139 results about "Local binary patterns" patented technology

The invention discloses an intelligent positioning method and system for can making stamping, and relates to the technical field of image processing. Comprising the following steps: acquiring a tank stamping part image, and segmenting the tank stamping part from a background by adopting a self-adaptive threshold segmentation algorithm to obtain segmented tank region image data; utilizing a moment-based sub-pixel edge detection method to accurately position the edge coordinates of the contour of the tank body, and obtaining the key dimension parameters of the tank body; extracting texture features of the surface of the tank body by adopting a gray-level co-occurrence matrix and a local binary pattern algorithm, and judging whether the texture features belong to surface defects or not through a support vector machine classification model; the method solves the problem that edge information is difficult to accurately extract when a traditional image processing method faces tank surface reflection and a complex background, ensures the accuracy of a measurement result by establishing a tank coordinate system and performing attitude correction, overcomes the problem that the tank is easy to deviate or incline in the production process, and improves the production efficiency. And high-efficiency and accurate quality detection of the tank stamping part is realized.

The invention relates to the technical field of remote sensing data processing and glacier area calculation, in particular to an unmanned aerial vehicle and satellite remote sensing data fused glacier area calculation method, which comprises the following steps of: cooperatively acquiring a satellite multispectral image and unmanned aerial vehicle high-resolution optical and LiDAR data, performing time synchronization, high-precision space registration and data enhancement processing, and calculating the glacier area through the unmanned aerial vehicle and satellite remote sensing data fusion. A satellite image glacier macroscopic feature and an initial mask are extracted by using a convolutional neural network and an NDSI / NDWI algorithm, and unmanned aerial vehicle image microscopic texture, edge and topographic features are acquired through a local binary pattern, edge detection and LiDAR point cloud; based on pyramid layering and a conditional random field, adopting a variance weighting algorithm to realize multi-scale feature level fusion; and after segmentation through an Otsu algorithm, calculating the area through a pixel counting method and introducing gradient correction, and evaluating the reliability through three types of precision. The method breaks through the limitation of a single data source, fuses macroscopic and microscopic features, improves the boundary positioning precision and calculation efficiency, and is suitable for glacier dynamic monitoring in a complex environment.

The invention discloses an image multi-modal feature extraction method, a ground feature classification and recognition method and a GIS image generation method. Comprising the following steps: firstly, extracting texture features from a target image by adopting a multi-directional statistical method fusing rotation invariant coding of a local binary pattern and a gray-level co-occurrence matrix, and extracting color features from the target image by adopting an LAB-HSV dual-color space collaborative analysis method to obtain features of different modes of the target image; and then according to the information values of the extracted color features and texture features, adjusting the weight ratio corresponding to the color features and the texture features so as to optimize the recognition precision of the classification model on complex ground features. And finally, according to a weight ratio corresponding to the color feature and the texture feature, performing weighted fusion on the color feature and the texture feature to obtain a corresponding multi-modal feature vector.

The invention discloses a metal surface defect detection and classification method, system, equipment and medium, and the method comprises the steps: processing images of different defect types through gray normalization, adaptive histogram equalization, a Gabor filter, a maximum entropy algorithm, morphological processing and an improved local binary pattern; carrying out defect position and size calculation on the processed image, and carrying out GUI (Graphical User Interface) measurement page design; the system, the equipment and the medium are used for realizing the metal surface defect detection and classification method. According to the method, the image processing effect is remarkable, the image contrast is improved, the defect boundary identification is enhanced, the accurate segmentation of the image and the detailed optimization of the structure are realized, the image features are accurately extracted, and efficient classification training is supported; the method has the advantages of improving image quality, enhancing defect detection precision and optimizing feature extraction and analysis, and can be widely applied to the field of high-precision image analysis such as metal defect detection, industrial quality control and computer vision.

The invention discloses an intelligent identification system for an osteoporosis area, belongs to the field of image processing calculation, and aims to solve the problems of limited technical coverage and lack of a dynamic optimization mechanism. In a feature extraction stage, a system combines traditional image processing and deep learning technologies in parallel, extracts bone trabecula multidirectional texture features by using a Gabor filter and a local binary pattern algorithm, analyzes bone contour curvature by combining Sobel edge detection and morphological operation, constructs geometric morphological parameters, and performs feature extraction on the bone trabecula. The local branch focuses on the porosity and arrangement rule of the bone trabecula by adopting a 3D convolutional network, the global branch is embedded into a compression excitation module based on an improved MobileNetV3 network to strengthen the overall morphological expression of the bone, the response intensity of a local microstructure is enhanced by space attention, the weight of global bone topological characteristics is calibrated by channel attention, and a multi-scale splicing strategy is combined, so that the overall morphological expression of the bone trabecula is optimized. And finally, outputting a fusion feature matrix after noise suppression, and remarkably improving the expression ability of pathological features.

The invention discloses an Internet of Things malicious traffic detection method and device and a storage medium, and the method comprises the following steps: S1, collecting malicious traffic data of Internet of Things equipment, and classifying and constructing a malicious traffic sample library; s2, converting the malicious traffic data into a grayscale image by adopting a text imaging method, and performing normalization, noise reduction and feature enhancement; s3, extracting local binary pattern features, global image features and high-order local automatic correction features, and constructing a malicious traffic feature database; s4, training the malicious traffic detection model by adopting a space-time capsule Transform, extracting space and time features, and performing classification training; s5, collecting real-time traffic data, calculating an abnormal score by using the trained model, and judging a traffic category; and S6, sending a detection result to a command and control server, triggering an alarm, and sending a blocking or isolating instruction to the attacked device. The method improves the accuracy and real-time performance of malicious traffic detection, and is suitable for security monitoring and protection of the Internet of Things.

The invention relates to the technical field of image processing, and discloses a morphology-based image texture feature extraction method, which comprises the following steps: an image preprocessing step: carrying out graying processing on an original image, and carrying out smoothing processing on a grayscale image by using a Gaussian filter; a morphological operation step: selecting structural elements suitable for image texture characteristics, performing expansion and erosion operation on the smoothed image, performing opening operation on the expanded image, and performing closing operation on the eroded image; and an adaptive feature selection step: carrying out local binary pattern feature extraction on the image after morphological processing, adaptively determining a threshold according to statistical distribution of LBP features, and segmenting the image into a foreground and a background. The image texture feature extraction method based on morphology aims at solving the problems that feature extraction is inaccurate, noise interference is likely to happen, and feature combination is complex in an existing image texture feature extraction method.

The invention provides a zinc-plated aluminum-magnesium steel strip surface coating image enhancement method, and relates to the technical field of image enhancement. A multi-scale feature extraction module provided by the invention adopts a method of combining an improved adaptive threshold local binary pattern and a directional gradient feature to extract edge textures and structural features under different scales; the feature selectivity enhancement module adopts an improved multi-scale direction response suppression and sparse activation enhancement method to perform direction saliency selection and detail region response improvement on the multi-scale feature map; and the cross-scale feature fusion module constructs a structural response graph based on local contrast variance, realizes pixel-level weighted fusion of a multi-scale feature graph, and finally outputs an enhanced zinc-aluminum-magnesium-plated steel strip surface coating image.

The invention discloses a thyroid cancer pathological image classification method and system based on multi-modal feature fusion and Bayesian optimization, and relates to the technical field of medical image processing, and the method comprises the steps: collecting a thyroid ultrasound image data set, and carrying out the preprocessing operation; extracting an improved local binary pattern feature, a Haralick texture feature and a VGG16 depth feature, and constructing a mixed feature space; and splicing the features in the mixed feature space into a 4119-dimensional mixed feature vector, and carrying out feature importance screening by utilizing ExtraTres. Improved local binary pattern features, Haralick texture features and VGG16 depth features are fused, a mixed feature space is constructed, feature importance screening and PCA dimension reduction are performed by using ExtraTrees, multi-level features of the image are effectively extracted, the accuracy of benign and malignant thyroid nodule classification is remarkably improved, meanwhile, network hyper-parameters are dynamically adjusted through a Bayesian optimization algorithm, and the classification accuracy of benign and malignant thyroid nodules is improved. And model convergence is accelerated in combination with a cosine annealing strategy, so that the generalization ability of the model is enhanced, and the model can be excellently expressed on different data sets.

The invention provides a bearing fault diagnosis method based on a one-dimensional local binary pattern and a Hankel matrix. The bearing fault diagnosis method comprises the following steps: acquiring a discrete vibration signal; performing first-order differential operation on the discrete vibration signal to obtain a differential signal; performing inherent time scale decomposition on the differential signal to obtain an inherent rotation component signal; performing quantization and signal reconstruction on each inherent rotation component signal by taking a root mean square as a quantization criterion of a one-dimensional local binary mode method to obtain a decimal feature signal; constructing a Hankel matrix of the decimal characteristic signal and performing signal reconstruction according to a covariance matrix of the Hankel matrix; performing spectral analysis on the reconstructed signal, calculating the fault characteristic frequency of the bearing, and then judging the state and the fault type of the bearing through a frequency component obtained through spectral analysis and the fault characteristic frequency of the bearing obtained through calculation. According to the bearing fault diagnosis method, noise can be effectively suppressed, the bearing fault feature information can be effectively extracted, and the bearing state and the fault type can be accurately identified.

The invention relates to an internal solitary wave identification and amplitude inversion method in mode data based on machine learning, and belongs to the technical field of ocean observation. In combination with a Mask-RCNN and a variational auto-encoder, firstly, sea surface height data is preprocessed and imaged, texture features are extracted through a local binary pattern algorithm, a labeled data set is constructed, model training is performed, and internal solitary wave stripes and positions thereof are identified from the labeled data set; through extraction and processing of temperature field data, the temperature field at the water depth is inversed by using a variational auto-encoder; and extracting the amplitude of the internal solitary wave in the temperature field based on the internal wave identification result. According to the method, large-scale and refined ocean mode data can be efficiently and accurately processed, and the efficiency and accuracy of data processing are remarkably improved. The method has a wide application prospect, and especially in marine disaster early warning, marine scientific research and internal wave mechanics research, the automatic identification and amplitude extraction capability of internal waves can be greatly improved.

The invention relates to the technical field of crop disease and insect pest image recognition, and particularly discloses a crop disease and insect pest image recognition method based on a large model, and the method comprises the steps: obtaining a multi-angle leaf image through high-resolution imaging equipment under a controllable illumination condition, and obtaining a target image in a unified format; extracting scab texture complexity features in combination with a local binary pattern and a gray-level co-occurrence matrix algorithm, and performing multi-channel statistical analysis on RGB and HSV color spaces to generate color heterogeneity feature vectors; further fusing the two types of features into a composite disease feature vector, inputting the composite disease feature vector into a probability model constructed based on a support vector machine and a Monte Carlo Dropout mechanism, and outputting probability distribution and confidence score of disease and pest categories; and dynamically adjusting a model training strategy according to a confidence level, triggering a feedback mechanism for a low-confidence sample, generating a synthetic image by using a conditional generative adversarial network, and optimizing model parameters in combination with incremental learning to realize stable identification modeling of rare or complex disease types.

The invention discloses a method and a system for automatically identifying primordial follicles in an ovary microscopic section image, which are used for realizing automatic identification and counting of primordial follicles in the microscopic image by carrying out image binaryzation, expansion corrosion processing, edge detection, circular feature extraction and texture feature analysis on the ovary microscopic section image dyed under a microscope. According to the method, a local binary pattern (LBP) is adopted to extract texture features, and primordial follicles in a microscopic slice image are effectively distinguished by combining edge detection and a hollow circular screening algorithm; the method has the characteristics of high processing speed, high precision and strong adaptability, and can be widely applied to ovarian slice analysis, assisted reproductive medicine and research of ovarian function related diseases.

The invention discloses a discharge channel extraction method and system based on edge detection and texture feature fusion, and belongs to the technical field of power equipment fault diagnosis and digital image processing, and the method comprises the steps: obtaining an ultraviolet weak light image of power equipment, and carrying out the preprocessing; multi-scale edge detection is executed based on the preprocessed image, edge information is fused through a multi-scale voting mechanism, and a candidate edge graph is generated by combining direction consistency connection fracture edges; extracting texture features of the pre-processed image, wherein the texture features comprise a rotation invariant local binary pattern uniformity feature and a multi-direction gray level co-occurrence matrix feature; according to a dynamic distribution weight coefficient of a discharge type, carrying out weighted fusion on the edge intensity of the candidate edge graph and the texture features, and generating a discharge channel confidence score graph; and carrying out binarization segmentation and contour optimization processing on the confidence score graph of the discharge channel, and extracting morphology quantization parameters of the discharge channel.

The invention discloses a carpet printing quality detection and automatic correction method based on machine vision. The carpet printing quality detection and automatic correction method comprises the following steps: S1, collecting and preprocessing a carpet printing image; s2, inputting the preprocessed carpet printing image into a PSPNet network to obtain a regional feature map; s3, performing response weight increase on the low-frequency texture loss region and the high-frequency edge dislocation region by adopting a region response enhancement strategy to generate a defect thermodynamic diagram; s4, dividing a thermodynamic diagram and extracting weighted LBP (Local Binary Pattern) features; s5, carrying out clustering division on the weighted LBP features, and judging whether the candidate region is a printing defect region or not by using a metric function; s6, constructing a regional difference mapping graph, and calculating correction parameters; s7, a control signal is sent, and jet printing parameters are adjusted to execute correction; and S8, collecting the corrected image, repeating the steps S2 to S7, and judging that the quality reaches the standard. Intelligent closed-loop control from detection to correction is achieved, the printing precision and efficiency are improved, and the method is suitable for intelligent production of carpet patterns.

The invention relates to a Ka-SAR remote sensing image fusion method and device based on texture feature extraction, and belongs to the technical field of image processing. Firstly, principal component analysis is performed on an optical remote sensing image; performing wavelet transform on the first principal component and the Ka-SAR remote sensing image to obtain a low-frequency detail component and a high-frequency detail component; performing texture feature extraction on the Ka-SAR remote sensing image by combining a genetic factor optimized cuckoo algorithm and a local binary pattern; enhancing a high-frequency detail component corresponding to the optical remote sensing image by using the extracted texture features, and performing wavelet inverse transformation on the enhanced high-frequency component and a low-frequency component of the Ka-SAR remote sensing image to obtain a new principal component; and carrying out principal component analysis inverse transformation on the residual principal components corresponding to the optical remote sensing image to obtain a fused image. According to the method, the extracted texture features are introduced into the fusion algorithm of the detail components after wavelet transformation, the method adapts to the imaging characteristics of Ka-SAR, and the method has a better effect.

The invention discloses an ultra-high-definition video stream adaptive coding method based on deep learning visual saliency, and the method comprises the steps: carrying out the five-scale Gaussian filtering processing and image pyramid construction of a video frame, and combining Sobel gradient, Laplacian edge and local binary pattern feature extraction to generate a multi-scale feature map; a pre-training saliency detection network is adopted, and a smooth saliency thermodynamic diagram is generated through processing of a feature adaptation layer, a residual encoder, a self-attention mechanism and a transposed convolution decoder; dividing the video frame into a high region, a middle region and a low region according to the saliency thermodynamic diagram, and establishing a regionalization coding parameter table; performing differentiated prediction modes, motion estimation and quantization strategies on different salient regions; and organizing coded data according to an H.265 / HEVC standard, and embedding the saliency thermodynamic diagram into supplementary enhancement information for transmission. According to the method, the important region concerned by the user can be intelligently identified, a differentiated coding strategy based on content semantics is realized, and the coding efficiency is remarkably improved.

The invention relates to the technical field of machine vision, in particular to an automatic recognition processing system and method for a multi-angle license plate image, electronic equipment and a storage medium, and the method comprises the steps: obtaining the multi-angle license plate image, carrying out the binarization processing of the image through employing a self-adaptive threshold segmentation algorithm, and extracting the contour of a license plate; correcting the license plate contour images at different angles by using perspective transformation; extracting local binary pattern features and HSV color histogram features of the corrected license plate contour image, performing character region cutting on the license plate by using a support vector machine (SVM) classifier, correcting a cutting result according to a license plate character arrangement rule to obtain an accurate character cutting image, constructing a multi-layer convolutional neural network, and obtaining a final license plate contour image. And inputting the cut character image into a network for identification and classification, and mapping and outputting license plate number information. According to the method, image processing, machine learning and deep learning technologies are comprehensively utilized, the accuracy and robustness of license plate recognition are comprehensively improved, and the method has a wide application prospect.

Disclosed here is a method of matching color and appearance of coatings containing at least one effect pigment. The method involves: obtaining, for a coating sample to be matched, sample color image data having pixel-specific color model properties; creating local binary patterns based on the pixel-specific color model properties; generating a binary pattern histogram for the local binary patterns, wherein the binary pattern histogram arranges the local binary patterns into N distinct bins to obtain N bin counts, and wherein the binary pattern histogram represents an appearance feature descriptor of the coating sample to be matched; and utilizing the binary pattern histogram for comparison against a previously generated binary pattern histogram that serves as an appearance feature descriptor of a candidate coating specimen.

The invention discloses a wood block surface flaw detection method based on image features, and belongs to the technical field of image data processing, and the method comprises the steps: obtaining an image of the surface of a target object, and carrying out the denoising and illumination normalization processing of the image, and obtaining a first image; performing wavelet transform decomposition to obtain edge distribution description data and shape description data corresponding to the first image, and generating geometric characteristic description; analyzing texture distribution of the first image in combination with a local binary pattern algorithm according to the geometric feature description, and generating a texture feature set; fusing the geometric feature description and the texture feature set to construct a multi-dimensional feature vector, and performing dimensionality reduction on the multi-dimensional feature vector by adopting principal component analysis to obtain a dimensionality-reduced feature vector; and inputting the dimension reduction feature vector into a support vector machine classifier, and outputting a defect classification result. The wood block surface flaw detection method based on the image features solves the problem that when an existing detection system faces complex flaw types, high-precision classification is difficult to achieve.

The invention relates to the technical field of machine vision detection, in particular to an automobile part surface defect online detection method and system. The method comprises the following steps: acquiring a grayscale image, calculating the size of a structural element for each pixel based on a local Gaussian Laplacian operator response variance, filtering to obtain a substrate image according to the size of the structural element, and differentiating to obtain a texture image. Determining a Gabor scale and a gray-level co-occurrence matrix statistical direction by using the size, and extracting a cooperative direction gray-level co-occurrence matrix feature; and a weight is set based on the size and is subjected to weighted fusion with a multi-scale rotation invariant local binary pattern feature to generate a texture saliency map, and texture defects are judged. On the substrate image, taking the gray value as the height, and determining a neighborhood calculation curvature feature based on the size to detect the substrate defect. According to the scheme, the image scale can be adaptively analyzed, the background texture is effectively inhibited, and therefore different types of tiny defects such as scratches and pits can be reliably detected.

The invention relates to the technical field of data security, and discloses an image hiding method and system based on a local binary pattern, and the method comprises the steps: calculating a texture feature matrix of the local binary pattern of a plaintext image; generating a three-dimensional chaotic sequence according to the texture feature matrix; constructing a measurement matrix by using the three-dimensional chaotic sequence; performing two-dimensional compressed sensing processing on the plaintext image by using the measurement matrix to obtain a measurement value matrix after the plaintext image is compressed; performing scrambling and diffusion operation on the measurement value matrix to obtain a ciphertext image; the ciphertext image is embedded into the carrier image to obtain the encrypted carrier image, so that the known plaintext attack can be effectively resisted, the imperceptibility of the encrypted carrier image is improved, the blind extraction effect can be realized, and the efficiency and security of image protection are greatly improved.

The invention discloses a submucous membrane multi-point thickness measuring method for endoscopic submucous membrane dissection. The submucous membrane multi-point thickness measuring method comprises the following steps that images are collected, wherein pathological images cut by the endoscopic submucous membrane dissection are obtained; image preprocessing: improving the brightness of the pathological image and the contrast ratio of a bright part, and smoothing the pathological image through Gaussian filtering; image feature extraction: extracting texture features of the pathological image, using a local binary pattern (LBP) algorithm, and generating a vertical coordinate feature map with the same size as the pathological image; feature fusion: superposing the preprocessed noise reduction image, the texture feature image and the ordinate feature map; submucous membrane pathological tissue segmentation: using a UNet neural network to carry out image segmentation task training on the superimposed image; calculating the thickness of multiple points; and quality evaluation. According to the method, the thickness of the submucous membrane is measured through the pathological tissue image, and ESD effect judgment and operation quality control are facilitated.

The invention relates to the technical field of oil and gas field databases, and discloses a data cross-modal association method and device in an oil and gas field database, equipment and a medium, and the method comprises the steps: receiving an original seismic waveform time sequence inputted in advance, and generating a time-frequency spectrogram through Fourier transform; receiving a pre-input rock core scanning image set, extracting local binary pattern texture features from the rock core scanning image set, and obtaining a spatially continuous three-dimensional rock core digital model based on the local binary pattern texture features; injecting the time-frequency spectrogram and the three-dimensional rock core digital model into a pre-generated hierarchical semantic framework to obtain a cross-modal unified semantic vector; constructing a comparative learning framework of the spectrogram and the logging text, and generating a time-space aligned semantic feature matrix based on the comparative learning framework; and based on the cross-modal unified semantic vector and the semantic feature matrix, obtaining a dynamic association map of the logging and the seismic waveform.

The invention discloses a character extraction method for a power transmission and transformation project document. The method comprises the following steps: acquiring data information of a target power transmission and transformation project document and preprocessing the data information to obtain a binary image of the target power transmission and transformation project document; noise detection, noise classification and noise reduction processing are carried out; carrying out character region positioning on the target power transmission and transformation project document; segmenting and extracting characters; character recognition is carried out based on a local binary pattern; and carrying out association and replacement of characters and completing character extraction of the target power transmission and transformation project document. The invention also discloses a system for realizing the character extraction method for the power transmission and transformation project document. According to the method, the image of the target power transmission and transformation project document is processed and extracted, and particularly the characters of the table part in the document are positioned, segmented, identified and replaced, so that the character extraction of the power transmission and transformation project document is realized, the reliability is higher, and the accuracy is better.

The invention discloses a circuit breaker fault diagnosis method based on global-local feature extraction. Comprising the following steps: 1, collecting vibration signals of a circuit breaker in a normal working condition and a fault state as original data; 2, extracting original time domains and frequency domains of the vibration signals of the circuit breaker operating mechanism in different states and time-frequency characteristics of a generalized S transformation matrix, and regarding the original time domains and frequency domains as global characteristics; 3, extracting local features of the vibration signals by using a texture feature extraction mode of matching a local binary pattern with a gray-level co-occurrence matrix; 4, further screening the features by using maximum correlation and minimum redundancy to obtain a feature set; and 5, in combination with a kernel extreme learning machine classifier and GL-mRMR feature extraction, obtaining a GL-mRMR-KELM model applied to circuit breaker vibration data classification. The method is used for fault diagnosis of a high-voltage circuit breaker, and solves the technical problems of low universality and poor accuracy under small samples in a current operating mechanism state diagnosis algorithm.

The invention discloses a flood water intelligent identification method based on an improved deep learning model, and belongs to the technical field of geological disaster information processing, and the method comprises the following steps: collecting and preprocessing data, and generating a data set; based on the generated data set, integrating Canny edge detection operator texture, normalized water body index texture and local binary pattern (LBP) operator texture to form a multi-feature fusion image data set; a DeepWFNet network model is constructed; inputting the multi-feature fusion image data set into a DeepWFNet network model for flood inundation range identification to obtain a flood identification result; and carrying out visual optimization and evaluation on the flood identification result. According to the method, the edge features, the spectral features and the texture features are added to be combined with the DeepWFNet model, the ability of the model to understand global information can be enhanced while the ability of local feature extraction is kept, and therefore the segmentation precision of the flood inundation area is remarkably improved.

The invention provides a mountainous area night animal tracking method and system based on multispectral and thermal imaging data fusion, and relates to the technical field of night animal tracking, and the method comprises the steps: synchronously obtaining a multispectral image sequence and a thermal imaging image sequence of a mountainous area night; performing multi-scale Retinex enhancement processing on the near-infrared image and the thermal image after registration to obtain an enhanced candidate target image; extracting a multi-source texture signature fusing a local binary pattern feature vector and a thermal gradient direction histogram for each candidate target, and constructing a multi-dimensional feature set in combination with geometric features obtained by morphological skeletonization; target association between adjacent frames is realized by adopting a nearest neighbor greedy matching algorithm, and a preliminary track segment is formed; and finally, removing abnormal trajectories, solving trajectory crossing and shielding conflicts through a sparse dynamic time warping algorithm, and generating an accurate and complete animal movement trajectory. According to the invention, conflicts caused by track crossing and shielding can be solved, and a continuous and accurate single animal movement track is output.

The invention discloses a sandstone slice image component identification method based on a GL-SLIC algorithm and semi-supervised learning. The method comprises the following steps: firstly, acquiring a sandstone slice image amplified by 200 times under single polarization, converting an RGB image into a CIE-Lab color space, and extracting a GLBP texture feature vector; then a GL-SLIC superpixel segmentation algorithm is constructed, and adaptive segmentation based on texture and color features is realized in combination with a Gabor filter and a local binary pattern; then implementing a region merging algorithm to generate complete mineral particles and pore fragments; finally, a classifier based on VGG16 and a discriminator based on ResNet18 are constructed, a semi-supervised self-training framework is adopted, a model is initialized by using about 6% of manual labeling samples, a high-confidence-coefficient pseudo-label extension training data set is generated through iteration, and automatic recognition of sandstone components such as quartz, pores, kaolinite, rock debris and a matrix is achieved. According to the method, the recognition accuracy of 96.3% on a test set is achieved, compared with a traditional method, the segmentation precision and the recognition accuracy are remarkably improved, the data labeling cost is greatly reduced, and an efficient technical scheme is provided for automatic analysis of geological images.

The embodiment of the invention belongs to the field of artificial intelligence, and relates to a face-scanning payment method, which comprises the following steps: when a face-scanning payment request is received, obtaining a first image of a customer through a POS terminal; performing image reconstruction on the first image through an image super-resolution reconstruction algorithm to obtain a high-resolution second image; inputting the second image into a face detection model to obtain a face region image in the second image; performing feature extraction on the face region image through a local binary pattern algorithm to obtain a face feature image; performing face recognition in a preset face feature database based on the face feature image to obtain an identity verification result of the face scanning payment request; and when the identity verification result shows that the client identity is legal, responding to the face scanning payment request to complete the face scanning payment operation. The invention further provides a face-scanning payment device, computer equipment and a storage medium. According to the invention, the accuracy of face-scanning payment of the POS terminal is improved.