Micro-mark detection method and device for jade ware based on multi-modal data fusion

Abstract

The embodiment of the application provides a kind of based on multimodal data fusion's jade ware micro mark detection method and device, comprising: obtaining the image data of the measured jade ware and the material parameter of the measured jade ware;Based on the image data of the measured jade ware, the material parameter and the preset classification algorithm model, the measured jade ware is classified and detected, and classification detection result is obtained, the classification detection result includes the micro mark type, processing technology, raw material and abrasive component, raw material source and weathering degradation data of the measured jade ware;According to the micro mark type, processing technology, raw material and abrasive component, raw material source and weathering degradation data of the measured jade ware, the full life cycle of the measured jade ware is inversely constructed;The classification detection result and the full life cycle of the measured jade ware are output by preset visual mode.The micro mark category is distinguished in combination with image data and material data and other multimodal data, and the recognition accuracy of micro mark category is improved.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to a method and apparatus for detecting micro-traces in jade artifacts based on multimodal data fusion. Background Technology

[0002] Micro-marks on ancient jade artifacts include processing marks, usage marks, and weathering marks. These marks serve as an objective record of the entire lifecycle of jade artifacts, from processing and use to burial. Furthermore, the accurate identification and data analysis of these various micro-marks are crucial for researching the craftsmanship, functional reconstruction, authenticity verification, and degradation mechanisms of ancient jade artifacts. This is of great value in reflecting the state of jade handicrafts since the Neolithic Age, the evolution of local productivity, and the preservation and utilization of cultural relics.

[0003] Currently, domestic and international analyses of various micro-marks are limited to using silicone to replicate the micro-marks and then observing them under a microscope. This is a contact-based detection method, which is not only cumbersome but also carries the risk of damaging precious organic residues (such as silk, jade-cutting abrasive, cinnabar, etc.) on the surface or inside the grooves of jade artifacts. Related technologies improve the observation angle and accuracy by adding optical lenses and light sources to detect various micro-marks on jade artifacts, but these are all limited to single-modal data and do not integrate compositional spectral and three-dimensional mechanical data. They cannot distinguish the types of micro-marks (such as weathering marks from natural weathering, processing marks from artificial polishing, and signs of use), leading to a high misjudgment rate. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and apparatus for detecting micro-traces in jade artifacts based on multimodal data fusion, so as to solve the technical problems in related technologies.

[0005] To achieve the above objectives, in a first aspect, embodiments of this application provide a method for detecting micro-traces in jade artifacts based on multimodal data fusion, the method comprising:

[0006] Acquire image data and material parameters of the jade artifact to be tested;

[0007] Based on the image data, material parameters, and preset classification algorithm model of the jade artifact under test, the jade artifact under test is classified and detected to obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test.

[0008] The entire life cycle of the jade artifact under test is constructed by inverting the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering and deterioration data.

[0009] The classification and testing results of the jade artifact under test, as well as its entire life cycle, are output through a preset visualization method.

[0010] As an optional embodiment, acquiring the image data of the jade artifact to be tested and the material parameters of the jade artifact to be tested includes:

[0011] Images of the jade artifact under test and its micro-trace features were acquired using an ultra-depth-of-field microscope, resulting in first image data corresponding to the jade artifact under test and second image data corresponding to the micro-trace features of the jade artifact under test.

[0012] The material parameters of the jade artifact under test are obtained by performing spectral analysis using a multispectral detection system. The material parameters of the jade artifact under test include the chemical elemental composition of the jade artifact under test and its corresponding mineralogical characteristics, as well as the elemental composition of the surface deposits of the jade artifact under test and its corresponding mineralogical characteristics.

[0013] As an optional embodiment, the classification and detection of the jade artifact based on the image data, material parameters, and a preset classification algorithm model to obtain the classification and detection result includes:

[0014] The first image data, the second image data, and the material parameters are input into the preset classification algorithm model;

[0015] Using the preset classification algorithm model, the micro-marks of the jade artifact under test are classified based on the first image data, the second image data, and the material parameters to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test;

[0016] The corresponding relationship between the micro-mark type of the jade artifact to be tested and the micro-mark formation parameters is established by the preset classification algorithm model to obtain the classification detection result.

[0017] As an optional embodiment, the step of classifying the micro-marks of the jade artifact under test based on the first image data, the second image data, and the material parameters using the preset classification algorithm model to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test includes:

[0018] The raw material parameters of the jade artifact to be tested are determined using the preset classification algorithm model and the first image data. The raw material parameters include the raw material and abrasive composition, and the source of the raw material.

[0019] The second image data is subjected to coordinate transformation using the preset classification algorithm model, so as to perform coordinate registration processing between the second image data and the first image data to obtain the image registration data of the jade artifact to be tested;

[0020] The spatial matching relationship between the image registration data of the jade artifact to be tested and the material parameters of the jade artifact to be tested is established using the preset classification algorithm model;

[0021] The preset classification algorithm model is used to call the preset micro-trace attribute library based on the raw material parameters of the jade artifact to be tested and the spatial matching relationship to determine the micro-trace type of the jade artifact to be tested;

[0022] If the micro-mark type is determined to be the first micro-mark type, the preset tool feature database is called through the preset classification algorithm model to predict the corresponding processing tool type and processing method of the micro-mark feature of the jade artifact to be tested, and the processing parameters of any micro-mark feature of the jade artifact to be tested are obtained. The preset tool feature database includes physical feature data of processing tools, and the physical feature data includes at least one of the following: hardness distribution parameters of processing tools, blade microstructure and motion trajectory simulation data.

[0023] As an optional embodiment, the step of classifying the micro-marks of the jade artifact under test based on the first image data, the second image data, and the material parameters using the preset classification algorithm model to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test further includes:

[0024] If the micro-trace type is determined to be the second micro-trace type, the surface attachment information data of the jade artifact to be tested in the material parameters are combined, and the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environment parameters of the micro-trace characteristics of the jade artifact to be tested. The material environment parameters include at least one of the soil pH value and groundwater activity data where the jade artifact to be tested is located.

[0025] As an optional embodiment, the step of using the preset classification algorithm model to call the preset micro-trace attribute library based on the spatial matching relationship to determine the micro-trace type of the jade artifact to be tested includes:

[0026] The micro-trace attribute items corresponding to the spatial matching relationship and the micro-trace features are determined from the preset micro-trace attribute library using the preset classification algorithm model.

[0027] The micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

[0028] As an optional embodiment, the preset visualization method includes at least one of the following: a quartz sand distribution heat map, a stress distribution map, a simulation map of the movement trajectory of the processing tool, and a curve showing the relationship between the applied force angle and the trace depth.

[0029] As an optional embodiment, the method further includes:

[0030] Based on the micro-mark type, processing technology, raw material and abrasive composition, source of raw materials and weathering and deterioration data of the jade artifact to be tested, the processing technology flow of the jade artifact to be tested is determined and constructed using the preset classification algorithm model. The processing technology flow includes at least one of the cutting, grinding and polishing processes of the jade artifact to be tested.

[0031] As an optional embodiment, the method further includes:

[0032] Collect third image data, fourth image data, and material data of jade artifacts. The third image data is an image of the jade artifact itself, and the fourth image data is an image of the micro-trace features of the tiny traces included on the jade artifact.

[0033] The third image data, fourth image data, and material data of the jade artifact are used to generate particle interaction samples and jade stress samples corresponding to the jade artifact through a preset finite element analysis algorithm and a preset discrete element method algorithm.

[0034] The preset machine learning algorithm model is obtained by training the particle interaction samples and the jade stress samples.

[0035] Secondly, embodiments of this application provide a micro-trace detection device for jade artifacts based on multimodal data fusion, the device comprising:

[0036] The data acquisition module is used to acquire image data of the jade artifact to be tested and the material parameters of the jade artifact to be tested;

[0037] The classification and detection module is used to classify and detect the jade artifact under test based on the image data, material parameters, and a preset classification algorithm model, and obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test.

[0038] The inversion construction module is used to invert and construct the entire life cycle of the jade artifact under test based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source and weathering and deterioration data.

[0039] The results output module is used to output the classification and testing results of the jade artifact under test and its entire life cycle through a preset visualization method.

[0040] The above technical solution has the following beneficial effects: Based on multimodal data such as image data and material data of jade artifacts, the jade artifacts are detected and analyzed to obtain elemental distribution data (e.g., raw material and abrasive composition, raw material source, and weathering and deterioration data) and micro-mark categories on the jade artifacts. This allows for the determination of the entire lifecycle data of the jade artifacts, from mining and processing to burial, and identifies the factors contributing to the formation of micro-marks. Combining multimodal data such as image data and material data to distinguish micro-mark categories improves the accuracy of micro-mark category identification. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is one of the flowcharts of a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application.

[0043] Figure 2 This is a schematic diagram of the system architecture used in a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application.

[0044] Figure 3 This is the second flowchart of a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application.

[0045] Figure 4 This is a schematic diagram of the image data of the jade artifact according to an embodiment of this application.

[0046] Figure 5 This is a schematic diagram of the elemental composition of a sample according to an embodiment of this application.

[0047] Figure 6 This is a schematic diagram of the mineralogical characteristics of a sample according to an embodiment of this application.

[0048] Figure 7 This is a schematic diagram of the stress distribution heat map according to an embodiment of this application.

[0049] Figure 8 This is a schematic diagram of the process inversion diagram of an embodiment of this application.

[0050] Figure 9 This is a structural block diagram of a jade artifact micro-trace detection device based on multimodal data fusion, according to an embodiment of this application.

[0051] Figure 10This is a structural block diagram of a computer-readable storage medium according to an embodiment of this application.

[0052] Figure 11 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] Figure 1 This is one of the flowcharts illustrating a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application. Figure 1 As shown in the figure, a method for detecting micro-traces in jade artifacts based on multimodal data fusion according to an embodiment of this application may include the following steps:

[0055] Step 101: Obtain the image data and material parameters of the jade artifact to be tested.

[0056] In this embodiment, an ultra-depth-of-field microscope can be used to acquire images of the jade artifact under test and its micro-trace features to obtain first image data corresponding to the jade artifact under test and second image data corresponding to the micro-trace features of the jade artifact under test; and a multispectral detection system can be used to perform spectral analysis on the jade artifact under test to obtain the material parameters of the jade artifact under test, wherein the material parameters of the jade artifact under test include the chemical elemental composition of the jade artifact under test and its corresponding mineralogical characteristics, and the elemental composition of the surface deposits of the jade artifact under test and its corresponding mineralogical characteristics.

[0057] As an example, the magnification of a super depth-of-field microscope can be, for example, 20 to 6000 times, and the resolution can be 12 million pixels. The super depth-of-field microscope can simultaneously acquire first and second image data. The first image data may include, but is not limited to, 2D (Two-Dimensional) morphological images, surface textures, and 3D (Three-Dimensional) topographic images (e.g., height, curvature) of the jade object under test. The 2D morphological and 3D topographic images can be in TIFF (Tag Image File Format). The second image data may include micro-trace stereoscopic data of the jade object under test, such as, but not limited to, processing marks, weathering indentations, etc. Figure 4As shown, the image data of the jade artifact under test were acquired using a super depth-of-field microscope. In the image, A is a 2D morphological image of the jade artifact under test, B is a 3D morphological image of the jade artifact under test, and C is a shadow enhancement image of the surface texture of the jade artifact under test.

[0058] As an example, a multispectral detection system may include, but is not limited to, LIBS (Laser Induced Breakdown Spectroscopy) and Raman spectroscopy. For instance, ultraviolet fluorescence (wavelength less than 365 nm) can be used to detect organic residues in the jade artifact under test (e.g., burning marks can be observed under ultraviolet fluorescence as a ring-shaped distribution of carbonized organic matter). LIBS can be used to directly scan the surface of the jade artifact to obtain data on its surface elemental composition, the regional distribution of weathering-related elements, and inorganic residues in cavities and depressions (specifically, LIBS can detect Na-U elements, with a spatial resolution of 10 μm and a total stroke range of 100 × 100 mm). 2 The material parameters of the jade artifact under test were obtained based on LIBS and Raman spectroscopy analysis. These parameters include, but are not limited to, the chemical elemental composition and mineralogical characteristics of the jade artifact, and the elemental composition and corresponding mineralogical characteristics of the surface deposits on the jade artifact. (See example...) Figure 5 and Figure 6 As shown. Among them, Figure 5 The horizontal axis represents the X-ray energy, corresponding to the characteristic X-ray energy excited by the chemical elements in the jade artifact being tested, expressed in KeV (Kilovolt Ampere Volt). The position of the characteristic energy peak can determine the composition of the chemical elements in the jade artifact being tested. The vertical axis represents the count rate per electron volt, i.e., the signal intensity distribution with energy, where cps is the counts per second, reflecting the intensity of the detected electron signal. / eV is the count normalized to a unit energy interval, used to eliminate the influence of energy bandwidth differences. The height (intensity) of the vertical axis peak reflects the content of the corresponding chemical element in the jade artifact being tested. Figure 6 In the diagram, the horizontal axis represents wavelength and the vertical axis represents reflectivity, thus reflecting or determining the chemical elements or mineralogical characteristics of the jade artifact being tested through emissivity.

[0059] Step 102: Based on the image data, material parameters and preset classification algorithm model of the jade artifact to be tested, the jade artifact to be tested is classified and detected to obtain the classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering and deterioration data of the jade artifact to be tested.

[0060] As an optional embodiment, the first image data, the second image data, and the material parameters can be input into a preset classification algorithm model. Then, the preset classification algorithm model is used to classify the micro-marks of the jade artifact under test based on the first image data, the second image data, and the material parameters to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test. Finally, the preset classification algorithm model is used to establish the correspondence between the micro-mark type and the micro-mark formation parameters of the jade artifact under test to obtain the classification detection result.

[0061] Furthermore, the raw material parameters of the jade artifact to be tested are determined using a preset classification algorithm model and the first image data. These raw material parameters include the composition of the raw material and abrasive, and the source of the raw material. The preset classification algorithm model is then used to perform coordinate transformation on the second image data to register the second image data with the first image data, obtaining image registration data for the jade artifact to be tested. A spatial matching relationship between the image registration data and the material parameters of the jade artifact to be tested is established using the preset classification algorithm model. Then, based on the raw material parameters and spatial matching relationship of the jade artifact to be tested, the preset classification algorithm model calls a preset micro-mark attribute library to determine the micro-mark type of the jade artifact to be tested. If the micro-mark type is determined to be the first micro-mark type, the preset classification algorithm model calls a preset tool feature database to predict the corresponding processing tool type and processing method for the micro-mark features of the jade artifact to be tested, obtaining the processing parameters for any micro-mark feature of the jade artifact to be tested. The preset tool feature database includes physical feature data of the processing tools, which includes at least one of the following: hardness distribution parameters, blade microstructure, and motion trajectory simulation data of the processing tools.

[0062] The preset tool feature database could be a NoSQL database (e.g., MongoDB), storing the content of various materials used for jade-cutting abrasives (e.g., quartz SiO2, corundum Al2O3, garnet, diamond, etc.) to define the abrasive particle properties (particle size distribution, Mohs hardness), and the mechanical parameters of various materials used for processing tools (e.g., bamboo, wood, animal hide, bronze, iron, hemp rope, etc.) to define tool properties. The preset micro-trace attribute database could be a MySQL relational database, used for managing jade artifact sample IDs, collection conditions, etc., and also storing material property mapping relationships, such as LIBS elemental data + Raman spectroscopy mineralogical data → jade hardness / brittleness; ultra-depth-of-field 3D roughness → polishing grading of "rough polishing / fine polishing" or the degree of use of "long-term-short-term-never". Cloud storage is used to ensure the security of the database data.

[0063] For example, coordinate registration can be performed by registering the micro-trace image with the image of the jade artifact under test using the SIFT (Scale-Invariant Feature Transform) algorithm or by manually marking points, while simultaneously aligning the LIBS elemental distribution map with the coordinate system of the super-depth-of-field 3D model. Spatial matching relationships can be semantic associations, establishing mapping rules such as "processing traces - jade-cutting abrasive elemental distribution" and "weathering depressions - secondary mineral elements." For instance, CaCO3 enrichment indicates groundwater activity and elements and secondary mineral characteristics co-buried with bronzes and ivory.

[0064] In this embodiment, feature extraction can be further performed based on spatial matching relationships to obtain feature-level fusion data. For example, morphological features (e.g., curvature, roughness) acquired by a super depth-of-field microscope are concatenated with the elemental distribution (elemental concentration) of LIBS to form a joint feature vector, which is used to identify and distinguish the processing stage of the jade artifact under test (e.g., wire cutting or grinding, where these processing steps require the participation of abrasives such as jade-cutting sand). Based on the feature-level fusion data, the classification and detection of the jade artifact under test can be further realized. For example, a preset classification algorithm model can use weighted voting (confidence 0.6:0.4) to determine the processing technology, the composition of the jade raw material and abrasive, the possible source of the jade raw material, and the weathering and deterioration mechanism, and finally obtain and output the classification and detection results.

[0065] Optionally, if the micro-trace type is determined to be the second micro-trace type, the surface attachment information data of the jade artifact to be tested is combined with the material parameters, and the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environment parameters of the micro-trace characteristics of the jade artifact to be tested. The material environment parameters include at least one of the soil pH value and groundwater activity data where the jade artifact to be tested is located.

[0066] As an optional embodiment, the step of using a preset classification algorithm model to call a preset micro-trace attribute library based on spatial matching relationship to determine the micro-trace type of the jade artifact to be tested can be specifically determined by using the preset classification algorithm model to determine the micro-trace attribute items corresponding to the spatial matching relationship and micro-trace features from the preset micro-trace attribute library, and the micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

[0067] In some embodiments, image data, material parameters, etc., can be preprocessed first. For example, image data can be reconstructed in three dimensions (MeshLab / CloudCompare), noise can be removed (e.g., by median filtering), and micro-trace features can be extracted (e.g., by edge gradient, depth distribution); and multispectral data such as material parameters can be processed by element matrix normalization (Z-score), and abrasive residues (e.g., Si, Al) can be identified and the analysis results stored through cluster analysis (K-means).

[0068] Step 103: Construct the full life cycle of the jade artifact under test based on the type of micro-marks, processing technology, raw materials and abrasive composition, source of raw materials, and weathering and deterioration data.

[0069] For example, the origin of the jade artifact can be traced by combining the raw materials (e.g., Mg / Si ratio). Specifically, the mining area of ​​the jade artifact can be determined by matching the raw materials with a database of known mining areas (e.g., amphibole jade, serpentine jade, marble jade). Further, the processing technology of the jade artifact can be inverted. Specifically, based on the micro-mark type, processing technology, raw material and abrasive composition, raw material source, and weathering data of the jade artifact, a preset classification algorithm model is used to determine and construct the processing flow of the jade artifact. The processing flow includes at least one of the cutting, grinding, and polishing processes of the jade artifact. For example, based on the directionality of micro-marks (which can be referenced from the coordinates of a super depth-of-field microscope) combined with residual elements of processing tools (e.g., metal tools containing Cu, Pb, Fe, etc.) and residual abrasive (including quartz SiO2, corundum Al2O3, garnet, diamond, etc.), the cutting-grinding-polishing process can be reconstructed. And / or environmental inferences can be made about the jade artifacts under test, such as inferring soil pH and groundwater activity based on the correlation between weathering trace morphology (e.g., honeycomb structure) and secondary elements (e.g., Fe2O3 enrichment). This allows for the reconstruction of the entire life cycle of the jade artifacts under test, from mining and processing to burial environment.

[0070] Step 104: Output the classification and testing results and the entire life cycle of the jade artifact to be tested through a preset visualization method.

[0071] For example, the preset visualization methods include, but are not limited to, at least one of the following: a quartz sand distribution heat map, a stress distribution map, a simulation diagram of the machining tool's motion trajectory, and a curve showing the relationship between the applied force angle and the mark depth. The stress distribution heat map output by visualization can be found in [reference needed]. Figure 7 As shown. The inverse diagram of the processing technology flow throughout the entire lifecycle can be found in [reference needed]. Figure 8 As shown, in Figure 8Figure A shows the spiral distribution characteristics on the surface of the jade ring (the jade artifact under test) simulated by calculation (i.e., the simulation diagram of the movement trajectory of the processing tool), which conforms to the Archimedean spiral originating from the same center. Figure B shows the jade ring (the jade artifact under test) after transformation from the Cartesian coordinate system to the polar coordinate system. The Archimedean spiral is mapped to a straight line with a slope of β (e.g., a stress distribution diagram). Figure C shows a schematic diagram of the device for making surface patterns on the jade ring (the jade artifact under test).

[0072] In some embodiments, this application may further include model training and construction of a preset classification algorithm model. Specifically, third image data, fourth image data, and material data of the jade artifact are collected, wherein the third image data is an image of the jade artifact itself, and the fourth image data is an image of the micro-trace features of the tiny marks included on the jade artifact; the third image data, fourth image data, and material data of the jade artifact are used to generate corresponding particle interaction samples and jade stress samples by using a preset finite element analysis algorithm and a preset discrete element method algorithm; a preset machine learning algorithm model is trained using the particle interaction samples and the jade stress samples to obtain a preset classification algorithm model.

[0073] Specifically, the pre-defined classification algorithm model may include, but is not limited to:

[0074] Data Input Layer: This layer contains input third-party image data, material data, and other data. Examples include LIBS element distribution (e.g., CSV (Comma-Separated Values, a plain text file format for storing tabular data)), Raman spectral peak-intensity relationship data (CSV), TIFF (Thickness-of-Field 3D Images), and micro-trace attribute libraries (JSON (JavaScript Object Notation)).

[0075] Physics Engine Layer: Particle interactions (such as friction of jade-cutting sand) can be simulated using the preset Discrete Element Method (DEM), and jade stress can be simulated using the preset Finite Element Method (FEM).

[0076] Machine learning layer: Transformer predicts motion trajectories, GAN generates missing mechanical parameters;

[0077] Visualization layer: WebGL real-time rendering of stress field / crack propagation.

[0078] Then, the aforementioned preset classification algorithm model is configured with hardware, including but not limited to computing nodes: GPU (accelerating parallel computing of DEM / FEM), interactive terminals: touch screen workstations that support gesture operation tool paths, and data storage using distributed storage (Ceph) to manage TB-level simulation data.

[0079] After the hardware configuration is completed, the dynamic modeling process of the preset classification algorithm model begins, for example:

[0080] ① Mining stage: The processing method is simulated using the Discrete Element Method (EDEM), such as simulating hammering / splitting (Python).

[0081] import edem

[0082] model=edem.Model(material="nephrite")

[0083] model.add_tool(type="stone_hammer",velocity=3m / s,angle=45°)

[0084] model.solve(steps=1000)

[0085] ② Processing stage: The contact between the coupling tool and the jade is simulated using the finite element method (Abaqus / ANSYS); for example, the contact between the tool and the jade is simulated using wire cutting and grinding wheel rotation.

[0086] Among them, wire cutting is defined as the tangential friction force between the hemp rope and the abrasive (μ = 0.3-0.6);

[0087] Grinding tool rotation: defined as the combined effect of angular velocity ω and normal pressure P.

[0088] ③ Burial stage: The phase field method is used to simulate weathering stress (COMSOL) and element diffusion (Fe). 2+ →Fe 3+ This can lead to volume expansion stress, fatigue cracks under cyclic temperature and humidity loads, etc.

[0089] Furthermore, machine learning-enhanced simulations are performed using a pre-defined classification algorithm model, for example:

[0090] ① Tool path inversion: Using Transformer networks to infer the force application patterns of ancient craftsmen from micro-trace directionality (super-depth data):

[0091]

[0092]

[0093] ① Parameter optimization: Parallel Bayesian optimization (Hyperopt+TPE)

[0094] Hyperopt is a Python-based Bayesian optimization library that supports parallel and asynchronous optimization; it uses TPE (Tree-structured Parzen Estimator) as the acquisition function, making it suitable for high-dimensional parameter spaces.

[0095] TPE (Tree-structured Parzen Estimator) is a probability density estimation method based on tree structure, suitable for handling high-dimensional parameter spaces, and improves search efficiency through hierarchical sampling.

[0096] Specifically, this can be achieved through the following code:

[0097]

[0098]

[0099] Finally, the preset classification algorithm model is verified and calibrated, for example:

[0100] During the positive verification process, a 3D-printed jade replica (Stratasys J850, material: photosensitive resin + mineral powder) was processed using real tools to compare the simulated / actual micro-marks.

[0101] During the reverse calibration process, the residual network (ResNet50) compares the simulated traces with the actual hyper-depth-of-field image.

[0102] loss=cosine_similarity(simulated_texture,real_texture)

[0103] ifloss>threshold:

[0104] adjust_FEM_mesh_refinement() # Dynamically refines the mesh

[0105] In summary, the training, modeling, and optimization of the preset classification algorithm model are achieved, ultimately resulting in the preset classification algorithm model used in the aforementioned... Figure 1 The method embodiment shown.

[0106] To enable those skilled in the art to clearly and accurately understand the technical solutions of the embodiments of this application, the following is combined with... Figure 2 and Figure 3 The technical solutions of the embodiments of this application will be further described in detail through examples.

[0107] in, Figure 2 This is a schematic diagram of the system architecture used in a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application. Figure 3 This is the second flowchart of a method for detecting micro-traces in jade artifacts based on multimodal data fusion, according to an embodiment of this application.

[0108] like Figure 2 As shown, the system used in the jade artifact micro-trace detection method based on multimodal data fusion according to an embodiment of this application includes at least: a super depth-of-field microscope, a multispectral detection system (e.g., including LIBS, Raman spectrometer, and ultraviolet fluorescence), a dynamic mechanical simulation platform (configured with a preset classification algorithm model, thus including a data input layer, a physics engine layer, a machine learning layer, and a visualization layer of the preset classification algorithm model), and a system configured for the dynamic mechanical simulation platform, such as a distributed storage facility, a touch screen workstation, and a GPU (Graphics Processing Unit).

[0109] exist Figure 2 Based on the system shown, through Figure 3 The process shown enables the detection of jade artifacts. Specifically, the jade artifact to be tested is placed as a sample on, for example, a data acquisition console to control the ultra-depth-of-field microscope and multispectral detection system to acquire data (image data and material parameters) of the jade artifact to be tested. The acquired data is then input into a preset classification algorithm model.

[0110] Furthermore, the pre-defined classification algorithm model can process this collected data as follows:

[0111] ① Extract data or information, such as extracting the chemical element composition and corresponding mineralogical characteristics of the jade artifact to be tested, the element composition and corresponding mineralogical characteristics of the surface attachments of the jade artifact to be tested, and extracting micro-traces (such as surface processing traces and defects) from image data.

[0112] ②The extracted information is then stored in an internal database. For example, a MySQL relational database is used to manage the sample ID and acquisition conditions of the jade artifacts to be tested, and NoSQL (such as MongoDB) is used to store unstructured images and multimodal data (i.e., image data and material parameters of the jade artifacts to be tested).

[0113] ③Then retrieve data from various databases and perform analysis. For example, retrieve parameters that match the data features from the preset micro-trace attribute library and preset tool feature database, so as to complete the analysis of processing tools, jade material data, etc., and present the analysis results quantitatively.

[0114] ④ Based on the analysis results of data such as processing tools and jade materials, further utilize machine learning to map the data of the analysis results, such as establishing the correlation between the sample (jade artifact to be tested) and the processing method;

[0115] ⑤ Output and display the analysis results, relationship mappings, and other data.

[0116] For example, the technical solution of this application is used to perform micro-trace analysis on jade artifacts unearthed from Sanxingdui:

[0117] First, material information of the target jade artifact (i.e., the jade artifact to be tested) is obtained through LIBS and Raman spectroscopy analysis, including its chemical elemental composition, mineralogical characteristics, and the elemental composition and mineralogical characteristics of its surface deposits. These test results will be provided to... Figure 2 The pre-defined classification algorithm model in the system shown serves as the data foundation for its subsequent analysis.

[0118] Secondly, based on the retrieval results of the corresponding materials in the database (e.g., jade sample IDs and collection conditions stored in the MySQL relational database), the ultra-depth-of-field microscope is operated to automatically search for polishing marks, processing marks, jade-cutting sand and other traces related to jade processing on the surface of the target jade artifact, as well as the disease characteristics of the target jade artifact surface (e.g., cracks, fractures, weathering and erosion). The images are then photographed to obtain, in turn, 2D and 3D composite images and optical shadow effect mode images corresponding to the target jade artifact.

[0119] Then, based on the images obtained by the ultra-depth-of-field microscope, the pre-defined classification algorithm model can call the system's database using its machine learning method and employ a multi-modal fusion method to invert the material and type of tool that left any processing mark on the target jade artifact (data provided by the ultra-depth-of-field microscope), and the specific operation of that tool when processing the target jade artifact (e.g., the force and angle of the engraving, the rotation speed of the grinding wheel, etc.). The inversion results are presented in a quantitative manner, including but not limited to quartz sand distribution heat maps, stress distribution maps, simulation diagrams of the processing tool's movement trajectory, and force angle-mark depth relationship curves.

[0120] Finally, based on the surface disease characteristics (data provided by ultra-depth-of-field microscope), combined with the obtained information on surface attachments (usually soil, data provided by LIBS) or information in the database, the preset classification algorithm model can also infer the burial environment or cause of the disease based on its machine learning method.

[0121] In summary, this application's embodiments utilize multimodal data, including image and material data, to detect and analyze jade artifacts. This yields elemental distribution data (e.g., raw material and abrasive composition, raw material origin, and weathering / deterioration data) and the types of micro-marks on the jade artifacts. This allows for the determination of the entire lifecycle data of the jade artifacts, from mining and processing to burial, and identifies the factors contributing to the formation of micro-marks. By combining multimodal data such as image and material data to differentiate micro-mark types, the accuracy of micro-mark identification is improved.

[0122] Furthermore, data acquisition from the jade artifacts under test using ultra-depth-of-field microscopes, LIBS, and Raman spectrometers can meet the needs of cultural relic preservation, achieving non-destructive, high-precision, and efficient data acquisition, avoiding the contact risks associated with silicone molding techniques in related technologies. The high magnification and resolution of ultra-depth-of-field microscopes improve the accuracy and efficiency of micro-trace acquisition, enabling the acquisition and measurement of micro-traces as narrow as 0.01µm, reducing the financial and time costs of data acquisition. The high spatial resolution and total travel range of LIBS allow the technical solution of this application to support micron-level cross-modal correlation, acquiring not only three-dimensional morphological data but also data on the composition and attachments of micro-trace regions.

[0123] Secondly, based on the images acquired by the ultra-depth-of-field microscope, it is compatible with the data acquired by the newly added LIBS and Raman spectrometers, which reduces the risk of damage to cultural relics caused by multiple replacements of testing equipment. It also realizes a multi-modal data fusion mode, enabling the inversion of the entire life cycle of jade artifacts, and provides an operable technical path for the systematic study of jade artifacts from mineral source determination to burial history.

[0124] Correspondingly, this application also provides an apparatus embodiment corresponding to the foregoing method embodiment. Figure 9 This is a structural block diagram of a jade artifact micro-trace detection device based on multimodal data fusion, according to an embodiment of this application. Figure 9 As shown, a micro-trace detection device for jade artifacts based on multimodal data fusion may include:

[0125] Data acquisition module 901 is used to acquire image data of the jade artifact to be tested and the material parameters of the jade artifact to be tested;

[0126] The classification and detection module 902 is used to classify and detect the jade artifact under test based on the image data, material parameters and preset classification algorithm model, and obtain the classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials and weathering and deterioration data of the jade artifact under test.

[0127] The inversion construction module 903 is used to invert and construct the entire life cycle of the jade artifact under test based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source and weathering deterioration data of the jade artifact under test.

[0128] The result output module 904 is used to output the classification and testing results of the jade artifact under test and its entire life cycle through a preset visualization method.

[0129] In summary, this application's embodiments utilize multimodal data, including image and material data, to detect and analyze jade artifacts. This yields elemental distribution data (e.g., raw material and abrasive composition, raw material origin, and weathering / deterioration data) and the types of micro-marks on the jade artifacts. This allows for the determination of the entire lifecycle data of the jade artifacts, from mining and processing to burial, and identifies the factors contributing to the formation of micro-marks. By combining multimodal data such as image and material data to differentiate micro-mark types, the accuracy of micro-mark identification is improved.

[0130] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0131] This application also provides a computer-readable storage medium 1000, such as... Figure 10 As shown, the computer-readable storage medium 1000 stores a computer program, which, when executed by a processor, implements the steps of the aforementioned micro-trace detection method and apparatus for jade artifacts. For example, when the computer program is executed by the processor, it implements the following steps:

[0132] Acquire image data and material parameters of the jade artifact to be tested;

[0133] Based on the image data, material parameters, and preset classification algorithm model of the jade artifact under test, the jade artifact under test is classified and detected to obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test.

[0134] The entire life cycle of the jade artifact under test is constructed by inverting the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering and deterioration data.

[0135] The classification and testing results of the jade artifact under test, as well as its entire life cycle, are output through a preset visualization method.

[0136] In some embodiments, the storage medium is further configured to store program code 1001 for performing the following steps:

[0137] Acquire image data and material parameters of the jade artifact to be tested;

[0138] Based on the image data, material parameters, and preset classification algorithm model of the jade artifact under test, the jade artifact under test is classified and detected to obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test.

[0139] The entire life cycle of the jade artifact under test is constructed by inverting the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering and deterioration data.

[0140] The classification and testing results of the jade artifact under test, as well as its entire life cycle, are output through a preset visualization method.

[0141] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. Of course, there are other types of readable storage media, such as quantum memories, graphene memories, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0142] This application also provides an electronic device 1100, such as... Figure 11 As shown, it includes one or more processors 1101, communication interface 1102, memory 1103 and communication bus 1104, wherein the processor 1101, communication interface 1102 and memory 1103 communicate with each other through communication bus 1104.

[0143] Memory 1103 is used to store computer programs;

[0144] When the processor 1101 executes the program stored in the memory 1103, it implements the steps of the aforementioned micro-trace detection method and apparatus for jade artifacts. For example, when the processor 1101 executes the program stored in the memory 1103, it implements the following steps:

[0145] Acquire image data and material parameters of the jade artifact to be tested;

[0146] Based on the image data, material parameters, and preset classification algorithm model of the jade artifact under test, the jade artifact under test is classified and detected to obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test.

[0147] The entire life cycle of the jade artifact under test is constructed by inverting the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering and deterioration data.

[0148] The classification and testing results of the jade artifact under test, as well as its entire life cycle, are output through a preset visualization method.

[0149] The processor 1101 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0150] Memory 1103 may include mass storage for data or instructions. For example, and not limitingly, memory 1103 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where suitable, memory 1103 may include removable or non-removable (or fixed) media. In a particular embodiment, memory 1103 is a non-volatile solid-state memory. In a particular embodiment, memory 1103 includes read-only memory (ROM). Where suitable, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0151] The communication bus 1104 includes hardware, software, or both, for coupling the aforementioned components together. For example, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, the bus may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0152] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0153] While this application provides method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the method can be executed sequentially as shown in the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0154] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0155] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0156] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0157] This application uses specific embodiments to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for detecting micro-traces in jade artifacts based on multimodal data fusion, characterized in that, The method includes: Acquire image data and material parameters of the jade artifact to be tested; Based on the image data, material parameters, and preset classification algorithm model of the jade artifact under test, the jade artifact under test is classified and detected to obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test. The entire life cycle of the jade artifact under test is constructed by inverting the micro-trace type, processing technology, raw material and abrasive composition, raw material source, and weathering and deterioration data. The classification and testing results of the jade artifact under test, as well as its entire life cycle, are output through a preset visualization method. The method further includes: Collect third image data, fourth image data, and material data of jade artifacts. The third image data is an image of the jade artifact itself, and the fourth image data is an image of the micro-trace features of the tiny traces included on the jade artifact. The third image data, fourth image data, and material data of the jade artifact are used to generate particle interaction samples and jade stress samples corresponding to the jade artifact through a preset finite element analysis algorithm and a preset discrete element method algorithm; the processing method is simulated by the discrete element method, and the contact between the coupling tool and the jade artifact is simulated by the finite element method. The preset machine learning algorithm model is trained by the particle interaction samples and the jade stress samples to obtain the preset classification algorithm model; The acquisition of image data and material parameters of the jade artifact to be tested includes: Images of the jade artifact under test and its micro-trace features were acquired using an ultra-depth-of-field microscope, resulting in first image data corresponding to the jade artifact under test and second image data corresponding to the micro-trace features of the jade artifact under test. The material parameters of the jade artifact under test are obtained by performing spectral analysis using a multispectral detection system. The material parameters of the jade artifact under test include the chemical elemental composition of the jade artifact under test and its corresponding mineralogical characteristics, as well as the elemental composition of the surface deposits of the jade artifact under test and its corresponding mineralogical characteristics.

2. The method according to claim 1, characterized in that, The method involves classifying and detecting the jade artifact based on its image data, material parameters, and a preset classification algorithm model to obtain classification results, including: The first image data, the second image data, and the material parameters are input into the preset classification algorithm model; Using the preset classification algorithm model, the micro-marks of the jade artifact under test are classified based on the first image data, the second image data, and the material parameters to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test; The corresponding relationship between the micro-mark type of the jade artifact to be tested and the micro-mark formation parameters is established by the preset classification algorithm model to obtain the classification detection result.

3. The method according to claim 2, characterized in that, The method involves classifying the micro-marks of the jade artifact under test based on the first image data, the second image data, and the material parameters using the preset classification algorithm model, thereby obtaining the micro-mark type and micro-mark formation parameters of the jade artifact under test, including: The raw material parameters of the jade artifact to be tested are determined using the preset classification algorithm model and the first image data. The raw material parameters include the raw material and abrasive composition, and the source of the raw material. The second image data is subjected to coordinate transformation using the preset classification algorithm model, so as to perform coordinate registration processing between the second image data and the first image data to obtain the image registration data of the jade artifact to be tested; The spatial matching relationship between the image registration data of the jade artifact to be tested and the material parameters of the jade artifact to be tested is established using the preset classification algorithm model; The preset classification algorithm model is used to call the preset micro-trace attribute library based on the raw material parameters of the jade artifact to be tested and the spatial matching relationship to determine the micro-trace type of the jade artifact to be tested; If the micro-mark type is determined to be the first micro-mark type, the preset tool feature database is called through the preset classification algorithm model to predict the corresponding processing tool type and processing method of the micro-mark feature of the jade artifact to be tested, and the processing parameters of any micro-mark feature of the jade artifact to be tested are obtained. The preset tool feature database includes physical feature data of processing tools, and the physical feature data includes at least one of the following: hardness distribution parameters of processing tools, blade microstructure and motion trajectory simulation data.

4. The method according to claim 3, characterized in that, The step of classifying the micro-marks of the jade artifact under test based on the first image data, the second image data, and the material parameters using the preset classification algorithm model to obtain the micro-mark type and micro-mark formation parameters of the jade artifact under test, further includes: If the micro-trace type is determined to be the second micro-trace type, the surface attachment information data of the jade artifact to be tested in the material parameters are combined, and the preset material feature database is called through the preset classification algorithm model to predict the corresponding material environment parameters of the micro-trace characteristics of the jade artifact to be tested. The material environment parameters include at least one of the soil pH value and groundwater activity data where the jade artifact to be tested is located.

5. The method according to claim 4, characterized in that, The step of using the preset classification algorithm model to call the preset micro-mark attribute library based on the spatial matching relationship to determine the micro-mark type of the jade artifact to be tested includes: The micro-trace attribute items corresponding to the spatial matching relationship and the micro-trace features are determined from the preset micro-trace attribute library using the preset classification algorithm model. The micro-trace type corresponding to the micro-trace attribute item is determined as the micro-trace type corresponding to any micro-trace feature in the jade artifact to be tested.

6. The method according to claim 5, characterized in that, The preset visualization methods include at least one of the following: a quartz sand distribution heat map, a stress distribution map, a simulation map of the movement trajectory of the processing tool, and a curve showing the relationship between the applied force angle and the trace depth.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Based on the micro-mark type, processing technology, raw material and abrasive composition, source of raw materials and weathering and deterioration data of the jade artifact to be tested, the processing technology flow of the jade artifact to be tested is determined and constructed using the preset classification algorithm model. The processing technology flow includes at least one of the cutting, grinding and polishing processes of the jade artifact to be tested.

8. A device for detecting micro-traces in jade artifacts based on multimodal data fusion, characterized in that, The device performs the jade artifact micro-trace detection method based on multimodal data fusion as described in any one of claims 1-7, and the device comprises: The data acquisition module is used to acquire image data of the jade artifact to be tested and the material parameters of the jade artifact to be tested; The classification and detection module is used to classify and detect the jade artifact under test based on the image data, material parameters, and a preset classification algorithm model, and obtain classification and detection results. The classification and detection results include the micro-trace type, processing technology, raw material and abrasive composition, source of raw materials, and weathering and deterioration data of the jade artifact under test. The inversion construction module is used to invert and construct the entire life cycle of the jade artifact under test based on the micro-trace type, processing technology, raw material and abrasive composition, raw material source and weathering and deterioration data. The results output module is used to output the classification and testing results of the jade artifact under test and its entire life cycle through a preset visualization method.

Images