1112 results about "Gradation" patented technology

The invention relates to the technical field of image data processing, in particular to a forge piece surface defect detection method and system based on machine vision. The method comprises the steps of obtaining a gray image of a to-be-detected forging surface; determining a boundary significance weight; determining a path consistency weight; screening the boundary significance weight and the path consistency weight to obtain a final weight; and carrying out local adaptive threshold segmentation on the final feature map to obtain a binary image, and carrying out defect identification on the surface of the forge piece to be detected based on a connected region in the binary image. According to the method, the boundary significance weight and the path consistency weight are constructed and are respectively used for accurately positioning defect edges and verifying structure continuity, texture interference is effectively inhibited, and false alarms are reduced; through adaptive Gabor filtering, the problem of a response blind area of a traditional method is solved, finally two weights are fused to modulate filtering response, and the accuracy of forging surface defect detection is improved.

The invention relates to the technical field of metal defect detection, and discloses an aluminum alloy round aluminum rod surface defect image super-resolution method. The method comprises the following steps: acquiring a low-resolution original image sequence of surface defects of the aluminum alloy round aluminum rod, and synchronously acquiring gray value distribution at different illumination angles through a multi-channel optical sensor; constructing a dynamic degradation model according to pixel displacement of adjacent frames in the original image sequence, extracting cross-scale defect features in the original image sequence, and taking output parameters of the dynamic degradation model as spatial constraint conditions of a feature extraction network; and a high-resolution defect image is generated through the multi-stage residual error reconstruction network, the high-resolution image output by the reconstruction network is fed back to the dynamic degradation model, and the frequency domain response coefficient of the spatial fuzzy kernel function is updated to form closed-loop optimization. The identification degree of defect features is improved, and a reliable image data basis is provided for accurate detection of the surface defects of the aluminum alloy round aluminum rod.

The invention relates to the technical field of computer vision, in particular to a defect segmentation positioning method and system for an inorganic mineral casting image, and the method comprises the following steps: calling an illumination image to analyze brightness, matching exposure parameters, splicing the image, analyzing a gradient, recognizing a defect, screening an effective region, calculating a gray variance, and constructing roughness weight recognition texture features. According to the method, the high-reflection area identification, the brightness gradient analysis, the pixel-level roughness weight and the structure tensor analysis are combined, the exposure interval can be dynamically adjusted when the casting image is processed, the defect type information is output in the direction, and the positioning information is generated by correcting the recognition position in combination with the actual coordinate of the target spot. The method has the advantages that the high-reflection area identification, the brightness gradient analysis, the pixel-level roughness weight and the structure tensor analysis are combined; the method has the advantages that the method is simple and easy to implement, detail loss of overexposure areas is reduced, the recognition precision of defect areas is improved, accurate area segmentation and classification processing are achieved, roughness weight calculation combining gray variance and pixel density is combined, the sensitivity to surface fine defects is enhanced, and the precision and reliability of defect positioning are improved.

The invention belongs to the technical field of deep learning, and particularly discloses an ultra-precision full-field displacement measurement method and system based on a convolutional variational auto-encoder. Comprising the following steps: acquiring a video when a to-be-detected structure is subjected to vibration deformation, and selecting a picture of a deformation position to construct a data set; training a deep learning model of the convolutional variational auto-encoder based on the data set; reconstructing the gray value of the original image by using the trained deep learning model to obtain a gray value containing infinitesimal displacement information; and carrying out displacement calculation on the reconstructed image by utilizing an optical flow method, and realizing ultra-precision displacement calculation on the to-be-measured structure according to gray value conversion. According to the method, the problem that the infinitesimal displacement smaller than the sensitivity limit is difficult to measure is solved, the problem that the to-be-measured structure is blocked and cannot be measured is solved by utilizing the characteristics of the generative deep learning model, and the basic data precision of displacement measurement is remarkably improved.

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 relates to the technical field of mode recognition and data recognition, and discloses an intelligent visual detection method for non-standard precision part surface microdefects, which comprises the following steps: acquiring surface gray level image data of a to-be-detected part, physically abandoning low-frequency components through discrete wavelet transform, and reserving high-frequency detail components to construct a frequency domain input tensor; constructing a double-flow reconstruction model containing a space domain coding network and a frequency domain coding network, and minimizing the distribution difference of the same feature between double-domain characterization through potential feature space consistency constraint joint optimization; the method comprises the following steps of: calculating a spatial domain residual image and a frequency domain residual image, combining a texture topological residual image extracted by structural tensor characteristic decomposition, and generating a comprehensive abnormal response image through weighted fusion to judge the defect, and effectively inhibiting macroscopic geometric contour interference through frequency domain decoupling and a topological check mechanism on the premise of not needing a standard geometric template. And sensitive perception and accurate identification of weak texture defects on the surface of the non-standard part are realized.

The invention discloses a metal processing detection system and method based on computer vision, and relates to the technical field of defect detection.Rotatable polarization filters are installed in front of a lens of a vision sensor, the polarization filters are arranged at four angles respectively, and four sets of polarization images are collected; calculating the polarization degree of each pixel point on the surface during metal processing by using the gray values of the four groups of polarization images, setting a polarization region interval, and dividing a metal surface reflection region into a specular reflection region and a diffuse reflection region; acquiring images of different wavebands by using a multispectral vision sensor, and constructing a multispectral image set; for the same wave band, the images of different exposure times are synthesized to obtain an HDR high dynamic range image; setting a weight for the HDR image of each wave band, and combining the weighting of the HDR image and the suppression of the polarization degree to carry out multispectral image fusion so as to obtain a final image; and a gray threshold value and an area threshold value are respectively calculated through the average value and the standard deviation, and the metal processing defects are judged by using the two threshold values.

The invention belongs to the technical field of inspection robot systems, and particularly relates to an inspection robot path planning method and system.The visual semantic perception module collects an industrial environment image through a top industrial camera, after graying and Gaussian filtering preprocessing, feature points are detected and matched through an ORB algorithm, and a path planning result is obtained; in combination with an illumination self-adaptive threshold screening mechanism, mismatching points are eliminated, semantics are marked, and a semantic feature map is constructed; the initial path planning module generates an initial path through a semantic cost-containing A * algorithm based on the map; the dynamic obstacle avoidance module captures a moving obstacle by using a visual sensor, and predicts a trajectory through Kalman filtering; the path optimization module combines an initial path and an obstacle track, optimizes the path by using quadratic programming of a fusion curvature constraint and an energy consumption model, and corrects positioning by fusing vision and IMU data through a dynamic weight fusion algorithm; and the execution feedback module generates an instruction according to the optimized path, re-triggers path optimization, forms a closed loop, and ensures the inspection stability.

The invention relates to the technical field of size measurement, in particular to a clock part size measurement method and system based on machine vision, and the method comprises the following steps: based on clock part surface data, analyzing reflection characteristics and pixel statistics, combining a light source angle to optimize imaging, comparing gray level distribution and shadow area, and screening an image with optimal marginal definition. And fusing the brightness and contour information, screening multi-direction size data, judging the stability of boundary pixels, and outputting a size measurement result. According to the method, multiple data features are automatically collected and fused in the collection process, parameter optimization of different surface structure information is combined, cross validation of multi-direction size information is synchronously completed in the measurement link, abnormal fluctuation data are eliminated, continuous judgment and result screening are achieved in the whole processing flow, and the accuracy of data processing is improved. The stable size data of batch parts can be efficiently obtained under the automatic discrimination process, the influence of abnormal interference on the output accuracy is reduced, and the uniformity and traceability of the measurement data are improved.

The invention discloses a shield muck coarse particle gradation real-time identification system and method based on multi-modal machine vision, and relates to the field of muck particle identification, and the system comprises a multi-modal data collection module which is composed of a plurality of groups of sensors and is used for collecting multi-modal data of muck particles; the edge calculation processing unit is used for preprocessing the multi-modal data; the analysis module is used for constructing a deep learning model and realizing grading prediction and mud content prediction; and the control module is used for real-time feedback and control including visualization, decision support and tunneling parameter adaptive adjustment. According to the system, accurate real-time analysis of geometric, image and material features of muck particles is realized through multi-modal sensor fusion and edge calculation efficient preprocessing in combination with feature-level / decision-level fusion and a lightweight deep learning model; by means of closed-loop control, the method has high adaptability and engineering intelligent feedback capacity, and muck grading recognition precision and tunneling parameter self-adaptive adjustment efficiency in shield construction are remarkably improved.

The invention discloses an enamel plate surface defect detection method based on machine vision, and relates to the technical field of enamel plate surface defect detection. The method comprises the following steps: acquiring an original image of an enamel plate, and fusing the original image through a point-by-point optimal gray fusion method to obtain a real-time reflection suppression image; a defect-free reflection suppression image of the enamel plate is collected, matching analysis is conducted on the defect-free reflection suppression image and the real-time reflection suppression image through an improved PaDiM algorithm, a difference texture area is obtained, and coordinates of the difference texture area are recorded; in the difference texture area, two types of image features are extracted through a scale attention feature extraction method and fused, a real-time and standard fusion matrix is obtained, and a defect detection result is obtained through similarity matching; and converting the coordinates of the difference region to obtain a defect positioning result, calculating a defect comprehensive score based on a defect detection result, and grading to complete the surface defect detection of the enamel plate.

The invention discloses a video anti-shake method and system based on multi-scale fusion and adaptive smoothing, relates to the technical field of video image processing, and aims to effectively solve the image quality problem caused by shake in a video shooting process. Gradient histograms and wavelet energy distribution characteristics of video frames are extracted through graying and normalization processing, and the gradient histograms and the wavelet energy distribution characteristics are input into a jitter type recognition network to recognize translation, rotation and Z-axis jitter probabilities. And further extracting motion, frequency domain and edge features, and generating multi-modal coupling features through combination of a dynamic feature interaction network and a dot product attention mechanism. And constructing a motion trajectory by using the features, optimizing the trajectory by using a texture perception double-layer smoothing strategy, introducing an adaptive penalty term into a dynamic planning cost function, and outputting a smooth motion compensation parameter. And finally, processing the boundary region through motion compensation and image extrapolation to generate an anti-shake video frame. Through multi-scale feature fusion and a self-adaptive smoothing strategy, the video anti-shake effect is effectively improved, and the method is suitable for complex scenes.

The invention relates to the technical field of visual control, in particular to a picture defect test equipment control system and method, and the system comprises a difference tensor construction module, a space-time constraint construction module, a strain response judgment module, a coupling focusing mapping module and a boundary stability evaluation module. According to the method, the multi-dimensional difference incidence relation is constructed by extracting the pixel gray difference value, the brightness gradient and the chrominance phase angle, and fine brightness fluctuation and color shift in a picture can be captured. The superposition of the time-space change rate enables the dynamic performance of image defects to be distinguished, and continuous and transient anomalies can be effectively recognized. And in combination with tensor strain ratio and difference amplitude analysis, an abnormal region can be adaptively recognized, and neglect of a traditional method on a complex scene is avoided. The weighted aggregation of the local energy response improves the stability of the defect boundary, ensures the accurate positioning and judgment consistency of the image defect, and significantly improves the reliability and accuracy of the detection result especially in dynamic change and complex illumination environments.

The invention discloses a visual filter tip modeling recognition and control system and a data interaction method thereof, and relates to the technical field of image recognition and intelligent control, and the method comprises the following steps: carrying out the continuous image collection of a filter tip through an industrial camera, and obtaining an image sequence of the filter tip in a conveying process; for each frame of image in the image sequence, extracting a transverse brightness change curve in a gray domain, and constructing an image brightness distribution matrix based on the spatial distribution of the filter tip in the image recognition area; according to the invention, by introducing a frequency domain analysis and risk prediction control mechanism, intelligent perception, quantitative evaluation and dynamic suppression of periodic optical interference are realized. The system can extract interference frequency characteristics, calculate the stability and occupancy ratio, predict and identify the risk in combination with a historical misjudgment model, dynamically adjust the duty ratio of the LED light source according to the risk result, break the resonance relation with the conveying rhythm, and suppress false characteristic interference. The method improves the accuracy, stability and yield of an identification system, and has good engineering application value.

The invention belongs to the technical field of image data processing, and discloses a driver fatigue state early warning method and system based on face recognition tracking, and the method comprises the steps: extracting a face region through semantic segmentation, splitting a single-channel gray-scale map, calculating the local complexity and noise degree of a pixel point, obtaining a window adjustment coefficient, and carrying out the adjustment of the window adjustment coefficient; the size of the adaptive window is determined, different pixel region features can be adapted in a targeted manner, and the processing deviation caused by a fixed window is effectively reduced; an illumination component is subsequently extracted based on an adaptive window, and the image is enhanced through a Retinex algorithm, so that the face image quality under complex illumination can be improved, and the detail definition is improved; and finally, the fatigue degree is detected in combination with a PERCLOS algorithm, so that the facial fatigue characteristics of the driver can be more accurately captured, and effective recognition and early warning of the fatigue state are realized. According to the invention, continuous and stable monitoring can be realized in the driving process, reliable guarantee is provided for driving safety of a driver, and the risk of accidents caused by fatigue driving is reduced.

The invention discloses a multi-channel image adaptive fusion method and system for industrial product surface defect detection. The method comprises the following steps: acquiring a multi-channel image of an industrial product surface defect, and carrying out gray normalization on the multi-channel image; for the multi-channel image after gray level normalization, according to characteristics of surface defects of different industrial products, setting a corresponding feature extraction method to carry out image feature extraction; a weighting strategy based on empirical prior is adopted for the extracted image features, the weights of the surface defects of the different industrial products are adjusted, and a fusion attention map is obtained; performing multi-resolution decomposition on the multi-channel image to obtain a low-frequency component and a high-frequency component; weighted summation is carried out on the low-frequency components of different channels based on the fusion attention map, and selective fusion is carried out on the high-frequency components of different channels; and carrying out layer-by-layer reconstruction on a fusion result of the low-frequency component and the high-frequency component to generate a fusion image. According to the method, the detection precision and the visualization effect of multiple types of defects are improved while the calculation efficiency is maintained.

The invention discloses a mold quality detection method and system based on image processing, and relates to the technical field of mold quality detection.The method comprises the steps that a high-precision industrial camera is installed over a mold to obtain a mold surface gray level image, and graying and smoothing are conducted on the obtained image; constructing a distribution model according to the reference distance distribution condition of each pixel point in the smoothed image, calculating a period strength degree, preliminarily screening the pixel points according to the period strength degree, and distinguishing the possibility of texture pixel points and non-texture pixel points; by using the difference between normal texture periodicity and crack randomness, through calculating the periodicity intensity degree, screening texture pixel points and non-texture pixel points, screening suspected texture pixel points, calculating the periodicity similarity, screening out a texture region and then carrying out iterative threshold segmentation, the detection problem caused by mixing of cracks and normal textures is solved; and the detection accuracy is improved.

The invention relates to the technical field of image processing, in particular to a vehicle-mounted battery gluing defect detection method based on machine vision, and the method comprises the steps: obtaining an original image of a vehicle-mounted battery gluing region, generating color smoothness through a dual-channel variance fusing brightness and saturation, constructing structure tensor analysis to determine local gradient disorder degree, and determining the gluing defect of a vehicle-mounted battery. The method comprises the following steps of: generating abnormal confidence of pixel points by synthesizing color smoothness and local gradient disorder, remodeling gray difference among the pixel points by using the abnormal confidence as a physical modulation factor to obtain a physical remodeling weight of an edge, and realizing pseudo gradient shielding in a graph theory segmentation framework by using the physical remodeling weight to obtain a pseudo gradient shielding result. And accurate segmentation is carried out on the original image so as to realize gluing defect detection. According to the method, the complete connectivity of the glue overflow defect area is improved, the situation that the chaos texture in the defect is misjudged as the boundary is avoided, and the gluing defect detection result is more accurate.

The invention provides a facial skin flaw enhancement method based on a Lab color space. The method comprises the following steps: firstly, acquiring an RGB face image and converting the RGB face image into a CIE Lab color space with uniform perception; then, performing differentiation treatment according to the manually selected skin flaw type: for the vascular flaw, extracting statistical characteristics of a component and driving adaptive nonlinear transformation, and generating a grey-scale map which highlights the red flaw; for pigment flaws, nonlinear transformation is carried out on the component L, and then collaborative linear weighting and feature amplification are carried out on the component L, the component a and the component b, so that a grey-scale map with highlighted pigment spots is generated. And finally, coloring the grey-scale map in the Lab color space through adjustable parameters to generate a high-contrast color enhanced image. The method overcomes the dependence on hardware and training data in the prior art, can clearly and adaptively enhance various flaws such as acnes, couperose streaks and color spots, shows robustness under different illumination, and can be widely applied to clinical beauty, later photography and real-time video processing.

The invention provides a stone gradation automatic detection method based on image processing, belongs to the technical field of image processing, and designs a two-dimensional convolution kernel capable of enhancing features according to the features that small-particle stones are bright in center, dark in edge and approximate to a circle by acquiring a gray image and a background image of a stone field through a video stream. Convolution operation is carried out on the image to improve the contrast ratio of the stone and the background, then an accurate binarized image is obtained through double-threshold segmentation and background difference processing, in order to further separate the adhered particles, the particle center is positioned by adopting distance transformation, and effective segmentation is carried out by combining a watershed algorithm. And according to the extracted particle contour, geometric parameters are calculated and the mass is estimated, so that a stone grading curve for evaluating the filling quality is automatically generated. According to the invention, rapid and non-contact automatic analysis of rockfill material grading is realized.

The invention relates to the technical field of health assessment, in particular to a traditional Chinese medicine health assessment method and system based on intelligent analysis, and the method comprises the steps: carrying out the multispectral image collection of the face and tongue picture of a user, carrying out the color gradation quantification processing and texture feature extraction of the obtained image data, and obtaining a face color gamut feature matrix and a tongue picture texture feature vector; and based on the tongue picture-complexion associated features and a syndrome description text input by the user, performing intelligent classification pre-judgment on traditional Chinese medicine syndrome types to obtain an initial syndrome label set, and based on user physique data, correcting the initial syndrome label set to obtain a syndrome feature fusion vector. Through the health fluctuation index and the health trend early warning signal, the change of the health condition of the user can be dynamically evaluated, and a personalized health intervention scheme is generated on the basis, so that the fluctuation of the health condition can be reflected in real time, intervention measures can be taken in time, and potential health risks can be prevented.

The application discloses a kind of detection and defense method of counterpatch, respectively based on abnormal positioning and edge detection.The detection method of counterpatch based on abnormal positioning utilizes clean image to train the generator-adversary network of encoder-decoder structure;The output image is obtained by inputting the image to be detected into the generator-adversary network, and the absolute error is obtained by subtracting and taking absolute value;The image region whose absolute error is greater than error threshold is the region where counterpatch is located;The detection method of counterpatch based on edge detection converts the image to be detected into gray scale image and carries out edge detection, and obtains edge image;The edge lines in edge image are connected into a closed area one by one, and the closed area whose area is less than the area of counterpatch region is the region where counterpatch is located.The application can detect counterpatch based on the two schemes of abnormal positioning and edge detection respectively, and blacken the region or use image restoration algorithm to restore the region to defend counterpatch.

The invention relates to the technical field of contour extraction, in particular to a knitted label edge contour extraction and optimization method, which comprises the following steps of: extracting an image edge gray scale trend and acquiring a fracture coordinate, extracting an edge track to generate a connection path, reconstructing an interference region connection path, converting rough edge region path distribution and screening out an abnormal path. According to the method, the gray abrupt change and edge interruption features in the image are identified, the fracture area is accurately positioned, structural integrity identification is enhanced, space correlation and direction fitting are carried out on edge endpoints in the interference area, the boundary recovery capability and the closure degree are improved, abnormal path segments are screened out through polar distribution, and therefore the detection accuracy is improved. Control nodes are set based on the position relation between the boundary segments and the overall chain, a boundary joint trend coordination structure is fused, the contour consistency and robustness under the complex background are improved, and the coherence recognition capability and extraction precision are enhanced.

The invention discloses a multi-modal image registration method and system based on deformation adaptation and computer equipment, and the method comprises the steps: collecting a plurality of groups of multi-modal images, carrying out the gray standardization, and constructing a diversified registration data set; building a registration network model comprising a pyramid coding module, a deformation adaptive module, a cross-modal interaction module and a registration parameter estimation module; inputting an image pair into the modules in sequence, respectively extracting basic feature mapping, deformation feature mapping and interaction enhancement feature mapping, and finally outputting an estimation conversion parameter matrix; a training process is supervised through a preset loss function, optimal network parameters are selected, and a trained registration model is obtained; in practical application, an image pair to be registered is input into the trained model, a conversion parameter matrix is obtained, and image registration is completed. The multi-modal image registration performance can be effectively improved, and the method still has good robustness and adaptability especially under the condition that serious geometric distortion and significant modal difference exist.

The invention relates to the technical field of machine vision detection and intelligent image processing, and discloses an intelligent track defect identification method based on machine vision. The track center is automatically positioned through a pixel coordinate system with the upper left corner as the original point in combination with row gray scale accumulation and maximum projection, the region of interest is dynamically intercepted, and background noise and calculation amount are effectively reduced. For the area, multi-angle equal-interval projection is adopted, pixels are mapped into a one-dimensional sequence, and the response to various strips and slender defects is improved. Each projection sequence is subjected to secondary trend fitting, a comprehensive residual image is constructed through the maximum residual, and defect signals are enhanced. According to the scheme, a threshold value is determined in a self-adaptive mode through statistics, four-neighborhood connected domain extraction and a dynamic area threshold value are combined, and a noise small domain is removed. Boundary, main direction, length and severity features are extracted from the remaining connected domains and mapped back to an original image, and efficient, accurate and automatic track defect intelligent recognition is achieved.

The invention discloses an optical compensation method for a display panel, which comprises the following steps of: shooting a gray scale test chart of the display panel at different exposure time, acquiring corresponding gray scale data, and establishing a quadratic polynomial fitting model of the exposure time and a gray scale value; and then, in combination with a Gamma correction principle, the Gamma value of the display panel is reversely deduced based on the fitting model, so that accurate mapping between the gray scale and the actual brightness is realized, the nonlinear influence of the display system is eliminated, the accuracy and reliability of a compensation algorithm are ensured, and the overall brightness reduction effect is further improved. And finally, combining the correction result, dividing the display panel into a plurality of grid areas, counting an average gray value of each grid, calculating a local compensation amount, generating a compensation lookup table (LUT), and applying the compensation lookup table to a real-time display compensation process. The display uniformity, the brightness consistency and the terminal visual effect of the panel can be improved, and good adaptability and practicability are achieved.

The invention belongs to the technical field of computer vision, and particularly relates to a blind hole plate hole depth measuring method and system based on distributed cameras 2D and 3D, and the method comprises the steps: projecting laser stripes through a laser, and synchronously collecting a laser stripe image and a blind hole plate 2D gray scale image through the distributed cameras; according to pixel gray scale distribution in a preset window on the laser stripes, adaptively selecting a Gaussian fitting method or a gray scale centroid method to carry out sub-pixel-level center extraction, and generating 3D height data of the blind hole plate; based on the 3D height data and the positioning holes, blind hole center positioning is carried out through affine transformation and image matching; and combining the 3D height data and the 2D grayscale image, judging the measurability of the blind hole according to 2D grayscale features, selectively starting hole depth calculation based on the 3D height data, and comprehensively evaluating the quality of the blind hole. According to the invention, the problems of specular reflection and deep hole measurement are effectively solved, and the precision and efficiency of blind hole depth measurement are remarkably improved.

The invention relates to the technical field of defect detection, and particularly discloses a high-precision defect detection system based on image difference and threshold processing, which comprises a registration image acquisition module, a fixed mask conversion module, an image difference detection module, a correction difference graph generation module and a defect set output module, the method comprises the following steps: firstly, completing affine registration by shape features, changing a fixed mask into a dynamic mask, and performing edge robustness in the mask to obtain a preprocessed image; local movement difference is carried out on the preprocessed image and the multiple reference images, fusion of a reference domain and a time domain is carried out to generate a difference response image, and candidate areas are extracted in combination with a dynamic mask; estimating and correcting a displacement field in the candidate range, synchronously mapping to obtain a correction difference graph and a correction mask graph, and determining a peripheral rejection area; according to the method, false alarm and missing detection are effectively reduced, and the method is suitable for online high-precision detection.

The invention discloses a vision enhancement robust digital dark watermarking method based on deep learning, a storage medium and equipment, and belongs to the technical field of digital image processing and information security. According to the method, a visual enhancement module comprising a self-adaptive watermark region adjustment module and a frequency enhancement module is constructed, and a multi-region local loss training mechanism and a screen shooting simulation module are combined, so that the visual quality of a watermark image is improved, and meanwhile, the robustness of the watermark image for resisting physical attacks such as screen shooting is enhanced. The specific processing flow comprises the following steps: acquiring an original image and watermark information; embedding the watermark information into the image by using an encoder, wherein an embedded region is optimized by a self-adaptive region guide matrix generated based on the image edge and gray information; in the model training process, a noise layer simulating screen shooting physical distortion is introduced, and the area weight is dynamically adjusted according to residual error distribution in the later stage of training so as to focus and optimize the image quality; watermark information is extracted from an image which may suffer from an attack by using a decoder.

The invention discloses an infrared small target detection method based on comparative learning and frequency gradient feature fusion, and aims to improve the detection precision. A current method faces three challenges that the contrast of an infrared image is low, space information is limited and is interfered by clutters, so that global context is missing, and robustness is insufficient; target structure features are weak and are similar to background gray, and texture extraction is difficult; an image background is complex, a target is tiny, missing detection and false alarm are caused frequently, and the distinguishing capacity of a foreground and the background is affected. For the first problem, a frequency attention perception fusion module is designed to improve semantic consistency and positioning precision. In order to solve the second problem, a textural feature enhancement module is designed to enhance textural feature representation. In order to solve the third problem, a temperature sensing comparison learning module is designed to improve the foreground and background distinction degree. In combination with the three designs, the model designed by the invention can accurately detect the small target in the infrared image, and is worthy of vigorous popularization.