38 results about "Flat-field correction" patented technology

The invention relates to a method for verifying a Mars sky radiance simulation result based on a Mars real-shot photo, and belongs to the technical field of Mars sky background radiance. Comprises: image acquisition; performing radiation calibration; correcting dark current; performing flat field correction; converting a radiation value; and geometric correction. The Mars sky radiance simulation method breaks through the dependence of an existing model on idealized hypothesis, performs dynamic verification by using actual shot image data, remarkably improves the authenticity and reliability of a Mars sky radiance simulation result, and effectively solves the problem of systematic deviation under a specific wave band; by constructing a complete process from image acquisition, radiation calibration, geometric modeling to brightness inversion and comparison verification, dynamic feedback and closed-loop correction of a theoretical radiation model are realized, model adaptability is improved, and fine modeling under multi-temporal and multi-meteorological conditions is supported; the method can be applied to an existing Mars rover navigation camera and an image processing link of the Mars rover navigation camera, does not need additional modification, has good engineering practicability and task compatibility, and is convenient to popularize and apply.

The invention discloses a detection method for fertilizer production, and relates to the technical field of fertilizer detection.The detection method comprises the following steps that a near-infrared multispectral visual detection system is installed at the working section before packaging of a fertilizer production line, the positions of a camera and an illumination source are adjusted, and multispectral images of fertilizer particles are collected; sequentially carrying out dark current correction and flat field correction on the acquired image, eliminating noise and uneven illumination, and then carrying out median filtering to remove random noise; selecting a waveband image with the best contrast ratio, separating particles from the background through threshold segmentation, and positioning each independent particle after optimizing the boundary through morphological processing; and based on the multi-band reflectivity difference, analyzing the surface material of the particles pixel by pixel, and counting the proportion of the coating area of each particle to obtain the coating coverage rate of the single particle. By introducing the near-infrared multispectral visual detection technology and the coating uniformity quantitative analysis model, non-destructive and high-precision online detection of the coating coverage rate of the fertilizer can be realized.

The utility model discloses a uniform light source device for flat field correction, and belongs to the field of flat field correction. The uniform light source device comprises an area light source, a shading box, a TEC (thermoelectric cooler) arranged inside or on the surface of the area light source and used for reducing the temperature of a light-emitting part of the area light source, the illuminance sensor is arranged at any illuminance non-zero position on a non-shielding light emitting path in the shading box and is used for indirectly judging the illuminance change of a light outlet of the shading box; and the controller is connected with the TEC control circuit and the light source driver, and controls the TEC working voltage and the light source driving voltage according to the illumination change fed back by the illumination sensor so as to ensure that the illumination of the light outlet of the shading box is kept stable. Based on the structure, the controller can adjust the temperature of the area light source through the TEC so as to maintain the temperature of the area light source to be constant, the illuminance change of the light outlet of the shading box is judged according to the illuminance sensor, the driving voltage of the light source is adjusted, and the uniformity of the area light source is improved.

The invention discloses a multispectral microscope blood cell automatic classification and counting system. The system is composed of a multispectral illumination and microscopic imaging module, a spectrum and geometric calibration module, a multispectral preprocessing and cell segmentation module, a multispectral discrimination index and spectral band weight adaptive updating module, a cell graph structure classification module, a man-machine interaction module, an online adaptive learning module and the like. The method comprises the following steps: acquiring a blood smear image by a system under a narrow-band multi-spectrum condition, constructing cellular spectrum-morphological characteristics by combining a multi-scale segmentation result after noise suppression, flat field correction and background deduction, generating a discrimination index with a self-adaptive spectrum band weight, and completing joint classification and counting on a cell map; and meanwhile, carrying out constrained increment updating on the spectral band weight and the classification model by utilizing an artificial correction result of the low-confidence-coefficient cells. Compared with a traditional single-channel microscopic imaging and static classification method, the method has higher classification accuracy and counting stability under different dyeing and imaging conditions, and the workload of manual recheck can be reduced.

Techniques are provided for facilitating supplemental flat field correction (SFFC) determination for infrared imaging systems and methods. In one example, a method includes capturing, by a focal plane array (FPA) of an imaging system, a first set of images of a first reference object in a scene while the first reference object is at a temperature associated with a second reference object when capturing the first set of images. The method further includes capturing, by the FPA, a second set of images of the second reference object. The method further includes determining SFFC values based on the first set of images and the second set of images. Related devices and systems are also provided.

The invention relates to a machine difference control method and a standard optical system. The method comprises the following steps: carrying out flat field correction on a camera under different working distances; shooting an object to be detected under different flat field correction conditions, selecting a plurality of feature points and measuring to obtain corresponding first feature values; measuring feature points of the same picture and the same position of the to-be-detected object, determining measurement data, and selecting a working distance with the minimum deviation as an optimal calibration distance; selecting a first camera which is qualified in calibration as a reference template, shooting the high-uniformity optical integrating sphere and extracting second characteristic values of uniformly distributed point locations; and comparing the third feature value extracted by each camera with the second feature value, and determining that the corresponding camera is calibrated to be qualified under the condition that the maximum difference value in the third feature value and the second feature value conforms to a preset specification, otherwise, performing calibration again. The method can improve the calibration precision, and effectively controls the machine difference.

The invention discloses a fruit edible rate online detection method and device based on sparse CT reconstruction. The method comprises the following steps: carrying out multi-angle sparse X-ray projection data acquisition on a fruit; carrying out dark field and flat field correction, cutting, zooming, enhancement and normalization preprocessing on the X-ray image; complementing sparse angle data by adopting an interpolation algorithm; generating a three-dimensional CT model by using a CT reconstruction algorithm; extracting a two-dimensional slice image based on axis rotation in a CT model, and extracting pulp and whole fruit areas by adopting a deep learning semantic segmentation network; and reconstructing a segmentation result into an edible rate model, and calculating the edible rate by combining the pulp density and the whole fruit mass. The detection device comprises a radiation source, an X-ray detector, a conveyor belt, an electric rotating table, a screw rod sliding table, a clamping device and the like, and supports online automatic data acquisition. The method realizes high-precision modeling of the internal structure of the fruit and automatic measurement of the edible rate, and has the advantages of high precision, high efficiency, wide adaptability and the like.

The application discloses a flat field correction method, a flat field correction system and a computer readable storage medium thereof. The flat field correction method comprises the following steps: providing a camera to be corrected and a blank wafer; collecting a dark field image of the blank wafer; collecting a bright field image of the blank wafer; and performing flat field correction calculation processing of the camera to be corrected according to the dark field image and the bright field image of the blank wafer. In the technical scheme, the blank wafer is used as a target object for flat field correction, the blank wafer is in a dust-free environment during production, is not easy to be polluted, and has extremely high consistency of wafer surface gray scale, so that the problems of difficulty in guaranteeing sufficient size and uniformity of a flat field target in the prior art can be solved.

Embodiments disclosed herein include a digital polymerase chain reaction (dPCR) operating system employing a digital image processing method for correcting illumination deviations in data associated with an array of sample plates comprising one or more arrays of sample partitions. In some embodiments, the method includes acquiring background image data corresponding to digital images acquired by the dPCR system through a camera after a background cycle of dPCR detection. For each partition, a local flat field correction coefficient is derived and applied to the background image data to obtain local offset corrected background image data. A global flat field correction coefficient set is then determined using the local-bias-corrected background data. And performing illumination deviation correction on the end point image data by jointly using local and global flat field correction coefficients to generate a deviation-corrected end point illumination value.

The application provides a kind of flat field correction parameter acquisition method and system of image sensor chip, it is related to image processing technical field, comprising: the gray value of the picture currently collected by image sensor chip is adjusted to within the preset bright field target gray value range, then in the preset erasing time range current erasing time is selected, and the dark field picture is obtained by erasing image sensor chip according to current erasing time;The gray value after erasing of dark field picture is obtained, and when the gray value after erasing is within the preset dark field target gray value range, the corresponding current erasing time and dark field picture are saved as dark field parameter;Otherwise, according to current erasing time, the preset erasing time range is reduced, and current erasing time is selected again.The beneficial effect is that the dark field parameter of image sensor chip can be automatically and quickly acquired, without manual intervention, effectively saving the time and labor cost of flat field correction, and solving the annoyance caused by the tedious flat field correction process for engineers.

The invention discloses a single-pixel imaging semiconductor wafer surface defect extraction method and system, and relates to the technical field of wafer defect extraction, and the method comprises the steps: carrying out the dark current deduction and brightness flat field correction of a defect-free wafer bright field image, generating a reference mask, dividing tiles, and building coordinate mapping; generating a defect sensitive pattern pair, performing tile-by-tile projection, performing integral acquisition by using a single-pixel detector, and performing complementary difference to obtain a phase shift difference group; in-phase and orthogonal components are obtained through four-step phase shift phase locking demodulation, defect global coordinates are estimated according to the phase and frequency slope, and a frequency domain suppression weight is constructed through a defect-free image Fourier spectrum to obtain saliency; and the defect type is judged through self-adaptive adjustment of the distance between the emitting end and the tile and saliency secondary difference. According to the method, the in-phase / orthogonal component and amplitude-phase distribution are directly solved by adopting the four-step phase shift method, the defect coordinates are solved by using the phase-frequency slope, image reconstruction is avoided, the calculation overhead is reduced, and the positioning precision is improved.

The application discloses a kind of edge camera's flat field correction method and device in multi-camera vision detection, which comprises: real-time acquisition of the image in the field of view of edge camera, identify and locate the edge profile of product in image, according to the range of product in field of view, the field of view is divided into product part and productless part;Based on the first correction coefficient of product part calculated by conventional flat field correction method, based on the first correction coefficient, according to the proportion of product part in field of view, the correction coefficient of productless part is calculated;The correction coefficient at the junction of adjacent area is smoothed, and the final flat field correction coefficient of each pixel in the entire field of view of edge camera is obtained, and the final flat field correction coefficient is applied to edge camera image acquisition, and flat field correction is completed.The scheme can improve the flat field correction effect and stability of edge camera.

The application discloses a deep learning-based limited-angle projection phase contrast CT image reconstruction method and device, which comprises the following steps: acquiring limited-angle projection data of X-ray phase contrast CT scanning through an equal-angle increment strategy; performing flat-field correction and dark-field correction preprocessing on the limited-angle projection data to obtain limited-angle projection data before phase recovery; performing preprocessing on the limited-angle projection data through a phase recovery strategy to obtain limited-angle projection data after phase recovery; performing CT reconstruction on the limited-angle projection data before and after phase recovery through a filtered back projection strategy to obtain CT images of the limited-angle projection before and after phase recovery; constructing a phase contrast CT intelligent image reconstruction network model and training; and performing reconstruction processing on the CT images of the limited-angle projection before and after phase recovery through the trained phase contrast CT intelligent image reconstruction network model to obtain reconstructed phase contrast CT images. The application can quickly and efficiently perform phase contrast CT image reconstruction, effectively suppress limited-angle reconstruction artifacts and improve image quality.

The invention discloses a halo prediction-based microscopic image shadow removal method, computer equipment, a storage medium and a program product. The objective of the invention is to solve the problem that flat-field correction needs multiple groups of flat-field correction in a zoom microscope, and to solve the problem that flat-field correction fails when exposure time is prolonged or shortened. According to the method, flat field correction does not need to be carried out on the image in advance, and the influence caused by texture introduction of the used white board in the flat field correction process is reduced. In addition, according to the collected image, the halo map is predicted in real time through the model, brightness compensation is carried out on the image according to the halo map, and the compensation effect is better.

Techniques are provided for facilitating supplemental flat field correction (SFFC) determination for infrared imaging systems and methods. In one example, a method includes capturing, by a focal plane array (FPA) of an imaging system, a first set of images of a first reference object in a scene while the first reference object is at a temperature associated with a second reference object when capturing the first set of images. The method further includes capturing, by the FPA, a second set of images of the second reference object. The method further includes determining SFFC values based on the first set of images and the second set of images. Related devices and systems are also provided.

The present disclosure provides a flat field correction method and device, electronic equipment and storage medium, and relates to the field of image processing, which comprises: acquiring multiple background pictures of different positions of an object to be detected; calculating first, second and third gray values of the multiple background pictures; generating a target background template image of the object to be detected according to the gray values of the multiple background pictures, the first, second and third gray values of each pixel point; and correcting an object to be detected image according to the target background template image. The method of the present disclosure does not need to guarantee the absolute blank state which is difficult to achieve when obtaining the correction template in the past, and the background template image is generated one by one according to the background pictures of the object to be detected, so that the noise reduction template is more targeted, and the quality of image noise reduction is improved.

The invention provides a color correction method, electronic equipment and a program product, and relates to the technical field of digital image processing. The method comprises the steps of obtaining a to-be-processed image; performing flat field correction on the to-be-processed image by using the color correction model to obtain a first intermediate image; performing gamma correction on the first intermediate image by using a color correction model to obtain a second intermediate image; performing white balance correction on the second intermediate image by using a color correction model to obtain a third intermediate image; and performing color correction on the third intermediate image by using a color correction model to obtain a fourth intermediate image as a target image subjected to color correction. Therefore, the problems that in a traditional digital image color correction mode, due to the fact that a model is too simplified, the color correction precision is insufficient, and especially obvious color cast is likely to be generated in an area with high color saturation or complex illumination can be solved.

The invention relates to the technical field of building leakage detection, and discloses a leakage source multi-dimensional positioning method based on building 360-degree infrared detection. The method comprises the following steps: acquiring 360-degree infrared image data of the periphery of a building through an infrared scanning device, and synchronously acquiring real-time environmental parameters; the method comprises the following steps: performing flat field correction and radiation calibration preprocessing on infrared image data to generate standard infrared image data, and extracting temperature gradient features and thermal anomaly features from the standard infrared image data to form an initial feature set; and completing normalization processing of the initial feature set in combination with real-time environmental parameters, inputting the initial feature set into a convolutional neural network model for feature learning, and outputting a thermal anomaly probability graph. And performing clustering analysis on the thermal anomaly probability graph to identify a thermal anomaly region, and determining the position coordinates of the leakage source through multi-dimensional space analysis combining deep learning and geometric constraint. The method can eliminate detection blind areas and reduce environmental interference, is accurate in positioning and wide in applicability, and is suitable for peripheral leakage detection of various buildings.

The invention discloses an X-ray image residual attention enhancement method and system based on deep learning, and belongs to the technical field of computer vision and artificial intelligence. The method comprises the steps that a low-dose X-ray image of the strain clamp is collected through an unmanned aerial vehicle platform, and dark field and flat field correction and normalization preprocessing are carried out; the preprocessed image is input into a deep neural network based on an encoder-decoder structure, the network adopts a multi-scale residual block to extract features, defect area feature response is enhanced through a joint channel-space attention mechanism, a residual learning strategy is utilized to output a residual image, and the residual image is superposed with the input image to obtain an enhanced image; and finally, inputting the enhanced image into a YOLO11 model improved by multi-scale feature fusion and an attention mechanism to realize accurate positioning and classification of defects. The system comprises X-ray imaging hardware and an edge computing software unit of an integrated preprocessing, enhancement and recognition module. According to the method, the problem of balancing noise suppression and detail reservation in the low-quality X-ray image is effectively solved, the accuracy and robustness of defect detection are remarkably improved, and the method is suitable for automatic intelligent inspection of the high-altitude power transmission line.

The application provides a pathological slide-based local adaptive flat field correction method and device and a readable storage medium thereof, and comprises the following steps: acquiring a pathological slide image containing background interference, and removing interference areas such as stickers through threshold masking; converting the image into an HSL color space, and only processing a luminance channel; performing overlapping block division on the luminance channel, calculating the average luminance of each block, and generating a correction factor matrix; performing local correction on the luminance channel through interpolation expansion of the matrix, and finally merging color channels and outputting a corrected image. Through a local adaptive block division strategy, the application effectively solves the luminance imbalance problem caused by uneven background and sticker interference in a pathological slide image, retains image details, and improves subsequent analysis accuracy.

The application belongs to the technical field of semiconductor detection, and particularly relates to an image processing method for silicon wafer detection and a silicon wafer detection device. The image processing method comprises the following steps: rotating and scanning a silicon wafer to obtain all images of the silicon wafer and coordinates of center points of the images; performing grouping flat field correction on the images according to the coordinate sizes of the center points of the images to obtain corrected images of the images; performing linear directional splicing on the corrected images, extracting a splicing image of adjacent corrected images, eliminating a splicing seam of the adjacent corrected images, obtaining a linear splicing image, and performing inverse polar coordinate conversion on the linear splicing image to obtain annular splicing images of each group; splicing adjacent annular splicing images, extracting a splicing image of adjacent annular splicing images, eliminating an annular splicing seam of the adjacent annular splicing images, and obtaining a complete splicing image. The application solves the problems of uneven gray scale and obvious splicing traces from the root by combining coordinate grouping correction and stage-by-stage splicing seam elimination.

This invention discloses a transparent liquid leakage detection system and method based on multispectral polarization imaging in the field of machine vision inspection technology. The system includes: acquiring image data of the surface to be inspected in multiple near-infrared bands and multiple polarization angles using a multispectral polarization imaging system; preprocessing the acquired image data, including dark current correction, flat-field correction, and image registration; calculating the Stokes vector for each pixel based on the preprocessed image data, and deriving the degree of polarization and polarization angle; and extracting multi-band spectral absorption ratio features based on the preprocessed image data, including calculating the intensity ratio between different near-infrared bands. This invention can effectively enhance the optical characteristics of transparent liquids, achieving high-contrast and high-precision recognition in complex backgrounds, and is suitable for high-precision identification of transparent liquids such as water stains and oil leaks on the surface of power plant equipment.

The application discloses a pixel-level instrument matrix calibration method of a four-channel metasurface polarization element, and particularly relates to the technical field of metasurface polarization detection and edge computing, and comprises the following steps: a polarization state generator is controlled to output a plurality of groups of known standard polarization states of Stokes vectors in a fixed order; four-channel subgraphs are collected; dark field subtraction, flat field correction and initial alignment are performed to obtain a standard response group; on the edge computing side, a local position group is unfolded in each channel subgraph for each target position, and is combined item by item according to the relationship that the four-channel responses can constitute the same observation vector to obtain a candidate position group set; and on the edge computing side, candidate position group construction and established pixel determination are first performed on the four-channel responses, and then pixel-level instrument matrix fitting, checking and abnormal recalculation are performed based on the established pixels.

The application discloses a kind of VCSEL far field test method and equipment, including to target product provides excitation signal, to make target product project laser spot to light screen;The distribution image of laser spot on light screen is photographed by infrared camera module, and sampling image is obtained, wherein the photographing center of infrared camera module is aligned with the laser emission center of target product;The first intermediate image is obtained by pre-processing to sampling image, and pre-processing includes flat field correction and distortion removal processing;Data intensity extraction is carried out to the first intermediate image, and energy distribution test data are obtained;According to energy distribution test data and preset relationship model, laser divergence angle test data are determined;Image convolution and numerical operation processing are carried out to the first intermediate image, and eye safety test data are determined.The application can obtain multiple test data through the first intermediate image, realize one-time completion multiple test, and be conducive to improving test efficiency.

Techniques are provided for facilitating assisted flat field correction (SFFC) determination for infrared imaging systems and methods. In one example, a method includes capturing, by a focal plane array (FPA) of an imaging system, a first set of images of a first reference object in a scene while the first reference object is at a temperature associated with a second reference object while the first set of images is captured. The method further includes capturing, by the FPA, a second set of images of a second reference object. The method further includes determining an SFFC value based on the first set of images and the second set of images. Related devices and systems are also provided.

The invention relates to the technical field of spectral analysis, in particular to a tissue identification method of a hyperspectral analyzer, which comprises the following steps: acquiring a three-dimensional data cube of an in-vitro tissue slice through a hyperspectral imaging system; pre-processing through flat field correction, dark current compensation and a filtering algorithm to generate standard spectral data; extracting local and global features by using a convolutional neural network and a Transform encoder to generate a high-dimensional feature vector; synchronously executing tissue classification and lesion grading prediction by adopting a multi-task learning framework; and dynamically adjusting a feature extraction strategy based on the difference between an output result and a historical database, updating model parameters through an online learning mechanism, and performing feedback optimization. According to the method, a chemical staining step is avoided, rapid and accurate tissue identification is realized, and the clinical decision-making efficiency is improved.

This invention specifically relates to a gas concentration measurement method, aiming to address the technical problems of existing gas concentration measurement methods, such as systematic inversion bias, sensitivity to environmental conditions, insufficient robustness to changes in system response, difficulty in balancing computational complexity and real-time performance, and insufficient inversion stability under low signal-to-noise ratio conditions. This invention detects a target area to obtain a reference spectral image, a spectral image of the gas to be measured, and a water vapor spectral image. Through dark-field and flat-field correction, it obtains the reference equivalent radiance, the equivalent radiance of the gas to be measured, and the equivalent radiance of water vapor. Normalization is performed using the reference equivalent radiance to obtain the logarithmic absorbance of the gas to be measured and the logarithmic absorbance of water vapor. Water vapor absorption interference is subtracted using the logarithmic absorbance of water vapor, finally yielding the concentration of the gas to be measured. This reduces the influence of water vapor absorption on the detection results and improves inversion stability.

This invention discloses a method, apparatus, and storage medium for constructing a real rainline layer dataset, belonging to the field of computer vision data processing and image enhancement. It involves acquiring a sequence of real rainline images under black background conditions, obtaining a rainless black field or a background image after dark / flat field correction, separating the rainline layer, performing upper quantile truncation and normalization, and adaptively determining the gamma coefficient based on saturation pixel ratio, etc., to obtain the final rainline layer. The final rainline layer is then quality-checked based on indicators such as background residue, overexposure saturation, fog dominance, and the proportion of slender rainline structures, and tags such as rainfall intensity level, exposure gain, and batch number are generated and stored to form a reusable rainline layer sample library.