58 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 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 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 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.

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 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.

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.

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 invention relates to the technical field of computer vision and industrial automatic detection, and discloses an equipment-manufacturing-oriented AI vision detection and defect identification method, which solves the problems proposed in the background technology, and comprises the following steps: synchronously acquiring a multi-modal image of a workpiece to be detected through a multi-light-source image acquisition system, and carrying out registration and preprocessing; edge detection is carried out on the preprocessed bright field image, a target contour is extracted, and the tangential gray scale gradient of each pixel point on the target contour is calculated; counting an average value and a variance of the tangential gray scale gradient based on a sliding window, preliminarily screening candidate defect areas according to whether the deviation between the current gradient and a window statistical characteristic exceeds a first preset threshold value, and judging a first type of defects; according to the method, a suspicious region is quickly positioned through a traditional image processing algorithm, fine identification is performed through a deep learning model, and the dependence on a large number of defect samples is reduced.

The invention relates to the technical field of microscopic detection, in particular to a microscopic imaging system with bright field imaging and phase difference imaging, which comprises an imaging module, a bright field imaging illumination module, a focusing module, a phase difference imaging illumination light source module and a control module. The problems that in the prior art, the switching time is long, the definition degree of images is prone to being affected in the switching process, the target form of bright field image and phase difference image shooting is changed, and result contrastive analysis is not facilitated are solved.

This invention relates to the field of image data processing technology, specifically to a method for information fusion between fluorescence images and pathological sections of lymphoma. The method involves acquiring a first image and a second image of a lymphoma tissue sample; the first image is a bright-field image, and the second image is a FISH image. In the first image, the degree of difference between each cell and normal cells, as well as the degree of difference between each tissue boundary and normal tissue boundaries, are analyzed to obtain cell abnormality indices and tissue abnormality indices, respectively. Based on the cell abnormality indices and tissue abnormality indices, a section abnormality index is determined, and the initial block size is adjusted based on the section abnormality index to obtain a target block size. Using the target block size as the block size, a two-stream convolutional network is used to fuse the first image and the second image to obtain a fused image. This invention improves the image fusion effect between FISH images and bright-field images of lymphoma pathological sections.

The application 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 two-dimensional bright field images, two-dimensional dark field images and three-dimensional profile data of code nails to be detected; pre-processing the multi-modal visual data to obtain bright field, dark field and three-dimensional image data suitable for a neural network model; inputting the three kinds of image data into a preset neural network model for defect recognition processing, outputting defect segmentation masks and defect category information; finally, quantitatively analyzing defects based on the output defect information, and determining whether the product is qualified according to engineering specification threshold values. The application can effectively solve the problem of insufficient detection capability for micro, low contrast and three-dimensional geometric defects in the prior art by fusing multi-dimensional and complementary visual information and using a specially designed neural network model for analysis.

The invention discloses a particle printing method, system and device based on fluorescent field and bright field time sequence imaging, and the method comprises the steps: monitoring a micro-fluidic chip sorting region under the condition of continuous illumination of a multi-color fluorescent field, and collecting a fluorescent image of the micro-fluidic chip sorting region in real time; when the target fluorescent particles are recognized in the fluorescent image, bright field illumination is automatically triggered, and a bright field image is collected; carrying out fusion analysis processing on the fluorescence image and the bright field image, and extracting multi-dimensional feature parameters; judging whether the multi-dimensional characteristic parameters meet printing conditions or not according to a preset multi-modal judgment rule; when the multi-dimensional characteristic parameters meet printing conditions, a printing instruction is sent; and in response to the printing instruction, controlling the pressure and motion control unit to drive the printing channel of the micro-fluidic chip to print the target fluorescent particles to the specified hole site of the microwell plate. According to the particle printing technology combining the advantages of fluorescence imaging and bright field imaging, comprehensive feature analysis and high-precision sorting of particles are achieved.

The embodiment of the invention provides a hysteresis effect artifact adaptive correction method and product of an image sensor, and the method comprises the steps: obtaining a first dark field signal and a second dark field signal, the first dark field signal being a reference signal, and the second dark field signal being a current monitoring signal; a target hysteresis effect parameter estimation value is determined according to the second dark field signal and the first dark field signal, and the target hysteresis effect parameter estimation value is used for conducting hysteresis effect compensation on a bright field image signal; and performing hysteresis effect compensation on the bright field image signal according to the target hysteresis effect parameter estimation value. According to the embodiment of the invention, the problem of direct tracking of the hysteresis effect parameter is converted into the problem of monitoring the proportion of the dark field signal which is easy to collect at high frequency, so that the high-frequency and self-adaptive image artifact correction is realized while the correction complexity and cost are remarkably reduced.

This invention provides a fingerprint recognition device, a manufacturing method, and a recognition method thereof. The fingerprint recognition device includes a substrate, an image sensor layer, a pressure-emitting film layer, an encapsulation layer, and a backlight module. The substrate includes a first surface and a second surface disposed opposite to each other. The image sensor layer is located on the first surface of the substrate; the pressure-emitting film layer is located on the side of the image sensor layer facing away from the substrate; the encapsulation layer is located on the side of the pressure-emitting film layer facing away from the image sensor layer; and the backlight module is located on the second surface of the substrate. This invention achieves high-precision fingerprint recognition by utilizing the characteristics of pressure transmission through the encapsulation layer, fluorescence generation in the pressure-emitting film layer under pressure, and the conversion of fluorescence into electrical charge by the image sensor layer, which can then be processed by an external algorithm circuit to obtain bright field image information.

The application provides a spiral phase contrast filter microscopic imaging system for improving AI recognition rate of biological cells, which comprises a light source, a pinhole diaphragm, a microscopic imaging system, a spiral phase plate and a charge coupled device (CCD), wherein the microscopic imaging system comprises a first condenser, a second condenser, a sample stage, an objective lens, a first mirror, a second mirror and a third condenser; the light beam of the light source is gathered after passing through the first condenser and passes through the pinhole diaphragm; the pinhole diaphragm converts the light beam of the light source into a point light source; the light beam of the point light source is parallelly irradiated onto the sample stage after passing through the second condenser; the spiral phase plate is located on the conjugate plane of the point light source emitted by the pinhole diaphragm and is used for performing radial Hilbert transform processing on the image in the frequency domain; the application can obtain an edge-enhanced image in the final imaging, and the application of the image to an AI recognition algorithm can significantly improve the recognition rate; compared with a bright field image, the AI recognition success rate of the application is greatly improved.

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 low-cost universal virtual phase contrast method and device based on a cylindrical lens; the method comprises the following steps: adding a cylindrical lens in a common bright field microscope of a Kohler illumination structure, so that the illumination light source forms asymmetric illumination, and a bright field image is obtained; a strong image carries more phase information; the obtained bright field image is input into a conditional generative adversarial neural network under credibility negative feedback after training, and a virtual phase contrast image is generated, so that the effect equivalent to a standard phase contrast image is realized at low cost. The application not only realizes the effect similar to the standard phase contrast microscope at low cost, but also is superior to the image of the standard phase contrast microscope in some applications (cell segmentation, cell recognition, etc.), and expands the application potential of the application in the fields of biomedicine, material science and the like.

The application provides an online image preprocessing scheme for aluminum plate surface defect detection, which is applied to the technical field of image processing and comprises the following steps: obtaining a stable aluminum plate running speed signal based on an interpolation method and a timing interrupt method; generating a first image based on the running speed signal; performing boundary cutting processing on the first image based on a difference method to obtain a second image containing only aluminum plate images; synthesizing bright field images and dark field images of the second image based on an RGB synthesis technology to generate a third image containing two perspective information; and obtaining an adaptive weight of an MSRCR algorithm based on the information entropy of the third image, and performing image feature enhancement processing on the third image based on the adaptive weight of the MSRCR algorithm to obtain a target image. The image processed by the image preprocessing scheme can remove the interference of defects in the image background and make the image foreground boundary clear.