CN112730326A - Intelligent identification device and method for rock slices - Google Patents
Intelligent identification device and method for rock slices Download PDFInfo
- Publication number
- CN112730326A CN112730326A CN202110181773.4A CN202110181773A CN112730326A CN 112730326 A CN112730326 A CN 112730326A CN 202110181773 A CN202110181773 A CN 202110181773A CN 112730326 A CN112730326 A CN 112730326A
- Authority
- CN
- China
- Prior art keywords
- rock
- mineral
- image
- rock slice
- microscopic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/41—Refractivity; Phase-affecting properties, e.g. optical path length
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/21—Polarisation-affecting properties
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1734—Sequential different kinds of measurements; Combining two or more methods
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an intelligent identification device and method for rock slices, wherein the device comprises: the microscopic image acquisition equipment acquires rock microscopic images of the rock slices; the mineral measurement imaging device acquires a mineral fingerprint image of the rock slice; and the image processing system is respectively connected with the microscopic image acquisition equipment and the mineral measurement imaging equipment, and identifies the rock slice based on the rock microscopic image and the mineral fingerprint image. The intelligent identification device for the rock slice acquires a rock microscopic image through the microscopic image acquisition equipment, acquires a mineral fingerprint image through the mineral measurement imaging equipment, digitally synthesizes the rock microscopic image and the mineral fingerprint image through the image processing system, identifies the rock slice, and finally outputs an identification report of the rock slice, so that the intelligent and automatic identification of the rock slice is realized, the influence of subjective factors of manual identification is avoided, the identification accuracy is high, and the identification speed is high.
Description
Technical Field
The invention belongs to the field of geological, petroleum geology and rock and ore experimental research, and particularly relates to an intelligent identification device and method for a rock slice sample.
Background
Rock (mineral) identification is the lead and basis of all research in the geological and energy mining industries. Since 1827, the scotland geologist william invention polarization microscope and lamella preparation method, the british geologist crifton applied this to rock research, grinding the rock into thin slices with thickness of 30 μ, observing the optical property of the mineral with transmitted light under the polarization microscope and accurately identifying, it becomes the basic means for identifying the rock (mineral). In recent 200 years, with the continuous progress of scientific technology, various new testing techniques and research methods are continuously introduced, but rock slice identification is used as the most intuitive and basic analysis method in the geological and petroleum industries.
The identification of rock (mineral) slices under a polarization microscope mainly comprises four aspects: 1. the mineral is the identification of the mineral, the mineral is a constituent unit of rock, and mineral information is generally obtained from the aspects of crystal form, cleavage and cleavage, color, pleochroism and absorptivity, interference color and birefringence, axiality, optical property and the like; 2. the structure, namely the judgment of the rock structure, is characterized in that the rock structure is also an important identification characteristic because three rock types (sedimentary rock, metamorphic rock and magmatic rock) have relative characteristic structures; 3. the measurement of the size, namely the grain size and the particle size, is finished by a scale bar carried by a microscope; 4. statistics, i.e. statistics of various mineral and structural components, is the basis for the accurate naming of rocks. The four aspects are combined with each other, so that the whole rock and ore identification process can be completed. At present, the traditional manual identification mode is mainly adopted for identifying the rock (mineral) slices.
The main problems existing in the traditional manual identification mode are as follows: the difficulty is high, the subjectivity is strong, the identification efficiency is low, and the accuracy is limited. The rock is the most complex multi-end-element solid mixture in the nature, and different combination modes of nearly 4000 natural minerals cause the natural complexity of the rock minerals and also cause high difficulty in rock and ore identification work. Most people go through 8-10 years of practice, tens of thousands of thin sheet identification learning and experience accumulation can be sufficient for the work, and the identification speed of 1 hour/piece is reached. And the traditional working mode taking experience as the leading mode also leads the cognitive specification and standard of the appraisers to the rock to be not completely unified, the appraisal conclusion of different appraisers has common deviation, and the accuracy cannot be ensured.
In recent years, with the application development of artificial intelligence in the field of image recognition, technical methods such as a support vector machine, a BP neural network and the like are widely adopted for the analysis of rock slice images. For example, according to spectral and textural features of a quartz sandstone image, a research method for quantitatively extracting quartz mineral features based on multi-scale segmentation is proposed by phyllanthus of the geological university of china (wuhan), and information such as boundaries of quartz particles, volume fractions, sizes, circumferences, lengths and orientations of long axes, ratios of long axes to short axes, solidity and morphological indexes of the quartz particles is obtained by taking a single polarization image of iron quartz sandstone as an experimental object (journal of the university of Jilin (version of Earth science), 2011). The Cheng nationality of the university of Western 'an oil and the like propose a rock granularity automatic classification method based on convolutional neural network deep learning, which realizes automatic image feature extraction through a convolutional neural network model, and simultaneously establishes a mode classification method to realize granularity automatic identification based on a slice image (journal of the university of Western' an oil (Nature science edition), 2107). On the basis of sandstone slice microscopic image analysis research, a sandstone microscopic image analysis software system is designed and developed by Hahuizhen and the like in Nanjing university, the sandstone slice microscopic image is firstly segmented based on an image segmentation method of superpixel segmentation and clustering to form superpixels with only a single mineral component, then the mineral microscopic image is used as training data, characteristic parameters such as color and local part are extracted to train a classifier to classify the superpixels, finally adjacent superpixels are combined to form complete mineral particles, the category components are calibrated, the software is used for analyzing the mineral components and the structural features in the Tibet sandstone slice microscopic image, and the classification accuracy rates of the three mineral contents are 92% of quartz, 42% of feldspar and 17% of detritus (computer science, 2017).
The technology has the following defects: only the technical methods such as image segmentation and BP neural network are provided to process a certain special rock slice image and identify a part of characteristic parameters such as particle size, boundary, granularity or category, so that the obtained rock characteristics are incomplete, the accurate identification of minerals is lacked, and the complete rock slice identification process is not involved.
In addition, the intelligent analysis device for the rock slice and the analysis method thereof are also invented by the Chinese geological university (Beijing), the device comprises an intelligent analysis upper computer and an intelligent analysis host computer, the intelligent analysis upper computer emits transmission light to be projected on the rock slice, the intensity of the projected light can be changed due to different physical properties of a matrix and particles in the rock slice, the projected light intensity is analyzed to distinguish the matrix and the particles, and the parameters such as the type, the size and the like of the particles are counted, for example, when the light intensity is less than 30, the region is considered as the rock matrix, and when the light intensity is more than 30, the region is considered as the particle region (the invention application number is 201710384999.8).
The disadvantages of this device are: the rock is a complex mixture with very strong heterogeneity, the composition components of the rock are not only transparent minerals, but also opaque minerals such as metals, and the identification of the rock slice can not be solved by only light transmittance.
In conclusion, the existing intelligent identification method cannot accurately identify the minerals in the rock, and cannot perform complete rock slice identification.
Disclosure of Invention
The invention aims to provide a quick and accurate intelligent identification method for a rock slice.
In order to achieve the above object, the present invention provides an intelligent rock slice identification device, comprising: the microscopic image acquisition equipment acquires a rock microscopic image of the rock slice; a mineralogical measurement imaging device that acquires a mineralogical fingerprint image of the rock slice; and the image processing system is respectively connected with the microscopic image acquisition equipment and the mineral measurement imaging equipment, and identifies the rock slice based on the rock microscopic image and the mineral fingerprint image.
Optionally, the microscopic image collecting device and the mineral measurement imaging device collect mineral fingerprint images in the same visual field.
Optionally, the microscopic image collecting apparatus includes a first light source, a first stage, a first objective lens, a polarizing device, a first CCD camera, a first base, and a first support; the polarization device comprises a polarizer and an analyzer, the polarizer and a first light source are arranged on the first base, and the first base is connected with the bottom of the first support; the middle part of the first bracket is provided with a first objective table, the first objective table is used for bearing the rock slice, the top of the first bracket is provided with a first lens cone, the first lens cone is provided with an analyzer, the bottom of the first lens cone is provided with a first installation objective converter, and the first installation objective converter is provided with a first objective; the top of the first lens cone is provided with a first CCD camera, and the first CCD camera collects rock microscopic images under single polarization or orthogonal polarization.
Optionally, the mineral measurement imaging device includes a second light source, a second objective table, a second objective lens, a measuring apparatus, a second CCD camera, a second base, and a second support; a second light source is arranged on the second base, and the second base is connected with the bottom of the second support; a second object stage is arranged in the middle of the second support and used for bearing the rock slice; the top of the second support is provided with a second lens barrel, the bottom of the second lens barrel is provided with a second objective lens mounting converter, and a second objective lens is arranged on the second objective lens mounting converter; and the top of the second lens barrel is provided with a measuring device and a second CCD camera, the measuring device measures and identifies minerals in the rock slice, and the second CCD camera collects mineral fingerprint images of the measuring device for mineral measurement and identification.
Optionally, the second light source provides light with a preset wavelength for the rock slice; the second objective is used for carrying out microscopic amplification and micro-area measurement on the rock slice under the irradiation of the light with the preset wavelength; the measuring device acquires the mineral refractive index in the rock slice measured by the microscopic magnification and the micro-area, determines the mineral type corresponding to the refractive index according to the refractive index, and marks the mineral type on the image measured by the microscopic magnification and the micro-area; and the second CCD camera collects the images of the measuring device after the mineral types are marked, and mineral fingerprint images are obtained.
Optionally, the image processing system includes a digital synthesis module, an intelligent recognition module and an output module, and the intelligent recognition module is connected to the digital synthesis module and the output module respectively.
Optionally, the digital synthesis module extracts the mineral type in the mineral fingerprint image, and marks the mineral type at a position corresponding to the mineral type in the rock microscopic image, so as to obtain an identification image of the rock slice.
Optionally, the intelligent identification module identifies the identification image of the rock slice by a digital image processing technology and a convolutional neural network technology to obtain mineral composition, structure, size and statistical information.
Optionally, the output module fills the image recognition result in a pre-stored analysis report template to generate a rock slice identification report.
In a second aspect, the present invention further provides an intelligent identification method for a rock slice, which utilizes the intelligent identification device for a rock slice, including: collecting rock microscopic images of the rock slice sample; acquiring a mineral fingerprint image of the rock slice; and identifying the rock slice based on the rock microscopic image and the mineral fingerprint image.
The invention has the beneficial effects that: the intelligent identification device for the rock slice acquires a rock microscopic image of the rock slice through the microscopic image acquisition equipment, acquires a mineral fingerprint image of the rock slice through the mineral measurement imaging equipment, digitally synthesizes the rock microscopic image and the mineral fingerprint image through the image processing system, identifies the rock slice, realizes intelligent and automatic identification of the rock slice, avoids the influence of subjective factors of manual identification, has high identification accuracy and high identification speed, and improves the identification efficiency.
The present invention has other features and advantages which will be apparent from or are set forth in detail in the accompanying drawings and the following detailed description, which are incorporated herein, and which together serve to explain certain principles of the invention.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
Fig. 1 shows a connection structure diagram of a rock slice intelligent authentication apparatus according to an embodiment of the present invention.
Fig. 2 shows a connection structure diagram of a microscopic image acquisition device of the intelligent rock slice authentication apparatus according to an embodiment of the present invention.
Fig. 3 shows a connection structure diagram of a microscopic image collector of the intelligent rock slice identification device according to one embodiment of the invention.
Fig. 4 shows a flow chart of a method of intelligent identification of rock slices according to an embodiment of the invention.
Description of the main reference numerals:
102. microscopic image acquisition equipment; 21. a first light source; 22. a first stage; 23. a first objective lens; 24. a first CCD camera; 25. a first base; 26. a first bracket; 27. a first barrel; 28. a first mount objective changer; 104. a mineral measurement imaging device; 41. a second light source; 42. a second stage; 43. a second objective lens; 44. a second CCD camera; 45. a second base; 46. a second bracket; 47. a measuring device; 48. a second mount objective changer; 49. a second barrel; 106. an image processing system.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below. While the following describes preferred embodiments of the present invention, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The invention provides an intelligent rock slice identification device, which comprises: the microscopic image acquisition equipment acquires rock microscopic images of the rock slices; the mineral measurement imaging device acquires a mineral fingerprint image of the rock slice; and the image processing system is respectively connected with the microscopic image acquisition equipment and the mineral measurement imaging equipment, and identifies the rock slice based on the rock microscopic image and the mineral fingerprint image.
Specifically, a microscopic image acquisition device acquires a rock microscopic image of a rock slice, a mineral measurement imaging device acquires a mineral fingerprint image of the rock slice, and then an image processing system performs digital synthesis on the rock microscopic image and the mineral fingerprint image, performs intelligent identification on the rock slice, and finally outputs an identification result.
According to the exemplary embodiment, the intelligent rock slice identification device collects rock microscopic images of rock slices through the microscopic image collection equipment, mineral fingerprint images of the rock slices are collected through the mineral measurement imaging equipment, the rock microscopic images and the mineral fingerprint images are digitally synthesized through the image processing system, intelligent identification and identification result output are conducted on the digitally synthesized images, intelligent and automatic identification of the rock slices is achieved, the influence of subjective factors of manual identification is avoided, the identification accuracy is high, the identification speed is high, and the identification efficiency is improved.
Alternatively, the microscopic image acquisition device and the mineral measurement imaging device acquire mineral fingerprint images under the same visual field.
Specifically, the microscopic image acquisition system and the mineral measurement imaging system acquire images under the same visual field, so that the texture features are the same.
As an alternative, the microscopic image acquisition equipment comprises a first light source, a first objective table, a first objective lens, a polarizing device, a first CCD camera, a first base and a first bracket; the polarizing device comprises a polarizer and an analyzer, the polarizer and a first light source are arranged on the first base, and the first base is connected with the bottom of the first support; the middle part of the first bracket is provided with a first objective table, the first objective table is used for bearing rock slices, the top of the first bracket is provided with a first lens cone, the first lens cone is provided with an analyzer, the bottom of the first lens cone is provided with a first installation objective converter, and the first installation objective converter is provided with a first objective; the top of the first lens cone is provided with a first CCD camera, and the first CCD camera collects rock microscopic images under single polarization or orthogonal polarization.
Specifically, the microscopic image collector is used for collecting a rock microscopic image, and includes, but is not limited to, a first light source, a first stage, a first objective lens, a polarizing device, a first CCD camera, a first base, and a first support.
The bottom and the first base fixed connection of first support, the middle part of first support is equipped with first objective table, and the top of first support is equipped with first lens cone. The polarizing device comprises a polarizer and an analyzer, the polarizer and a first light source are arranged on a first base, the analyzer is arranged on a first lens barrel, a first installation objective lens converter is arranged at the bottom of the first lens barrel, a first objective lens is arranged on the first installation objective lens converter, a first CCD camera is arranged at the top of the first lens barrel, a rock slice sample is placed on a first objective table, and the rock slice sample is amplified through the first light source and the first objective lens and collected through the first CCD camera to obtain a rock microscopic image under single polarization light or orthogonal polarization light.
The first light source is a monochromatic light source, emits visible light and can quickly and flexibly adjust light; the first objective table is a horizontal platform for placing a rock slice sample; the first objective lens is used for carrying out microscopic amplification on the rock slice, the direction and the polarization direction of the polarizer are fixed, and light rays are changed into linearly polarized light in a single direction after passing through the polarizer; the position of the analyzer is not fixed, the analyzer can be pushed in or out in a translation way, and the direction and the polarization direction of the analyzer can be freely adjusted; the first CCD camera collects rock microscopic images to obtain the rock microscopic images under orthogonal polarization.
As an alternative, the mineral measurement imaging device comprises a second light source, a second objective table, a second objective lens, a measuring device, a second CCD camera, a second base and a second support; a second light source is arranged on the second base, and the second base is connected with the bottom of the second support; a second objective table is arranged in the middle of the second support and used for bearing the rock slices; the top of the second bracket is provided with a second lens barrel, the bottom of the second lens barrel is provided with a second objective lens mounting converter, and a second objective lens is arranged on the second objective lens mounting converter; the top of the second lens cone is provided with a measuring device and a second CCD camera, the measuring device measures and identifies minerals in the rock slice, and the second CCD camera collects mineral fingerprint images of the measuring device for mineral measurement and identification.
Specifically, the mineral measurement imager is used for acquiring a mineral fingerprint image and comprises, but is not limited to, a second light source, a second object stage, a second objective lens, a measuring device, a second CCD camera, a second base and a second support.
The bottom of the second support is fixedly connected with the second base, a second objective table is arranged in the middle of the second support, a second lens cone is arranged at the top of the second support, a second objective lens is arranged on the second lens cone, a measuring device is arranged above the objective lens of the second lens cone, and a second CCD camera is arranged above the measuring device. The second light source is arranged on the second base, the second light source irradiates the second objective table from the lower side to place a rock slice sample, the second objective lens carries out microscopic amplification on the rock slice on the second objective table, and the measuring device carries out measurement and identification on minerals in the rock slice after the microscopic amplification.
The second light source mainly excites the specific wavelength light for measurement on the rock slice, and the wavelength of the specific wavelength light depends on the measuring device; the second objective table is a horizontal platform for placing the rock slice sample; microscopic amplification is carried out on the rock slice by the second objective lens; the measuring device measures and identifies minerals in the rock based on physical or chemical characteristics; the second CCD camera collects mineral fingerprint images, and the mineral fingerprint images are images which correspond to the rock microscopic images and are formed by accurately naming various minerals.
Alternatively, the second light source provides light of a preset wavelength to the rock slices; the second objective is used for carrying out microscopic amplification and micro-area measurement on the rock slice under the irradiation of light with the preset wavelength; the measuring device obtains the mineral refractive index in the rock slice which is subjected to microscopic amplification and micro-area measurement, determines the mineral type corresponding to the refractive index according to the refractive index, and marks the mineral type on the image which is subjected to microscopic amplification and micro-area measurement; and the second CCD camera collects the images of the measuring device after the mineral types are marked, and mineral fingerprint images are obtained.
Specifically, the method adopted by the measuring device is refractive index measurement, a second light source excites specific wavelength light for measurement, the specific wavelength light irradiates a rock slice sample on a second objective table, the rock slice sample is subjected to microscopic amplification through a second objective lens, the measuring device measures the mineral refractive index of a rock micro-region of the rock slice after the microscopic amplification, identifies the mineral based on the refractive index, determines the type of the mineral corresponding to the refractive index, marks the type of the mineral on the rock slice image after the microscopic amplification, collects a rock slice image after the mineral type is marked by a second CCD, takes the rock slice image after the mineral type is marked as a mineral fingerprint image, obtains a mineral fingerprint image under the same visual field as the rock microscopic image, and gives accurate names to various minerals on the rock microscopic image by the mineral fingerprint image.
Preferably, the image processing system comprises a digital synthesis module, an intelligent identification module and an output module, wherein the intelligent identification module is respectively connected with the digital synthesis module and the output module.
Alternatively, the intelligent identification module extracts the mineral types marked in the mineral fingerprint image, marks the mineral types at the positions corresponding to the mineral types in the rock microscopic image, and obtains the identification image of the rock slice.
As a preferred scheme, the intelligent identification module identifies the identification image of the rock slice through a digital image processing technology and a convolutional neural network technology to obtain mineral components, structure, size and statistical information.
Preferably, the output module fills the image recognition result into a pre-stored analysis report template to generate the rock slice identification.
Specifically, the image processing system is composed of a digital synthesis module, an intelligent identification module and an output module.
The digital synthesis module is mainly used for digitally synthesizing the rock microscopic image and the mineral fingerprint image, as the microscopic image acquisition system and the mineral measurement imaging system acquire images under the same visual field, the texture characteristics are the same, the digital synthesis module firstly extracts the mineral types marked in the mineral fingerprint image and marks the mineral types at the positions corresponding to the mineral types in the rock microscopic image, the rock microscopic image marked with the mineral types is used as an identification image of a rock slice, and the identification image comprises all the characteristics of the rock microscopic image and the precise type names of various minerals in the image.
The intelligent identification module is mainly used for obtaining information such as minerals, structures, sizes, statistics and the like in an image through a digital image processing technology and a convolutional neural network technology after receiving a rock slice identification image, and then matching the information to a category corresponding to rocks to realize high-performance rock identification on the rock slice.
And the output module is mainly used for writing the identification result of the rock slice image into the corresponding rock slice identification report template according to the format and then storing the identification result to generate the corresponding rock slice identification report.
According to the intelligent identification method for the rock slices, the intelligent identification device for the rock slices comprises the following steps: collecting rock microscopic images of the rock slices; acquiring a mineral fingerprint image of a rock slice; and identifying the rock slice based on the rock microscopic image and the mineral fingerprint image.
Specifically, a microscopic image acquisition device acquires a rock microscopic image of the rock slice, a mineral measurement imaging device acquires a mineral fingerprint image of the rock slice, and the rock microscopic image and the mineral fingerprint image are digitally synthesized by an image processing system to identify the rock slice.
According to an exemplary embodiment, the intelligent identification method for the rock slice is used for acquiring a rock microscopic image of the rock slice, acquiring a mineral fingerprint image of the rock slice, digitally synthesizing the rock microscopic image and the mineral fingerprint image, identifying the rock slice, realizing intelligent and automatic identification of the rock slice, avoiding the influence of subjective factors of manual identification, having high identification accuracy and high identification speed, and improving the identification efficiency.
Alternatively, obtaining the identification result of the rock slice based on the rock microscopic image and the mineral fingerprint image comprises: and extracting the mineral types marked in the mineral fingerprint image, marking the mineral types at the positions corresponding to the mineral types in the rock microscopic image, and obtaining an identification image of the rock slice.
Specifically, the rock microscopic image and the mineral fingerprint image are digitally synthesized, as the microscopic image acquisition system and the mineral measurement imaging system acquire images under the same visual field, the texture characteristics are the same, the mineral type marked in the mineral fingerprint image is firstly extracted, the mineral type is marked at the position corresponding to the mineral type in the rock microscopic image, and the rock microscopic image marked with the mineral type is used as an identification image of a rock slice, wherein the identification image comprises all characteristics of the rock microscopic image and the precise type name of each mineral in the image.
Through a digital image processing technology and a convolutional neural network technology, information such as minerals, structures, sizes, statistics and the like in the image is obtained, then the information is matched with the corresponding categories of rocks, and the rock slices realize high-performance rock recognition.
And writing the recognition result of the rock slice image into a corresponding rock slice identification report template according to the format, and then storing to generate a corresponding rock slice identification report.
Example one
Fig. 1 shows a connection structure diagram of a rock slice intelligent authentication apparatus according to an embodiment of the present invention. Fig. 2 shows a connection structure diagram of a microscopic image acquisition device of the intelligent rock slice authentication apparatus according to an embodiment of the present invention. Fig. 3 shows a connection structure diagram of a microscopic image collector of the intelligent rock slice identification device according to one embodiment of the invention.
Referring to fig. 1, 2 and 3, the intelligent identification device for rock slices comprises: the microscopic image acquisition device 102 is used for acquiring a rock microscopic image of the rock slice by the microscopic image acquisition device 102; a mineralogical measurement imaging device 104, wherein the mineralogical measurement imaging device 104 acquires a mineralogical fingerprint image of the rock slice; and an image processing system 106, wherein the image processing system 106 is respectively connected with the microscopic image acquisition device 102 and the mineral measurement imaging device 104, and identifies the rock slice based on the rock microscopic image and the mineral fingerprint image.
Wherein, the microscopic image acquisition device 102 and the mineral measurement imaging device 104 acquire mineral fingerprint images under the same visual field.
The microscopic image collecting device 102 includes a first light source 21, a first stage 22, a first objective 23, a polarizing device, a first CCD camera 24, a first base 25, and a first support 26; the polarizing device comprises a polarizer and an analyzer, the polarizer and the first light source 21 are arranged on the first base 25, and the first base 25 is connected with the bottom of the first support 26; a first objective table 22 is arranged in the middle of the first support 26, the first objective table 22 is used for bearing rock slices, a first lens barrel 27 is arranged at the top of the first support 26, an analyzer is arranged on the first lens barrel 27, a first objective lens mounting converter 28 is arranged at the bottom of the first lens barrel 27, and a first objective lens 23 is arranged on the first objective lens mounting converter 28; the top of the first lens cone 27 is provided with a first CCD camera 24, and the first CCD camera 24 collects rock microscopic images under single polarization or orthogonal polarization.
The mineral measurement imaging device 104 comprises a second light source 41, a second objective table 42, a second objective lens 43, a measuring device 47, a second CCD camera 48, a second base 45 and a second bracket 46; the second base 45 is provided with a second light source 41, and the second base 45 is connected with the bottom of the second bracket 46; a second object stage 42 is arranged in the middle of the second support 46, and the second object stage 42 is used for bearing the rock slices; a second lens barrel 49 is arranged at the top of the second bracket 46, a second objective lens mounting converter 48 is arranged at the bottom of the second lens barrel 49, and a second objective lens 43 is arranged on the second objective lens mounting converter 48; the top of the second lens cone 49 is provided with a measuring device 47 and a second CCD camera 44, the measuring device 47 measures and identifies minerals in the rock slice, and the second CCD camera 44 collects mineral fingerprint images of the mineral measuring and identifying device.
Wherein the second light source 41 provides light with a preset wavelength for the rock slice; the second objective 43 performs microscopic amplification and micro-area measurement on the rock slice under the irradiation of light with a preset wavelength; the measuring device 47 acquires the mineral refractive index of the rock slice subjected to microscopic amplification and micro-area measurement, determines the mineral type corresponding to the refractive index according to the refractive index, and marks the mineral type on the image subjected to microscopic amplification and micro-area measurement; the second CCD camera 44 collects the images of the measuring device after the mineral species are marked, obtaining a mineral fingerprint image.
The image processing system 106 includes a digital synthesis module, an intelligent recognition module, and an output module, where the intelligent recognition module is connected to the digital synthesis module and the output module, respectively.
The digital synthesis module extracts the mineral types marked in the mineral fingerprint image, marks the mineral types at the positions corresponding to the mineral types in the rock microscopic image and obtains the identification image of the rock slice of the rock sample.
The intelligent identification module identifies the identification image of the rock slice through a digital image processing technology and a convolutional neural network technology to obtain mineral components, structure, size and statistical information.
And the output module fills the image recognition result into a pre-stored analysis report template to generate a rock slice identification report.
Example two
Fig. 4 shows a flow chart of a method of intelligent identification of rock slices according to an embodiment of the invention.
As shown in fig. 4, the intelligent identification method for rock slices, which uses the intelligent identification device for rock slices, comprises:
step 1: collecting rock microscopic images of the rock slices;
step 2: acquiring a mineral fingerprint image of a rock slice;
and step 3: and identifying the rock slice based on the rock microscopic image and the mineral fingerprint image.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (10)
1. An intelligent rock slice identification device, comprising:
the microscopic image acquisition equipment acquires a rock microscopic image of the rock slice;
a mineralogical measurement imaging device that acquires a mineralogical fingerprint image of the rock slice;
and the image processing system is respectively connected with the microscopic image acquisition equipment and the mineral measurement imaging equipment, and identifies the rock slice based on the rock microscopic image and the mineral fingerprint image.
2. The intelligent rock slice identification device of claim 1 wherein the microscopic image acquisition device acquires an image of a mineral fingerprint in the same field of view as the mineral measurement imaging device.
3. The intelligent rock slice identification device of claim 2, wherein the microscopic image acquisition equipment comprises a first light source, a first stage, a first objective lens, a polarizing device, a first CCD camera, a first base and a first bracket;
the polarization device comprises a polarizer and an analyzer, the polarizer and a first light source are arranged on the first base, and the first base is connected with the bottom of the first support;
the middle part of the first bracket is provided with a first objective table, the first objective table is used for bearing the rock slice, the top of the first bracket is provided with a first lens cone, the first lens cone is provided with an analyzer, the bottom of the first lens cone is provided with a first installation objective converter, and the first installation objective converter is provided with a first objective;
the top of the first lens cone is provided with a first CCD camera, and the first CCD camera collects rock microscopic images under single polarization or orthogonal polarization.
4. The intelligent rock slice identification device of claim 3, wherein the mineral measurement imaging device comprises a second light source, a second stage, a second objective lens, a measuring device, a second CCD camera, a second base and a second bracket;
a second light source is arranged on the second base, and the second base is connected with the bottom of the second support;
a second object stage is arranged in the middle of the second support and used for bearing the rock slice;
the top of the second support is provided with a second lens barrel, the bottom of the second lens barrel is provided with a second objective lens mounting converter, and a second objective lens is arranged on the second objective lens mounting converter;
and the top of the second lens barrel is provided with a measuring device and a second CCD camera, the measuring device measures and identifies minerals in the rock slice, and the second CCD camera collects mineral fingerprint images of the measuring device for mineral measurement and identification.
5. The intelligent rock slice authentication device of claim 4, wherein the second light source provides light of a preset wavelength to the rock slice;
the second objective is used for carrying out microscopic amplification and micro-area measurement on the rock slice under the irradiation of the light with the preset wavelength;
the measuring device acquires the mineral refractive index in the rock slice measured by the microscopic magnification and the micro-area, determines the mineral type corresponding to the refractive index according to the refractive index, and marks the mineral type on the image measured by the microscopic magnification and the micro-area;
and the second CCD camera collects the images of the measuring device after the mineral types are marked, and mineral fingerprint images are obtained.
6. The intelligent rock slice authentication device of claim 1, wherein the image processing system comprises a digital synthesis module, an intelligent recognition module and an output module, the intelligent recognition module being connected to the digital synthesis module and the output module, respectively.
7. The intelligent rock slice identification device of claim 6, wherein the digital synthesis module extracts the mineral species in the mineral fingerprint image and marks the mineral species at a position corresponding to the mineral species in the rock microscopic image to obtain an identification image of a rock slice.
8. The intelligent rock slice identification device of claim 5, wherein the intelligent recognition module recognizes the identification image of the rock slice through digital image processing technology and convolutional neural network technology to obtain mineral composition, structure, size and statistical information.
9. The intelligent rock slice identification device of claim 6, wherein the output module fills the image recognition result in a pre-stored analysis report template to generate a rock slice identification report.
10. An intelligent rock slice identification method using the intelligent rock slice identification device according to any one of claims 1 to 9, comprising:
collecting rock microscopic images of the rock slices;
acquiring a mineral fingerprint image of the rock slice;
and identifying the rock slice based on the rock microscopic image and the mineral fingerprint image.
Priority Applications (11)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181773.4A CN112730326A (en) | 2021-02-08 | 2021-02-08 | Intelligent identification device and method for rock slices |
| CN202110654275.7A CN113435458A (en) | 2021-02-08 | 2021-06-11 | Rock slice image segmentation method, device and medium based on machine learning |
| CN202110653323.0A CN113537235A (en) | 2021-02-08 | 2021-06-11 | Rock identification method, system, device, terminal and readable storage medium |
| CN202110654942.1A CN113435459A (en) | 2021-02-08 | 2021-06-11 | Rock component identification method, device, equipment and medium based on machine learning |
| CN202110655073.4A CN113435460A (en) | 2021-02-08 | 2021-06-11 | Method for identifying brilliant particle limestone image |
| CN202110654212.1A CN113435457A (en) | 2021-02-08 | 2021-06-11 | Clastic rock component identification method, clastic rock component identification device, clastic rock component identification terminal and clastic rock component identification medium based on images |
| CN202110653812.6A CN113435456A (en) | 2021-02-08 | 2021-06-11 | Rock slice component identification method and device based on machine learning and medium |
| PCT/CN2021/121840 WO2022166232A1 (en) | 2021-02-08 | 2021-09-29 | Rock identification method, system and apparatus, terminal, and readable storage medium |
| JP2023548202A JP2024508688A (en) | 2021-02-08 | 2021-09-29 | Methods, systems, devices, terminals and readable storage media for identifying rocks |
| EP21924229.4A EP4290470A1 (en) | 2021-02-08 | 2021-09-29 | Rock identification method, system and apparatus, terminal, and readable storage medium |
| US18/264,654 US20240054766A1 (en) | 2021-02-08 | 2021-09-29 | Rock identification method, system and apparatus, terminal, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181773.4A CN112730326A (en) | 2021-02-08 | 2021-02-08 | Intelligent identification device and method for rock slices |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112730326A true CN112730326A (en) | 2021-04-30 |
Family
ID=75596607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110181773.4A Pending CN112730326A (en) | 2021-02-08 | 2021-02-08 | Intelligent identification device and method for rock slices |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112730326A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113378825A (en) * | 2021-07-09 | 2021-09-10 | 中海石油(中国)有限公司 | Sandstone slice image identification method and system based on artificial intelligence |
| CN113569623A (en) * | 2021-06-11 | 2021-10-29 | 中国石油化工股份有限公司 | Method and device for determining material components, terminal and readable storage medium |
| CN113569624A (en) * | 2021-06-11 | 2021-10-29 | 中国石油化工股份有限公司 | Method and device for determining components of clastic rock, terminal and readable storage medium |
| CN113779341A (en) * | 2021-06-11 | 2021-12-10 | 中国石油化工股份有限公司 | Database-based mineral type determination method, device, terminal and medium |
-
2021
- 2021-02-08 CN CN202110181773.4A patent/CN112730326A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569623A (en) * | 2021-06-11 | 2021-10-29 | 中国石油化工股份有限公司 | Method and device for determining material components, terminal and readable storage medium |
| CN113569624A (en) * | 2021-06-11 | 2021-10-29 | 中国石油化工股份有限公司 | Method and device for determining components of clastic rock, terminal and readable storage medium |
| CN113779341A (en) * | 2021-06-11 | 2021-12-10 | 中国石油化工股份有限公司 | Database-based mineral type determination method, device, terminal and medium |
| CN113378825A (en) * | 2021-07-09 | 2021-09-10 | 中海石油(中国)有限公司 | Sandstone slice image identification method and system based on artificial intelligence |
| CN113378825B (en) * | 2021-07-09 | 2024-04-05 | 中海石油(中国)有限公司 | Sandstone sheet image identification method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112730326A (en) | Intelligent identification device and method for rock slices | |
| CN108074231B (en) | Magnetic sheet surface defect detection method based on convolutional neural network | |
| CN105352873B (en) | The characterizing method of shale pore structure | |
| CN102297660B (en) | Measuring method of shield tunnel lining segment seam open width and apparatus thereof | |
| CN102253016B (en) | Microscopic fluorescence identification method for arene component of oil gas inclusion | |
| CN101915738A (en) | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique | |
| CN107449782A (en) | Phone housing side edge surface defect digitizes quantitative detection system | |
| US11488401B2 (en) | Prostate cancer tissue image classification with deep learning | |
| CN100357725C (en) | Method and device for rapidly detecting tenderness of beef utilizing near infrared technology | |
| CN103345617A (en) | Method and system for recognizing traditional Chinese medicine | |
| CN108152216A (en) | A kind of drilling three-dimensional mineral map plotting method based on core EO-1 hyperion scan image | |
| CN107884412B (en) | Annual ring information detection device and method for conifer tree core | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| Chen et al. | Feasibility study on automated recognition of allergenic pollen: grass, birch and mugwort | |
| Chopard et al. | Automated sulfides quantification by multispectral optical microscopy | |
| CN116883394B (en) | Diamond quality detection method based on image data processing | |
| CN108335310B (en) | Portable grain shape and granularity detection method and system | |
| CN110427943A (en) | A kind of intelligent electric meter technique for partitioning based on R-CNN | |
| CN112884058A (en) | Fritillaria variety identification method and system based on image and hyperspectrum combination | |
| CN201522431U (en) | Rock debris substance image analyzer | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| Karasik | A complete, automatic procedure for pottery documentation and analysis | |
| CN106203351A (en) | The method of crack Intelligent Recognition classification | |
| CN116087198B (en) | Highway road surface situation data acquisition equipment and automatic rapid detection system thereof | |
| CN109214433A (en) | A kind of method that convolutional neural networks distinguish liver cancer differentiation grade |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210430 |
|
| WD01 | Invention patent application deemed withdrawn after publication |