A method, device, equipment and readable storage medium for identifying coal gangue

Abstract

The present invention discloses a gangue identification method, device, equipment and readable storage medium, comprising: obtaining a laser speckle image of a mixture of coal and gangue to be identified; inputting the laser speckle image of the mixture of coal and gangue into a pre-constructed gangue identification model, and the gangue identification model outputs the identified gangue information. The present invention improves the reliability of the recognition of artificially designed features due to changes in lighting conditions in the natural image recognition method.

Description

Technical Field

[0001] The present invention relates to the technical field of coal gangue identification, and in particular to a coal gangue identification method, device, equipment and readable storage medium. Background Art

[0002] Coal is an important primary energy source for development, which strongly supports the steady and rapid development of economy and society. Coal gangue is the main solid waste generated in the process of coal mining. With the increase of coal mining activities, the accumulation of coal gangue has greatly increased, becoming one of the largest industrial residues. On the one hand, efficient coal gangue identification can greatly reduce the impact of coal gangue on coal preparation efficiency during coal processing and reduce the damage to production equipment; on the other hand, it can reduce the amount of coal gangue hoisted and reduce the harm of coal gangue to the natural environment such as soil, air and water sources.

[0003] With the continuous development of computer vision technology and deep learning technology, gangue image recognition has become one of the main technologies for dry coal preparation. The traditional gangue image recognition process mainly includes two parts: image feature extraction and recognition model establishment. The recognition accuracy is largely determined by the designed feature extraction method. However, due to the obvious influence of lighting conditions on the artificially designed and extracted gangue image features, the reproduction effect of many gangue image recognition technologies is not ideal, which is not conducive to the promotion of industrial application of gangue image recognition technology. Gangue image recognition based on deep learning theory can be achieved through multi-layer nonlinear transformation adaptive learning and extraction of multi-layer significant features of the image on the basis of big data, so as to achieve accurate identification of coal and gangue. However, due to the instability of the industrial site gangue image acquisition environment and the complexity of my country's mineral species, the existing gangue data set is small in scale, and it is difficult to ensure that it contains diverse mineral information. Deep learning models are mostly trained through transfer learning, and the generalization ability of the model has not been effectively evaluated. Therefore, it is still necessary to study new gangue image recognition methods suitable for industrial promotion and integrate and innovate existing technologies. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a coal gangue identification method, device, equipment and readable storage medium, which improves the reliability of artificially designed feature recognition due to changes in lighting conditions in natural image recognition methods.

[0005] In order to solve the above technical problems, the present invention is implemented by the following technical solutions:

[0006] A method for identifying coal gangue, comprising:

[0007] Acquire a laser speckle image of a mixture of coal and coal gangue to be identified;

[0008] The laser speckle image of the mixture of coal and coal gangue is input into a pre-constructed coal gangue recognition model, and the coal gangue recognition model outputs recognized coal gangue information.

[0009] Furthermore, before inputting the laser speckle image of the mixture of coal and gangue into the pre-built gangue recognition model, the method further includes:

[0010] The laser speckle image of the mixture of coal and coal gangue is preprocessed.

[0011] Furthermore, the preprocessing of the laser speckle image of the mixture of coal and coal gangue includes:

[0012] performing filtering processing on the laser speckle image of the mixture of coal and coal gangue;

[0013] The laser speckle image of the mixture of coal and coal gangue after filtering is subjected to image enhancement processing.

[0014] Furthermore, the method for constructing the gangue identification model includes:

[0015] Acquire a coal gangue training data set, wherein the coal gangue training data set includes several groups of coal gangue training data, and each group of the coal gangue training data includes: a coal gangue laser speckle image and grayscale features and texture features corresponding to the coal gangue laser speckle image;

[0016] The gangue training data set is used to train the SVM model to obtain the gangue recognition model.

[0017] Furthermore, the obtaining of the coal gangue training data set includes:

[0018] Acquire laser speckle images of a plurality of coal and gangue mixtures;

[0019] Performing filtering on the laser speckle image of each mixture of coal and coal gangue;

[0020] Performing image enhancement processing on each laser speckle image of the mixture of coal and coal gangue after filtering;

[0021] Performing image segmentation on each laser speckle image of the mixture of coal and coal gangue after image enhancement processing to obtain a number of laser speckle images of coal gangue;

[0022] The size of each gangue laser speckle image is normalized;

[0023] The grayscale features and texture features of each coal gangue laser speckle image after size normalization are extracted to obtain the coal gangue training data set.

[0024] Furthermore, the grayscale features include grayscale mean and grayscale variance, as follows:

[0025]

[0026]

[0027]

[0028] Where m is the grayscale mean; σ 2 is the grayscale variance; p(b) is the probability of each grayscale level; b is a grayscale level in the gangue laser speckle image; n(b) is the number of pixels with grayscale level b; M*N is the total number of pixels in the gangue laser speckle image;

[0029] The texture features include angular second-order moment, entropy, contrast and inverse variance, as follows:

[0030]

[0031]

[0032]

[0033]

[0034] Where ASM is the angular second-order moment; ENT is entropy; CON is contrast; IDM is inverse variance; P(j,k|l,α) is the frequency of occurrence of adjacent pixel pairs with one gray value j and the other gray value k in all α directions of the pixel point (x, y) in the coal gangue laser speckle image with an adjacent interval of l, and k represents the gray value, and l is the adjacent interval.

[0035] A gangue identification device, comprising:

[0036] An acquisition module, used for acquiring a laser speckle image of a mixture of coal and coal gangue to be identified;

[0037] The recognition module is used to input the laser speckle image of the mixture of coal and coal gangue into a pre-constructed coal gangue recognition model, and the coal gangue recognition model outputs the recognized coal gangue information.

[0038] Furthermore, it also includes:

[0039] A beam expander disposed above the mixture of coal and coal gangue to be identified, a laser disposed above the beam expander, an industrial camera disposed above the mixture of coal and coal gangue to be identified, and a computer;

[0040] The laser is used to emit laser light to the mixture of coal and coal gangue to be identified through the beam expander;

[0041] The beam expander is used to expand and enlarge the laser beam and then irradiate it onto the surface of the mixture of coal and coal gangue to be identified;

[0042] The industrial camera is used to collect the laser speckle image of the mixture of coal and coal gangue to be identified;

[0043] The acquisition module and the identification module are embedded in the computer, and the acquisition module acquires the laser speckle image of the mixture of coal and coal gangue to be identified through the industrial camera.

[0044] A device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a coal gangue identification method when executing the computer program.

[0045] A computer-readable storage medium stores a computer program, wherein the computer program implements the steps of a coal gangue identification method when executed by a processor.

[0046] Compared with the prior art, the present invention has at least the following beneficial effects:

[0047] The invention provides a coal gangue identification method, which additionally introduces a laser light source, obtains a laser speckle image of a mixture of coal and coal gangue to be identified, inputs the laser speckle image of the mixture of coal and coal gangue into a pre-constructed coal gangue identification model, and the coal gangue identification model outputs the identified coal gangue information. The laser speckle image of the mixture of coal and coal gangue contains rich grayscale and texture information of the surface of coal gangue. Compared with other light sources, laser has the characteristics of strong anti-interference, strong directionality and strong coherence, so that the laser speckle image of the mixture of coal and coal gangue to be identified can better cope with the change of ambient light. Under complex industrial conditions, the laser speckle image of the mixture of coal and coal gangue is less affected by the collected light factors, the obtained image information is more reliable, and there is no radiation hazard, which effectively improves the problem of unstable coal gangue identification caused by changes in ambient light in the natural image recognition method.

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is an overall flow chart of a method for identifying coal gangue of the present invention;

[0051] Figure 2 It is a schematic diagram of a coal gangue identification system of the present invention;

[0052] Figure 3 This is the coal gangue laser speckle image area of ​​the embodiment of the present invention.

[0053] Among them: 1-laser, 2-beam expander, 3-industrial camera, 4-belt conveyor, 5-coal gangue, 6-computer, 7-adjustable LED light source. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] As a specific embodiment of the present invention, Figure 1 As shown, a method for identifying coal gangue specifically comprises the following steps:

[0056] S1. Obtaining a laser speckle image of a mixture of coal and coal gangue to be identified.

[0057] like Figure 2 As shown, in this embodiment, the mixture of coal and coal gangue is transported by a belt conveyor 4, and the mixture of coal and coal gangue contains coal gangue 5. A beam expander 2, a laser 1 and an industrial camera 3 are set above the belt conveyor 4, and the industrial camera 3 is connected to a computer 6. The laser emitting end of the laser 1 faces the beam expander 2. When the mixture of coal and coal gangue reaches a fixed position, the laser 1 emits a coherent laser beam, and the laser is expanded and enlarged by the beam expander 2 and then irradiated to the surface of the mixture of coal and coal gangue to be identified. The industrial camera 3 collects a spatial free speckle image of the mixture of coal and coal gangue, that is, collects a laser speckle image of the mixture of coal and coal gangue to be identified. Finally, the industrial camera 3 sends the collected laser speckle image of the mixture of coal and coal gangue to be identified to the computer 6 for processing.

[0058] Preferably, it also includes an adjustable LED light source 7, which is connected to the computer 6 and is used for supplementary light.

[0059] In this embodiment, the laser 1 is a red light semiconductor laser, the industrial camera 3 is a CMOS camera, and the exposure time of the CMOS camera is set to 3000 μs.

[0060] S2. Inputting the laser speckle image of the mixture of coal and coal gangue into a pre-constructed coal gangue recognition model, and the coal gangue recognition model outputs recognized coal gangue information.

[0061] As a more preferred real-time method, since the laser beam propagates in the air, it is affected by suspended air particles to generate shot noise. Therefore, before inputting the laser speckle image of the mixture of coal and gangue into the pre-built gangue recognition model, the method further includes:

[0062] Performing filtering processing on the laser speckle image of the mixture of coal and coal gangue, specifically, using Gaussian filtering on the laser speckle image of the mixture of coal and coal gangue to be identified to improve the image quality;

[0063] The laser speckle image of the mixture of coal and coal gangue after filtering is subjected to image enhancement processing. Specifically, the brightness and contrast of the laser speckle image of the mixture of coal and coal gangue to be identified are adjusted by using limited contrast adaptive histogram equalization.

[0064] In this implementation, the method for constructing the gangue identification model is as follows:

[0065] a. Obtain a coal gangue training data set, wherein the coal gangue training data set includes several groups of coal gangue training data, each group of the coal gangue training data includes: a coal gangue laser speckle image and grayscale features and texture features corresponding to the coal gangue laser speckle image.

[0066] Specifically, the obtaining of the coal gangue training data set includes:

[0067] a1. Obtain laser speckle images of several coal and gangue mixtures.

[0068] a2. Perform filtering processing on the laser speckle image of each mixture of coal and coal gangue. Specifically, use Gaussian filtering on the laser speckle image of each mixture of coal and coal gangue to improve the image quality.

[0069] a3. Perform image enhancement processing on the laser speckle image of each coal and gangue mixture after filtering. Specifically, use contrast-limited adaptive histogram equalization to adjust the brightness and contrast of the laser speckle image of each coal and gangue mixture.

[0070] a4. Perform image segmentation on each laser speckle image of the coal and gangue mixture after image enhancement processing to obtain several laser speckle images of gangue (such as Figure 3 In this embodiment, the maximum inter-class variance adaptive threshold algorithm is used to segment the laser speckle image of each coal and gangue mixture.

[0071] a5. Normalize the size of each coal gangue laser speckle image.

[0072] a6. Extracting the grayscale features and texture features of each size-normalized gangue laser speckle image to obtain the gangue training data set;

[0073] Preferably, the grayscale features include grayscale mean and grayscale variance. Specifically, the grayscale mean and grayscale variance are extracted based on the grayscale statistical histogram, as follows:

[0074]

[0075]

[0076]

[0077] Where m is the grayscale mean; σ 2 is the grayscale variance; p(b) is the probability of each grayscale level; b is a grayscale level in the gangue laser speckle image; n(b) is the number of pixels with grayscale level b; M*N is the total number of pixels in the gangue laser speckle image.

[0078] The texture features include angular second-order moment, entropy, contrast and inverse variance. Specifically, angular second-order moment, entropy, contrast and inverse variance are extracted based on the gray-level co-occurrence matrix, as follows:

[0079]

[0080]

[0081]

[0082]

[0083] Where ASM is the angular second-order moment; ENT is entropy; CON is contrast; IDM is inverse variance; P(j,k|l,α) is the frequency of occurrence of adjacent pixel pairs with one gray value j and the other gray value k in all α directions of the pixel point (x, y) in the laser speckle image of coal gangue, where α is usually 0. °, 45°, 90°, 135°, j and k represent gray values, and l represents the adjacent interval.

[0084] The gray-level co-occurrence matrix is ​​defined by the joint probability density of pixels at two locations, which not only reflects the brightness distribution characteristics, but also reflects the position distribution between pixels with the same brightness in space.

[0085] The angular second moment, also known as energy (ASM), reflects the uniformity of the grayscale distribution and the coarseness of the texture. The entropy value reflects the randomness of the image information. When all values ​​in the co-occurrence matrix are equal or the pixel values ​​show the greatest randomness, the entropy is the largest. The contrast reflects the clarity of the image and the depth of the texture grooves. The inverse variance reflects the degree of local change in the image texture.

[0086] b. Using the gangue training data set to train the SVM model, to obtain the gangue recognition model.

[0087] Specifically, during training, not only the gangue training data set but also the gangue test data set are included. The SVM model is constructed for recognition, and the gangue recognition results are evaluated with reference to the precision and recall rate, where:

[0088]

[0089]

[0090] Precision is the proportion of correct predictions in the data predicted as positive; Recall is the proportion of correct predictions in the data that is actually positive; TP means predicting the positive class as positive; FP means predicting the negative class as positive; and FN means predicting the positive class as negative.

[0091] The present invention provides a coal gangue identification device, comprising:

[0092] The acquisition module is used to acquire the laser speckle image of the mixture of coal and coal gangue to be identified.

[0093] The recognition module is used to input the laser speckle image of the mixture of coal and gangue into a pre-constructed gangue recognition model, and the gangue recognition model outputs the recognized gangue information.

[0094] like Figure 2As shown, in this embodiment, the coal gangue identification device includes: a beam expander 2 arranged above the mixture of coal and coal gangue to be identified, a laser 1 arranged above the beam expander 2, an industrial camera 3 arranged above the mixture of coal and coal gangue to be identified, an adjustable LED light source 7 and a computer 6 arranged above the mixture of coal and coal gangue to be identified, the laser 1, the industrial camera 3 and the adjustable LED light source 7 are respectively connected to the computer 6, the acquisition module and the identification module are embedded in the computer, and the acquisition module is connected to the identification module.

[0095] The laser is used to emit laser to the mixture of coal and coal gangue to be identified through a beam expander; the beam expander is used to expand and amplify the laser and then irradiate it to the surface of the mixture of coal and coal gangue to be identified; the industrial camera is used to collect the laser speckle image of the mixture of coal and coal gangue to be identified; the acquisition module obtains the laser speckle image of the mixture of coal and coal gangue to be identified through the industrial camera, the recognition module inputs the laser speckle image of the mixture of coal and coal gangue into a pre-constructed coal gangue recognition model, and the coal gangue recognition model outputs the recognized coal gangue information.

[0096] In one embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding functions; the processor described in the embodiment of the present invention can be used to implement the operation of a coal gangue identification method.

[0097] In one embodiment of the present invention, a method for identifying coal gangue can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by a processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data.

[0098] The computer storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0103] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for identifying coal gangue, characterized in that: include: Acquire a laser speckle image of a mixture of coal and coal gangue to be identified; Inputting the laser speckle image of the mixture of coal and gangue into a pre-constructed gangue recognition model, the gangue recognition model outputting recognized gangue information; The method for constructing the coal gangue identification model comprises: Acquire a coal gangue training data set, wherein the coal gangue training data set includes several groups of coal gangue training data, and each group of the coal gangue training data includes: a coal gangue laser speckle image and grayscale features and texture features corresponding to the coal gangue laser speckle image; Using the gangue training data set to train the SVM model, to obtain the gangue recognition model; The step of obtaining a coal gangue training data set includes: Acquire laser speckle images of a plurality of coal and gangue mixtures; Performing filtering on the laser speckle image of each mixture of coal and coal gangue; Performing image enhancement processing on each laser speckle image of the mixture of coal and coal gangue after filtering; Performing image segmentation on each laser speckle image of the mixture of coal and coal gangue after image enhancement processing to obtain a number of laser speckle images of coal gangue; The size of each gangue laser speckle image is normalized; Extracting the grayscale features and texture features of each size-normalized coal gangue laser speckle image to obtain the coal gangue training data set; The grayscale features include grayscale mean and grayscale variance, which are as follows: In the formula, is the grayscale mean; is the grayscale variance; is the probability of each gray level; is a gray level in the laser speckle image of coal gangue; The gray level is The number of pixels; is the total number of pixels in the laser speckle image of coal gangue; The texture features include angular second-order moment, entropy, contrast and inverse variance, as follows: In the formula is the angular second moment; is entropy; is the contrast; is the inverse variance; is the pixel point in the laser speckle image of coal gangue All Direction, adjacent interval is One of the grayscale values ​​in the pixel pair is taken , and another gray value is The frequency of occurrence of adjacent pixel pairs, and Represents the gray value, Adjacent intervals.

2. A method for identifying coal gangue according to claim 1, characterized in that: Before inputting the laser speckle image of the mixture of coal and gangue into the pre-built gangue recognition model, the method further includes: The laser speckle image of the mixture of coal and coal gangue is preprocessed.

3. A method for identifying coal gangue according to claim 2, characterized in that: The preprocessing of the laser speckle image of the mixture of coal and coal gangue includes: performing filtering processing on the laser speckle image of the mixture of coal and coal gangue; The laser speckle image of the mixture of coal and coal gangue after filtering is subjected to image enhancement processing.

4. A coal gangue identification device, characterized in that: include: An acquisition module, used for acquiring a laser speckle image of a mixture of coal and coal gangue to be identified; An identification module, used for inputting the laser speckle image of the mixture of coal and gangue into a pre-built gangue identification model, and the gangue identification model outputs the identified gangue information; The method for constructing the gangue identification model comprises: Acquire a coal gangue training data set, wherein the coal gangue training data set includes several groups of coal gangue training data, and each group of the coal gangue training data includes: a coal gangue laser speckle image and grayscale features and texture features corresponding to the coal gangue laser speckle image; Using the gangue training data set to train the SVM model, to obtain the gangue recognition model; The step of obtaining a coal gangue training data set includes: Acquire laser speckle images of a plurality of coal and gangue mixtures; Performing filtering processing on the laser speckle image of each mixture of coal and coal gangue; Performing image enhancement processing on each laser speckle image of the mixture of coal and coal gangue after filtering; Performing image segmentation on each laser speckle image of the mixture of coal and coal gangue after image enhancement processing to obtain a number of laser speckle images of coal gangue; The size of each gangue laser speckle image is normalized; Extracting the grayscale features and texture features of each size-normalized coal gangue laser speckle image to obtain the coal gangue training data set; The grayscale features include grayscale mean and grayscale variance, which are as follows: In the formula, is the grayscale mean; is the grayscale variance; is the probability of each gray level; is a gray level in the laser speckle image of coal gangue; The gray level is The number of pixels; is the total number of pixels in the laser speckle image of coal gangue; The texture features include angular second-order moment, entropy, contrast and inverse variance, as follows: In the formula is the angular second moment; is entropy; is the contrast; is the inverse variance; is the pixel point in the laser speckle image of coal gangue All Direction, adjacent interval is One of the grayscale values ​​in the pixel pair is taken , and another gray value is The frequency of adjacent pixel pairs, and Represents the gray value, Adjacent intervals.

5. A gangue identification device according to claim 4, characterized in that: Also includes: A beam expander disposed above the mixture of coal and coal gangue to be identified, a laser disposed above the beam expander, an industrial camera disposed above the mixture of coal and coal gangue to be identified, and a computer; The laser is used to emit laser light to the mixture of coal and coal gangue to be identified through the beam expander; The beam expander is used to expand and enlarge the laser beam and then irradiate it onto the surface of the mixture of coal and coal gangue to be identified; The industrial camera is used to collect the laser speckle image of the mixture of coal and coal gangue to be identified; The acquisition module and the identification module are embedded in the computer, and the acquisition module acquires the laser speckle image of the mixture of coal and coal gangue to be identified through the industrial camera.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a coal gangue identification method as described in any one of claims 1 to 3 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a coal gangue identification method as described in any one of claims 1 to 3 are implemented.

Images