118 results about "Bright field image" patented technology

The invention provides a metal product surface flaw detection method and system based on machine vision, and belongs to the technical field of machine vision. The method comprises the following steps: constructing a multi-modal image data set through bright field image acquisition, dark field image acquisition and three-dimensional point cloud data acquisition of the surface of a detected metal product, and registering the multi-modal image data set; based on the registration multi-modal image data of pixel-level alignment, pixel-level defect segmentation is carried out by adopting a double-flow diffusion Transform model, and a defect segmentation map is output; and on the basis of the defect segmentation image and the registered multi-modal image data, through segmentation image binaryzation and region extraction, multi-dimensional defect feature extraction and quantification, defect classification and report generation, a final defect detection report is output, and the metal product surface defect detection method is completed. The invention effectively solves the core pain points of low precision, poor robustness and insufficient generalization ability for unknown defects in metal surface flaw detection, and provides an automatic detection method with high reliability and high precision.

The invention relates to a glass flaw recognition method, system and equipment based on image enhancement and a medium. The method comprises the following steps: acquiring a multi-view image set of to-be-detected glass; respectively carrying out region-of-interest extraction on the vertical dark field image, the horizontal dark field image, the vertical bright field image and the horizontal bright field image to obtain multiple groups of image blocks; combining a plurality of image sub-blocks with the same position in each group of image blocks to obtain a standard image sub-block group; inputting the standard image sub-block group into a pre-trained glass flaw detection model to obtain a detection result and a classification probability corresponding to each image sub-block at the same position; and based on a preset channel fusion weight, performing weighted fusion on the detection results at the same position according to the corresponding classification probability to obtain a glass flaw recognition result at the corresponding position. According to the method, through region-of-interest extraction, channel separation feature extraction and fusion probability output under an independent view angle, the accuracy of glass flaw automatic identification is improved.

The invention provides a defect detection method and device and electronic equipment, and belongs to the technical field of automatic optical detection.The defect detection method comprises the steps that a bright field image and a dark field image of a to-be-detected area of a wafer are obtained; feature extraction is carried out on the bright field image and the dark field image, and multi-feature spatial data is constructed; performing context analysis on the multi-feature space data, and determining context attribute information corresponding to each local area in the to-be-detected area of the wafer; according to the context attribute information, self-adaptive fusion weights of all the local areas are generated, and the self-adaptive fusion weights comprise weight components corresponding to the bright field image and the dark field image respectively; and according to the adaptive fusion weight, carrying out fusion processing on the bright field image and the dark field image to generate a defect enhanced image. Complementary information in bright and dark field multi-mode image data can be deeply mined, rough background noise can be inhibited, and feature expression of weak defects can be remarkably enhanced.

The invention relates to the technical field of detection, in particular to a high-throughput bacterial colony detection sensor based on multi-mode optics and spectrum fusion and a detection method thereof.The method comprises the steps that data of a bright field image, a multi-channel fluorescence image and a near infrared spectrum of a bacterial colony to be detected are collected, and metadata in the collection process is recorded synchronously; preprocessing the data, and extracting multi-dimensional features of bacterial colonies from the preprocessed data; performing fusion processing on the multi-dimensional features in combination with space-time sequence information; identifying and classifying bacterial colonies according to the fused multi-dimensional features; and generating a detection report containing traceability information according to a result after identification and classification. Through multi-modal synchronous data acquisition, targeted data preprocessing, multi-dimensional feature fusion and standardized recognition and classification, high-throughput accurate detection of bacterial colonies is realized, manual intervention is reduced, and reliability and traceability are improved.

The invention discloses a blue glass detection method and system, and the method comprises the steps: configuring dynamic adaptive illumination based on the defect type and stress distribution of blue glass; generating a bright field light source, a dark field light source and a polarization field light source based on dynamic adaptive illumination, and performing exposure to obtain three light source images; synchronously acquiring bright-field light source, dark-field light source and polarization-field light source images to obtain a fused image; separating the bright field image, the dark field image and the polarization field image based on the fused image, extracting defects in the bright field and the dark field, and extracting stress distribution of the polarization field; and taking the bright field image, the dark field image and the polarization field image as input, constructing a defect-stress model, and outputting a defect type and a stress feature level. Through multi-light-source fusion (bright field, dark field and polarization) and model construction, efficient and accurate detection of defect types and stress distribution is realized.

The invention relates to the technical field of material analysis, in particular to a light microscope-field emission electron microscope combined shale rock slice analysis and identification method, which comprises the following steps of: firstly, combining a brightness distribution condition represented by a bright field image of a shale rock slice and a birefringence deviation condition represented by a cross polarization image from an optical angle; determining a mineral discrimination index representing an atomic number agent; applying offsets of different sizes based on the distribution condition of mineral discrimination indexes and the surface fluctuation condition of shale rock slices, and determining a position offset vector by combining gray scale gradient distribution on the basis; and finally, determining the cross-scale positioning and more accurate electron microscope objective table coordinates corresponding to each pixel point in combination with a position offset vector in a pixel coordinate conversion process based on an image physical distance scale and rotation translation processing, so that the cross-scale positioning accuracy of the optical microscope and the field emission scanning electron microscope is higher. The reliability of analyzing and identifying the shale rock slice is obviously improved.

The invention discloses a code nail stamping defect detection method and system based on machine vision, and belongs to the technical field of industrial automation quality control. The method comprises the following steps: acquiring multi-modal visual data such as a two-dimensional bright field image, a two-dimensional dark field image and three-dimensional contour data of a to-be-detected code nail; preprocessing the multi-modal visual data to obtain bright field, dark field and three-dimensional image data adaptive to a neural network model; inputting the three kinds of image data into a preset neural network model for defect identification processing, and outputting a defect segmentation mask and defect category information; and finally, performing quantitative analysis on the defects based on the output defect information, and judging whether the product is qualified or not according to an engineering specification threshold value. According to the method, multi-dimensional and complementary visual information is fused, and a specially designed neural network model is adopted for analysis, so that the problem of insufficient detection capability of tiny, low-contrast and three-dimensional geometric defects in the prior art can be effectively solved.

The invention discloses a Hu sheep primary hepatocyte separation effect intelligent evaluation system based on image recognition, and belongs to the technical field of biomedical engineering and intelligent detection. The physical mapping relation between the non-uniform illumination light field and the three-dimensional curved surface form and the tension state of the optical soft spherical shell is established; and the data field generation module is used for projecting serialized structured light based on the physical mapping relation, collecting a bright field image sequence generated by the structured light, synchronously collecting a fluorescence image, carrying out physical field association on modulation information carried by the bright field image sequence and topological information of the fluorescence image, and generating a high-dimensional native response data field. According to the method, the contact ridge line of the high-density adhesion Hu sheep primary hepatocytes can be accurately identified by constructing the optical soft spherical shell model and coupling mapping of the light field and the physical state of the cells, the problems of under-segmentation and over-segmentation are effectively avoided, and the extracted morphological parameters such as the area and the perimeter of the cells better fit the reality.

The invention discloses a wafer surface defect detection system and method based on a high-speed line scanning camera, and belongs to the technical field of wafer defect detection, and the system comprises an illumination system which is used for providing bright field illumination and illumination with an adjustable illumination angle, and forming a line light spot with an adjustable size on the surface of a wafer through a line light spot generation device; the wafer scanning assembly comprises a carrying table used for carrying a wafer and a displacement control assembly used for driving the carrying table to move; the imaging system comprises a bright field imaging assembly; the high-speed line scanning camera is used for carrying out high-speed scanning imaging on the signals collected by the imaging system and balancing the signal-to-noise ratio, the dynamic range and the detection resolution through a programmable pixel merging function; and the control system is used for coordinating and controlling all system components and realizing parameter optimization and online self-adaptive calibration. According to the invention, high-resolution and high-sensitivity wafer surface micro-nano defect detection can be realized while high detection speed is ensured.

The invention discloses a vortex spinning yarn defect detection method and system based on computer vision, and relates to the technical field of textile industry quality control and image recognition, and the method comprises the steps: obtaining a bright field image sequence and a dark field image sequence, and collecting a yarn position signal and an air pressure pulsation signal of a spindle vortex field; performing track modeling and inter-frame displacement compensation on the bright field image sequence to generate a yarn structured displacement image; constructing an airflow fiber-carrying feature map; performing spatial registration and fusion on the yarn structured displacement image and the airflow fiber-carrying feature map to obtain a dual-channel feature map; generating a defect cause directivity judgment instruction; marking a defect position based on defect information of the defect cause directivity judgment instruction, and generating a process parameter adjustment suggestion signal; and constructing a defect-process feedback sample set. The air vortex spinning yarn defect detection system effectively solves the key problems that an existing air vortex spinning yarn defect detection system is single in detection dimension, defect causes cannot be distinguished, and real-time process closed-loop feedback is lacked.

The invention discloses a biased binocular visual odometer method and device based on strawberry cuttlefish bionics. The biased binocular visual odometer method comprises the following steps: synchronously acquiring a bright field image and a dark field image collected by a biased binocular camera and inertial data of an inertial measurement unit; constructing a perceptual attention weight grid according to the bright field image and the dark field image, and performing brightness normalization processing on the bright field image and the dark field image; extracting lateral visual features based on the normalized image and the perceptual attention weight grid; and fusing the biased visual features with the inertial data, and solving through nonlinear optimization to obtain a carrier pose estimation result. According to the invention, the dynamic range of the binocular vision system is expanded, and the imaging and sensing capabilities of the system in an HDR scene are improved. And meanwhile, the positioning precision and robustness of the binocular visual odometer in an HDR scene are improved.

Methods for distinguishing particles in a fluid sample are disclosed. In one embodiment, the method includes acquiring a background SIMI image and a background brightfield image of a membrane filter while the membrane filter is free of a fluid sample, introducing a fluid sample onto the membrane filter, acquiring a SIMI image and a brightfield image of filtered particles resting on the membrane filter, distinguishing between the filtered particulates and the membrane filter based on the background SIMI image, generating a particle mask based on the SIMI image, and detecting beads via the particle mask. Methods for distinguishing particulates include distinguishing between viable and non-viable cell populations, distinguishing between cellular and non-cellular particulates, distinguishing between biological and non-biological particulates, distinguishing between first and second protein types, determining stability of monoclonal antibody drugs, identifying beads in a cell therapy, and detecting bacteria.

The application relates to a kind of mitochondria-based single cell feature extraction and analysis method and system, comprising: obtaining the multiple modal images such as bright field image, nucleus fluorescent image and mitochondria fluorescent image of single cell;Image preprocessing is carried out to the three modal images obtained;For different structures such as mitochondria, morphological and texture features are extracted, and feature analysis is carried out;Further, through the fusion of mitochondria and machine learning technology, the automatic classification of cells is realized.The application is used for the classification of human cervical epithelial cells (H8) and cervical cancer cells (HeLa), and the machine learning analysis of morphological features and texture features shows the potential of mitochondria in the classification of cervical cells.The application has strong applicability, can be combined with machine learning and other analysis methods, and can be applied to various biological cells, has universality, and is easy to popularize.

According to the high-throughput drug screening method and system based on large-view-field imaging and machine learning, data acquisition of high-throughput organs or tumor balls is achieved through a large-view-field biological imaging system, the data acquisition process is accelerated, and the integrity of original image information is guaranteed; a two-stage image processing means that a lightweight target detection model is connected with a semantic segmentation model is adopted, so that the calculation parameter quantity is reduced, heterogeneity interference is removed, and the image information integrity is ensured while the accurate acquisition of the individual image contour of the organoid or the tumor ball is realized; for organoid image acquisition, a Z-axis scanning strategy is combined with a screening strategy based on IOU and a definition function, so that information acquisition integrity and subsequent organoid activity prediction precision are ensured; in combination with a machine learning model based on an ensemble learning principle for a regression task, the activity prediction of the bright field image of the organoid or tumor sphere is realized, and the influence of a traditional method on the activity of a culture is avoided.

This invention relates to the field of materials analysis technology, specifically to a method for analyzing and identifying shale thin sections using a combination of optical microscopy and field emission scanning electron microscopy. First, from an optical perspective, the method combines the brightness distribution of bright-field images of shale thin sections with the birefringence deviation of cross-polarized images to determine mineral discrimination indices representing atomic number proxies. Then, based on the distribution of the mineral discrimination indices and the surface undulations of the shale thin sections, different biases are applied, and the positional bias vector is determined by combining this with the gray-level gradient distribution. Finally, based on the physical distance scale of the image and the pixel coordinate transformation process involving rotation and translation, the positional bias vector is used to determine the electron microscope stage coordinates corresponding to each pixel point for more accurate cross-scale positioning. This improves the accuracy of cross-scale positioning using optical microscopy and field emission scanning electron microscopy, significantly enhancing the reliability of shale thin section analysis and identification.

The invention relates to the technical field of heat dissipation substrate detection and correction, in particular to a multi-spectral detection and automatic correction system and method for the flatness of a heat dissipation substrate, and the method comprises the steps that a multi-spectral acquisition module emits a plurality of light beams with different wavelengths to the detected heat dissipation substrate; collecting multispectral image data and generating a multidimensional image data set comprising an RGB image, a multispectral image, a laser image, a bright field image and a dark field image; the temperature field construction module receives the multi-dimensional image data set, calculates the spectral reflectivity of each point on the surface and constructs temperature field distribution; the flatness evaluation module receives the temperature field distribution, performs homogenization processing, calculates flatness offset and judges whether the flatness offset exceeds a preset threshold value or not; when the flatness offset exceeds a threshold value, the automatic correction module determines correction force distribution based on thermal-structural coupling analysis and applies correction force by selecting at least one mode of an electric field, a magnetic field, pressure or mechanical adjustment, automatic correction of the flatness is achieved, and the detection precision and reliability are remarkably improved.

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.

The invention discloses a foreign matter detection method, device and system and electronic equipment, and belongs to the technical field of foreign matter detection. The foreign matter detection method comprises the following steps: acquiring a bright field image of a detection surface of a target sensor; determining a background response baseline corresponding to the detection surface in the bright field image based on the response characteristics of the bright field image; comparing the response feature of each pixel in the bright field image with the background response baseline to obtain deviation information between each pixel and the corresponding pixel of the detection surface; and obtaining a foreign matter detection result of the target sensor based on each piece of deviation information. No extra special tool is needed, and automatic detection of foreign matters on the surface of the sensor can be realized.

The invention relates to the technical field of cloud and machine vision, in particular to a high-precision multi-light-field contact lens edge defect detection method and device based on cloud-machine vision, and the method comprises the steps: obtaining a multi-light-field original image of a printed contact lens soaked in water of a glass bowl, and carrying out the preprocessing of the multi-light-field original image, obtaining a bright field image, a dark field image and a preprocessed image; performing glass bowl detection on the preprocessed image, and extracting geometric features of the glass bowl; contour feature extraction is performed on the printed contact lenses in the glass bowl area based on the geometric features of the glass bowl; and then based on the extracted images and features, executing rough detection and edge defect detection under a Cartesian coordinate system and a polar coordinate system. The contact lens image acquired by the high-resolution camera is further utilized, the image is automatically identified, and whether the corresponding product is normal or not is judged, so that the purposes of reducing the labor cost, saving the time and improving the production yield are achieved.

The invention relates to the field of machine vision, in particular to a heterogenous contact lens image registration method and system based on a depth model, and the method comprises the steps: obtaining a bright field image and a point light source image of a contact lens; preprocessing the bright field image to obtain a first preprocessed image; preprocessing the point light source image to obtain a second preprocessed image; performing multi-scale feature fusion on the first pre-processed image and the second pre-processed image to obtain fusion features; a two-dimensional matrix is extracted from the multi-scale feature fusion process; and registering the bright field image and the point light source image based on the two-dimensional transformation matrix. The invention provides a depth model-based heterogeneous contact lens image registration method. The method aims at overcoming the limitation of a traditional registration technology in processing a multi-source heterogeneous image, and the robustness, accuracy and adaptability of registration are improved through feature learning of deep learning and nonlinear modeling capacity.

A method of analyzing images of a biological specimen using a computational model is described, the method including processing a cell image of the biological specimen and a phase contrast image of the biological specimen using the computational model to generate output data. The cell image is a composite of a first brightfield image of the biological specimen at a first focal plane and a second brightfield image of the biological specimen at a second focal plane. The method further includes performing a comparison of the output data and reference data, and improving the computational model based on the comparison of the output data and the reference data. The method further includes thereafter processing additional image pairs according to the computational model to further improve the computational model based on a comparison of additional output data generated by the computational model and additional reference data.

The invention discloses a cell multi-modal analysis system and method based on a micro-fluidic chip, and the system comprises a data collection and processing module which is used for inputting a mixed cell sample, a first cell sample screened by a cell classification module and a second cell sample output by a cell three-dimensional reconstruction module into the micro-fluidic chip, respectively acquiring a first bright field image, a second bright field image and a third bright field image; the cell classification module is used for receiving the first bright field image, outputting a cell category probability value through a cell classification model, screening a first cell sample and feeding back the first cell sample to the data acquisition and processing module; the cell three-dimensional reconstruction module is used for receiving the second bright field image, outputting a second cell sample through a cell reconstruction model, and feeding back the second cell sample to the data acquisition and processing module; and the cell deformation analysis module is used for receiving the third bright field image and outputting deformation data through a cell deformation model. According to the invention, cell multi-modal analysis can be accurately and quickly carried out at low cost.

The invention provides a CT (Computed Tomography) image data processing method, which comprises the following steps of: closing a radiation source, and acquiring a group of dark field image sequences according to a designed frame rate; starting a radiation source, and acquiring a group of bright field image sequences according to a designed frequency; calculating a gray average value sequence of the bright field sequence according to a formula; obtaining a polynomial through polynomial fitting, and resampling by using a polynomial function; moving the detector to a position, starting a radiation source for exposure, collecting a group of images, and calculating a mean value image of the group of images to obtain a reference bright field image; and storing the reference bright field image sum, and calculating the image bright field value of the position in actual use. According to the method, the dark field value and the bright field value corresponding to each projection drawing can be calculated to calibrate the bright field and the dark field of the detector, bright field calibration does not need to be independently carried out at each position, the calibration speed is high, the stored bright field data is less, the time can be saved, and the data storage space can be reduced.

This invention provides a visual detection method and system for coating uniformity, belonging to the field of image processing. The method includes: obtaining the corresponding pixels in each modal image based on the positions of pixels in four matching pairs among all matching pairs of the brightfield image of the coating to be detected and the brightfield image corresponding to each modality; dividing the brightfield image of the coating to be detected into several regions based on the value of each pixel in the H channel of the HSV color space; and obtaining the uneven coating region based on the grayscale value of the corresponding pixel in the darkfield image and the relative thickness of the corresponding pixel in the narrowband spectral image within each region of the brightfield image of the coating to be detected. This invention aims to solve the problem of relatively low accuracy in detecting coating uniformity using a single modal image.

This invention discloses a strong backlight imaging method based on a DMD (Digital Modulator-Demiller), belonging to the field of optical imaging technology. This method involves spatial pixel-level matching and synchronous triggering feedback between the camera and the DMD. Under strong backlight imaging conditions, the strong backlight passing through the target and the light reflected from the target together form the incident light, which sequentially passes through the imaging lens, the DMD target surface, the relay matching imaging lens, and the camera target surface. The overall grayscale value is reduced by the DMD mask to obtain an initial image containing target contour information. Based on this image, an initial mask is generated for differential grayscale modulation of the target and background areas. Further, local overexposed areas are detected and pixel-level masks are generated. Simultaneously, a high bit-depth grayscale modulation mode of the DMD is introduced to finely suppress brightness in locally bright areas, ultimately obtaining an image of the target without overexposure and with clear details. This invention can effectively suppress overexposure and improve imaging contrast under strong backlight conditions, and is suitable for high dynamic range backlight imaging scenarios.

The present application relates to the technical field of pollen detection, and particularly relates to a pollen sampling imaging detection method based on microfluidics, a microfluidic chip and a system, which comprises: collecting pollen and injecting liquid phase, enriching pollen based on a microfluidic chip; shooting and processing the pollen to obtain a global image and a slice image; performing multi-level subsampling processing based on an attention mechanism to obtain an extracted feature map, and then performing multi-parameter detection to obtain a regression result for fusion. In view of the problem that the pollen detection method in the prior art is poor in timeliness and difficult to accurately count, the microfluidic chip is introduced to enrich the pollen aerosol transferred by the liquid phase, thereby avoiding the loss of morphology, and then the collection and identification process of the bright field image is performed, the multi-level attention of the slice image and the global image is identified respectively, the segmentation result of the pollen group distributed in multiple slices is obtained, and the segmentation result is regressed and fused into the global image, so that the pollen can be effectively quantified and classified in an online scene.

This invention relates to the field of image processing technology and discloses an intelligent method for judging the surface quality of cold-rolled strip steel based on image processing. The method includes: acquiring bright-field and dark-field images of the strip steel surface, fusing the two images to obtain a preprocessed image; segmenting the preprocessed image to obtain the actual defect region; extracting the geometric features, texture features, and frequency domain features of the actual defect region to construct a multi-dimensional feature vector; identifying the defect category based on the multi-dimensional feature vector, reconstructing the three-dimensional morphology of the defect, and calculating the defect severity index; establishing a configurable defect weight system, calculating the overall coil quality score, and automatically outputting the quality grade. This invention achieves accurate detection, quantitative evaluation, and refined quality grading of surface defects in cold-rolled strip steel, effectively improving the intelligence and precision of surface quality control of cold-rolled strip steel, and can be widely applied to the online quality inspection process of various cold-rolled strip steel production enterprises.

The invention provides a system and a method for measuring the height of a tiny object, and the system comprises a light source module, and a projection light path of the light source module is provided with a projection slit; the light source module is used for outputting a light strip, the light strip irradiates a tiny object attached to a substrate, and a reflected light beam is formed after the light strip is reflected by the tiny object; the bright field imaging module and the light source module are symmetrically arranged about the normal of the substrate plane, and an imaging light path of the bright field imaging module is provided with an imaging slit; the bright field imaging module is used for collecting the reflected light beam and generating an image according to the reflected light beam; the processing module is used for acquiring the image and calculating the height of the tiny object according to the image; wherein the projection slit and the imaging slit are both rectangular diaphragms, and the length direction of the slits is consistent with the direction of light bars passing through the slits. The measurement system can meet the requirement for measuring the depth of field and improve the measurement precision of the height of a tiny object.

The application provides a kind of adaptive scaling method and system of laboratory multi-gain image detector, belongs to the field of image processing and detector scaling technology, detector has N gain, method includes: respectively in each gain position acquisition dark field image and multilevel radiance bright field image;For each pixel under each gain position, based on the multilevel radiance response data fitted response function collected, gain coefficient and bias term of each pixel under each position are obtained;Select reference gain position, calculate the pixel level equivalent gain ratio and bias compensation of other positions relative to reference position, establish cross-position mapping lookup table;Gain independent correction model is constructed, the original image collected under any gain position is mapped to uniform response reference, and the corrected image is output.The application can realize full-position coverage, independently calibrate each gain position of detector, establish complete pixel level response model, and solve the pain point of re-calibration after multi-position switching.