Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

23results about How to "Reduce aliasing" patented technology

Visual Mangban high-order morphological image segmentation method and system based on state space

The invention discloses a visual Mangban high-order morphological image segmentation method and system based on a state space, and relates to the technical field of medical image segmentation. According to the method, the advanced high-order morphological technology and the state space model are fused, so that precise segmentation of the tiny lesion area in the medical image is realized. According to the method, an HMM-VSS module and a U-shaped network feature extraction encoder are utilized, a multi-scale attention mechanism and morphological operation are combined, local and global features in an image are effectively captured and enhanced, and noise interference is reduced at the same time. Besides, through an optimized Transform framework and an introduced SCA Bridge module, the method provided by the invention has the advantages that the calculation efficiency is maintained, and the feature fusion and information extraction capabilities are remarkably improved. Experimental results show that the method is remarkably improved in the aspects of image segmentation accuracy, robustness and processing speed, and an efficient and reliable technical solution is provided for the field of medical image analysis.
Owner:SHENZHEN LONGHUA DISTRICT PEOPLES HOSPITAL

Wrapped yarn surface defect detection method and system

InactiveCN119151904AHighly modulated responsereduce aliasingImage enhancementImage analysisYarnEngineering
The invention relates to the technical field of footwear products, in particular to a wrap yarn surface defect detection method and system. Firstly, a composite grating image is collected and projected to the surface of wrap yarn to obtain a light intensity function; and obtaining a wrapped phase based on the light intensity function. Secondly, performing preliminary unwrapping by adopting an optimized MSE algorithm to obtain phase data; performing phase recovery by using Fourier transform processing; performing phase adjustment according to the phase difference to obtain an unwrapped phase; phase distribution corresponding to the unwrapped phase is obtained, error calculation is carried out on the phase distribution and expected phase distribution, a phase value is adjusted, and phase unwrapped data are obtained. Then, calculating an absolute phase by using a nonlinear model; and calculating the gradient of the data in the absolute phase, calculating the amplitude of the gradient according to the size and direction of the gradient, and determining the position of the defect by applying threshold processing. And finally, performing morphological post-processing on the defect image, extracting defects, and realizing detection of the surface defects of the wrap yarn. According to the invention, the accuracy and efficiency of wrap yarn surface defect detection can be improved.
Owner:ZHUJI ZHONGXIN CHEMICAL FIBER CO LTD

Anti-aliasing optimization method for image rendering and related equipment thereof

The invention discloses an anti-aliasing optimization method for image rendering and related equipment thereof, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, aiming at a preset Gaussian texture map, generating a multi-level Gaussian texture map by adopting a resolution degradation sampling technology of a multi-level gradually-distant texture principle so as to adapt to rendering requirements of different precisions; and then, for the Gaussian texture map of each resolution level, independently training a corresponding 3D rendering model to ensure that the model can accurately match and optimize the image details of the resolution level. When an actual image is processed, the most suitable 3D rendering model is automatically matched according to the resolution of the to-be-processed image. And finally, performing image rendering on the image by using the matching model, and generating a sawtooth-free 3D image. The invention further relates to the technical field of block chains, and the Gaussian texture map can be stored on block chain nodes. According to the method, the rendering efficiency and quality are effectively improved, and particularly, the anti-aliasing effect for edge and texture details is remarkable.
Owner:PING AN TECH (SHENZHEN) CO LTD

Method and device for eliminating moire through combined linear transformation and storage medium

The invention discloses a method and device for eliminating moire through combined linear transformation and a storage medium. The method and device are used for improving the moire elimination effect on the basis that image feature information is reserved in the defect detection process. The method comprises the steps that a first image is acquired, and an effective area is searched in the first image; angular point coordinates of the effective area are calculated; carrying out geometric correction on the angular point coordinates to generate corrected angular point coordinates; generating a conversion matrix according to the angular point coordinates and the corrected angular point coordinates; converting the first image into a corrected image by using the conversion matrix; calculating a pixel gray value of the corrected image by adopting a bilinear interpolation method and combining the gray of the effective area of the first image, and inserting the pixel gray value into the corrected image; calculating a scaling factor according to the real magnification and the specified magnification, and generating a scaling vector according to the scaling factor; according to the zoom vector, performing affine transformation and compression on the corrected image to generate a second image; and processing the gray value of the pixel point of the second image by adopting a bilinear interpolation method.
Owner:SHENZHEN SEICHITECH TECHN CO LTD

Method and system for detecting fungaltoxin in feed

The invention relates to a method and a system for detecting fungaltoxin in feed. The method comprises the following steps: acquiring a data sequence which is measured by a detector of HPLC (High Performance Liquid Chromatography) equipment and contains the content of fungaltoxin in the feed; the method comprises the following steps: acquiring an appearance time range when each mycotoxin is subjected to HPLC (High Performance Liquid Chromatography), determining an average value of data sequence fragments not in the time range, determining the number of EMD decomposition according to permutation entropy, determining a variance of white noise added during each EMD decomposition based on the average value, adding the white noise to the data sequence, and then performing EMD decomposition to obtain a corresponding EMD decomposition value; removing abnormal values of all first modal components obtained by EMD decomposition to obtain a first modal component mean value; obtaining noise according to the first modal component mean value, subtracting the noise from the data sequence to obtain a denoised data sequence, calculating the permutation entropy of a denoised data sequence fragment, and if the reduction of the permutation entropy is smaller than a preset value, repeating the above process on the denoised data sequence to obtain a denoised data sequence; otherwise, the content of the fungaltoxin is obtained based on the denoised data sequence.
Owner:XUZHOU LONGZHICHUANG BIOTECHNOLOGY CO LTD

Image processing method and system

ActiveCN119299873Areduce aliasingTransition continuousImaging processingImaging quality
The invention provides an image processing method and system. The method comprises the following steps: determining a first zoom coefficient in the horizontal direction and a second zoom coefficient in the vertical direction; obtaining a first pixel range corresponding to each pixel point in the second image in the first image based on the first zoom coefficient and the second zoom coefficient; a compensation coefficient is determined based on the reduction multiple between the first image and the second image, the first pixel range is expanded through the compensation coefficient, a second pixel range is obtained in the first image, and the compensation coefficient is increased along with increasing of the reduction multiple; and calculating a pixel mean value and a pixel weight of each pixel in the second pixel range in the first image based on the second pixel range, and determining a pixel value of each pixel in the second image based on the pixel mean value and the pixel weight of each pixel in the second pixel range so as to suppress sawteeth generated when the first image is reduced to the second image. The method can be used for inhibiting sawteeth generated during image reduction so as to improve the image quality.
Owner:SHANGHAI WEIJING SEMICONDUCTOR CO LTD

Magnesium-aluminum alloy double-color spraying method and sprayed component thereof

PendingCN118904693Arich appearancereduce aliasingCoatingsSpecial surfacesMixing effectHuman eye
The invention discloses a magnesium-aluminum alloy double-color spraying method and a sprayed part thereof. The method comprises the following steps: spraying a layer of primer on the surface of an alloy part; spraying a layer of first colored paint on the surface of the primer; spraying a layer of second colored paint on the surface of the first colored paint; carving off part of the second color paint on the first color paint; and spraying a layer of transparent and colorless finish paint on the carved second colored paint. According to the method, the first colored paint is sprayed on the surface of the alloy part, and then the second colored paint is sprayed on the surface of the first colored paint, so that a color superposition effect or a mixing effect can be formed, more diversified appearances can be created, the second layer of paint is removed from the surface of the first layer of paint through carving, and the part of the first layer of paint is revealed; due to the fact that the complexity of multiple times of coating and shielding is avoided, the first colored paint and the second colored paint exist on the surface of the product at the same time can be visually seen by human eyes, the connecting position is neat, and the effect meets the standard of automobile exterior parts.
Owner:ANHUI SHENGLI PRECISION MFG TECH CO LTD

Pixel control circuit and method and display panel

The invention belongs to the technical field of display panels, and provides a pixel control circuit and method and a display panel, the display panel comprises a plurality of pixel units, each pixel unit comprises a first sub-pixel unit and a second sub-pixel unit, and the pixel control circuit comprises a first control module, a second control module and a third control module. The third control module is used for connecting the corresponding second sub-pixel unit into the circuit in a specified state, so that the second sub-pixel unit is controlled by a line scanning signal and / or a data signal to be in an activated state; wherein the specified state comprises at least one of the fault of the first sub-pixel unit and the sawtooth phenomenon of the display picture. The second sub-pixel unit can be connected when the first sub-pixel unit breaks down, and the phenomenon of cross bright lines is eliminated. In addition, when a sawtooth phenomenon occurs in a display picture, smooth transition can be carried out on the sawtooth state by accessing the second sub-pixel units, and the sawtooth phenomenon is weakened.
Owner:CHONGQING HKC OPTOELECTRONICS TECH CO LTD +1

Snapshot type spectrum stereo imaging device and method based on light field segmentation and coding

The embodiment of the invention discloses a snapshot type spectrum stereo imaging device and method based on light field segmentation and coding. The device comprises a light field imaging structure subsystem, a snapshot type spectrum imaging structure subsystem and a data reconstruction subsystem. The light field imaging structure subsystem is used for acquiring light field distribution information of a target object; the snapshot type spectral imaging structure subsystem is used for segmenting and coding the light field distribution information, compressing and sparsely sampling the light field distribution from the spatial dimension, and carrying out spectral dispersion on the spectral dimension to obtain light field spectrum aliasing data; wherein the light field map aliasing data comprises light field information and spectral information of a target scene at the same time; and the data reconstruction subsystem is used for carrying out light field atlas data recovery reconstruction on the light field atlas aliasing data to obtain a single-spectrum light field image sequence. According to the invention, convenient and accurate light field spectrum image acquisition can be realized, and real-time high-precision reconstruction of the light field spectrum image is achieved.
Owner:TIANJIN NORMAL UNIVERSITY

Image rendering method and device and electronic equipment

The embodiment of the invention discloses an image rendering method and device and electronic equipment. The method comprises the steps that an image picture collected by a target camera is written into a target rendering texture; obtaining a width value and a height value of the target rendering texture in a three-dimensional space according to the resolution of the target rendering texture, the pixel ratio per unit and the zoom factor; constructing a cylinder model according to the width value and the height value of the target rendering texture in the three-dimensional space, and obtaining the horizontal resolution and the vertical resolution corresponding to the cylinder model; constructing a three-dimensional grid according to the horizontal resolution and the vertical resolution corresponding to the cylinder model; performing image rendering on the three-dimensional grid according to textures in the target rendering textures; according to the method, scene rendering is performed in combination with the rendering texture, and scene content does not need to be drawn on a buffer, so that one-time additional texture sampling is reduced, the whole rendering process is simplified, and meanwhile, the rendering quality can be improved.
Owner:WEBANK (CHINA)

Complex material-oriented multi-path full-frequency global illumination neural rendering method and system

The invention discloses a complex-material-oriented multi-path full-frequency global illumination neural rendering method and system, and belongs to the technical field of computer graphics, and the method comprises the steps: carrying out the scene query of light emitted by pixels, and obtaining a primary geometric buffer and a multi-path mixed geometric buffer of the multi-time ejection of the light; respectively extracting main frequency features and multi-path sub-frequency features in a neural feature field based on the two features; performing directed graph structured modeling based on the multi-path sub-frequency features to obtain propagation features representing light path propagation information and global features representing overall light path information; performing multi-path frequency joint feature fusion based on the dominant frequency feature, the propagation feature and the global feature to generate a fusion feature with a full-frequency feature; and estimating a final radiation brightness value of the pixel based on the fusion feature, and completing neural rendering of global illumination. According to the method, efficient modeling and high-quality drawing of multi-path full-frequency global illumination under a complex material can be realized, and the sense of reality and dynamic consistency of a rendered image are remarkably improved.
Owner:ZHEJIANG UNIV

Methods, systems, and media of spectral bow correction

ActiveCN115790845BBend correction is simple and intuitiveNo need to add designsRadiation pyrometrySpectrum investigationCurve fittingEngineering
The application provides a spectrum bending correction method, system and medium, relates to the fields of spectral imagers and satellite remote sensing technology, and comprises the following steps: S1, selecting a solar spectrum image as sample data for spectrum bending correction, and performing curve fitting on the sample data; S2, calculating the bending degree of each column of a to-be-corrected image according to the fitted curve; and S3, correcting each column of the to-be-corrected image by using the time shift property of Fourier transform according to the bending degree of each column, completing the correction of all column data, and obtaining complete corrected spectrum image data. The application can not need to increase the design and manufacturing difficulty of a spectral element or a slit, not need complex calculation, only use the time shift property of discrete Fourier transform to process image data, and simply and intuitively complete spectrum bending correction.
Owner:SHANGHAI SATELLITE ENG INST

Wafer bonding alignment deviation closed-loop compensation method and system based on visual-infrared fusion and calibration point array combined constraint

PendingCN122825875AReduce alignment errorsreduce aliasing
The application provides a wafer bonding alignment deviation closed-loop compensation method and system based on visual-infrared fusion and calibration point array combined constraint, comprising: setting a first calibration point array on an upper wafer to be bonded, and setting a second calibration point array on a lower wafer to be bonded; collecting a visible light image of the upper wafer and an infrared image of the lower wafer; establishing a coordinate correspondence relationship between a visible light image coordinate system and an infrared image coordinate system, and converting the coordinates of the visible light image and the infrared image to a unified coordinate system; establishing a calibration point correspondence relationship, and determining an alignment deviation parameter; generating a compensation control instruction to drive an alignment execution mechanism to perform compensation adjustment; returning to execute the above steps after each round of compensation adjustment until the alignment error is less than a preset threshold, so that the application adopts a combination of visible light detection and infrared detection to avoid the fuzzy superposition error caused by the fact that the upper and lower calibration points in the traditional scheme both depend on the infrared image.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

Urban pipe network data loading method and system

The invention provides an urban pipe network data loading method and system in the technical field of urban pipe network management. The method comprises the steps that S1, a server compresses and encrypts urban pipe network data to obtain encrypted pipe network data and sends the encrypted pipe network data to a client; s2, the client obtains modeling data and a texture map based on the encrypted pipe network data; s3, creating a plurality of first pipe network models by the browser of the client based on the modeling data, and optimizing geometric data of each first pipe network model to obtain a second pipe network model; s4, mapping the texture map to the second pipe network model to obtain a third pipe network model; s5, setting a rendering area based on the visual field of the camera, and pre-loading each third pipe network model in the rendering area to a buffer area; and S6, performing real-time rendering on each third pipe network model in the buffer area, and loading and caching a rendering result through an asynchronous loading technology. The method has the advantage that the urban pipe network data loading speed is greatly increased.
Owner:ARCHITECTURAL DESIGN INST FUKIEN PROV

Fine-grained feature aggregation-based end-to-end UAV infrared pedestrian detection method

The invention discloses an end-to-end UAV (Unmanned Aerial Vehicle) infrared pedestrian detection method based on fine-grained feature aggregation, and relates to the technical field of crossing of computer vision, an infrared detection technology and edge intelligent calculation. Comprising the following steps: acquiring infrared pedestrian image data, preprocessing the infrared pedestrian image data, and inputting the preprocessed infrared pedestrian image data into a detection model; performing multi-scale feature extraction on the preprocessed infrared pedestrian image data through a backbone network of the detection model; performing multi-scale feature fusion on shallow features extracted by the backbone network by adopting an attention mechanism; carrying out multi-scale feature fusion learning on deep features extracted by the backbone network by adopting a re-parameterization technology; and the fused features are optimized through a multi-path attention mechanism detection head, and a detection result is output. According to the invention, high-precision and high-real-time pedestrian detection is realized in a complex infrared scene.
Owner:ZHEJIANG NORMAL UNIV +3

Method for calculating optimal tilt angle of object for x-ray cl three-dimensional reconstruction and application thereof

The application discloses a kind of object optimal tilt angle calculation method and application of X-ray CL three-dimensional reconstruction, and the method comprises:1, the geometric model of three-dimensional reconstruction algorithm of X-ray CL scanning mode is established,2, the geometric parameter relationship of CL scanning mode is determined, the projection address expression is solved,3, projection address relative error formula is calculated according to projection address expression,4, the influence of object tilt angle on projection address relative error is calculated, and gradient descent method is used, the relationship between object thickness and optimal tilt angle is solved, and polynomial fitting method is used, and object thickness and optimal tilt angle relationship formula are fitted.The object tilt angle of the application is optimized in the process of CL three-dimensional reconstruction, can improve the accuracy of CL three-dimensional reconstruction algorithm, and reduce the interlaced phenomenon after reconstruction.
Owner:HEFEI UNIV OF TECH

Distributed parallel three-dimensional scene texture generation method based on diffusion model

The invention discloses a distributed parallel three-dimensional scene texture generation method based on a diffusion model, which relates to a three-dimensional scene texture generation technology, and comprises the following steps: using texture features and topographic data as input to train a generator network; constructing a texture generation model generated by the diffusion model in combination with the diffusion model and the generator network; making an elevation map according to the topographic data, and creating a color image or a texture image according to the processed terrain classification data or texture style data; the color image or the texture image and the elevation map pair input are converted into feature representation, the extracted features are combined with three-dimensional geometric information in the diffusion model, and then a texture image is generated through a texture generation model; according to the method, the propagation and distribution process of the information in the scene and the diffusion and change process of factors such as illumination, shadow and reflection on the texture are simulated through the diffusion model, so that the realistic and diversified three-dimensional scene texture is generated.
Owner:ANHUI SUN CREATE ELECTRONICS

Three-dimensional wind field inversion method and device for space-borne conical scanning Doppler radar

ActiveCN121634106BImprove space coverageExpand the retrieval areaRadio wave reradiation/reflectionRadar observationsConical scanning
The application provides a kind of spaceborne conical scanning Doppler radar three-dimensional wind field inversion method and device, the method comprises: the radar observation strip area is divided into multiple sub-blocks, and there is area overlap between adjacent sub-blocks, and the horizontal wind field of each height layer is parameterized in each sub-block with piecewise continuity variation assumption;Variational method is used to obtain the optimal horizontal wind field parameter of each height layer in each sub-block, and the horizontal wind field in each sub-block is determined according to the optimal horizontal wind field parameter, the horizontal wind field of the corresponding position of each sub-block in the overlapping area is linearly weighted and fused to obtain the final horizontal wind field;The horizontal divergence is calculated according to the optimal horizontal wind field parameter of each height layer in each sub-block, and the vertical wind field is obtained by integrating the horizontal divergence in the height direction using the atmospheric mass conservation equation, and the vertical wind field of the corresponding position of each sub-block in the overlapping area is linearly weighted and fused to obtain the final vertical wind field.The application realizes the continuous and robust three-dimensional wind field inversion of spaceborne conical scanning Doppler radar.
Owner:NANJING UNIV

Shell assembly, preparation method and electronic equipment

The invention relates to a shell assembly and a preparation method thereof, and electronic equipment. The shell assembly comprises a shell body; the outer part is attached to the shell body, and the outer part covers the shell body; wherein the shell body and the appearance piece are respectively provided with a first part and a second part, the second part is connected to the edge of the first part, an acute angle is formed between the extension line of the thickness of the edge of the second part and the surface of the first part, and the angle is larger than a first preset angle threshold value. The shell assembly has the advantages of being simple in appearance and high in preparation yield.
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD

A multi-wavelength ppg non-invasive blood glucose estimation system based on spectral reconstruction

PendingCN122498836Areduce aliasingfully excavatedSpectral responseGlucose blood
This application relates to the field of non-invasive blood glucose detection technology and provides a multi-wavelength PPG non-invasive blood glucose estimation system based on spectral reconstruction. The system includes: an acquisition module for acquiring the emission spectral response curve of the light-emitting unit and the spectral response curve of the photoelectric receiving unit of a signal acquisition device; an acquisition module for acquiring demographic information of the subject, the subject's PPG signal, temperature and humidity signals, and time information; a determination module for determining the target absorption curve of the subject; a reconstruction module for spectrally reconstructing the subject's PPG signal to obtain the subject's spectral tensor; an encoding module for jointly encoding the spectral tensor, temperature and humidity signals, and time information to obtain fused features; and an estimation module for inputting the fused features into a blood glucose estimation model to obtain the blood glucose estimation result for the subject. This application can improve the accuracy and individual adaptability of non-invasive blood glucose estimation.
Owner:CENT SOUTH UNIV

Glass window ink jet printing method, controller and ink jet printing equipment

The invention discloses a glass window ink jet printing method, a controller and ink jet printing equipment, and the glass window ink jet printing method comprises the steps: controlling a nozzle of an ink jet printer to move according to the position information of a jet printing area, so as to form an ink dam at the edge of the jet printing area; curing the printing ink dam; and the spray head is controlled to move in a reciprocating mode so that the outer side of the ink dam can be filled with ink flush with the ink dam. The ink dam is jet-printed on the edge of the jet-printing area through the nozzle of the ink-jet printer, the ink dam prevents ink jet-printed in the jet-printing area from moving towards the inner edge of the jet-printing area, and the flatness of the inner edge of the glass window is improved. And moreover, the printing ink jet-printed on the jet-printing area is fused with the printing ink dam during curing, so that the generation of sawteeth or defects is reduced.
Owner:SHENZHEN INJETE ADDITIVE TECHNOLOGY CO LTD

Arc-shaped front angle tooth alloy band saw blade with function of preventing blockage of saw dust

The invention discloses an arc-shaped front angle tooth alloy band saw blade with a function of preventing blockage of saw dust, and relates to the technical field of metal cutting tools, the arc-shaped front angle tooth alloy band saw blade comprises a saw blade body, a plurality of saw teeth are arranged on one side of the saw blade body, and each saw tooth comprises a tooth rear edge and a front edge. According to the saw blade, the special arc-shaped front angles are arranged on the front edges of the saw teeth, so that the saw blade can better cut into a metal material in the cutting process, smaller saw dust is generated, the cutting efficiency can be improved, damage to equipment and operators is reduced, and the saw blade is suitable for popularization and application. Meanwhile, due to the design of the front angles of the arc-shaped teeth, generated saw dust can be wound together more tightly, a saw dust roll with a smaller diameter is formed, the saw dust roll is convenient to discharge, and scratches and pollution to the surface of a workpiece in the cutting process can be reduced; meanwhile, the front blade with the arc-shaped front angle is adopted, so that the impact resistance of the tooth tip can be enhanced, and in the cutting process, the tooth tip can keep good stability and durability even if a hard material or an emergency situation is encountered.
Owner:ZHEJIANG ZHIHONG PRECISION TOOLS CO LTD

Flower exhibition digital stylized reconstruction system using image sampling and artificial intelligence

The invention provides a flower exhibition digital stylized reconstruction system utilizing image sampling and artificial intelligence, digital reconstruction of a flower exhibition site is realized by utilizing an image sampling and artificial intelligence technology, the system comprises six modules of image sampling, processing, style model, intelligent generation, interaction control and virtual guide, and the image sampling module captures a high-definition image; the image processing module optimizes and extracts features; the style model module accurately reconstructs style parameters through a combination algorithm of a diffusion model and a Lora model group; the intelligent generation module redraws the stylized image by using the diffusion model in combination with the parameters; the interaction control module is used for realizing interaction of cue words and parameters through a Touch designer in combination with a comfyUI component, sampling conversion feedback in real time, and improving interactivity in cooperation with touch and gesture feedback; the virtual navigation module assists the user in navigation, the system generates a smooth surface through a Poisson reconstruction algorithm, the model quality is ensured, and the overall design improves the user experience.
Owner:GUANGZHOU ACADEMY OF FINE ARTS