383 results about "Image contrast" patented technology

The invention discloses a single image super-resolution reconstruction method and system based on wavelet transform and cross-domain feature fusion. According to the method, firstly, a low-resolution RGB image is mapped to a high-dimensional feature space through a shallow feature extraction module; performing up-sampling and discrete wavelet decomposition on the features by using a wavelet feature mixing module to obtain multi-band features; low-frequency and high-frequency depth features are respectively extracted through a double-branch structure, cross-domain fusion is realized by means of a deformable cross attention mechanism, and the feature expression ability is enhanced in combination with residual connection; and finally, reconstructing a high-resolution image through convolution, up-sampling and regularization processing. In the training process, a pixel-level loss function is adopted to optimize network parameters, the multi-frequency-domain feature sensitivity is effectively improved, texture and structure information is balanced, the image contrast, definition and structural integrity are improved, and high-quality real-time super-resolution reconstruction can be achieved.

The invention discloses a cross-modal retrieval model optimization method and system based on illusion enhancement. The method comprises the steps that a similar illusion text generation module generates a similar illusion text based on an original training data set, a language model and a prompt template; the data set construction module combines the illusion-like text and the original image-text pair into an enhanced training data set; the fine tuning optimization module encodes image, original text and illusion-like text features through an image or text encoder, calculates text-to-image contrast loss and image-to-text illusion enhancement contrast loss, and optimizes model parameters of the encoding adapter and the text encoder in combination with an improved contrast loss function. According to the method, the problems of low precision and poor efficiency caused by illusion interference of a multi-modal model in intelligent driving scene retrieval are solved, and the accuracy of cross-modal retrieval is remarkably improved by utilizing illusion to generate data enhancement and dynamic loss constraint.

The invention provides an infrared image frequency division enhancement method based on a diffusion model, and the method comprises the steps: firstly carrying out the multi-scale frequency domain decomposition of an infrared image through discrete wavelet transform, and dividing the image into a low-frequency component and a high-frequency component; in the low-frequency component processing process, a diffusion equation is constructed in combination with a thermal radiation physical model, and discretization solution is performed by using a finite difference method. The high-frequency component is converted from a space domain to a frequency domain through Fourier transform, energy distribution of the high-frequency component is analyzed, and a diffusion probability function is adjusted. In the fusion stage, according to the signal-to-noise ratio of the local area of the image, the fusion weight of the low-frequency component and the high-frequency component is dynamically adjusted, the processing results of all the local areas are integrated in a weighted fusion mode, and finally the high-quality enhanced infrared image is generated. The method has excellent performance in improving image contrast, definition and detail performance, is suitable for the fields of security monitoring, military reconnaissance, industrial detection and the like, and can effectively improve monitoring, analysis and detection effects.

The invention discloses a sapphire substrate automatic defect detection and classification method based on visual inspection, and relates to the technical field of visual inspection and image processing, and the method comprises the steps: carrying out the adaptive threshold segmentation and phase consistency detection of a multi-modal image data set, and carrying out the fusion, and obtaining a joint defect probability graph; extracting defect candidate areas from the joint defect probability graph, and generating unified feature representation; inputting the unified feature representation into a double-branch neural network, performing fusion and classification through a cross attention mechanism, outputting a defect classification result, performing reconstruction by using a NeRF algorithm, outputting a defect three-dimensional shape, and generating a three-dimensional shape map; and generating a defect thermodynamic diagram based on the three-dimensional morphology map, performing space-time correlation analysis in combination with equipment process parameters, and outputting a sapphire substrate defect process analysis report. According to the method, the image contrast and the defect characterization capability are improved, so that the comprehensiveness and the sensitivity of detection are remarkably enhanced.

The invention discloses a method for measuring the particle size of metal powder by using a scanning electron microscope, which comprises the following steps: step 1, sample treatment: adhering a small conductive adhesive tape on a sample table, sprinkling metal powder on the adhered conductive adhesive tape, and purging to obtain the conductive adhesive tape adhered with the metal powder; step 2, parameter setting: setting acceleration voltage, working distance, diaphragm, image contrast, brightness, magnification times and scanning speed of a scanning electron microscope to observe the conductive adhesive tape adhered with the metal powder obtained in the step 1 to obtain an electronic image of metal powder particles; and processing and calculating the electronic image of the metal powder particles by using software to obtain the average particle size of the metal powder particles. According to the method disclosed by the invention, a solvent is not needed to disperse the sample, pollution of the solvent to the sample is effectively avoided, and the result is more accurate than that of directly measuring the particle size by using length software.

The invention discloses an image edge feature enhancement correction fusion method based on a guide filter, and aims to solve the problems that detail features of a low-illumination visible light image and an infrared image are not obvious, focusing edge information is not clear, and registration of a multi-focus image is wrong. The invention provides an edge feature enhancement correction fusion method based on a guide filter. In the illumination enhancement stage, a visible light image is divided into a base layer and a detail layer through a guide filter, and the image contrast and detail information are enhanced. For an infrared image, an infrared background is reconstructed by using a quadtree decomposition and Bezier interpolation method, unclear focusing edge feature information is extracted, and the visibility of image details is enhanced. And finally, reconstructing the two processed images by using a multi-scale weighted gradient method, and performing fusion by calculating large-scale and small-scale weight scales.

The invention provides a multi-scale pyramid weighted fusion underwater image enhancement method based on double prior, and the method comprises the steps: obtaining a degraded underwater image, and carrying out the global and local cooperation body color calibration of the degraded underwater image; decomposing the color correction image into a base layer, a detail layer and a noise layer by adopting a variational decomposition algorithm; performing spectral prior and transmissivity loss constraint on the base layer image to obtain a defogged image; fusing the detail layer image and the noise layer image to obtain a filtered image; performing enhancement processing on the filtered image by adopting a nonlinear mapping and contrast enhancement strategy to obtain an enhanced image; performing multi-level feature integration and reconstruction on the defogged image and the enhanced image by adopting a multi-scale pyramid adaptive weighted fusion method to obtain an underwater image with natural color and high visual definition; according to the method, the traditional image processing and variational optimization thought is combined to effectively correct the color deviation of the degraded underwater image, the image contrast and the detail definition are improved, and the visualization effect of the underwater image is improved.

The invention discloses an overexposure and underexposure image enhancement method, device, equipment and medium, and the method comprises the steps: enabling an image decomposition network to respectively receive a first illumination image and a second illumination image through employing two encoder-decoder networks sharing the weight, and extracting multi-scale illumination distribution information through multi-scale connection; the image reconstruction module outputs a corresponding reflectivity component and a brightness component, the image enhancement network adopts an image enhancement sub-network to adjust illumination distribution and suppress noise based on the reflectivity component and the brightness component, and the image reconstruction module multiplies the adjusted reflectivity component with an illumination image element by element and outputs an enhanced image. According to the method, the technical effects of effectively recovering image details, reducing noise interference and improving real-time performance under the overexposure or underexposure condition are reflected, the method is particularly suitable for complex environments such as power equipment monitoring, the contrast ratio of the enhanced image is better, artifacts are fewer, the calculation burden is reduced, and efficient batch processing prediction is supported.

The invention provides an embedded image enhancement method and system for a large-target-surface image sensor. According to the method, temperature gradient distribution and environment humidity data of a large-target-surface image sensor are collected, and an environment parameter matrix and a temperature noise mapping model are constructed in an associated mode; and correcting optical distortion of the incident light signal by using the liquid crystal modulator array, and outputting an original image. Then through a double-path module, a main path extracts noise features, and an auxiliary path separates color shift features caused by humidity; and verifying the physical consistency of the characteristics based on a thermodynamic equation and screening effective data. And finally, dynamically optimizing the image contrast, the dynamic range and the target details by the embedded processor, and outputting an enhanced image. Through environmental parameter modeling, dual-path feature separation and physical verification, temperature and humidity interference is effectively suppressed, and detail enhancement and color fidelity of the large-target-surface image sensor are improved.

The invention discloses a road target detection method and device based on bimodal feature fusion and weak light enhancement, and relates to the field of target detection. And the weak light enhancement target detection model performs enhancement and target detection on the road image under the weak light condition. And the bimodal target detection model performs target detection on the road image under the normal light condition. The weak light enhancement target detection model carries out feature extraction through a multi-scale feature attention module, and carries out image feature brightness enhancement through a brightness enhancement module. The image quality is improved, the image contrast is kept, and the target detection accuracy of the weak light image is greatly improved. The bimodal target detection model adopts a double-branch training strategy, the rich capture capability of visible light on target color and texture features under a normal illumination condition is fully exerted, the advantage of a target contour is highlighted in combination with the penetration characteristic of infrared light, and the target recognition capability under the conditions of complex background, shielding and long-distance blurring is remarkably improved.

The invention provides a long-depth-of-field integrated imaging display, a long-depth-of-field integrated imaging method and a long-depth-of-field integrated imaging system. The long-depth-of-field integrated imaging display comprises an image processor, a display, a microlens array and a quartic phase mask, the pupil position of each micro lens of the micro lens array is correspondingly integrated with a quartic phase mask; the image processor is used for acquiring a to-be-displayed image and constructing an element image array; performing inverse convolution processing on each element image in the element image array based on a preset phase mask function, and constructing a preprocessed element image array matrix; performing negative value processing on the preprocessed element image array matrix to obtain a preprocessed element image array; and the display is used for displaying the preprocessed element image array, so that the preprocessed element image array generates a long depth-of-field image through the micro-lens array and the quartic phase mask. According to the invention, defocus blurring is effectively suppressed without introducing an extra complex optical structure, a long depth-of-field image is generated on the premise of ensuring the image contrast, and the integrated imaging display quality is improved.

The invention relates to an automatic blood vessel segmentation method and system for a CT image. The method comprises the following steps: acquiring an enhanced CT image and a plain-scan CT image at the same position; inputting the enhanced CT image to a pre-trained first blood vessel automatic segmentation model to obtain a first blood vessel segmentation result; and registering the enhanced CT image and the plain-scan CT image to mark and map the first blood vessel segmentation result to the plain-scan CT image so as to obtain a second blood vessel segmentation result. The method has the advantages that a deep learning model (such as a registration network based on U-Net or Transform) is utilized to calculate a deformation field, and in combination with multi-scale feature enhancement and regularization strategies, the precision and stability of enhanced CT and plain-scan CT image registration are improved, and artifacts and local distortion in the deformation field are reduced; in order to solve the problem that the contrast difference of a plain scanning CT image and an enhanced CT image is significant, a compensation strategy of multi-modal texture and intensity distribution is introduced, such as adversarial loss and structural similarity index (SSIM) optimization, so that registration is more robust among different modals.

The invention discloses an AI algorithm-based apparent defect detection method, system and device, and relates to the technical field of apparent defect detection. The appearance defect detection method based on the AI algorithm comprises the following steps: detecting defects of a high-reflection area; shadow area defect detection; and detecting defects of the sunken area. According to the method, the appearance defect area of the metal product to be detected is obtained through the AI visual sensor, the identification accuracy of the defect area in the high-reflection area is quantified, image contrast optimization judgment is carried out, then the area identification accuracy in the shadow area is quantified, and angle light source optimization judgment is carried out; and finally, the identification accuracy of the defect area in the concave area is quantified, and camera parameter optimization judgment is carried out, so that the identification accuracy of the specified appearance defect feature in the concave area corresponding to the high-transmittance and high-reflection metal is realized. The problem that in the prior art, high-transmittance and high-reflection metal is low in appearance defect feature recognition accuracy in a corresponding concave area in the appearance defect detection process is solved.

The invention relates to the technical field of artificial intelligence and electronic manufacturing detection, and discloses an ultra-thin printed circuit board defect detection method and system based on AI vision. The objective of the invention is to solve the technical problems of poor imaging quality, high missed detection and false detection rate, weak generalization ability and difficulty in consideration of efficiency and precision caused by buckling deformation, surface reflection and tiny and diverse defects of an ultrathin printed circuit board in the existing detection technology. The method comprises the following steps: performing multi-angle image acquisition through a composite illumination module and a high-resolution linear array camera; geometric correction is carried out on the image by using an SIFT algorithm and affine transformation, and the image contrast is enhanced by using a CLAHE algorithm; generating a defect candidate region through the lightweight full convolutional network; and carrying out accurate classification and identification on the candidate region by using a deep residual network. According to the technical scheme, high-precision, high-efficiency and low-false-alarm detection of the tiny defects of the ultrathin printed circuit board can be achieved, and the automation level and adaptability of detection are remarkably improved.

The invention relates to the technical field of defect detection, in particular to a defect detection method and system based on a microwave frequency crystal resonator, and the method comprises the steps: forming a microwave probe through a microwave frequency crystal resonator array, placing a to-be-detected material below the microwave probe, and setting a scanning area and scanning step lengths in two directions on the surface of the material; controlling the probe to perform point-by-point scanning according to step length, and collecting a plurality of reflection coefficients of each sampling point to form an echo signal matrix; performing singular value decomposition on the matrix, applying an adjustable coefficient to a first singular value and a second singular value, and adaptively selecting an optimal coefficient according to imaging quality to reconstruct an echo signal; performing two-dimensional Fourier transform on the reconstructed matrix, constructing a spatial filter in combination with probe spacing and defect depth to perform phase compensation, performing two-dimensional Fourier transform to obtain a defect image, and performing threshold segmentation on the defect image to obtain a binary image only containing defects; and analyzing the connected regions to obtain the gravity center position of each defect and the defect area determined by the pixel number and the single pixel area. The problems of serious clutter interference, insufficient defect imaging contrast ratio, difficulty in quantitative evaluation of defect size and the like in the existing microwave detection can be solved.

The application discloses a method for rapidly and nondestructively detecting the quality of silicon carbide crystals, which comprises the following steps: placing the silicon carbide crystals on a computer tomography (CT) carrier table, and rapidly and nondestructively detecting the typical defects in the silicon carbide crystals by means of computer tomography under specific parameters, image contrast and the identification of the topographic features, so as to directly obtain the defect topography, density distribution and the evolution of the defects with the growth process of the measured ingot at different sections, and significantly improve the visualization degree of the defects in the silicon carbide crystals.

The invention relates to the technical field of optical imaging and three-dimensional measurement, in particular to a multispectral structured light path system which comprises a light source module used for generating multi-wavelength light; the collimation system module is composed of any one of one or more lenses, and an aperture diaphragm is arranged on the first face. When the system is used, a multispectral light source design is adopted, the system can meet the three-dimensional measurement requirements of various complex material surfaces, the system adaptability is conveniently and remarkably improved, the image contrast is enhanced through multi-wavelength structured light projection, and the measurement precision is improved. The method effectively reduces the mismatching rate, improves the precision and reliability of three-dimensional reconstruction, achieves the simultaneous obtaining of multispectral information and structured light three-dimensional shape information, expands the application capability of the system in the high-end fields of material recognition, surface defect detection and the like, employs an integrated optical path design, is compact in structure, is high in reliability, and is suitable for large-scale popularization and application. And miniaturization and engineering application of the system are facilitated, and the portability and practicability of the equipment are improved.

The invention relates to the technical field of bar code identification, and discloses a rapid image matching incomplete bar code accurate identification method, which comprises the following steps: carrying out image contrast enhancement processing based on bar code candidate area response on an incomplete bar code image; positioning a bar code area of the incomplete bar code image after contrast enhancement, and detecting and marking an incomplete area in the bar code area; carrying out inference and reconstruction processing on the incomplete area based on a bar code standard coding rule and a statistical redundancy mode; and carrying out identification decoding and redundancy check on the reconstructed bar code image. According to the method, through a multi-step processing mode of image contrast enhancement, incomplete area positioning and labeling, reconstruction based on coding rules and redundancy modes and identification verification, rapid and accurate identification of the incomplete bar code is realized, and under the condition that partial information of the bar code is missing, fuzzy and interfered, the bar code structure can still be effectively recovered, and the identification accuracy of the bar code is improved. And the accuracy, the stability and the robustness of bar code identification are obviously improved.

Disclosed in the present invention are an infrared non-uniformity noise correction method and system. The method comprises the following steps: determining whether an infrared imaging device has moved, if yes, acquiring non-uniformity correction values and non-uniformity correction value change amounts of pixel points on the basis of a gradient matrix and a truth value matrix, and performing corresponding updating processing on the pixel points; completing iterative calculation of a bias matrix of the current image frame on the basis of the updated pixel points; and performing non-uniformity correction on the current image frame on the basis of the bias matrix. The present invention first extracts a clear non-uniform noise pattern by means of the bias matrix, and then corrects the non-uniform noise by means of the bias matrix, so that the non-uniform noise in the infrared image can be significantly reduced, and the details of a target object are not lost, and thus, the image contrast and quality are greatly improved.

The invention relates to a distribution line unmanned aerial vehicle inspection image fusion method and system and a medium, and the method comprises the steps: carrying out the aerial inspection of a distribution line through a high-resolution visible light camera and an infrared thermal imaging camera carried by an unmanned aerial vehicle, and obtaining the image data of a key part; performing denoising processing on the acquired multi-modal image to reduce interference caused by environmental factors and sensor noise, and then enhancing the image contrast and improving the definition of image details through a histogram equalization method to obtain denoised and enhanced intermediate preprocessing data; according to the method, a power distribution line unmanned aerial vehicle image fusion model composed of an encoder and a decoder is constructed, image fusion is performed on source images of different modalities after denoising and enhancement, so that data advantages of different modalities are fully utilized, richer result images are generated, more comprehensive line state information can be provided, and the reliability of the power distribution line unmanned aerial vehicle image fusion is improved. More accurate state evaluation and fault diagnosis are realized, the inspection efficiency and accuracy are improved, the cost is reduced, and the safety is improved.

The invention discloses an intelligent enhancement method for a road image under a low-illumination condition, and belongs to the technical field of computer vision and video processing, and the method comprises the following steps: S1, calculating an actual illumination value of a current road scene; s2, adaptively adjusting the exposure time; s3, targeted noise reduction; s4, color temperature correction; s5, enhancing the image contrast; s6, performing strong light suppression to obtain a final current road scene image; under extremely low illumination, the image signal-to-noise ratio is increased by more than 40%, the color rendition degree is larger than or equal to 90%, clear full-color images can be output without external light supplementation, meanwhile, the strong light inhibition rate of vehicle headlights and the like is larger than or equal to 95%, the overexposure area is reduced to be lower than 5% of the original area, the algorithm processing delay is smaller than or equal to 40 ms, the real-time monitoring requirement is met, and the method is suitable for highway night scenes.

The invention provides a target object camera array imaging method based on multi-view-field deconvolution turbulence resistance, and relates to the technical field of image deblurring or deconvolution image processing based on a physical model, and the method comprises the steps: S1, building a physical model in which atmospheric turbulence affects the imaging quality of a target object, building a camera array imaging system, and carrying out the imaging of the target object; obtaining a target object image in a turbulence environment; s2, establishing a multi-view-field affine transformation registration model, and performing image registration through affine transformation to obtain a plurality of same-view-field image sequences of the target object; s3, performing deconvolution by using a convolution kernel of a point spread function of a preset optical system, enhancing the contrast of the target object image, and estimating the target object image; and S4, performing Fourier ring correlation operation based on the contrast-enhanced target object image, and performing adaptive iteration deconvolution again to obtain a recovered anti-turbulence target object image. According to the method, pre-deconvolution is performed on the original image, background noise is suppressed, and adaptive iteration deconvolution is performed after the image autocorrelation cumulant is calculated, so that anti-turbulence imaging is realized.

The invention belongs to the technical field of image contrast, particularly relates to a water conservancy safety monitoring system based on dynamic vision, and aims to solve the problems that in an existing water conservancy safety monitoring process, the image quality and the recognition accuracy are remarkably reduced under complex and dynamically changing illumination and environment conditions, and the image quality is poor. In order to solve the problems of unstable monitoring performance and insufficient reliability caused by the lack of adaptive optimization and multi-source information deep fusion capability, the invention provides the following scheme: the system comprises a data acquisition module, the data acquisition module is connected with an illumination evaluation module, the illumination evaluation module is connected with a scene classification module, and the scene classification module is connected with a data processing module. According to the invention, through a dynamic vision technology, adaptive image enhancement and multi-source data fusion of a water conservancy project under complex illumination and environment conditions are realized, the image quality and defect identification accuracy of all-weather monitoring are significantly improved, and the environmental adaptability and reliability of the system are enhanced.

The invention discloses a method and device for evaluating the printing quality of a two-dimensional code, a terminal and a medium. The method comprises the steps that a to-be-evaluated image corresponding to a to-be-evaluated two-dimensional code is acquired; based on a preset image defect type, evaluating the to-be-evaluated image to obtain a defect evaluation result corresponding to the preset image defect type, the preset image defect type including an image contrast defect, a reflectivity defect, a modulation defect and an edge contrast defect; and obtaining a target quality evaluation result corresponding to the to-be-evaluated two-dimensional code based on the preset image defect type and the defect evaluation result corresponding to the preset image defect type. The invention aims to improve the efficiency and accuracy of detecting the printing quality of the two-dimensional code.

The invention relates to the technical field of medical image recognition, in particular to a meibomian gland duct state analysis system based on image recognition, which comprises a meibomian gland duct enhancement module, a duct opening positioning module, a texture and structure fusion module, a multi-scale segmentation module and a boundary optimization module. According to the method, by screening background interference pixels and enhancing the image contrast of the catheter area, the identifiability of the catheter structure can be remarkably improved, the positioning accuracy of the catheter opening point is improved, feature fusion is achieved by extracting the area gray difference and combining the texture contrast distribution, and the overall presentation definition of the catheter lesion area is enhanced; by setting multi-scale segmentation parameters and extracting region feature point information, the boundary reduction degree and segmentation integrity of a catheter region are improved, edge adjustment is performed by calling boundary pixel gradient data, the expression effect of key information in a catheter image is enhanced in the whole process, the image support degree of pathological judgment is improved, and the accuracy of pathological judgment is improved. And the judgment difficulty caused by non-uniform image quality is relieved.

The invention discloses an image fusion method based on a double-branch feature decoupling auto-encoder, and belongs to the field of computer vision and image processing. According to the method, for the problems of modal pollution and structural distortion in infrared and visible light image fusion, structural semantic information and high-frequency texture details of a source image are extracted respectively by constructing a content feature coding module and a detail feature coding module, and feature decoupling is achieved. And performing deep fusion on the decoupled features by using an adaptive feature weighting mechanism, and reconstructing a fused image with infrared target saliency and visible light detail definition through a shared decoder. According to the method, an end-to-end two-stage training strategy is adopted for optimization, complex prior or post-processing is not needed, the effects of improving the fused image contrast, edge preservation and target recognition performance are remarkable, and the method is suitable for the fields of weak light monitoring, intelligent perception, unmanned system navigation and the like.

The invention relates to the technical field of computer vision, and discloses a computer vision-assisted dental restoration adaptation system, which comprises an image acquisition module, an image processing module, an adaptation evaluation module, a central control module and a feedback optimization unit, high-resolution image data, including visible light images, three-dimensional scanning data and infrared images, of the interior of the oral cavity and a restoration body are obtained through multi-source imaging equipment of the image acquisition module, the form, texture and temperature distribution characteristics of the oral cavity environment are captured, and the image contrast and the alignment precision are enhanced in combination with the illumination control unit and the positioning calibration unit. Data integrity and detail visibility are ensured, and a reliable basis is provided for subsequent image processing; the image processing module performs preprocessing, feature extraction and segmentation on the acquired image data, so that the accuracy and efficiency of adaptive state analysis are improved.

Systems and methods for removing the bias induced by noise from power Doppler images to achieve improvements of microvessel image contrast are provided. In one example, the noise-induced bias can be suppressed by utilizing the characteristics of uncorrelated noise in the ultrasound image from data acquired or compounded at different transmitting angles. In another example, the noise-induced bias can be suppressed due to the lack of correlation between adjacent ultrasound images. These example implementations may also be combined, as will be described below.

The invention discloses an underwater image enhancement method and system based on three-input multi-scale fusion. The method comprises the following steps: carrying out visibility recovery on an image to be processed; performing contrast enhancement through a nonlinear mapping function; carrying out enhancement processing on the contour of the high response area; respectively calculating a Laplacian contrast weight map, a saliency weight map and a saturation weight map of the three processed images; linearly combining all types of weight maps to obtain an aggregation weight map, and normalizing the aggregation weight to obtain a normalized weight map; decomposing the three processed images into a Laplacian pyramid, decomposing the normalized weight map into a Gaussian pyramid, and performing fusion through upward sampling and addition reconstruction; carrying out smoothing processing and edge-preserving sharpening processing on the fused image to obtain an image after underwater image enhancement and restoration; according to the method, the color cast problem of the underwater image is solved, the image contrast is effectively improved, and the texture details of the image are improved.