70 results about "Sobel operator" patented technology

The invention relates to the technical field of image processing, in particular to a lens edge detection method and system based on image generation, and the method comprises the following steps: collecting a lens image through an industrial camera, carrying out the weighted graying, extracting an edge coordinate through a Laplace operator, constructing an edge pixel coordinate set, and carrying out the image processing; screening an edge validity marking result by combining a gray difference threshold, calculating a phase difference between a gradient direction and light source incidence based on a Sobel operator, extracting pixels in a consistent direction, carrying out spatial clustering, generating a lens edge pixel cluster, and fitting a continuous curve to construct a complete lens edge contour. Noise and reflection interference are restrained through pixel neighborhood gray difference, effective pixels are screened in combination with a gradient direction and light source incident phase relation, edge direction consistency is enhanced, pixels are clustered according to spatial continuity and gradient intensity, contours are continuously fitted based on pixel cluster distribution, and lens edge integrity and geometric consistency under complex illumination are improved.

The invention discloses a road underground defect AI intelligent identification method based on a three-dimensional radar image, and the method comprises the steps: setting electromagnetic wave parameters of ground penetrating radar equipment, and carrying out the multi-view image collection; the gray gradient change rate of the C-Scan image is calculated through a Sobel operator, the road state is identified, and a road disease area corresponding to the abnormal color plaque is extracted; constructing an advancing direction road defect type identification model, and identifying the road defect type of the road disease area; constructing a depth direction road defect type identification model, and identifying the road defect type of the road disease area; and according to the road defect type identification accuracy of the model, performing model optimization in combination with a preset accuracy threshold. According to the method, the problems of single parameter setting, high image interference misjudgment rate, insufficient defect identification precision and the like in traditional ground penetrating radar detection are effectively solved, and high-precision, multi-dimensional and intelligent identification of road underground structure diseases is realized.

The invention discloses a crack sub-pixel precision edge detection method based on an improved Canny operator. The crack sub-pixel precision edge detection method comprises the steps of obtaining a crack image corresponding to a structural body surface crack; the crack image is preprocessed; carrying out gradient calculation on the preprocessed crack image through an improved Sobel operator to obtain a gradient image containing a gradient magnitude and a gradient direction; performing non-maximum suppression on the gradient image, adaptively obtaining an optimal threshold by adopting an improved maximum between-class variance method, judging a crack edge according to the optimal threshold, and further obtaining a coarse edge pixel-level image; processing edge information in the coarse edge pixel-level image by using a Zernike orthogonal moment to obtain coordinates of sub-pixel edge points; and connecting all the sub-pixel edge points, and outputting a crack detection result image. On the basis, the crack edge detection precision is improved to a sub-pixel level.

The invention relates to a lightweight traffic road semantic segmentation method based on multi-scale feature fusion, and belongs to the field of intelligent driving. The method solves the problems that precision and speed are difficult to balance and small target recognition accuracy is low in real-time application of a traditional semantic segmentation method. According to the technical scheme, context information is extracted by adopting a Vision Transform branch, space information is extracted by adopting a CNN branch, a model is optimized through feature fusion and alignment loss during training, and only the CNN branch is used during reasoning; sobel operator edge detection, a multi-scale feature fusion module and a feature distribution simulation module are integrated. The method has the technical effects that high-precision semantic segmentation is realized, the small target recognition capability is remarkably improved, and meanwhile, the real-time processing speed is ensured.

The invention relates to a reconstructed image anti-aliasing processing method based on an adaptive sampling rate, belongs to the technical field of CT (Computed Tomography) reconstructed image processing, and solves the problem that the existing anti-aliasing processing method for a CT reconstructed image is poor in effect. The anti-aliasing processing method for the reconstructed image comprises the following steps: preprocessing the reconstructed image to obtain a to-be-processed image; performing edge extraction on the to-be-processed image based on a preset gradient threshold and a preset Sobel operator, and segmenting the to-be-processed image into a to-be-replaced image region and a reserved image region; determining an adaptive sampling rate based on the horizontal direction edge pixel connection number and the vertical direction edge pixel connection number of all sawtooth vertex pixels in the to-be-processed image; determining a pixel value of each pixel in the to-be-replaced image region based on the adaptive sampling rate and the to-be-processed image, and obtaining a replaced image region; and combining the replaced image area and the reserved image area to obtain an image after anti-aliasing processing. And the anti-aliasing effect of the CT reconstructed image is improved.

The invention belongs to the technical field of building boundary segmentation, and provides a remote sensing image building boundary segmentation method based on a U-net network model, and the method comprises the steps: extracting a gradient magnitude image through a Sobel operator, generating a binary boundary mask, dynamically adjusting the weight of a convolution kernel in combination with a gradient direction, and enhancing the feature extraction capability of a boundary region; boundary artifacts output by cavity convolution are suppressed through a high-frequency residual boundary mask, an artifact area is restored in combination with gradient direction constraint, and original detail features are reserved; calculating complexity scores based on boundary density and tortuosity, adaptively selecting voidage, and balancing global context and local detail capture capability; extracting a high-frequency component through a Laplace operator, marking an artifact point by combining a dynamic threshold value, and repairing an abnormal region by utilizing a neighborhood gradient direction; the method solves the performance bottleneck of a traditional method in a boundary fuzzy, artifact interference and receptive field fixed scene, and is suitable for remote sensing image analysis tasks such as urban planning and disaster assessment.

The invention discloses a method and a system for reconstructing a cavity shielded by a shallow reinforcing mesh. The method comprises the following steps: constructing a layered medium scene containing the shallow reinforcing mesh and the cavity; acquiring image data information with different shielding states and preprocessing the image data information to construct a reconstruction data set; constructing a reconstruction initial model of the cavity shielded by the shallow reinforcing mesh, and training to obtain a reconstruction model of the cavity shielded by the shallow reinforcing mesh; and adopting the obtained reconstruction model of the cavity shielded by the shallow reinforcing mesh to reconstruct the actual cavity shielded by the shallow reinforcing mesh. According to the method, multiple types of training data are acquired through a constructed layered medium scene containing a shallow reinforcing mesh and a cavity, and a reconstruction model of the cavity shielded by the shallow reinforcing mesh, which comprises a U-shaped network, a Sobel operator, an attention mechanism, a residual structure, an average mechanism and a jump connection scheme, is trained; therefore, the reconstruction of the cavity under the shielding of the shallow reinforcing mesh can be realized, the reliability is higher, the accuracy is better, and the reconstruction efficiency is higher.

The invention discloses a power transmission line icing thickness detection method and system based on deep learning, and relates to the technical field of image processing and power transmission line online detection, and the method comprises the steps: collecting an icing image of a power transmission line through a standardized dual-light optical device, and carrying out the image preprocessing, and generating an original data set; and performing image segmentation on the original data set, training the deep neural network model by using the lightweight YOLACT network, and performing evaluation. Edge detection is carried out through a multi-direction Sobel operator template, an Otsu method is adopted for binarization processing and nonlinear operator filtering denoising, a boundary chain code array is extracted based on a boundary tracking algorithm of a topological structure, and the MASK of an original power transmission line is determined. And acquiring an image of the power transmission line by using a dual-light camera, performing camera calibration, performing registration and fusion on the calibrated image, and outputting a calculation result of the icing thickness of the power transmission line by using the trained neural network. According to the invention, the detection precision and efficiency are improved, and the thickness estimation deviation caused by image errors is reduced.

The invention discloses a natural gas hydrate CT image threshold segmentation method and a storage medium, and belongs to the technical field of natural gas hydrate detection.The method comprises the steps that S1, a natural gas hydrate sample image obtained through synchrotron radiation CT scanning is obtained, the image is preprocessed, and a central area image is obtained; s2, performing edge recognition on the preprocessed central region image by using a convolutional neural network and combining a Sobel operator to obtain an edge feature matrix; s3, clustering the edge feature matrix by adopting a KMeans clustering algorithm, and determining gray boundary values of the solid particles and the methane bubbles; s4, removing gray scale parts of solid particles and methane bubbles in the image according to the gray scale boundary value, and performing maximum and minimum normalization processing on the residual gray scale values of water and hydrates to obtain a gray scale probability density; and S5, drawing a normalized gray probability density map according to the gray probability densities of all the images, and determining a threshold segmentation range of the hydrate according to the probability density peak displacement. The method can automatically extract the hydrate threshold range, and improves the segmentation precision.

The invention discloses an endoscope video frame specular reflection highlight detection method and system, and belongs to the field of endoscope optical detection. The method comprises the following steps: firstly, converting an endoscope video frame into a grey-scale map; a Sobel operator is utilized to extract edge gradient to generate a binary image gradient mask, and meanwhile, a binary image highlight mask is generated by obtaining an area with the brightness obviously higher than the average level of a grey-scale map; dividing the binary image gradient mask and the binary image highlight mask into image blocks, adaptively adjusting the sizes of the blocks according to the highlight ratio of the image blocks so as to fuse the binary image gradient mask and the binary image highlight mask, and performing morphological processing and region screening to obtain a final binary image highlight mask of the grey-scale image; and carrying out time domain compensation on the final binary image highlight mask to obtain a specular reflection highlight detection result of the endoscope video frame. The accuracy, integrity and robustness of specular reflection highlight detection of the endoscope video frame are effectively improved.

The application discloses a reconstruction method and system for a cavity under a shallow reinforcement net shelter, and comprises the following steps: constructing a layered medium scene containing a shallow reinforcement net and a cavity; acquiring image data information with different shelter states and preprocessing to construct a reconstruction data set; constructing a reconstruction initial model for the cavity under the shallow reinforcement net shelter and training to obtain a reconstruction model for the cavity under the shallow reinforcement net shelter; and using the obtained reconstruction model for the cavity under the shallow reinforcement net shelter to perform actual reconstruction for the cavity under the shallow reinforcement net shelter. The application acquires multiple types of training data through the constructed layered medium scene containing the shallow reinforcement net and the cavity, and trains the reconstruction model for the cavity under the shallow reinforcement net shelter which comprises a U-shaped network, a Sobel operator, an attention mechanism, a residual structure, an average mechanism and a skip connection scheme. Therefore, the application can not only realize the reconstruction for the cavity under the shallow reinforcement net shelter, but also has higher reliability, better accuracy and higher reconstruction efficiency.

This invention provides a method and apparatus for detecting surface defects in steel based on an improved YOLOv11. The method includes: integrating an EA module into the backbone network of YOLOv11, combining the Sobel operator edge detection idea with an attention mechanism, significantly enhancing the network's ability to perceive the geometric edges of defects, effectively improving the detection performance of low-contrast defect-background boundaries, and enhancing the ability to identify key defects such as cracks; by integrating three MSA modules into the neck network, the model's ability to capture multi-scale information in the feature space is significantly improved; the special position design of the EA module enhances the network's attention to horizontal and vertical gradient features during the final fusion of multi-scale feature representations, avoiding excessive interference with original features or highly abstract features; and achieving end-to-end processing from the original image to the defect detection result, significantly improving the detection performance of low-contrast defects and cross-scale defects on the surface of steel equipment.

This invention discloses an intelligent quality detection method and system for rainbow films based on image recognition, belonging to the field of image processing technology. The method includes convolving a rainbow film image using the Sobel operator to generate a binary mask, generating a filtered morpholuminescence map, performing a one-dimensional Fourier transform on the filtered morpholuminescence map, calculating the direction angle of the complex curl using the arctangent binary function, extracting the principal phase field, calculating the continuous phase field, convolving the continuous phase field to generate a smoothed continuous phase field, and calculating the gradient magnitude of the smoothed continuous phase field to generate a binary defect mask. This invention generates a high-quality morpholuminescence map through multi-level feature extraction and adaptive segmentation, enhancing the continuity of fringes and the distinguishability of defects. By constructing a smooth and continuous phase field and combining it with statistical thresholds for adaptive identification of defect regions, it improves the robust recognition capability for complex interference patterns.

The application discloses a global mesoscale frontal automatic identification method based on a sliding window threshold value, and comprises the following steps: performing pretreatment operation of erosion missing value and noise filtering on input data; calculating frontal intensity according to an improved Sobel operator; marking a candidate frontal area according to a sliding window threshold value; obtaining final frontal area product data by using multiple mathematical morphological operators; forming a candidate frontal line according to multiple direction frontal intensity extreme values and a mask of the frontal area product; and finally obtaining frontal line product data by using multiple mathematical morphological operators. The method provided by the application is not susceptible to noise, is not sensitive to absolute gradient intensity, can identify mesoscale fronts missed by existing algorithms, solves the problem that traditional marine frontal identification methods are sensitive to absolute gradient and cannot identify weak fronts, and the identified frontal has better continuity, and has good applicability to global or regional sea areas.

The present application relates to the technical field of intelligent control and industrial visual detection of beneficiation process, and discloses an industrial-grade ore belt boundary identification method based on multi-frame time sequence fusion. A multi-branch hollow boundary enhancement unit is constructed based on deep convolution, different convolution kernel sizes, and a Sobel operator. A feature extraction and fusion module is constructed based on unbiased convolution, time sequence cross-channel difference, the multi-branch hollow boundary enhancement unit, and multi-head attention. A feature enhancement module is constructed based on deep separable convolution and the multi-branch hollow boundary enhancement unit. A prediction module is constructed based on the multi-branch hollow boundary enhancement unit. An identification model is constructed based on the feature extraction and fusion module, the feature enhancement module, and the prediction module. Continuous multi-frame pictures in an industrial field are acquired, and after preprocessing, the multi-frame pictures are input into the identification model to obtain ore belt boundary identification results. Based on the ore belt boundary identification results, sorting is performed, and the problem that existing table sorting and identification methods cannot effectively identify ore belt boundaries is solved.

The invention provides a method for improving the image definition of a color CMOS camera through an AI recognition technology. According to the method, data are collected from a public image data set, and the data are used for training of a capsule network model and implementation of adaptive filtering, so that the understanding of improvement of image definition is further deepened. And then evaluating the restored image by using an improved Sobel operator, so as to provide more comprehensive and more efficient image definition evaluation. And finally, the optimized model is deployed in a color CMOS camera, so that the real-time image definition during shooting is improved, and the model is more mature and the image definition is further improved by collecting user feedback and real-time image data. According to the invention, the quality of the image shot by the CMOS camera can be obviously improved, and better user experience is provided.

The embodiment of the application provides a rail corrugation identification method, system and storage medium, and belongs to the technical field of railway track detection. The rail corrugation identification method comprises the following steps: inputting preprocessed rail corrugation true value image data into an image segmentation identification model to extract global semantic features and local texture features; generating edge features through a Sobel operator after performing channel averaging on the output of the intermediate feature extraction stage, and fusing the global semantic features, the local texture features and the edge features to obtain a segmentation mask graph; inputting ROI image segments cut based on the segmentation mask graph and features extracted by the intermediate feature extraction stage for target detection into a target detection network, performing regression calculation based on a bounding box overlap optimization loss, and outputting a rail corrugation detection result. Through multi-scale feature extraction and channel space attention fusion, the scheme effectively improves the positioning accuracy and segmentation robustness of the rail corrugation area.

The application discloses a kind of based on FPGA's video real-time defogging method, utilize the similarity between video stream frame design pipeline architecture to execute step: using the sky area segmentation algorithm of fusion minimum channel value and four direction Sobel operator gradient value, the sky area and non-sky area of foggy image are segmented;First, the minimum channel value of sky area is taken as the channel component of atmospheric light value average, then the atmospheric light value is calculated;First, the initial transmittance of whole foggy image is calculated, the initial transmittance of non-sky area is not handled, using the difference value of minimum channel mean value and the minimum channel value of single pixel based on the transmittance adaptive compensation mechanism designed, the initial transmittance of sky area is revised and handled, and the final transmittance is obtained;Based on atmospheric light value, final transmittance and atmospheric scattering model, foggy image is restored to no fog image.The method can maintain low complexity while ensuring defogging performance, easy to FPGA deployment.

The invention discloses a real-time video defogging method based on an FPGA (Field Programmable Gate Array), which is implemented by designing a pipeline architecture by utilizing the similarity between video stream frames and comprises the following steps of: segmenting a sky region and a non-sky region of a foggy image by using a sky region segmentation algorithm fusing a minimum channel value and a four-direction Sobel operator gradient value; the minimum channel values of the sky area are averaged to serve as an atmospheric light value channel component, and then an atmospheric light value is obtained through calculation; the method comprises the following steps: firstly, calculating the initial transmissivity of a whole foggy image, not processing the initial transmissivity of a non-sky area, and correcting the initial transmissivity of a sky area by adopting a transmissivity adaptive compensation mechanism designed based on a difference value between a minimum channel mean value and a minimum channel value of a single pixel to obtain a final transmissivity; and restoring the foggy image into a fogless image based on the atmospheric light value, the final transmissivity and the atmospheric scattering model. According to the method, the low complexity can be maintained while the defogging performance is ensured, and FPGA deployment is easy.

The present application relates to the technical field of liquid crystal display, specifically to a dynamic backlight control method and system of high-efficiency liquid crystal display module, comprising the following steps: S1, collecting image data, human eye fixation point distribution data and preference information for image brightness and color combination; S2, using the collected data to train a CNN-RNN hybrid model; S3, based on the sensitivity of human eye to brightness change, introducing a JND threshold, and designing a brightness weighting function; S4, weighting and averaging the image brightness according to the CIE 1931 brightness curve; S5, using a Sobel operator to detect the brightness mutation area; the present application effectively reduces the influence of brightness mutation on the visual system by introducing a JND threshold and designing a reasonable brightness weighting function and dynamic compensation strategy, thereby reducing visual fatigue; the Sobel operator is used to detect the brightness mutation area, and a dynamic compensation coefficient is applied to finely adjust the pixel value, realizing pixel-level brightness optimization, thereby maintaining high contrast and delicate image quality, and reducing energy consumption.

The invention discloses an electrical equipment infrared spectrum identification method and system based on feature fusion. The method comprises the following steps: acquiring infrared images of a plurality of different visual angles and constructing a data set; carrying out feature extraction on the multi-view infrared images by adopting a deep learning network, and fusing the features of the infrared images of different views; adjusting the weight of each view angle feature according to the definition and integrity of the target in the infrared images of different view angles, calculating a gradient value of the infrared image based on a Sobel operator as a definition index, and obtaining an integrity index based on a target area proportion; and training the model through the data set, and predicting the center point coordinates of each component in the power equipment. A multi-view image acquisition and self-adaptive feature fusion strategy is adopted, image features of different angles are integrated through a feature pyramid network (FPN), a self-adaptive weight distribution mechanism is designed, weights of all view angles are dynamically adjusted according to target definition and integrity, and information loss caused by angle changes is effectively reduced.

The invention discloses a single-image camera internal reference calibration method based on a direct-facing posture and focal length constraint, and the method comprises the steps: firstly, setting a calibration plate with a dot array and a camera, and enabling the view field of the camera to comprise all clear images of the calibration plate; then the calibration plate is adjusted to carry out horizontal adjustment and pitching adjustment in sequence, so that the camera directly faces the calibration plate; and in the adjusting process, the offset of each circle center on the calibration plate and the adjacent circle centers of the next row and column in the xy direction of the pixel coordinate system is calculated in real time, so that each circle center on the calibration plate meets the constraint condition. The optimal focal plane is further determined by adopting a mode of calculating the global gradient of the image by adopting a Sobel operator. And finally, collecting a picture, firstly calculating the distance between the circle center of all dots and the adjacent circle center, then calculating the object distance and the image distance through simultaneous magnification and a Gaussian imaging formula, and further calculating the internal reference of the camera. According to the method, the internal reference of the camera is conveniently, quickly and accurately calibrated by using a single image.

The embodiment of the invention provides a remote sensing image cloud distribution discrete degree detection method, device and equipment, and is applied to the technical field of remote sensing image processing. The method comprises the steps of calculating a synthetic wave band pixel gradient value based on a blue-green wave band gray value of a to-be-detected remote sensing image; based on a Sobel operator, calculating a pixel normalization synthesis waveband gradient value according to the synthesis waveband pixel gradient value; generating a cloud mask binary image based on the to-be-detected remote sensing image; removing cloud spots of which the area is smaller than a first area threshold value on the cloud mask binary image, extracting and calculating the mean value of normalized synthesis waveband gradient values of edge pixels of the cloud spots of which the area is larger than a second area threshold value, and calculating the total mean value of the mean values; and judging whether the total mean value is smaller than a first threshold value, and if yes, determining that the cloud distribution dispersion degree of the to-be-detected remote sensing image is cloud distribution relative aggregation. On the basis, the discrete degree of the thin cloud can be accurately described, so that the discrete degree of the cloud in the image is detected.

The invention provides a low-dose CT (Computed Tomography) image denoising method fusing gradient extraction and mixed loss. Comprising the following steps: S1, acquiring a low-dose CT image as input, performing numerical truncation and normalization preprocessing on input data, and constructing a de-noising model based on a U-Net backbone network; s2, constructing a gradient extraction module at the output end of the U-Net backbone network in parallel, extracting high-frequency edge features of the image in horizontal and vertical directions by using a Sobel operator, and mapping the image from an intensity domain to a gradient magnitude domain; s3, constructing a mixed loss function including pixel consistency loss, structural similarity loss and gradient perception loss; and S4, calculating the difference between the predicted image and the gold standard image by using the mixed loss function, and optimizing network parameters through back propagation to obtain a denoised CT image. According to the method, competition conflicts between mean square errors and structure indexes can be effectively relieved, and edge artifacts of a high-density skeleton region are eliminated while noise is suppressed.

The invention relates to a CT image anti-aliasing processing method, belongs to the technical field of CT image processing, and solves the problem that the existing CT image anti-aliasing processing method is poor in effect. The processing method comprises the following steps: preprocessing a sawtooth CT image to obtain a to-be-processed image; performing edge extraction on the to-be-processed image based on a preset gradient threshold and a preset Sobel operator, and segmenting the to-be-processed image into a to-be-replaced image region and a reserved image region; determining a pixel value of each pixel in the to-be-replaced image area according to a preset sampling rate and the to-be-processed image, and obtaining a replaced image area; and combining the replaced image area and the reserved image area to obtain an image after anti-aliasing processing. And the anti-aliasing effect is improved.

The invention discloses an anti-resonance optical fiber identification and high-precision axis alignment method based on end face characteristics, and relates to the technical field of optical fiber fusion splicers, and the method comprises the following steps: S1, collecting end face images of multiple types of anti-resonance optical fibers, the multiple types of anti-resonance optical fibers including a basic type and a complex nested type; preprocessing the acquired image, wherein the preprocessing comprises graying, Gaussian blur denoising, Sobel operator gradient calculation, binaryzation and morphological operation; s2, preprocessing the acquired image, including graying, Gaussian blur denoising, Sobel operator gradient calculation, binaryzation and morphological operation; according to the anti-resonance optical fiber identification and high-precision axis alignment method based on the end face features, the end face feature differences of anti-resonance optical fibers of different structures are deeply excavated, a two-stage classification framework of large class distinguishing-subdivision identification is innovatively constructed, and the adaptability and accuracy of classification identification of the multi-structure anti-resonance optical fibers are remarkably improved.

The invention discloses a phase unwrapping algorithm for optical coherence elastography, and relates to the technical field of phase unwrapping. The algorithm is based on an improved U-Net architecture, a network comprising an encoder, a decoder and a jump connection mechanism is constructed, the core is cooperated with an EGA module through a multi-branch Inception residual module in the encoder, the multi-branch Inception residual module extracts different receptive field phase features through five parallel convolution branches, the EGA module calculates gradients through a Sobel operator, attention weights are generated, and the attention weights are calculated through the EGA module. Strengthening phase edge and gradient mutation region response; the decoder removes residual noise through transposition convolution up-sampling, fusion of high and low layer features for fine reconstruction, and optional smoothing filtering. The method solves the problems that a traditional algorithm is low in precision, poor in robustness and low in speed under the scenes of low signal-to-noise ratio, strong speckle disturbance and severe phase gradient change, achieves high precision, high robustness and rapid unwrapping of OCE phase signals, adapts to complex tissue deformation and large-view-field rapid reconstruction requirements, and can be widely applied to the fields of clinical diagnosis, biomedical research and the like.

The present application relates to radar data processing technical field, specifically to a kind of radar layer position tracking method of fusing confidence clustering and wavelet energy discrimination, comprising the following steps: S1, the gray processing is carried out to each frame radar image and the candidate layer position point of the edge gradient greater than threshold is extracted using Sobel operator;S2, detect and eliminate outlier, false edge and low confidence point;S3, according to confidence weighted clustering to generate structure point;S4, optimal trajectory is spliced using DTW algorithm to form layer position path;S5, calculate wavelet energy variation rate to correct deviated path;S6, curve fitting and smoothing to generate final layer position trajectory.The present application, by outlier elimination, confidence weighted clustering, dynamic path planning and wavelet energy auxiliary correction mechanism, improves the accuracy, continuity and robustness under complex structure region of radar layer position tracking.

The invention discloses an image tampering positioning method and system based on edge guidance and multi-scale feature fusion. The method comprises the following steps: firstly, constructing a deep learning framework based on a Vision Transformer (ViT) backbone network, and realizing efficient modeling of local and global tampering features in an image in combination with a content awareness residual module; in order to improve the accuracy and robustness of tampering region detection, an edge guiding strategy is designed, and the strategy combines a Sobel operator, morphological operation and an edge segmentation loss function to reinforce tampering boundary feature expression, so that the sensitivity to an unnaturally fused region is improved. The invention further provides a multi-scale supervision mechanism, a coordinate attention module is combined, the model is guided to fuse semantic features under different scales, and the adaptive detection capability of the model on tampering regions with different scales is enhanced. In the implementation process, in the training stage, the detection performance of the model on image tampering is gradually improved by optimizing all modules of the deep learning network; and then, inputting an image to be detected by using the trained network, and automatically identifying and positioning a tampering region in the image. The method can effectively detect and position the tampering area of the image, has a wide application prospect, and can provide a more reliable and efficient image tampering detection solution especially in the fields of digital forensics, image content security and the like.

The invention discloses a near monochromatic light source color-mixed white light achromatic high-quality imaging method, and belongs to the technical field of optical imaging and image processing. Comprising the following steps: S1, configuring a red, green and blue near-monochromatic mixed white light source; s2, collecting standard color card data and white standard area reference data under a xenon lamp and mixed-color white light; s3, correcting color deviation in mixed color white light source imaging based on the color card data and the reference data; s4, by taking the green channel as a reference, adjusting and synchronously correcting the position offset and intensity calibration of the red and blue channels; and S5, based on a Sobel operator, enhancing the image contrast. By adopting the near monochromatic light source mixed color white light achromatic high-quality imaging method, the problems of near monochromatic light imaging chromatic aberration and channel position offset are solved, and achromatic, high-definition and high-color-rendition high-quality imaging is realized.