11 results about "Flat-field correction" patented technology

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.

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 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.

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.

The application discloses a background image processing method and device, and belongs to the field of industrial visual detection. The background image processing method comprises the following steps: determining an optimized gray value corresponding to a target pixel point based on the difference between the pixel average value corresponding to the obtained initial image of a product to be detected and the pixel value of the target pixel point, a gain coefficient and a target value; determining a self-flat-field correction image based on the optimized gray value corresponding to each pixel point in the initial image; and determining a defect feature map corresponding to the product to be detected based on the self-flat-field correction image. The background image processing method can transform the initial image into an image with uniform gray values without losing image details, and then determine the defect feature map based on the self-flat-field correction image, so that the defect detection of the product with complex and changeable image background and large gray value fluctuation is met, the accuracy and precision of the detection result are high, the product is not easy to be missed or misdetected, and the application range is wider.

This invention provides an automatic method for extracting the shock layer and boundary of a blunt-nosed body based on high-speed camera images. It utilizes high-frequency imaging of the shock tube or shock tunnel experiment process using a high-speed camera, maps pixels to physical coordinates using spatial calibration, selects the region of interest in the image sequence and calculates the light intensity time series, and automatically identifies the effective time window of the experiment through rate of change analysis. Within the effective time window, representative frames are selected or averaged, and after dark flat-field correction, a one-dimensional light intensity profile is extracted. The location of the shock layer boundary is determined using a combination of gradient maxima and relative brightness thresholds. Finally, sub-pixel-level fitting and physical quantity conversion of the continuous boundary are achieved through conformal piecewise cubic interpolation. This invention, by constructing an automated boundary extraction process based on high-speed camera images, enables real-time identification and visualization of the shock layer location, providing reliable support for flow field structure diagnosis and quantitative analysis of experimental data.

This invention relates to a real-time prediction method for bright-field microscope plan images based on neural networks. The method includes acquiring images of bright-field microscopes from multiple scenes and their corresponding plan images; obtaining the corresponding brightness-corrected images according to the plan correction formula; designing and constructing a neural network architecture to directly predict the plan images of the microscope images; constructing a loss function to train the neural network architecture for predicting the plan images; and training the neural network architecture for predicting the plan images of the microscope images: using the acquired images as a training set, the designed loss function is used to train the neural network architecture to train the corresponding model; finally, brightness non-uniformity correction is applied to the microscope images. This invention, through the design of an efficient neural network architecture, directly predicts the corresponding plan image from the input image, enabling real-time and rapid correction of brightness non-uniformity in microscope images. It is unaffected by the number of images, the contents of the images, or the color, size, and density of objects in the images.