Microscopic image processing device and method based on data driving

Abstract

The invention provides a microscopic image processing device and method based on data driving, and relates to the technical field of intelligent equipment, the microscopic image processing device comprises a fixing and structure supporting system, a rotation control system, a microscope system and an image acquisition and processing system; wherein the fixing and structure supporting system comprises an objective table and a fixing piece; the microscope system comprises a carrying disc, an eyepiece, an objective lens and a focal length adjusting circuit, and is used for carrying out microscopic observation on a to-be-identified sheet; the rotation control system comprises a high-precision motor, a driving rotating shaft and a gear, and the to-be-identified sheet in the groove rotates under the condition that the gear and the driving rotating shaft are driven by the high-precision motor; and the image acquisition and processing system comprises an image acquisition module and an image processing module and is used for acquiring a microscopic image of the to-be-identified slice and identifying and analyzing mineral components based on the microscopic image. Through motor driving and software linkage, the microscopic image acquisition efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent devices, and in particular to a data-driven microscopic image processing device and method. Background Art

[0002] Shale, sandstone and carbonate rock are common and important types of sedimentary rocks, and their mineral composition has a profound impact on geological research and resource development. Traditional mineral identification methods usually rely on manual observation and chemical analysis, which is not only inefficient, but also prone to subjectivity due to human interference, limiting the scope of application and accuracy. At present, many microscope imaging systems still rely on manual operation. Users need to manually adjust the microscope settings and take images. This method is not only time-consuming but also easily affected by human factors, resulting in inconsistency in image acquisition. At the same time, traditional image processing methods have low acquisition efficiency and lack of flexibility when facing complex detection links. Summary of the invention

[0003] The purpose of the present invention is to solve the problem of low efficiency and lack of flexibility in current microscopic detection and image acquisition, and to provide a data-driven microscopic image processing device and method.

[0004] The technical solution of the embodiment of the present application is implemented as follows: The first aspect of the embodiment of the present application provides a data-driven microscopic image processing device, comprising: a fixing and structural support system, a rotation control system, a microscope system, and an image acquisition and processing system; wherein: The fixing and structural support system includes a stage and fixing parts; The microscope system comprises a carrier plate, an eyepiece, an objective lens and a focus adjustment circuit. The carrier plate is provided with a groove for accommodating the thin slice to be identified. The eyepiece, the objective lens and the focus adjustment circuit cooperate to perform microscopic observation on the thin slice to be identified. The rotation control system comprises a high-precision motor, an active rotating shaft and a gear, and the sheet to be identified in the groove rotates when the high-precision motor drives the gear and the active rotating shaft; The image acquisition and processing system includes an image acquisition module and an image processing module, which are used to acquire the microscopic image of the thin slice to be identified, and identify and analyze the mineral composition based on the microscopic image.

[0005] Optionally, the rotation control system also includes a motor control circuit and a rotation transmission; the rotation transmission is connected to the gear, and the high-precision motor adjusts the angular velocity of the rotation transmission when receiving an angular velocity adjustment instruction transmitted by the motor control circuit, thereby changing the angular velocity of the sheet to be identified.

[0006] Optionally, the gear includes a pinion and a gear; the rotary transmission, the active rotating shaft and the pinion are in contact and connected with each other, and the pinion is connected to the gear via gear teeth.

[0007] Optionally, the number of teeth on the large gear is twice the number of teeth on the small gear.

[0008] Optionally, the microscope system further includes: a mirror wall and a fixed axis; the microscope system is connected to the fixed axis via the mirror wall; and the object carrier is connected to the fixed axis.

[0009] Optionally, the microscope system further comprises a lens barrel; the lens barrel is movably connected to the fixed axis via the lens wall.

[0010] Optionally, the specimen carrier is movably connected to the fixed axis and has a degree of freedom in the direction of the optical axis of the microscope system.

[0011] A second aspect of the embodiment of the present application provides a data-driven microscopic image processing method, which is applied to the microscopic image processing device described in the first aspect, comprising: Sending a control instruction to the rotation control system to adjust the rotation angle of the sheet to be identified in the groove; Receiving microscopic images of the thin slice to be identified at different rotation angles collected by the microscope system; The micrographic image is preprocessed, and the micrographic image is segmented and identified based on deep learning to determine the mineral information contained in the micrographic image.

[0012] Optionally, the preprocessing of the micrographic image includes grayscale processing, denoising processing and image enhancement processing.

[0013] Compared with the prior art, the technical solution provided by this application has the following beneficial effects: The present invention provides a data-driven microscopic image processing device and method, which improves the efficiency of microscopic image acquisition through motor drive and software linkage, reduces manual operation and errors, and ensures high-precision mineral identification. The combination of automatic rotation and real-time microscopic imaging makes the mineral composition analysis process more efficient and repeatable, which helps to accelerate the progress of mineral research and resource exploration. The highly integrated design of the device makes it easy to operate and maintain in a laboratory environment, lowers the technical threshold, and promotes the intelligent development of geological research and mineral resource development. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1A schematic diagram of the structure of a data-driven microscopic image processing device provided in an embodiment of the present application; wherein: 1. image after mineral identification; 2. computer system; 3. rotation control circuit; 4. high-precision motor; 5. stage; 6. rotation transmission device; 7. active rotating shaft; 8. small gear; 9. large gear; 10. stage; 11. image photographing circuit; 12. fixed shaft; 13. slice to be identified; 14. integrated circuit box; 15. mirror wall; 16. objective lens; 17. eyepiece; 18. lens barrel; 19. converter; 20. focal length adjustment circuit; 21. motor control circuit; 22. screw; 23. microscope base; Figure 2 A schematic diagram of a process flow of a data-driven microscopic image processing method provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] Below, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present application. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present application.

[0016] The terms used herein are only for describing specific embodiments and are not intended to limit the present application. The terms "include", "comprising", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0017] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0018] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some blocks or combinations thereof in the block diagrams and / or flow charts may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions, when executed by the processor, may create a device for implementing the functions / operations described in these block diagrams and / or flow charts.

[0019] In some embodiments, see Figure 1 , Figure 1 A schematic diagram of the structure of a data-driven microscopic image processing device provided in an embodiment of the present application; the data-driven microscopic image processing device provided in an embodiment of the present application comprises: a fixing and structural support system, a rotation control system, a microscope system and an image acquisition and processing system; wherein, The fixing and structural support system includes a loading platform 5 and a fixing member 22. The loading platform 5 can be used to carry a loading tray 10.

[0020] The microscope system includes a carrier plate 10, an eyepiece 17, an objective lens 16 and a focus adjustment circuit 20. The carrier plate is provided with a groove for accommodating the thin slice to be identified. The eyepiece, the objective lens and the focus adjustment circuit cooperate to perform microscopic observation of the thin slice to be identified. The eyepiece 17 and the objective lens 16 can provide a variety of magnifications for observation through flexible combination, and the focus adjustment line 20 is used to adjust the clarity. The thin slice to be identified can be a thin slice made by sampling the mineral to be detected.

[0021] The rotation control system includes a high-precision motor 4, an active rotating shaft 7 and a gear. The sheet to be identified rotates when the high-precision motor 4 drives the gear and the active rotating shaft 7. Here, the gear includes a pinion 8 and a large gear 9. Here, the pinion and the large gear are not different in size, but in that the large gear has more teeth; the rotation transmission device 6, the active rotating shaft 7 and the pinion 8 are in contact with each other, and the pinion 8 is connected to the large gear 9 through gear teeth. The rotation control system can also include a motor control circuit 21 and a rotation transmission device 6; the rotation transmission device 6 is connected to the gear. When the high-precision motor 4 receives the angular velocity adjustment instruction transmitted by the motor control circuit 21, it adjusts the angular velocity of the rotation transmission device 6, thereby changing the rotation angular velocity of the sheet to be identified. It should be noted that there are two ways to set the angular velocity of the high-precision motor 4. One is to set it with the help of the button of the motor itself, and the other is to use a computer system to control the high-precision motor 4 with the help of the motor control circuit to set the rotation speed.

[0022] Exemplarily, the rotator 6 receives the power transmitted by the high-precision motor 4, driving the driving shaft 7 and the pinion 8 to rotate at an angular velocity of W1. The large gear 9 is connected to the fixed shaft 11 and coupled with the pinion 8, and the pinion 8 drives the large gear 9 to rotate at an angular velocity of W2.

[0023] The image acquisition and processing system includes an image acquisition module and an image processing module, which are used to acquire the microscopic image of the thin slice to be identified, and identify and analyze the mineral composition based on the microscopic image.

[0024] The computer system 2 may include an image acquisition module, an image processing module, and may also include a storage module and an image processing and analysis module. The image acquisition module is used to acquire the microscopic image of the thin slice to be identified in real time and transmit it to the computer; the image processing module can be used to perform a series of preprocessing operations on the microscopic image; the storage module is used to store the microscopic image; the image processing and analysis module is used to perform mineral image segmentation and identification based on deep learning. The microscope system is connected to the computer system 2 through the image photography circuit 11, and the image acquisition module is used to acquire orthogonal polarized mineral microscopic images 1 at different angles in real time, and then the image processing module is used to preprocess the acquired microscopic image, and finally the image processing and analysis module is used to perform mineral image segmentation and identification using a deep learning method on the preprocessed image.

[0025] In some embodiments, the number of teeth on the large gear is twice the number of teeth on the small gear.

[0026] For example, the number of teeth of the pinion 8 is 16, and the number of teeth of the large gear 9 is 32, then the angular velocity W1 of the pinion 8 is twice the angular velocity W2 of the large gear 9, that is, W1=2W2. The thin film 13 to be identified is placed in the groove of the carrier plate 10 and connected to the large gear 9, that is, the rotational angular velocity of the thin film 13 to be identified is W2, and the carrier plate 10 is fixed, so the position of the thin film does not change and only the rotation is changed.

[0027] In some embodiments, the microscope system further includes: a mirror wall 15 and a fixed shaft 12 ; the microscope system is connected to the fixed shaft 12 via the mirror wall 15 ; and the object carrier 10 is connected to the fixed shaft 12 .

[0028] In some embodiments, the microscope system further includes a lens barrel 18 ; the lens barrel 18 is movably connected to the fixed shaft 12 via a lens wall 15 .

[0029] Here, the lens barrel 18 can slide on the fixed shaft 12 along the optical axis direction of the microscope system. During the sliding process, the object distance between the objective lens 16 and the object plate 10 changes accordingly.

[0030] In some embodiments, the specimen tray 10 is movably connected to the fixed shaft 12 and has a degree of freedom in the direction of the optical axis of the microscope system.

[0031] Similar to the above, the sample tray 10 can slide on the fixed shaft 12 along the optical axis direction of the microscope system. During the sliding process, the object distance between the sample tray 10 and the objective lens 16 changes accordingly.

[0032] The embodiment of the present invention improves the efficiency of collecting microscopic images through motor drive and software linkage, reduces manual operation and errors, and ensures high-precision mineral identification. The combination of automatic rotation and real-time microscopic imaging makes the mineral composition analysis process more efficient and repeatable, which helps to accelerate the progress of mineral research and resource exploration. The highly integrated design of the device makes it easy to operate and maintain in a laboratory environment, lowers the technical threshold, and promotes the intelligent development of geological research and mineral resource development.

[0033] In some embodiments, see Figure 2 , Figure 2 A schematic flow chart of a data-driven microscopic image processing method provided in an embodiment of the present application; an embodiment of the present application provides a data-driven microscopic image processing method, which is applied to the above-mentioned microscopic image processing device, including: S210, sending a control instruction to the rotation control system to adjust the rotation angle of the loading plate.

[0034] Here, the rotation angle can be a preset value, such as 5°, that is, every time the specimen plate rotates 5°, a microscopic image is collected using the microscope system. It should be noted that this preset value can be adjusted according to the detection accuracy requirement. The higher the accuracy requirement, the smaller the preset value, and there is no restriction on this.

[0035] S220, receiving microscopic images of the thin slice to be identified at different rotation angles collected by the microscope system.

[0036] A panoramic image can be obtained by acquiring microscopic images of the thin slice to be identified at different rotation angles and stitching these microscopic images.

[0037] S230, pre-processing the micrographic image, and segmenting and identifying the micrographic image based on deep learning to determine the mineral information contained in the micrographic image.

[0038] In some embodiments, the microscopic pattern is pre-processed, including grayscale processing, denoising processing and image enhancement processing.

[0039] Grayscale processing of microscopic images can reduce computational complexity and remove interference caused by color, so that the image recognition system can focus more on the brightness information of the image. Reducing or eliminating noise in the image through filtering techniques (such as mean filtering, median filtering, Gaussian filtering, etc.) can improve the clarity of microscopic images and the accuracy of feature extraction. Improving the visual effect of the image by adjusting the brightness and contrast of the image or using histogram equalization can make the image features more obvious and improve the robustness of the recognition system. It should be noted that preprocessing can also include other methods, such as geometric transformation and normalization, which are not enumerated.

[0040] In some optional embodiments, a large amount of microscopic image data is collected to construct a data set and annotate it. The annotation work usually includes determining the type, position, shape and other information of the mineral in the image. The diversity of data is increased by flipping, rotating, scaling and other operations to improve the generalization ability of the model. According to the task requirements, a suitable deep learning model, such as a convolutional neural network (CNN), is selected. In the microscopic image segmentation and recognition tasks, commonly used models include FCN (Fully Convolutional Network), U-Net, Mask R-CNN, etc. The model is trained using annotated data sets. During the training process, the weights of the model are updated by the back propagation algorithm to minimize the loss function. The deep learning model extracts features from the image through multi-layer convolution and pooling operations. Based on the extracted features, the model classifies each pixel to achieve image segmentation. The segmentation results are post-processed, such as removing small areas, filling holes, etc., to improve the accuracy of segmentation. The segmented area is mapped to a predefined mineral category. The area is classified based on the extracted features and a classifier (such as a softmax classifier) ​​to determine the mineral category to which it belongs. The output of the deep learning model can include information such as mineral type, location, shape, etc.

[0041] It should be noted that the data-driven microscopic image processing method provided in the embodiment of the present application and the data-driven microscopic image processing device provided in the embodiment of the present application are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned data-driven microscopic image processing device, and the repeated parts will not be repeated.

[0042] In some embodiments, see Figure 3 , Figure 3 The electronic device 300 provided in the embodiment of the present application includes a processor 310 and a memory 320; the memory 320 stores a computer program, wherein the computer program implements the above-mentioned data-driven microscopic image processing device when executed by the processor.

[0043] Specifically, the processor 310 may include, for example, a general-purpose microprocessor, an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 310 may also include an onboard memory for cache purposes. The processor 310 may be a single processing unit or multiple processing units for executing different actions of the method flow according to the embodiment of the present application.

[0044] The memory 320 may be any medium capable of containing, storing, conveying, propagating or transmitting instructions. For example, the memory 320 may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device, component or propagation medium. Specific examples of the memory 320 include: a magnetic storage device, such as a magnetic tape or a hard disk (HDD); an optical storage device, such as a compact disk (CD-ROM); a random access memory (RAM) or flash memory; and / or a wired / wireless communication link.

[0045] The present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned data-driven microscopic image processing device is implemented. The computer-readable medium may be included in the device / apparatus / system described in the above-mentioned embodiment; or it may exist independently without being assembled into the device / apparatus / system. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed, the method according to the embodiment of the present application is implemented.

[0046] According to an embodiment of the present application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, optical cable, radio frequency signal, etc., or any suitable combination of the above.

[0047] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present application. In particular, without departing from the spirit and teachings of the present application, the features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present application. Therefore, the scope of the present application should not be limited to the above-described embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims.

Claims

1. A data-driven microscopic image processing device, characterized in that: include: Fixing and structural support system, rotation control system, microscope system and image acquisition and processing system; among them, The fixing and structural support system includes a stage and fixing parts; The microscope system comprises a carrier plate, an eyepiece, an objective lens and a focus adjustment circuit. The carrier plate is provided with a groove for accommodating the thin slice to be identified. The eyepiece, the objective lens and the focus adjustment circuit cooperate to perform microscopic observation on the thin slice to be identified. The rotation control system comprises a high-precision motor, an active rotating shaft and a gear, and the sheet to be identified in the groove rotates when the high-precision motor drives the gear and the active rotating shaft; The image acquisition and processing system includes an image acquisition module and an image processing module, which are used to acquire the microscopic image of the thin slice to be identified, and identify and analyze the mineral composition based on the microscopic image.

2. The data-driven microscopic image processing device according to claim 1, characterized in that: The rotation control system also includes a motor control circuit and a rotation transmission device; the rotation transmission device is connected to the gear, and the high-precision motor adjusts the angular velocity of the rotation transmission device when receiving the angular velocity adjustment instruction transmitted by the motor control circuit, thereby changing the angular velocity of the thin sheet to be identified.

3. The data-driven microscopic image processing device according to claim 2, characterized in that: The gears include a pinion and a gear; the rotary transmission, the active rotating shaft and the pinion are in contact and connection with each other, and the pinion is connected to the gear via gear teeth.

4. The data-driven microscopic image processing device according to claim 3, characterized in that: The number of teeth of the large gear is twice the number of teeth of the small gear.

5. The data-driven microscopic image processing device according to claim 1, characterized in that: The microscope system further comprises: a mirror wall and a fixed axis; the microscope system is connected to the fixed axis via the mirror wall; and the object carrier is connected to the fixed axis.

6. The data-driven microscopic image processing device according to claim 5, characterized in that: The microscope system also includes a lens barrel; the lens barrel is movably connected to the fixed axis through the lens wall.

7. The data-driven microscopic image processing device according to claim 5, characterized in that: The object carrier is movably connected to the fixed axis and has a degree of freedom in the direction of the optical axis of the microscope system.

8. A data-driven microscopic image processing method, applied to the microscopic image processing device according to claims 1-7, characterized in that: include: Sending a control instruction to the rotation control system to adjust the rotation angle of the loading plate; receiving microscopic images of the thin slice to be identified at different rotation angles collected by the microscope system; The micrographic image is preprocessed, and the micrographic image is segmented and identified based on deep learning to determine the mineral information contained in the micrographic image.

9. The data-driven microscopic image processing method according to claim 8, characterized in that: The preprocessing of the micrographics includes grayscale processing, denoising processing and image enhancement processing.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images