of research, a large number of standard IR spectrograms have been accumulated, and on the basis of the accumulated IR spectrograms, a plurality of databases, such as a KnowItAll ultraviolet visible spectrum database, satler (Sadtler)Database, national institute of standards and technology (National Institute of Standards and Technology),Ultraviolet-visible spectrum library databases, and the like. And comparing the spectrum of the detected substance with the standard spectrum of the known substance in the material spectrum library to realize the identification of the substance type. However, such methods still have certain limitations, not only the positions and the numbers of the X-axis coordinate points need to be strictly unified, but also the situation that the peak shape of the same substance is greatly changed is difficult to deal with. The rack may be analyzed using an ultraviolet-visible spectrometer to collect sample data. For example, ultraviolet-visible spectrometers are used in setting up the test conditions. And adopting the transmittance to remove the background peak.
And step S130, obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result.
According to the discrimination result, the classification of the yellow pearls in the yellow pearl data can be obtained, namely, different yellow pearls are screened and classified by a standard method for judging the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls.
As a preference in this embodiment, the pre-trained discriminant model includes: the similarity calculation result of the ultraviolet-visible spectrum data, the difference traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls, and the correlation coefficient calculation result of the correlation between the patterns of the Nanyang natural yellow pearls and the standard patterns respectively; and determining a calculation method corresponding to the weight with the highest recognition confidence according to the calculation result, and obtaining a criterion for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl.
In specific implementation, the similarity calculation result of the ultraviolet-visible spectrum data includes:
the cosine similarity is adopted to distinguish the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl, the cosine value of the included angle in the cosine similarity calculation result is closer to 1, the higher the similarity is proved, and the name of the standard curve pointed by the value closest to 1 is used as the judging standard for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl.
The difference traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls comprises the following steps:
traversing peak position characteristics of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls by adopting a differential traversal method, selecting a calculation interval of 300-600 nm by adopting a traversal valley searching method, and calculating and comparing the peak and valley sizes of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls.
It is understood that peak searching matching is to find characteristic peak positions of infrared spectrum of a substance and match according to characteristic absorption peaks. At present, a peak searching and matching method is generally adopted in an infrared standard spectrum library of a Thermo Fisher infrared spectrometer, and the quality requirements of the method on the spectrum are high. Therefore, for the map data with poor quality, a series of calculation processes such as smoothing are needed to be performed on the original data, some fine characteristic peak positions with a discrimination basis can be lost in the process of processing, and a large number of maps cannot be identified or are erroneously identified. The mode of finding the peak position of the infrared spectrum characteristic of the substance is also adopted in the embodiment of the application, but the mode is not used only.
The calculation results of the correlation coefficients of the correlation between the patterns of the Nanyang natural yellow pearls and the patterns of the Nanyang dyed yellow pearls and the standard patterns respectively comprise:
And traversing the correlation between the standard patterns of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls and the comparison patterns by adopting a correlation coefficient method, wherein the correlation is close to the name of the standard curve pointed by the value of 1.
Further, according to the calculation result, determining a calculation method corresponding to the weight (calculation factor or specific gravity of each calculation method in the model) with the highest recognition confidence (highest recognition accuracy), and obtaining a criterion for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl. It should be noted that the discrimination criteria herein may be based on the ultraviolet-visible spectrum to automatically detect the natural yellow pearl in the south ocean and the dyed yellow pearl in the south ocean.
As a preference in this embodiment, the pre-trained discriminant model further comprises: obtaining a similarity calculation result of the ultraviolet-visible spectrum data by calculating the similarity between the Nanyang natural yellow pearl sample data and the Nanyang dyed yellow pearl sample data; obtaining a differential traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls by traversing the peak position characteristics of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls; obtaining a correlation coefficient calculation result of the correlation between the pattern of the Nanyang natural yellow pearl and the pattern of the Nanyang dyed yellow pearl by calculating the correlation between the pattern of the Nanyang natural yellow pearl sample data and the pattern of the Nanyang dyed yellow pearl sample data and a preset standard pattern respectively; and determining a standard for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl based on the similarity calculation result, the difference traversal calculation result and the correlation coefficient calculation result.
In specific implementation, the similarity calculation result of the ultraviolet-visible spectrum data is obtained by calculating the similarity between the Nanyang natural yellow pearl sample data and the Nanyang dyed yellow pearl sample data:
illustratively, the cosine similarity is used to distinguish between Nanyang natural yellow pearl and dyed yellow pearl, and the cosine similarity of the sample data is calculated using the following formula
Wherein the cos (θ) cosine value represents cosine similarity, a i And b i Representing the components of vectors a and b.
Then, the name of the pearl represented by the standard curve of the natural/dyed yellow pearl pointed by the value (1-0.9) of which the cosine value of the included angle is closest to 1 in the cosine similarity calculation result is used as a judgment conclusion for distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl. For example, the cosine similarity between the unknown spectral line and the natural yellow pearl standard curve SY-02 (shown in FIG. 3) is 0.98, and the result of the cosine similarity determination is Nanyang natural yellow pearl.
Obtaining a differential traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls by traversing the peak position characteristics of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls in the sample data:
Illustratively, a differential traversal method is used to obtain the Y-coordinate value of each spectral line, and the peak and trough of the spectral line are found by subtracting the previous value from the subsequent value. Traversing unknown pearl peak position characteristics, adopting a traversing valley searching method to find out a minimum value, selecting a calculation interval of 300-600nm, and judging that the index position of the minimum value is smaller than 400nm, namely the Nanyang natural yellow pearl.
Obtaining a correlation coefficient calculation result of the correlation between the pattern of the Nanyang natural yellow pearl and the pattern of the Nanyang dyed yellow pearl by calculating the correlation between the pattern of the Nanyang natural yellow pearl sample data and the pattern of the Nanyang dyed yellow pearl sample data and a preset standard pattern respectively:
illustratively, the correlation between the standard patterns (SY-02, D-FY-01 are shown in FIG. 3) and the contrast patterns of the Nanyang natural yellow pearl and the dyed yellow pearl is traversed by adopting a correlation coefficient method, and the correlation coefficient of the spectral line of the unknown sample and the spectral line of the natural yellow pearl SY-02 is 0.98, so that the unknown sample is the Nanyang natural yellow pearl.
And finally, determining a standard for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl based on the similarity calculation result, the difference traversal calculation result and the correlation coefficient calculation result.
As a preferable mode in this embodiment, the standard map is obtained by: the sample data of the Nanyang natural yellow pearls and the discrete data files of the sample data of the Nanyang dyed yellow pearls are selected in advance to be a typical map data as a unified standard; and carrying out unified processing on the rest other sample data according to the unified standard.
In the specific implementation, the sample signal data are subjected to the pre-treatment, a piece of typical map data is selected from discrete data files of the Nanyang natural yellow pearl and Nanyang dyed yellow pearl samples to serve as a standard, and the rest other data are subjected to the unified treatment according to the standard data, so that the wavelength data points of all the data are kept consistent.
In addition, in an embodiment of the present application, there is also provided a jewelry detection method including: obtaining the classification of the yellow pearls by adopting the yellow pearl classification method for unknown samples; outputting classification results of any one of the yellow pearls to be further tested; and jewelry detection is carried out according to the classification result.
According to the method for automatically detecting the Nanyang yellow pearls based on the infrared spectrum difference peak searching algorithm, the Nanyang yellow pearls, the multi-component Nanyang yellow pearls, the Nanyang yellow pearls and the organic matter-treated Nanyang yellow pearls can be automatically and effectively distinguished. The unknown sample is put into an infrared spectrum reflection bracket to derive discrete data, and a computer program gives the conclusions of 'Nanyang yellow pearl', 'needing further inspection', and can be imported into the existing jewelry detection system to be used as a jewelry detection method.
In some embodiments, the method further comprises: obtaining the classification of the yellow pearls by adopting the yellow pearl classification method to the sample of the yellow pearls which is unknown whether to be filled with organic matters; outputting the classification result of any one of the yellow pearl which is treated by organic matters and non-organic matters and needs to be further tested; and jewelry detection is carried out according to the classification result.
In specific implementation, the unknown southern American yellow pearl sample which is filled with the organic matters is put into an infrared spectrum transmission bracket to lead out discrete data, and a computer program gives conclusions of 'treatment', 'non-treatment', 'further inspection' and can be led into the existing jewelry detection system to further promote the intelligent development of jewelry detection, thereby being beneficial to the supervision of jewelry industry.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
There is also provided, in accordance with an embodiment of the present application, an apparatus for classifying yellow pearls for implementing the above method, as shown in fig. 2, the apparatus including:
An acquisition module 210, configured to acquire yellow pearl data to be processed;
the discriminating module 220 is configured to obtain a discriminating result in the yellow pearl data to be processed through a pre-trained discriminating model, where the discriminating model is obtained through machine learning training using multiple sets of data, and each set of data in the multiple sets of data includes: sample data of Nanyang natural yellow pearls and sample data of Nanyang dyed yellow pearls;
and the classification module 230 is configured to obtain classification of the yellow pearl in the yellow pearl data according to the discrimination result.
It should be noted that, in the acquiring module 210 according to the embodiment of the present application, the detecting step is performed instead of the training step. That is, in the actual detection, first, the yellow pearl data to be processed needs to be acquired. At this time, it is not known whether there is a natural yellow pearl of south ocean or a dyed yellow pearl of south ocean in the yellow pearl data to be treated, that is, it is necessary to classify the yellow pearl data to be treated.
Illustratively, the automatic identification of the natural yellow pearl in the south ocean and the dyed yellow pearl in the south ocean can be realized by inputting the discrete original data of the ultraviolet-visible spectrum.
The discrimination module 220 in the embodiment of the present application obtains the discrimination result in the yellow pearl data to be processed through a pre-trained discrimination model, and it can be understood that the discrimination result is the classification of the yellow pearl data.
Preferably, the sample data of the Nanyang natural yellow pearl at least comprises ultraviolet-visible spectrum data of the Nanyang natural yellow pearl, and the sample data of the Nanyang dyed yellow pearl at least comprises ultraviolet-visible spectrum data of the Nanyang dyed yellow pearl.
Further, the judging model is obtained through machine learning training by using multiple groups of data, and the judging model is obtained through supervised machine learning training according to a training set and a verification set. In training the model, each set of data in the plurality of sets of data includes: sample data of natural yellow pearl in south ocean and sample data of dyed yellow pearl in south ocean. That is, in the training phase, sample data of both the Nanyang natural yellow pearl and the Nanyang dyed yellow pearl are input into the model for training.
Illustratively, preparing a yellow pearl sample, cleaning the surface of the Nanyang yellow pearl sample, placing the Nanyang yellow pearl sample into an ultraviolet-visible spectrometer analysis bracket at normal temperature, randomly measuring data points of the sample as test signal data, collecting the sample signal data, and forming an editable discrete data file for storage. I.e. to the sample data.
The automatic detection of the color of the Nanyang yellow pearl belongs to the category of searching the similarity by using organic and inorganic spectrum data, and in an alternative implementation, a database spectrum similarity matching map can be established. Through years of research, a large number of standard IR spectrograms have been accumulated at present, and a plurality of databases are formed on the basis of the standard IR spectrograms, such as a KnowItAll ultraviolet visible spectrum database, a Sadtler (Sadtler) database, a national institute of standards and technology (National Institute of Standards and Technology) database, a database of,Ultraviolet-visible spectrum library databases, and the like. And comparing the spectrum of the detected substance with the standard spectrum of the known substance in the material spectrum library to realize the identification of the substance type. However, such methods still have certain limitations, not only the positions and the numbers of the X-axis coordinate points need to be strictly unified, but also the situation that the peak shape of the same substance is greatly changed is difficult to deal with. The rack may be analyzed using an ultraviolet-visible spectrometer to collect sample data. For example, when setting up test conditionsAn ultraviolet-visible spectrometer is used. And adopting the transmittance to remove the background peak.
According to the discrimination result, the classification module 230 of the embodiment of the present application can obtain the classification of the yellow pearl in the yellow pearl data, that is, the yellow pearls with different classifications are screened and classified by the standard method for determining the yellow pearls with natural yellow pearls in the south ocean and the yellow pearls with dyed south ocean.
It will be apparent to those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored in a memory device for execution by the computing devices, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
In order to better illustrate the yellow pearl classification method in the application, the implementation process specifically comprises the following steps:
and S1, debugging an ultraviolet-visible spectrometer, and deducting a background peak.
S2, cleaning the surfaces of a Nanyang natural yellow pearl sample and a dyed yellow pearl sample, adopting an ultraviolet-visible spectrometer to randomly and respectively measure data points of the samples as test signal data, collecting, adopting a transmittance mode to collect a spectrum, wherein the integration time is 100-200S, the collection interval is 200-1000nm, and an editable discrete data file is formed and stored to obtain a Nanyang natural yellow pearl sample set (500 spectrograms) and a dyed yellow pearl sample set (500 spectrograms); the sample sets are respectively prepared according to the proportion of 6:4 are randomly divided into training and testing sets.
Step S3, pre-processing is carried out on the sample signal data: and (3) selecting a piece of typical spectrum data from discrete data of the Nanyang natural yellow pearl sample and the dyed yellow pearl sample as a standard, selecting SY-02 in the graph 3 as a standard spectrum of the natural yellow pearl, selecting D-FY-01 in the graph 3 as a standard spectrum of the dyed yellow pearl, and carrying out unified treatment on the rest other data according to the standard respectively, so that the wavelength data points and the data length of all the data are consistent.
And S4, distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl by adopting cosine similarity, and calculating the cosine similarity of the sample data by adopting the following formula.
Wherein the cos (θ) cosine value represents cosine similarity, a i And b i Representing the components of vectors a and b.
S5, taking the pearl name represented by a natural/dyed yellow pearl standard curve pointed by a value (1-0.9) with the cosine value closest to 1 in the cosine similarity calculation result as a judgment conclusion for distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl; for example, the cosine similarity between the unknown spectral line and the natural yellow pearl standard curve SY-02 is 0.85 or 0.98, and the cosine similarity is further detected.
And S6, acquiring Y coordinate values of each spectral line by adopting a differential traversal method, and finding out peaks and troughs of the spectral lines by adopting a method of subtracting a previous value from a subsequent value. Traversing unknown pearl peak position characteristics, adopting a traversing valley searching method to find out a minimum value, selecting a calculation interval of 300-600nm, and judging that the index position of the minimum value is smaller than 400nm, namely the (Nanyang) natural yellow pearl. Meanwhile, the sizes of peaks and valleys are calculated and compared, and a judgment standard is written.
And S7, traversing the correlation between the standard patterns (SY-02 and D-FY-01) of the Nanyang natural yellow pearls and the dyed yellow pearls and the contrast patterns by adopting a correlation coefficient method, wherein the correlation coefficient between the spectral line of an unknown sample and the spectral line of the natural yellow pearls SY-02 is 0.98, 0.86 or 0.85, and the unknown sample is the (Nanyang) natural yellow pearls. At the same time, decision criteria are written.
And S8, continuously iterating cosine similarity results, difference traversal results and correlation coefficient results of hundred pieces of ultraviolet-visible spectrum data, searching a fixed weight parameter with the highest recognition accuracy by adjusting weight ratios occupied by the three methods, and obtaining the unknown sample which is (Nanyang) natural yellow pearl under the comprehensive weight ratio (2:7:1) with the highest recognition accuracy. While writing the decision program.
The computer language can be Python, C and the like, a discriminating program for detecting the Nanyang natural yellow pearl and the dyed yellow pearl is written, 40% of data in the test set is detected, and the detection result proves that the accuracy rate of the method for synthesizing the method based on cosine similarity, traversing valley searching and correlation coefficient by utilizing the ultraviolet-visible spectrum is more than 95%.
The method can automatically detect the Nanyang natural yellow pearl and Nanyang dyed yellow pearl based on ultraviolet-visible spectrum. By inputting the ultraviolet-visible spectrum discrete original data, the automatic identification of the natural yellow pearl and the Nanyang dyed yellow pearl can be realized.
An embodiment of the application also provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
Alternatively, in the present embodiment, the above-described storage medium may be configured to store a computer program for performing the steps of:
s1, obtaining yellow pearl data to be processed;
s2, obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearls of south ocean and sample data of dyed yellow pearls of south ocean;
and S3, obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
An embodiment of the application also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
s1, obtaining yellow pearl data to be processed;
s2, obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearls of south ocean and sample data of dyed yellow pearls of south ocean;
and S3, obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments and optional implementations, and this embodiment is not described herein.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method of sorting yellow pearls, the method comprising:
obtaining yellow pearl data to be treated;
obtaining a discrimination result in the yellow pearl data to be processed through a discrimination model trained in advance, wherein the discrimination model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of natural yellow pearls of south ocean and sample data of dyed yellow pearls of south ocean;
obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result;
the method for classifying the yellow pearls comprises the following specific implementation procedures:
step S1, debugging an ultraviolet-visible spectrometer and deducting a background peak;
s2, cleaning the surfaces of a Nanyang natural yellow pearl sample and a dyed yellow pearl sample, adopting an ultraviolet-visible spectrometer to randomly and respectively measure data points of the samples as test signal data, collecting, acquiring a graph in a transmittance mode, wherein the integration time is 100-200S, and the acquisition interval is 200-1000nm, so as to form an editable discrete data file for storage, and obtaining a Nanyang natural yellow pearl sample set and a dyed yellow pearl sample set; randomly dividing the sample set into a training set and a testing set according to the proportion;
Step S3, pre-processing is carried out on the sample signal data: respectively picking out a piece of typical map data from discrete data of the Nanyang natural yellow pearl sample and the dyed yellow pearl sample as a standard, and respectively carrying out unified processing on the rest other data according to the standard, so that wavelength data points and data lengths of all the data are consistent;
s4, distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl by adopting cosine similarity, and calculating the cosine similarity of sample data by adopting the following formula;
wherein the cos (θ) cosine value represents cosine similarity, a i And b i Representing the components of vectors a and b;
s5, taking the pearl name represented by the natural/dyed yellow pearl standard curve pointed by the value of the cosine value a closest to 1 of the included angle in the cosine similarity calculation result as a judgment conclusion for distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl;
step S6, a differential traversal method is adopted to obtain Y-coordinate values of each spectral line, and a method of subtracting a previous value from a subsequent value is adopted to find out peaks and troughs of the spectral lines; traversing unknown pearl peak position characteristics, adopting a traversing valley searching method to find out a minimum value, selecting a calculation interval of 300-600nm, and judging that the index position of the minimum value is smaller than 400nm, namely the Nanyang natural yellow pearl; meanwhile, calculating and comparing the sizes of peaks and valleys appearing on the two, and writing in a judgment standard;
And S7, traversing the correlation between the standard patterns and the contrast patterns of the Nanyang natural yellow pearls and the dyed yellow pearls by adopting a correlation coefficient method, and judging whether the unknown sample is the Nanyang natural yellow pearls.
2. The method of claim 1, wherein the sample data of the south ocean natural yellow pearl comprises at least uv-vis spectrum data of the south ocean natural yellow pearl, and wherein the sample data of the south ocean colored yellow pearl comprises at least uv-vis spectrum data of the south ocean colored yellow pearl.
3. The method of claim 2, wherein the pre-trained discriminant model comprises:
the similarity calculation result of the ultraviolet-visible spectrum data, the difference traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls, and the correlation coefficient calculation result of the correlation between the patterns of the Nanyang natural yellow pearls and the standard patterns respectively;
and determining a calculation method corresponding to the weight with the highest recognition confidence according to the calculation result, and obtaining a criterion for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl.
4. The method of claim 2, wherein the pre-trained discriminant model further comprises:
obtaining a similarity calculation result of the ultraviolet-visible spectrum data by calculating the similarity between the Nanyang natural yellow pearl sample data and the Nanyang dyed yellow pearl sample data;
obtaining a differential traversal calculation result of the peak position characteristics of the Nanyang natural yellow pearls and the peak position characteristics of the Nanyang dyed yellow pearls by traversing the peak position characteristics of the Nanyang natural yellow pearls and the Nanyang dyed yellow pearls;
obtaining a correlation coefficient calculation result of the correlation between the pattern of the Nanyang natural yellow pearl and the pattern of the Nanyang dyed yellow pearl by calculating the correlation between the pattern of the Nanyang natural yellow pearl sample data and the pattern of the Nanyang dyed yellow pearl sample data and a preset standard pattern respectively;
and determining a standard for distinguishing the Nanyang natural yellow pearl from the Nanyang dyed yellow pearl based on the similarity calculation result, the difference traversal calculation result and the correlation coefficient calculation result.
5. A method according to claim 3, wherein the standard profile is obtained by:
The sample data of the Nanyang natural yellow pearls and the discrete data files of the sample data of the Nanyang dyed yellow pearls are selected in advance to be a typical map data as a unified standard;
and carrying out unified processing on the rest other sample data according to the unified standard.
6. A jewelry inspection method, the jewelry inspection method comprising:
obtaining a classification of the yellow pearl by the method of classifying the yellow pearl according to any one of claims 1 to 5 for an unknown sample;
outputting classification results of any one of the yellow pearls to be further tested;
and jewelry detection is carried out according to the classification result.
7. The method of claim 6, wherein the method further comprises:
obtaining a classification of yellow pearls from a sample of yellow pearls of south ocean, unknown whether or not it has been subjected to organic filling, by the method of classification of yellow pearls according to any one of claims 1 to 5;
outputting the classification result of any one of the yellow pearl which is treated by organic matters and non-organic matters and needs to be further tested;
and jewelry detection is carried out according to the classification result.
8. A device for sorting yellow pearls, said device comprising:
The acquisition module is used for acquiring yellow pearl data to be processed;
the judging module is used for obtaining a judging result in the yellow pearl data to be processed through a pre-trained judging model, wherein the judging model is obtained through machine learning training by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: sample data of Nanyang natural yellow pearls and sample data of Nanyang dyed yellow pearls;
the classification module is used for obtaining the classification of the yellow pearls in the yellow pearl data according to the discrimination result;
the classification module is further configured to:
debugging an ultraviolet-visible spectrometer and deducting a background peak;
cleaning the surfaces of a Nanyang natural yellow pearl sample and a dyed yellow pearl sample, adopting data points of the ultraviolet-visible spectrometer to randomly and respectively measure the samples as test signal data, collecting, adopting a transmittance mode to collect a map, wherein the integration time is 100-200s, the collection interval is 200-1000nm, and forming an editable discrete data file for storage to obtain a Nanyang natural yellow pearl sample set and a dyed yellow pearl sample set; randomly dividing the sample set into a training set and a testing set according to the proportion;
Pre-processing sample signal data: respectively picking out a piece of typical map data from discrete data of the Nanyang natural yellow pearl sample and the dyed yellow pearl sample as a standard, and respectively carrying out unified processing on the rest other data according to the standard, so that wavelength data points and data lengths of all the data are consistent;
distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl by adopting cosine similarity, and calculating the cosine similarity of sample data by adopting the following formula;
wherein the cos (θ) cosine value represents cosine similarity, a i And b i Representing the components of vectors a and b;
the name of the pearl represented by the natural/dyed yellow pearl standard curve pointed by the value of the cosine value a closest to 1 of the included angle in the cosine similarity calculation result is used as a judgment conclusion for distinguishing the Nanyang natural yellow pearl from the dyed yellow pearl;
step S6, a differential traversal method is adopted to obtain Y-coordinate values of each spectral line, and a method of subtracting a previous value from a subsequent value is adopted to find out peaks and troughs of the spectral lines; traversing unknown pearl peak position characteristics, adopting a traversing valley searching method to find out a minimum value, selecting a calculation interval of 300-600nm, and judging that the index position of the minimum value is smaller than 400nm, namely the Nanyang natural yellow pearl; meanwhile, calculating and comparing the sizes of peaks and valleys appearing on the two, and writing in a judgment standard;
And traversing the correlation between the standard spectrum and the contrast spectrum of the Nanyang natural yellow pearl and the dyed yellow pearl by adopting a correlation coefficient method, and judging whether the unknown sample is the Nanyang natural yellow pearl.
9. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions which, when executed, cause the processor to perform the method of any of claims 1 to 5 and/or the method of claim 6.
10. A computer readable storage medium storing one or more programs, which when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the method of any of claims 1-5 and/or the method of claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219593.1A CN115905881B (en) | 2022-09-30 | 2022-09-30 | Yellow pearl classification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211219593.1A CN115905881B (en) | 2022-09-30 | 2022-09-30 | Yellow pearl classification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115905881A CN115905881A (en) | 2023-04-04 |
| CN115905881B true CN115905881B (en) | 2023-10-20 |
Family
ID=86477298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211219593.1A Active CN115905881B (en) | 2022-09-30 | 2022-09-30 | Yellow pearl classification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115905881B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117388249A (en) * | 2023-10-07 | 2024-01-12 | 国家珠宝玉石首饰检验集团有限公司 | Method and device for identifying luminous pearl |
| CN117405645B (en) * | 2023-12-14 | 2024-03-29 | 珠宝玉石首饰国检集团深圳研究所有限公司 | Qualitative detection method, device, storage medium and system for black butterfly shellfish pearls |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105866074A (en) * | 2016-05-26 | 2016-08-17 | 国土资源部珠宝玉石首饰管理中心深圳珠宝研究所 | Quick detection method and detection device of diamond luminescent spectrum |
| CN109709063A (en) * | 2019-02-14 | 2019-05-03 | 重庆市计量质量检测研究院 | Emerald identification method based on terahertz time-domain spectroscopic technology |
| CN110542659A (en) * | 2019-09-06 | 2019-12-06 | 四川大学 | pearl luster detection method based on visible light spectrum |
| CN111398208A (en) * | 2020-04-22 | 2020-07-10 | 谭贵平 | Method for rapidly identifying traditional art jadeite by utilizing near-infrared technology |
| CN113008865A (en) * | 2021-03-04 | 2021-06-22 | 北京华泰诺安探测技术有限公司 | Method, device, medium and equipment for identifying jewelry jade |
| CN113657240A (en) * | 2021-08-12 | 2021-11-16 | 浙江工业大学 | Unbalanced-like pearl classification method based on multi-view image amplification |
| CN115112598A (en) * | 2022-08-23 | 2022-09-27 | 国检中心深圳珠宝检验实验室有限公司 | Modeling method, model and detection method of automatic jade detection model |
-
2022
- 2022-09-30 CN CN202211219593.1A patent/CN115905881B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105866074A (en) * | 2016-05-26 | 2016-08-17 | 国土资源部珠宝玉石首饰管理中心深圳珠宝研究所 | Quick detection method and detection device of diamond luminescent spectrum |
| CN109709063A (en) * | 2019-02-14 | 2019-05-03 | 重庆市计量质量检测研究院 | Emerald identification method based on terahertz time-domain spectroscopic technology |
| CN110542659A (en) * | 2019-09-06 | 2019-12-06 | 四川大学 | pearl luster detection method based on visible light spectrum |
| CN111398208A (en) * | 2020-04-22 | 2020-07-10 | 谭贵平 | Method for rapidly identifying traditional art jadeite by utilizing near-infrared technology |
| CN113008865A (en) * | 2021-03-04 | 2021-06-22 | 北京华泰诺安探测技术有限公司 | Method, device, medium and equipment for identifying jewelry jade |
| CN113657240A (en) * | 2021-08-12 | 2021-11-16 | 浙江工业大学 | Unbalanced-like pearl classification method based on multi-view image amplification |
| CN115112598A (en) * | 2022-08-23 | 2022-09-27 | 国检中心深圳珠宝检验实验室有限公司 | Modeling method, model and detection method of automatic jade detection model |
Non-Patent Citations (1)
| Title |
|---|
| "基于多光谱数据分析的宝石种属自动鉴别算法及软件";顾浩;《万方平台》;第1-69页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115905881A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115905881B (en) | Yellow pearl classification method and device, electronic equipment and storage medium | |
| CN109142317B (en) | Raman spectrum substance identification method based on random forest model | |
| CN110717368A (en) | Qualitative classification method for textiles | |
| CN101692052B (en) | Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea | |
| WO2022116594A1 (en) | Fiber quality grade online test system and application thereof | |
| CN105043998B (en) | One kind differentiates the haploid method of corn | |
| CN103235095A (en) | Water-injected meat detection method and device | |
| CN108844917A (en) | A kind of Near Infrared Spectroscopy Data Analysis based on significance tests and Partial Least Squares | |
| CN111443043B (en) | Hyperspectral image-based walnut kernel quality detection method | |
| CN101738373A (en) | Method for distinguishing varieties of crop seeds | |
| CN103822897A (en) | White spirit appraising and source-tracing method based on infrared spectroscopy | |
| CN110749565A (en) | Method for rapidly identifying storage years of Pu' er tea | |
| CN111398233A (en) | Laser spectrum detection method for red wine quality | |
| CN111965167A (en) | Method and device for predicting element composition and calorific value of solid waste | |
| CN111523587A (en) | Woody plant species spectrum identification method based on machine learning | |
| CN105761272A (en) | Pure substance quantity determination method in imaging spectrum mixed pixels | |
| CN110887798B (en) | Nonlinear full-spectrum water turbidity quantitative analysis method based on extreme random tree | |
| CN116858822A (en) | Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum | |
| CN111398208A (en) | Method for rapidly identifying traditional art jadeite by utilizing near-infrared technology | |
| CN110231300A (en) | A kind of lossless method for quickly identifying true and false Aksu red fuji apple | |
| CN113642629B (en) | Visualization method and device for improving reliability of spectroscopy analysis based on random forest | |
| CN113744075A (en) | Agricultural product nutrition quality grade classification system based on artificial intelligence | |
| CN111693484A (en) | Sesame oil variety identification method based on terahertz time-domain spectroscopy | |
| CN113191618A (en) | Millet producing area tracing method based on mid-infrared spectrum technology and feature extraction | |
| Yang et al. | Nondestructive detection method of egg quality based on multi-sensor information fusion technology |
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 |