14 results about "Gabor filter bank" patented technology

The invention provides a real-time processing method for endoscopic image blood vessel enhancement and microcirculation evaluation, which comprises the following steps of: processing an original endoscopic image, and locally enhancing a brightness channel through a contrast-limited adaptive histogram equalization technology; self-adaptive frequency domain-space domain decomposition is realized based on local texture complexity analysis; performing multi-scale Hessian matrix blood vessel detection on the low-frequency component; applying a directional Gabor filter bank to the high-frequency component; spatial-temporal feature fusion is realized through multi-resolution pyramid optical flow calculation; synchronously completing blood vessel probability prediction, blood vessel diameter estimation and blood flow direction prediction by using a lightweight multi-task deep learning network; the blood flow velocity is analyzed and calculated based on a speckle mode, the perfusion density is subjected to accelerated statistics through an integrogram, and vascular morphological parameters are extracted by adopting an improved skeleton algorithm. According to the invention, an enhanced blood vessel visualization effect and a real-time microcirculation quantitative evaluation function can be provided, and the overall improvement of the endoscope image processing quality and efficiency is realized.

The invention relates to the field of rotating machinery fault diagnosis, and discloses a bearing fault diagnosis method based on a physical perception KAM network, and the method comprises the steps: carrying out the discretization of a bearing vibration signal through a Gabor filter group based on physical prior initialization, and generating modal feature lexical elements with physical frequency band meanings; and inputting the lexical elements into a PC-KAM backbone network, calculating a hidden state vector by using a state space model branch, and dynamically adjusting the position of a primary function node of a Kolmogov-Arnod network branch to realize collaborative dynamic feature extraction. In the training stage, an orthogonal subspace constraint and physical perception low-rank adaptation fine tuning mechanism is introduced. And finally, searching a historical fault case, performing multi-modal fusion on the historical fault case and the deep feature sequence, mapping a fusion representation into a soft prompt, and inputting the soft prompt into a large language model to generate a diagnosis report. According to the method, the problems of poor physical interpretability of characteristics and few-sample diagnosis under variable working conditions are effectively solved, and the generalization and decision-making ability of a diagnosis system are improved.

The invention discloses a casting riser image recognition method based on machine learning, and the method comprises the steps: carrying out the texture enhancement of a casting gray level image based on cross guide filtering, and forming a texture enhancement image data set; parallel straight line textures of the enhanced image are detected in a mode of combining a directional Gabor filter bank and direction consistency analysis; performing connected region analysis on a potential riser region, and performing triple screening through an area range, an aspect ratio range and a brightness contrast ratio; extracting an area feature, an edge feature, a texture feature and a shape feature of the riser candidate region, and marking the type of the riser candidate region to form a training sample set; a random forest classifier is introduced, the training sample set is input into the random forest classifier for training, a riser classifier is obtained, and the types of classified risers in the casting image are obtained; accurate positioning and classification of the casting risers are achieved, technical support is provided for automation and intelligentization of casting cleaning, and remarkable practical value is achieved.

The invention provides a circular curve burr detection method and system based on multi-scale phase consistency and a contour model, and a medium, and the method comprises the steps: constructing a multi-scale Log-Gabor filter group, and carrying out the convolution calculation of an input image, and obtaining a response vector; calculating phase consistency measurement of each pixel point, extracting an initial edge point set, fitting an initial circular contour, performing energy minimization evolution on the initial circular contour based on an active contour model, and fitting a real contour of burrs; constructing a two-dimensional feature vector; carrying out fusion discrimination on the two-dimensional feature vectors based on a linear weighted score function, and outputting a burr detection result; according to the method, phase consistency is used as a core image feature, so that the detection algorithm has natural invariance for uneven illumination, brightness change and contrast difference, and under the scene of failure caused by poor image quality in the prior art, the contour edge can still be stably and completely extracted, and the omission ratio is remarkably reduced.

The invention relates to the technical field of image processing, in particular to a textile gray fabric singeing adaptive control method, which comprises the following steps of: respectively acquiring an optical image and an infrared thermal image before and after singeing, quantifying a two-dimensional hairiness index matrix and texture parameters before singeing through a U-Net network and a Gabor filter bank, and calculating the singeing quality of the textile gray fabric. Generating a singed warp and weft heat energy diagram by combining a super-resolution reconstruction technology; fusing the warp and weft heat energy diagram, the two-dimensional hairiness index matrix and the texture parameters into a unified textile gray fabric fingerprint through a space coordinate alignment algorithm; a strategy generation-singeing prediction dual-module deep learning model is constructed, a strategy generation network generates singeing parameters according to fingerprints, a singeing prediction network predicts the parameters and compares the parameters with an optimal target, and self-adaptive control is carried out on flame intensity and form and textile fabric speed and tension. The textile grey cloth singeing self-adaptive control is realized through image recognition.

The application discloses a two-stage SAR image edge detection method based on saliency, and belongs to the technical field of image processing. Anisotropic filtering is used to smooth the input image, so as to filter out noise and retain edge information as much as possible. A Gauss difference operator is used to highlight edge regions and suppress flat regions; a Gabor filter bank and maximum processing are used to generate an edge saliency map, on the saliency map, edge regions have higher saliency values, and other regions are suppressed more thoroughly. Non-maximum suppression and double-threshold processing are used to perform edge rough extraction from the SME, so as to obtain primary edges containing false alarms. A neighborhood discrimination strategy is used to eliminate false alarms from the primary edges, so as to obtain a final edge detection result. Therefore, the application has good scalability, and the detection result has excellent accuracy.

This invention provides a method, apparatus, and device for detecting transformer oil leakage based on physical information, relating to the field of power equipment inspection technology. The method includes: constructing an adaptive channel Gabor attention module based on a learnable Gabor filter bank and a channel attention generator; constructing a feature extraction network based on this Gabor attention module to extract multi-scale texture features; constructing a feature fusion network based on an anisotropic dilated convolutional pyramid pooling module to fuse multi-scale texture features and output the oil leakage probability corresponding to each pixel in the image; establishing a transformer oil leakage detection model based on the feature extraction network and the feature fusion network; establishing a loss function based on the gravity rationality of the oil leakage probability of each pixel and training the detection model; and identifying the oil leakage area in the transformer image based on the trained model. This invention can improve the accuracy and robustness of transformer oil leakage detection, meeting the actual needs of intelligent inspection in power systems.

The invention relates to a machine vision detection method for helical gear wear. The method comprises the following steps: step 1, image acquisition: acquiring a gear image; the main direction of the tooth surface is detected in real time through Hough transformation, a direction-adjustable Gabor filter bank is constructed, dynamic deformation of the gear is compensated, and relevant abrasion characteristics are highlighted; step 3, multi-resolution feature decoupling is carried out; 4, physical field constraint deep learning: inputting the enhanced image and strain field data into ResNet-101, and outputting a wear probability thermodynamic diagram; 5, dynamic deformation sensing registration: calculating three-dimensional deformation, using the three-dimensional deformation as a rigid constraint term of an ICP algorithm to compensate dynamic deformation, and carrying out point cloud adaptive alignment registration; 6, working condition self-adaptive decision making: calculating the membership degree of the current working condition, calculating a dynamic threshold value, and combining a probability graph threshold value, a physical field residual error and a deformation abnormal value to carry out comprehensive decision making; and step 7, health state evaluation and early warning: calculating an abrasion index.

The present application belongs to the technical field of image processing, and particularly relates to a composite board welding quality detection method and system based on image processing, which comprises the following steps: performing morphological gradient and threshold segmentation preprocessing on the collected welding image to obtain a welding area image; calculating a defect spread index for any pixel point in the welding area image, and determining an optimal frequency in combination with a frequency boundary and the maximum and minimum values of the defect spread index; correcting a basic bandwidth by using the fluctuation of the optimal frequency of the neighborhood pixel points to determine a dynamic bandwidth; constructing a pixel-by-pixel adaptive Log-Gabor filter bank by using the optimal frequency and the dynamic bandwidth, extracting a defect energy distribution map, and identifying defects. The present application realizes adaptive adjustment of filter parameters through physical width perception, solves the problem that fixed parameters cannot take into account different types of defects, and improves the accuracy of quality detection.

The application discloses a fabric defect detection method based on abnormal perception weighted tensor robust component analysis, and belongs to the technical field of machine vision and industrial surface defect detection. The method comprises the following steps: a multi-scale multi-direction Gabor filter bank is used to convolve a fabric image to construct a multi-dimensional observation feature tensor; probability densities of feature responses of all channels are fitted, and are converted into self-information abnormality degrees based on information theory to construct a spatial prior weight tensor which is decoupled from iterative optimization; an adaptive group sparse norm double constraint optimization model is constructed, an alternating direction multiplier method is used to iteratively solve the model under a two-stage optimization strategy, a feature tensor is decomposed into a low-rank background tensor and a sparse defect tensor; the sparse defect tensor is reconstructed, fused and post-processed, and a defect saliency map is output. The application realizes complete decoupling of weight distribution and iterative numerical value, dynamically suppresses low-quality channels, detects weak defects with high fidelity under a zero-sample condition, and effectively reduces a false positive rate.

This application relates to the interdisciplinary field of geotechnical engineering and computer vision, and discloses an image recognition and analysis system for shallow foundation reinforcement conditions. The system includes an image acquisition and separation module for acquiring the foundation video stream and dividing it into a pre-reinforcement steady-state image, a dynamic sequence during reinforcement, and a post-reinforcement steady-state image; a transient displacement calculation module for solving the dynamic sequence and extracting the transient displacement field gradient mean and transient principal displacement vector angle; a frequency domain directional filtering module for mapping the principal displacement vector angle to orthogonal directions and constructing a directional two-dimensional Gabor filter bank to process the steady-state image; a spectral feature calculation module for calculating the high-frequency texture energy integral and outputting the directional compaction anisotropy index; and a state quantification evaluation module for fusing the displacement field gradient mean and anisotropy index to generate a reinforcement state index. This invention establishes a cross-domain mapping between macroscopic deformation and microscopic texture, improving the accuracy of foundation compaction assessment and realizing adaptive closed-loop control of foundation reinforcement construction.

The present application relates to the technical field of machine vision and image data, and particularly relates to a method for detecting defects on the surface of galvanized layer of electric iron accessories based on machine vision. The method comprises the following steps: obtaining a surface image of the electric iron accessories, constructing a multi-scale Gabor filter bank and calculating the real part and the imaginary part of the convolution response, and constructing a ridge line phase asymmetry index for each pixel point of the surface image; constructing a local structure tensor to determine the dominant direction of the neighborhood, and combining the gradient distribution to construct a neighborhood texture topological consistency coefficient; using the neighborhood texture topological consistency coefficient to construct a nonlinear gain weight, modulating the comprehensive amplitude energy of the pixel points determined by the Gabor filter bank to generate a defect saliency map, and determining the defect detection result through double-threshold hysteresis segmentation. The method can effectively distinguish linear defects from zinc flower grain boundary texture from the physical mechanism, suppresses the background interference while retaining weak defects, and improves the accuracy of the surface defect detection of the galvanized layer of the electric iron accessories.

The invention belongs to the technical field of image processing, and particularly relates to a composite board welding quality detection method and system based on image processing, and the method comprises the steps: carrying out the morphological gradient and threshold segmentation preprocessing of a collected welding image, and obtaining a welding region image; for any pixel point in the welding area image, a defect broadening index is calculated, and the optimal frequency is determined in combination with the frequency boundary and the maximum and minimum value of the defect broadening index; the basic bandwidth is corrected according to the fluctuation condition of the optimal frequency of the neighborhood pixel points, and the dynamic bandwidth is determined; and constructing a pixel-by-pixel self-adaptive Log-Gabor filter bank by utilizing the optimal frequency and the dynamic bandwidth, extracting a defect energy distribution diagram and identifying defects. According to the invention, adaptive adjustment of filter parameters is realized through physical width sensing, the problem that different types of defects cannot be considered by fixed parameters is solved, and the accuracy of quality detection is improved.

The invention relates to the technical field of remote sensing image processing, and particularly discloses a feature fusion pyramid remote sensing target detection method based on frequency perception. The method comprises the steps that a public data set is preprocessed, a remote sensing target detection model containing a four-layer feature fusion structure and a frequency sensing module is constructed, the frequency sensing module extracts features through a specific Gabor filter bank and carries out activation, pooling, splicing, convolution fusion and other processing, a feature fusion pyramid serves as a neck embedded detection frame, and a remote sensing target is obtained. And performing target detection on the to-be-detected remote sensing image after training. According to the method, the problems of insufficient small target detection capability and easy false detection or missing detection in a complex background and multi-scale target scene in the existing method are solved, multi-scale features and local detail information are effectively integrated, the precision, robustness and environmental adaptability of remote sensing target detection are remarkably improved, and the method is suitable for popularization and application. Reliable technical support is provided for the fields of geographic information systems, environment monitoring, urban planning and the like.