Beneficiation exploration analysis and classification method and system
By automating image acquisition and intelligent analysis, combined with core image processing and multi-parameter fusion, the problems of low efficiency and poor accuracy in traditional core sampling and analysis have been solved, achieving efficient and accurate identification of rock and mineral types, and reducing exploration costs and resource waste.
Patent Information
- Application Number
- CN202510938253.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-08
- Publication Date
- 2025-10-28
AI Technical Summary
Traditional core sampling and analysis relies on manual visual observation, which is inefficient and easily affected by subjective factors. Existing image analysis methods have low accuracy in identifying mineral types, leading to increased blind exploration and mining and waste of resources.
Automated image acquisition and intelligent analysis methods are employed to identify rock and mineral types by acquiring and preprocessing core images, determining rock types, and recognizing mineral types. This is combined with multi-parameter fusion to identify rock and mineral types, infer mineralization mechanisms, and assess resource potential.
It improves the efficiency and accuracy of core analysis, reduces exploration costs, and provides scientific evidence to reduce resource waste and blind exploration.
Smart Images
Figure CN120852862A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of mineral exploration technology, and specifically to a mineral processing exploration analysis and classification method and system. Background Art
[0002] In the field of oil exploration and development, core samples, as the direct carriers of underground geological information, contain crucial guidance for exploration and mining decisions based on their mineral types and distribution information. In traditional mineral processing exploration, the analysis of core samples relies heavily on manual visual observation and experience-based judgment. This method is not only inefficient but also susceptible to subjective interference, making it difficult to accurately identify mineral types under complex geological conditions. This leads to increased blind exploration and mining, resulting in significant resource waste and escalating exploration costs.
[0003] With the development of computer technology, some image recognition technologies have begun to be applied to core analysis. However, existing image analysis methods often suffer from low accuracy in identifying mineral types due to insufficient image resolution and incomplete extraction of mineralization features. This makes it impossible to efficiently plan subsequent exploration and mining processes based on the identification results. Therefore, there is an urgent need for a method and system that can quickly and accurately acquire core sampling images and accurately identify mineral types through intelligent image analysis, thereby enabling selective exploration and mining to improve the efficiency of oil exploration and the scientific nature of resource development. Summary of the Invention
[0004] In view of this, in order to solve the problems mentioned in the background technology, a mineral processing exploration analysis and classification method and system are proposed.
[0005] The technical solution adopted by the present invention to solve its technical problem is as follows: Firstly, the present invention provides a mineral processing exploration analysis and classification method, comprising the following steps:
[0006] Step 1: Image Acquisition: Images of the surface and each slice layer of the collected core samples are acquired. The acquired images are preprocessed, labeled, and compiled to obtain an image set of the core samples.
[0007] Step 2, Rock Type Determination: Obtain the core color based on the core sample image set, and preliminarily define the range of rock types of the core sample by combining the rock type library corresponding to the core color system. Also, obtain the degree of crystallization, grain size, geometric shape and grain contact relationship of the crystals to determine the rock type of the core sample.
[0008] Step 3, Mineral Type Identification: Based on the comparison results of the gray values of the core sample image and the gray value range of the mineralized body, the mineralized body area is identified and marked, and the distribution form and mineralization intensity of the mineralized body in the core are obtained to identify the mineral type of the core sample.
[0009] Step 4: Conclusion Output: Based on the rock type and mineral type of the core sample, infer the mineralization mechanism and assess the mineral resource potential, and provide feedback.
[0010] Secondly, the present invention also provides a mineral processing exploration and analysis classification system, comprising:
[0011] Image acquisition module: Acquires images of the surface and each slice layer of the core sample, preprocesses the acquired images, annotates them, and summarizes them to obtain an image set of the core sample.
[0012] Rock type determination module: Based on the image set of the core sample, the color of the core is obtained. Combined with the rock type library corresponding to the core color system, the range of rock types of the core sample is initially defined. The crystallization degree, grain size, geometric shape and grain contact relationship of the crystals are obtained to determine the rock type of the core sample.
[0013] Mineral type identification module: Based on the comparison results of the gray value of the core sample image and the gray value range of the mineralized body, the mineralized body region is identified and marked, and the distribution form and mineralization intensity of the mineralized body in the core are obtained to identify the mineral type of the core sample.
[0014] Conclusion output module: Based on the rock type and mineral type of the core sample, infer the mineralization mechanism and assess the mineral resource potential, and provide feedback.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0016] 1. Improved analysis efficiency: This invention replaces manual visual observation with automated image acquisition and intelligent analysis, reducing manual operation procedures and significantly improving the efficiency of core analysis.
[0017] 2. Rock type identification: This invention integrates multiple parameters such as core color classification, crystal crystallization degree, grain size, geometric morphology and grain contact relationship to comprehensively extract rock and mineral characteristics to determine rock type, thereby improving the accuracy of rock type identification and classification.
[0018] 3. Mineral type identification: This invention identifies mineral types by marking mineralized areas through grayscale value comparison, obtaining the distribution pattern and mineralization intensity of mineralized bodies in the core, and improving the accuracy of mineral type identification and classification through quantitative analysis of mineralization characteristics. Attached Figure Description
[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic diagram of the method flow of the present invention.
[0021] Figure 2 This is a system module connection diagram of the present invention.
[0022] Figure 3 This is a flowchart illustrating the overall workflow of the present invention. Detailed Implementation
[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0024] Please see Figure 1 and Figure 3 As shown, the first aspect of the present invention provides a mineral processing exploration analysis and classification method, comprising the following steps:
[0025] Step 1: Image Acquisition: Images of the surface and each slice layer of the collected core samples are acquired. The acquired images are preprocessed, labeled, and compiled to obtain an image set of the core samples.
[0026] For example, the specific analysis process of step one is as follows:
[0027] Core samples were collected from the target rock strata using a drilling rig, and the sampling location and depth were recorded.
[0028] Surface images of core samples are acquired using image acquisition equipment.
[0029] The core samples were sliced into equal-thickness sections according to the set rules, and images of each slice layer were acquired.
[0030] The surface images and slice images of the core samples are preprocessed, including image correction, noise reduction and enhancement.
[0031] Each preprocessed image is labeled with a type, which includes surface and slice layer.
[0032] The labeled images are then compiled to obtain an image set of the core samples.
[0033] It should be noted that a rock core is a cylindrical rock sample extracted from underground rock strata through drilling or other methods. It is a direct physical carrier of underground geological structure and mineral composition, containing key information such as rock mineral composition, structure, and pore characteristics.
[0034] It should be noted that before core sampling, potential mineralization areas are delineated through geological mapping and geophysical exploration to determine the target area and depth for core sampling.
[0035] It should be noted that core sampling follows specific standards to ensure that the obtained core samples can accurately reflect the underground geological characteristics.
[0036] It should be noted that the types of image acquisition equipment include, but are not limited to, high-resolution scanners, microscopes, spectrometers, etc., and the resolution of the image acquisition equipment reaches the micrometer level to ensure that mineral particles, crystal morphology and mineralization details are clearly distinguishable.
[0037] It should be noted that image correction in preprocessing is to eliminate interference such as uneven lighting and distortion, while noise reduction and enhancement are achieved by using Gaussian filtering and edge sharpening to highlight mineral boundaries and mineralization features.
[0038] Step 2, Rock Type Determination: Obtain the core color based on the core sample image set, and preliminarily define the range of rock types of the core sample by combining the rock type library corresponding to the core color system. Also, obtain the degree of crystallization, grain size, geometric shape and grain contact relationship of the crystals to determine the rock type of the core sample.
[0039] For example, the specific analysis process of step two is as follows:
[0040] The RGB values of each image in the core sample image set are obtained and statistically analyzed to obtain the RGB value set. Combined with the RGB value and color correspondence table stored in the database, the color set of the core sample is obtained.
[0041] The color system of the core sample is determined based on the color set of the core sample. The color system includes light color system, dark color system, and light color system.
[0042] Based on the established rock type library corresponding to each color system of the core sample, the corresponding rock type library is selected according to the color system to which the core sample belongs, and the range of rock types of the core sample is initially defined.
[0043] The similarity of each image of the core sample with the sample images of crystals in the core stored in the database is used to identify crystalline regions, and the crystalline regions in each image of the core sample are statistically analyzed.
[0044] The area of each crystalline region in each image of the core sample is obtained and summed to obtain the total area of the crystalline region in the core sample image. The ratio of the total area of the crystalline region to the total area of the core region is calculated to obtain the degree of crystallization of the crystals in the core sample.
[0045] The boundary contours of each crystalline region in each image of the core sample are traced to obtain the length of the crystalline region. The maximum length of the crystalline region is recorded as the grain size of the crystal in the core sample.
[0046] Based on the crystalline regions in each image of the core sample, the crystalline regions and their distribution on the surface of the rock sample and in each slice layer are obtained. A spatial model of the crystals in the rock sample is constructed, and the geometric morphology of the crystals in the core sample is obtained.
[0047] The relative positional relationships between crystals in the spatial model are obtained, and combined with the crystal positional relationships corresponding to various crystal particle contact relationships, the particle contact relationships of crystals in the core sample are obtained.
[0048] Based on the crystal information corresponding to each rock type within the rock type range of the core sample, and combined with the degree of crystallization, grain size, geometric shape and grain contact relationship of the crystals in the core sample, the rock type of the core sample is matched.
[0049] In one specific embodiment, the light color scheme includes colors such as white, light gray, and flesh-pink, and the corresponding rock types include sandstone, limestone, and quartzite; the dark color scheme includes colors such as gray-black, dark gray, and black, and the corresponding rock types include shale, mudstone, and basalt; the light color scheme includes colors such as red, purplish-red, and green, where the rock types corresponding to red and purplish-red include sandstone and shale, and the rock types corresponding to green include marine sandstone and shale.
[0050] It should be noted that the specific method for identifying crystalline regions in core sample images is as follows: the core sample image is compared with the images of crystalline samples stored in the database. Regions with a similarity greater than or equal to a set threshold are recorded as crystalline regions, and regions with a similarity less than the set threshold are recorded as amorphous regions. Each crystalline region in the core sample image is then statistically analyzed.
[0051] It should be noted that the degree of crystallization is expressed as a percentage.
[0052] It should be noted that the length of the crystalline region refers to the longest possible length of the crystalline region.
[0053] It should be noted that the geometric shapes of crystals include hexagonal prisms, cubes, rhombohedrons, columnar, tabular, acicular, and plate-like structures.
[0054] It should be noted that the grain contact relationship of crystals refers to the contact relationship between crystals, such as mosaic, mottled, and granular contact relationships.
[0055] For example, the specific analysis process for obtaining the color system to which the core sample color belongs is as follows:
[0056] S1: Set the color library corresponding to light, dark, and bright colors.
[0057] S2: Determine whether the core sample color set contains a color from the light color library. If it does, the core sample color belongs to the light color library; otherwise, execute S3.
[0058] S3: Determine whether the core sample color set contains colors from the dark color library. If it does, the core sample color belongs to the dark color library; otherwise, the core sample color belongs to the light color library.
[0059] It should be noted that light colors have a higher priority than dark colors, and dark colors have a higher priority than light colors.
[0060] For example, the specific analysis process for obtaining the rock type of the core sample is as follows: extract the crystal information corresponding to each rock type stored in the database, and filter out the crystal information corresponding to each rock type within the range of rock types of the core sample. The crystal information includes the range of crystallization degree, grain size range, geometric shape and grain contact relationship.
[0061] Based on the degree of crystallization, grain size, geometric shape, and grain contact relationship of the crystals in the core sample, we obtain the sub-items that match the crystal information of the core sample with the crystal information of each rock type.
[0062] Based on the weights of each sub-item in the set crystal information, the weights of the matching sub-items are obtained by filtering.
[0063] Based on the sub-items and their weights of the matching between the crystal information of the core sample and the crystal information of each rock type, the matching degree between the core sample and each rock type is obtained through weighted fusion analysis.
[0064] The rock type corresponding to the maximum matching degree is recorded as the rock type of the core sample.
[0065] It should be noted that a match is considered to be achieved if the degree of crystallinity and particle size are within their respective ranges, and if the geometric shape and particle contact relationship are consistent.
[0066] It should be noted that the weights of each sub-item in the crystal information are set according to their confidence level in assessing the similarity of rock types.
[0067] In this embodiment, the present invention comprehensively extracts rock and mineral characteristics by integrating multiple parameters such as core color classification, crystal crystallization degree, grain size, geometric morphology and grain contact relationship to determine rock type, thereby improving the accuracy of rock type identification and classification.
[0068] Step 3, Mineral Type Identification: Based on the comparison results of the gray values of the core sample image and the gray value range of the mineralized body, the mineralized body area is identified and marked, and the distribution form and mineralization intensity of the mineralized body in the core are obtained to identify the mineral type of the core sample.
[0069] For example, the specific analysis process of step three is as follows: using image processing technology to obtain the gray values of each image of the core sample and comparing them with the set gray value range of the mineralized body image. If a gray value belongs to the gray value range of the mineralized body image, then the area where the gray value is located is recorded as the mineralized body area.
[0070] The mineralization regions in each image of the core sample were statistically analyzed and marked.
[0071] To obtain the distribution pattern and mineralization intensity of mineralized bodies in the core.
[0072] Based on the distribution patterns and mineralization intensity ranges of mineralized bodies corresponding to various types of minerals stored in the database, the mineral type of the core sample is matched.
[0073] It should be noted that mineralized bodies are aggregates of useful minerals or elements that have accumulated to a certain extent in geological bodies during the mineralization process, but have not yet reached the level of exploitable industrial grade.
[0074] It should be noted that mineralized bodies differ from surrounding rocks in physical properties and chemical composition, which can cause them to appear with different grayscale values in images such as core scans and CT scans.
[0075] For example, the specific analysis process for obtaining the distribution of mineralized bodies in the core sample is as follows: based on the mineralized body regions in each image of the core sample, the mineralized body regions and their distribution on the surface of the rock sample and in each slice layer are obtained; the three-dimensional spatial mapping technology is used to reconstruct the three-dimensional model of the mineralized bodies in the core sample to obtain the spatial distribution of the mineralized bodies in the core sample.
[0076] Based on the pre-defined spatial distribution characteristics of mineralized bodies in various distribution patterns in the core, the distribution patterns of mineralized bodies in the core sample are obtained.
[0077] It should be noted that the distribution of mineralized bodies in the core may include, but is not limited to, layered, vein-like, disseminated, and nodular forms. In a specific embodiment, if the mineralized body is interspersed in the core as fine veins, it is considered a vein-like distribution; if the mineralized body is uniformly dispersed in the core, it is considered a disseminated distribution.
[0078] For example, the specific analysis process for obtaining mineralization intensity is as follows: based on each mineralized body region in each image of the core sample, obtain the number of pixels in the mineralized body region and the number of pixels in the core region in each image of the core sample, and statistically obtain the total number of pixels in the mineralized body region and the total number of pixels in the core region in the core sample image.
[0079] The mineralization intensity of the core sample is obtained by calculating the ratio of the total number of pixels in the mineralized body region to the total number of pixels in the core region.
[0080] It should be noted that mineralization intensity is expressed as a percentage.
[0081] In this embodiment, the present invention marks the mineralized body area by comparing gray values, obtains the distribution pattern and mineralization intensity of the mineralized body in the core to identify the mineral type, and improves the accuracy of mineral type identification and classification through quantitative analysis of mineralization characteristics.
[0082] Step 4: Conclusion Output: Based on the rock type and mineral type of the core sample, infer the mineralization mechanism and assess the mineral resource potential, and provide feedback.
[0083] For example, the specific analysis process of step four is as follows: based on the established correspondence between rock type and ore type and deposit type and mineralization cause, the deposit type and mineralization cause corresponding to the core sample are matched according to the rock type and ore type of the core sample.
[0084] Based on the set ore body size grade corresponding to each rock type and the grade grade corresponding to each mineral type, and combined with the rock type and mineral type of the core sample, the ore body size grade and grade grade corresponding to the core sample are screened.
[0085] Based on the pre-defined quantitative mapping relationship between ore body size, grade, and mineral resource potential, the mineral resource potential corresponding to the core sample is obtained according to the ore body size and grade corresponding to the core sample.
[0086] In this embodiment, the present invention replaces manual visual observation with automated image acquisition and intelligent analysis, reduces manual operation procedures, and greatly improves the efficiency of core analysis.
[0087] In this embodiment, the present invention, based on rock type and mineral type identification, infers the mineralization mechanism and assesses resource potential, providing a scientific basis for subsequent exploration and mining processes, reducing exploration blindness, and minimizing resource waste and exploration costs.
[0088] See Figure 2 As shown, a second aspect of the present invention provides a mineral processing exploration analysis and classification system, including an image acquisition module, a rock type judgment module, a mineral type identification module, and a conclusion output module.
[0089] The image acquisition module is connected to the rock type judgment module and the mineral type identification module, respectively, and the conclusion output module is connected to the rock type judgment module and the mineral type identification module, respectively.
[0090] The image acquisition module is used to acquire images of the surface and each slice layer of the core sample. After preprocessing the acquired images, they are labeled and summarized to obtain an image set of the core sample.
[0091] The rock type determination module is used to obtain the core color based on the core sample image set, preliminarily define the range of rock types of the core sample by combining the rock type library corresponding to the core color system, and obtain the crystallization degree, grain size, geometric shape and grain contact relationship of the crystals to determine the rock type of the core sample.
[0092] The mineral type identification module is used to identify and mark mineralized areas based on the comparison results between the gray values of the core sample image and the gray value range of the mineralized body, and to obtain the distribution form and mineralization intensity of the mineralized body in the core sample, thereby identifying the mineral type of the core sample.
[0093] The conclusion output module is used to infer the mineralization mechanism and assess the mineral resource potential based on the rock type and mineral type of the core sample, and to provide feedback.
[0094] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.
[0095] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.
[0096] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0097] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.
[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0099] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A mineral processing exploration and classification method, characterized in that, include: Step 1: Image Acquisition: Images of the surface and each slice layer of the collected core samples are acquired. The acquired images are preprocessed, labeled, and summarized to obtain an image set of the core samples. Step 2, Rock Type Determination: Obtain the core color based on the core sample image set, and preliminarily define the range of rock types of the core sample by combining the rock type library corresponding to the core color system. Also, obtain the crystallization degree, grain size, geometric shape and grain contact relationship of the crystals to determine the rock type of the core sample. Step 3, Mineral Type Identification: Based on the comparison results of the gray values of the core sample image and the gray value range of the mineralized body, the mineralized body area is identified and marked, and the distribution form and mineralization intensity of the mineralized body in the core are obtained to identify the mineral type of the core sample; Step 4: Conclusion Output: Based on the rock type and mineral type of the core sample, infer the mineralization mechanism and assess the mineral resource potential, and provide feedback.
2. The mineral processing exploration and classification method according to claim 1, characterized in that: The specific analysis process of step one is as follows: Core samples were collected from the target rock strata using a drilling rig, and the sampling location and depth were recorded. Surface images of core samples are acquired using image acquisition equipment; The core samples were sliced into equal-thickness sections according to the set rules, and images of each slice layer were acquired. The surface images and slice images of the core samples are preprocessed, including image correction, noise reduction and enhancement. Each preprocessed image is labeled with a type, which includes surface and slice layer. The labeled images are then compiled to obtain an image set of the core samples.
3. The mineral processing exploration and classification method according to claim 1, characterized in that: The specific analysis process for step two is as follows: The RGB values of each image in the core sample image set are obtained and statistically analyzed to obtain the RGB value set. Combined with the RGB value and color correspondence table stored in the database, the color set of the core sample is obtained. The color system of the core sample is obtained based on the color set of the core sample, and the color system includes light color system, dark color system and light color system; Based on the established rock type library corresponding to each color system of the core sample, the corresponding rock type library is selected according to the color system to which the core sample belongs, and the range of rock types of the core sample is initially defined. The similarity of each image of the core sample with the sample images of crystals in the core stored in the database is compared to identify the crystalline regions, and the crystalline regions in each image of the core sample are counted. The area of each crystalline region in each image of the core sample is obtained and summed to obtain the total area of the crystalline region in the core sample image. The area of the core region in each image of the core sample is obtained and summed to obtain the total area of the core region in the core sample image. The ratio of the total area of the crystalline region to the total area of the core region is calculated to obtain the degree of crystallization of the crystals in the core sample. The boundary contours of each crystalline region in each image of the core sample are traced to obtain the length of the crystalline region. The maximum length of the crystalline region is recorded as the grain size of the crystal in the core sample. Based on the crystalline regions in each image of the core sample, the crystalline regions and their distribution on the surface of the rock sample and in each slice layer are obtained. A spatial model of the crystals in the rock sample is constructed, and the geometric morphology of the crystals in the core sample is obtained. Obtain the relative positional relationships between crystals in the spatial model, and combine them with the crystal positional relationships corresponding to various crystal particle contact relationships to obtain the particle contact relationships of crystals in the core sample; Based on the crystal information corresponding to each rock type within the rock type range of the core sample, and combined with the degree of crystallization, grain size, geometric shape and grain contact relationship of the crystals in the core sample, the rock type of the core sample is matched.
4. The mineral processing exploration and classification method according to claim 3, characterized in that: The specific analytical process for obtaining the color system to which the core sample belongs is as follows: S1: Set the color library corresponding to light, dark, and bright colors; S2: Determine whether the core sample color set contains a color from the bright color library. If it does, the core sample color belongs to the bright color library; otherwise, execute S3. S3: Determine whether the core sample color set contains colors from the dark color library. If it does, the core sample color belongs to the dark color library; otherwise, the core sample color belongs to the light color library.
5. The mineral processing exploration and classification method according to claim 3, characterized in that: The specific analytical process for obtaining the rock type of the core sample is as follows: Extract the crystal information corresponding to each rock type stored in the database, and filter out the crystal information corresponding to each rock type within the rock type range of the core sample. The crystal information includes the crystallization degree range, grain size range, geometric shape and grain contact relationship. Based on the degree of crystallization, grain size, geometric morphology, and grain contact relationship of the crystals in the core sample, obtain the sub-items that match the crystal information of the core sample with the crystal information of each rock type; Based on the weights of each sub-item in the set crystal information, the weights of the matching sub-items are obtained by filtering. Based on the sub-items and weights of the matching between the crystal information of the core sample and the crystal information of each rock type, the matching degree between the core sample and each rock type is obtained through weighted fusion analysis. The rock type corresponding to the maximum matching degree is recorded as the rock type of the core sample.
6. The mineral processing exploration and classification method according to claim 1, characterized in that: The specific analysis process in step three is as follows: Image processing techniques are used to obtain the gray values of each image of the core sample and compare them with the gray value range of the mineralized body image. If a gray value belongs to the gray value range of the mineralized body image, the area where the gray value is located is recorded as the mineralized body area. The mineralization regions in each image of the core sample were statistically analyzed and marked. To obtain the distribution pattern and mineralization intensity of mineralized bodies in the core; Based on the distribution patterns and mineralization intensity ranges of mineralized bodies corresponding to various types of minerals stored in the database, the mineral type of the core sample is matched.
7. The mineral processing exploration and classification method according to claim 6, characterized in that: The specific analytical process for obtaining the distribution pattern of mineralized bodies in the core is as follows: Based on the mineralized areas in each image of the core sample, the mineralized areas and their distribution on the surface of the rock sample and in each slice layer are obtained. The three-dimensional spatial mapping technology is used to reconstruct the three-dimensional model of the mineralized body in the core sample to obtain the spatial distribution of the mineralized body in the core sample. Based on the pre-defined spatial distribution characteristics of mineralized bodies in various distribution patterns in the core, the distribution patterns of mineralized bodies in the core sample are obtained.
8. A mineral processing exploration and classification method according to claim 6, characterized in that: The specific analytical process for obtaining mineralization intensity is as follows: Based on the mineralized areas in each image of the core sample, the number of pixels in the mineralized areas and the number of pixels in the core area are obtained in each image of the core sample. The total number of pixels in the mineralized areas and the total number of pixels in the core area are then calculated. The mineralization intensity of the core sample is obtained by calculating the ratio of the total number of pixels in the mineralized body region to the total number of pixels in the core region.
9. The mineral processing exploration and classification method according to claim 1, characterized in that: The specific analysis process in step four is as follows: Based on the established correspondence between rock type and ore type and deposit type and mineralization cause, the corresponding deposit type and mineralization cause of the core sample are matched according to the rock type and ore type of the core sample. Based on the set ore body size level and grade level corresponding to each rock type, and combined with the rock type and ore type of the core sample, the ore body size level and grade level corresponding to the core sample are screened. Based on the pre-defined quantitative mapping relationship between ore body size, grade, and mineral resource potential, the mineral resource potential corresponding to the core sample is obtained according to the ore body size and grade corresponding to the core sample.
10. A mineral processing exploration and analysis classification system, characterized in that, include: Image acquisition module: Acquires images of the surface and each slice layer of the core sample, preprocesses the acquired images, annotates them, and summarizes them to obtain an image set of the core sample; Rock type determination module: Based on the image set of the core sample, the color of the core is obtained. Combined with the rock type library corresponding to the core color system, the range of rock types of the core sample is initially defined. The crystallization degree, grain size, geometric shape and grain contact relationship of the crystals are obtained to determine the rock type of the core sample. Mineral type identification module: Based on the comparison results of the gray value of the core sample image and the gray value range of the mineralized body, the mineralized body region is identified and marked, and the distribution form and mineralization intensity of the mineralized body in the core are obtained to identify the mineral type of the core sample; Conclusion output module: Based on the rock type and mineral type of the core sample, infer the mineralization mechanism and assess the mineral resource potential, and provide feedback.