380 results about "Transmission image" patented technology

The invention discloses a photovoltaic glass defect detection method and system based on image recognition, particularly relates to the technical field of visual inspection, and is used for solving the problem that defect recognition is interfered by optical artifacts caused by a film layer interference effect on the surface of coated glass. The method comprises the following steps: extracting interference characteristics through a reflection image to generate an optical artifact distribution diagram, positioning an interference region in a transmission image frequency domain space, constructing a process response template in combination with a sedimentary pulse frequency, and executing polarization coherence screening and time-varying deconvolution collaborative filtering to eliminate artifacts; based on energy ratio dynamic decision reinspection or defect classification process implementation, inherent optical noise and real physical defects of a material are effectively separated, and the accuracy and reliability of coated glass defect detection are remarkably improved.

The invention discloses a power transmission image compression quality evaluation method based on multichannel fusion, belongs to the technical field of smart power grids, and solves the problem of how to enhance adaptive evaluation performance of image quality in scenes with different compression ratios. A multichannel feature processing module introduces learnable offset to realize dynamic alignment and effective fusion of multichannel features; the multi-scale attention fusion module is combined with multi-scale feature extraction and an attention mechanism, learnable position codes are introduced, and the sensitivity to local structure changes is enhanced while the global perception ability is ensured; the self-adaptive quality evaluation module captures different scale features and local information by constructing residual connection and a multi-branch structure, performs weighted fusion on multi-channel fusion features in combination with a dynamic weight generation mechanism, and realizes accurate judgment of the quality of a complex scene image under different compression levels; while the image compression distortion perception capability is improved, the adaptive evaluation performance of the image quality in scenes with different compression ratios is effectively enhanced.

The invention provides an image data secure transmission method, computing equipment and a computer storage medium. The method is applied to a data sender, and comprises the following steps: executing a first image encryption algorithm, and performing encryption processing on a transmission image through an image key to obtain a ciphertext of the transmission image; executing a first key encryption algorithm, and performing encryption processing on the image key through an encryption key to obtain an encrypted image key; the first image encryption algorithm is different from the first key encryption algorithm; and forming a transmission data packet from the ciphertext, the encryption key and the encrypted image key, and transmitting the transmission data packet to a data receiver. Therefore, a proper image encryption algorithm is adopted for the image data, and a proper key encryption algorithm is adopted for the image key, so that real-time performance and security are both considered in the image data encryption process through a mixed encryption mode.

The invention discloses an optical fiber transmission image recovery method and device based on a complex amplitude regulation metasurface diffraction device, and the method comprises the steps: obtaining the complex amplitude distribution of each diffraction layer through the training of a diffraction neural network, designing a corresponding metasurface array, and preparing a cascaded metasurface diffraction device with a complex amplitude regulation function, deploying a cascade metasurface diffraction device to the far end of the multimode optical fiber and performing complex amplitude modulation on emergent circularly polarized light to realize high-resolution or high-sampling-rate image recovery; or an optical fiber transmission inverse matrix is solved by using an analytical method, and a corresponding metasurface array is designed, so that the single-layer metasurface diffraction device with a complex amplitude regulation and control function is prepared; and deploying the single-layer metasurface diffraction device to the far end of the few-mode optical fiber and carrying out complex amplitude modulation on emergent circularly polarized light to realize low-resolution or low-sampling-rate image recovery. Miniaturization of a multimode optical fiber imaging system can be realized, and the image recovery quality is effectively improved based on complex amplitude modulation of the metasurface diffraction device.

The invention relates to the technical field of machine vision image analysis, in particular to a lubricating oil abrasive particle quality analysis method and system based on machine vision, and the method comprises the steps: obtaining a thickness distribution diagram of an oil residual layer on the surface of an abrasive particle through a gray ratio relation between a first transmission image and a second transmission image; performing optical compensation on the first transmission image to obtain a final compensation image, and performing phase consistency edge detection to obtain an abrasive particle edge enhanced image; calculating the polarization reflectivity ratio of each abrasive particle area; extracting the mirror reflection intensity difference of each abrasive particle in the abrasive particle edge enhanced image; and when the abrasive particles are analyzed as metal attributes according to the polarization reflectivity ratio and the specular reflection intensity difference, identifying the morphological characteristic parameters of the abrasive particles, matching the morphological characteristic parameters with a pre-stored abrasive particle wear characteristic library, and outputting a quality evaluation report of the lubricating oil according to a matching result. The influence of oil film interference is effectively inhibited, the metal particles are accurately distinguished, and high-precision analysis on the lubricating oil abrasive particles is realized.

The invention relates to the field of spectral imaging, in particular to a double-step Fabry-Perot interference snapshot imaging spectrometer, which comprises a telescopic system, a micro lens array, a Fabry-Perot array interference system and an area array detector, and is characterized in that the telescopic system is used for collecting a target light field and carrying out view field limitation and collimation on the target light field; the Fabry-Perot array interference system is used for modulating a target light field into an interference light field array, the Fabry-Perot array interference system comprises two step lenses which are orthogonal in the step direction, the highest steps of the two step lenses are tightly attached, and an air gap with the thickness changing in a checkerboard-shaped two-dimensional increasing mode is formed between the two step lenses; the microlens array is used for imaging the interference light field array onto the area array detector through each imaging channel; and the area array detector is used for receiving the transmission image field of the microlens array to obtain an interference image array. The invention has the advantages of small volume, light weight, compact structure, static state, stability, reliability and the like.

There is provided a method for inspecting still hot glass containers. The method includes, for each container, acquiring at least one transmission image of the container illuminated by a source of a light passing through the container and at least one infrared radiation image of the container. The method also includes analyzing at least one transmission image and at least one infrared radiation image and ensuring a matching of at least part of the transmission image and at least part of the infrared radiation image. The method also includes classifying the container, from at least one transmission image and at least one infrared radiation image, matched with each other, in order to identify, for a container, at least one type of defect.

An X-ray inspection apparatus includes a conveyance unit configured to convey articles, an X-ray irradiation unit configured to irradiate the articles conveyed by the conveyance unit with X-rays, an X-ray detection unit configured to detect X-rays transmitted through the articles, an image generation unit configured to generate an X-ray transmission image based on a detection result by the X-ray detection unit, and a calculation unit configured to calculate, based on the X-ray transmission image, the total amount of the articles conveyed per predetermined time by the conveyance unit.

The invention relates to the field of nuclear waste bin transmission image reconstruction. The invention discloses an SA-ResNeXt-based method for reconstructing a nuclear waste bin detection image of an array detector, which can accurately reconstruct a nuclear waste bin chromatography TGS transmission image under sparse transmission scanning. The method comprises the following steps: S1, performing a simulation experiment on the nuclear waste bin based on Geant4 simulation software to obtain training data, and performing a real experiment to obtain verification data; establishing a database for the training data and the verification data; s2, constructing a ResNeXt neural network model according to the transmission image characteristics of the nuclear waste bin; s3, training data in the database are selected to train the ResNeXt neural network model; an optimized ResNeXt neural network model is obtained; and selecting verification data in the database, inputting the optimized ResNeXt neural network model, and realizing reconstruction of the nuclear waste bin transmission image through the optimized ResNeXt neural network model. By adopting the method, the reconstruction accuracy of the TGS image can be greatly improved, and the reconstruction speed can be improved.

The invention relates to the technical field of wood defect detection, in particular to an X-ray-based sliding plate wood internal defect online detection system and a method thereof.The system comprises an X-ray imaging module, an infrared thermal imaging module, an image preprocessing module, a wood texture trend analysis module, a feature fusion module, a defect detection module and a defect positioning module; the X-ray imaging module and the infrared thermal imaging module collect a transmission image and a thermal image of wood respectively, the image preprocessing module carries out denoising, normalization, background removal and filtering processing on the images, the wood texture trend analysis module extracts wood surface texture trend information, the feature fusion module determines a fusion weight coefficient according to the texture trend information, and the fusion weight coefficient is used for analyzing the wood surface texture trend information. The feature fusion module is used for fusing the features of the X-ray transmission image and the infrared thermal image to generate a fused feature map, the defect detection module is used for carrying out deep learning analysis on the fused feature map to detect internal defects of wood, and the defect positioning module is used for outputting defect position coordinate information.

The invention discloses an unmanned aerial vehicle image semantic transmission and question-answering system and method driven by a large language model, and an image semantic extraction and quantification module carries out the semantic feature extraction of an original image captured by an unmanned aerial vehicle through a semantic encoder, and discretizes a feature vector through a codebook mechanism, and is used for wireless channel transmission. And the image reconstruction module recovers the transmission image from the semantic level according to the received discrete vector corresponding to the codebook shared by the receiving end and the transmitting end. And the image subtitle generation module takes the image recovered by the image reconstruction module as input, and generates text description information by using a BLIP subtitle generation system. And the cue word generation module generates a section of cue word according to the user task description and the text description information output by the image subtitle generation module. And the large language model question-answering module outputs natural language response to guide the next action of the unmanned aerial vehicle according to the cue word. According to the method, the robustness and efficiency of wireless image transmission under the condition of low signal-to-noise ratio are improved, the interpretability of a question answering system is improved, and the method has a certain practical value.

The invention discloses an image defogging method for an extremely complex environment, a medium and a program product, and the method comprises the steps: inputting an obtained real-time degraded image into a pre-trained clear image extraction network, and generating a defogged clear image; the training method of the clear image extraction network comprises the following steps: inputting a historical degraded image into an atmospheric light extraction module to obtain an atmospheric light value; inputting the historical degraded image into a clear image extraction network to obtain a clear image; inputting the historical degraded image into a transmission image extraction network to obtain a transmission image; inputting the obtained clear image, the projection image and the atmospheric light value into an atmospheric scattering model to obtain a synthetic degraded image; and based on a first error between the synthesized degraded image and the historical degraded image and a second error between the clear image and the standard clear image, adjusting parameters of the clear image extraction network and the transmission image extraction network, and completing training of the clear image extraction network and the transmission image extraction network. According to the invention, the image defogging effect can be effectively improved.

The invention provides a lens detection method and system, and the method comprises the steps: sequentially enabling transmission light to penetrate through a to-be-detected lens for imaging based on a plurality of different exposure values, and determining a plurality of candidate images; performing fusion according to the plurality of candidate images to determine a transmission image of the to-be-detected lens; identifying the transmission image to determine a plurality of abnormal pixel points of which the pixel values are smaller than a pixel threshold value; determining a defect area according to all the abnormal pixel points; and determining a detection result of the to-be-detected lens according to the defect area. Through the above detection method, the detection of the lens is more comprehensive, and the detection result is more reliable.

The invention discloses a defect detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a transmission image and a reflection image; respectively inputting the transmission image and the reflection image into an image contour extraction model to obtain contour images of the transmission image and the reflection image; wherein the image contour extraction model is trained by using a plurality of transmission images, reflection images and contour diagrams of the transmission images and the reflection images in advance; matching the generated contour image of the transmission image with the contour image of the reflection image to obtain contour matching coordinate points; matching the transmission image and the reflection image based on the contour matching coordinate points; pixel values of all pixel points on the transmission image and the reflection image are calculated and added to obtain a composite image; and comparing the pixel value of each pixel point on the synthesized image with a threshold value to determine a defect pixel point and a position coordinate thereof.

The invention belongs to the technical field of bridge structure defects, and particularly discloses an underwater bridge structure defect identification method based on machine vision, and the method comprises the steps: firstly, employing a water surface monitoring camera to detect water surface moving objects around a pier, and carrying out the recognition of the underwater bridge structure defects based on the types, distribution density and motion trails of the objects; constructing a static distribution interference factor and a dynamic motion interference factor, and performing weighted fusion to generate a water body detection interference coefficient. Meanwhile, the water turbidity and the real-time flow velocity are obtained by means of an underwater sensor, and the light supplementing distance, the red light proportion and the shutter speed are dynamically adjusted in combination with the water detection interference coefficient. Then, the ROV is controlled to descend with the axis of the pier as the spiral center, visible light and ray transmission images are synchronously collected according to the adjusted parameters, a panoramic image is formed through fusion splicing, finally, defect danger indexes are output through image recognition and fed back, efficient detection and accurate evaluation of the state of the pier are achieved, and reliability and effectiveness of defect recognition are enhanced.

The present invention achieves low-delay image transmission and low-delay remote control by optimally controlling, in accordance with a band, the bit rate of each transmission image from an automatic driving control device to a remote control device. The automatic driving control device calculates an estimated bit rate that corresponds to a band which is available for image transmission to the remote control device, calculates an image priority for each image captured by a plurality of cameras, and transmits only a high-priority image for which low-delay transmission at not more than the estimated bit rate is determined to be possible. A remote support device switches, in accordance with an image received from the automatic driving control device, an image to be displayed on a display unit to one of a camera-captured image, a composite image of the camera-captured image and a 3D CG image, and the 3D CG image, and displays said one image.

The invention discloses a femtosecond laser three-dimensional pumping detection imaging method, which belongs to the technical field of ultrafast laser observation, and particularly comprises the following steps of: generating a laser pulse by using an ultrashort pulse laser, splitting the laser pulse by using a beam splitter to generate two beams of pulse light, namely pumping light and detection light, ablating a material by using the pumping light as an excitation source, reflection or transmission imaging is realized at different moments after the probe light passes through the time delay table; a detection angle is freely adjusted in space around a sample to be detected by rotating the light path propagation system, and a detection mode is switched between a reflection mode and a detection mode by rotating the imaging system; a multi-angle two-dimensional transient image is fused into a three-dimensional graph, plasma and a double-temperature model are expanded, the electronic dynamic characteristics of three-dimensional space distribution and the plasma eruption process can be calculated in an ultrafast scale, and three-dimensional information of a femtosecond laser ablation material is reduced. The problem that an existing imaging method cannot achieve three-dimensional imaging of the femtosecond laser processing ultrafast process at any angle in the space is solved.

The utility model provides a prism and a display device, the prism comprises a first surface, a second surface, a third surface and a fourth surface, the first surface, the second surface and the third surface are connected pairwise, one end of the fourth surface is connected with one end of the second surface, and the other end of the fourth surface extends in a direction far away from the third surface; wherein the image source light enters the first surface from the third surface, is totally reflected to the second surface, is finally totally reflected to the first surface and is transmitted to the eyes of a human body; the real light is transmitted into human eyes through the fourth surface, the second surface and the first surface. The prism is provided with the four surfaces, the first surface and the second surface are used for totally reflecting the light emitted by the image source and the light of the real world, and the third surface and the fourth surface are used for transmitting the light of the image source and the light of the real world, so that the light angle of the light of the image source and the light of the real world entering the prism is corrected. The image imaging effect of the prism is enhanced, so that the display device is smaller and lighter.

An X-ray inspection device includes a conveying unit, an X-ray irradiation unit, an X-ray detection unit, and a control unit configured to inspect whether foreign matter is included in an article based on an X-ray transmission image. The control unit performs a first inspection of using a predetermined threshold value to inspect whether the foreign matter having a lower attenuation rate of X-rays than the article is included in the article, performs a second inspection of using a machine learning algorithm to inspect whether the foreign matter is included inside the article, and determines that the foreign matter is included in the article in a case where the foreign matter common to inspection results of the first inspection and the second inspection is included in the article.

The invention discloses a lightweight copper ore sorting method based on dual-energy X-rays. The lightweight copper ore sorting method comprises the following steps that a dual-energy X-ray transmission graph of copper ore is collected; a CBAL2-Net model is constructed; an improved ResNet-50 model is constructed; taking the CBAL2-Net model as a student model, taking the improved ResNet-50 model as a teacher model, and designing a comprehensive knowledge distillation strategy to perform distillation operation on the student model and the teacher model to obtain a Res-CBAL2-Net model; the collected images are input into a Res-CBAL2-Net model, and the copper ore is sorted; according to the method, based on the constructed student model and the improved teacher model, a comprehensive strategy fusing multiple different distillation strategies is designed to conduct knowledge transfer on the model, the target model Res-CBAL2-Net is obtained, and compared with an existing mainstream model, the accuracy of copper ore separation is greatly improved.

The invention relates to the field of spectral imaging, in particular to a checkerboard Fabry-Perot interference snapshot imaging spectrometer, which comprises a telescopic system, a micro-lens array, a Fabry-Perot array interference system and an area array detector, and is characterized in that the telescopic system is used for collecting a target light field and carrying out view field limitation and collimation on the target light field; the Fabry-Perot array interference system is used for modulating a target light field into an interference light field array and comprises a parallel flat plate and a checkerboard step mirror, the step height is distributed in a checkerboard-shaped two-dimensional decreasing mode, and an air gap with the thickness changing in a two-dimensional increasing mode is formed between the parallel flat plate and the checkerboard step mirror. The thickness of each area of the air gap corresponds to one optical path difference; the microlens array is used for imaging the interference light field array onto the area array detector through each imaging channel; and the area array detector is used for receiving the transmission image field of the microlens array to obtain an interference image array. The invention has the advantages of small volume, light weight, compact structure, static state, stability, reliability and the like.

The invention provides a physical guidance-based sparse coding-driven underwater image enhancement method, a program, equipment and a storage medium. The method comprises the following steps: constructing a physical guidance preprocessing method based on a Jaffe-McGammy model, and adaptively estimating an underwater transmission image and background light to realize preliminary degradation recovery; elastic regularization sparse coding is adopted, and through sparsity and smoothness combined constraint, salient structure information such as edges and textures of the image is effectively extracted, so that the image definition and the detail recovery capability are enhanced; cross-channel attention fusion is adopted, a multi-scale context modeling and channel interaction mechanism is introduced, and a physical degradation graph is combined for guidance, so that color consistency and semantic expression integrity between channels are remarkably improved, and the problems of color shift and information loss in an existing method are solved. According to the method, through joint optimization of multiple loss functions, the constructed underwater image enhancement network keeps the illumination accuracy, texture continuity and structural integrity of the image in multiple dimensions at the same time.

The invention discloses a copper ore preselection method based on a generative adversarial network and low-rank linear pooling. The copper ore preselection method comprises the following steps that a high-energy X-ray transmission image and a low-energy X-ray transmission image of copper ore are obtained; fusing the high-energy X-ray transmission image and the low-energy X-ray transmission image by adopting an improved generative adversarial network to obtain a dual-energy X-ray fusion image; constructing a copper ore pre-selection model; inputting the high-energy, low-energy and dual-energy X-ray fusion images of the copper ore into the model for feature extraction, fusing each extracted feature vector by adopting low-rank trilinear pooling, and then classifying to obtain a pre-selection result of the copper ore; according to the copper ore pre-selection model designed by the invention, through improving low-rank bilinear pooling and using a low-rank trilinear pooling feature fusion strategy, combined representation solution of three image features is realized, multi-modal data input requirements can be met, and the classification performance of copper ore target ore and waste rock is further improved.

The invention relates to a mask defect detection system based on polarization transmission and reflection combination. The system comprises a laser; the first polarization beam splitter is used for carrying out polarization beam splitting on the laser beam to generate P polarized light and S polarized light; the transmission light path is used for performing optical processing and polarization state adjustment on the P polarized light and then projecting the P polarized light to a mask plate; the reflection light path is used for performing optical processing and polarization state adjustment on the S polarized light and then projecting the S polarized light to a mask plate; the imaging light path is used for imaging when the P polarized light is transmitted from the mask plate to obtain a transmission image, and imaging when the S polarized light is reflected from the mask plate to obtain a reflection image; and the storage and operation module is connected with the imaging light path and is used for storing and operating the transmission image and the reflection image so as to analyze whether the mask has defects or not. According to the invention, transmission and reflection dual-polarization light path imaging is adopted, and various mask plate defects can be simultaneously and effectively detected.

An X-ray inspection device includes a transport unit, an X-ray irradiation unit configured to irradiate an article with X-rays, an X-ray detection unit configured to detect the X-rays in each of a plurality of energy bands, an X-ray transmission image generation unit configured to generate a plurality of X-ray transmission images on the basis of the X-rays in each of the plurality of energy bands, and an inspection unit configured to inspect whether or not a foreign matter is present or absent in the article on the basis of a difference image between the plurality of generated X-ray transmission images. The inspection unit detects a first foreign matter having a higher specific gravity than the article using a first threshold value and detects a second foreign matter having a lower specific gravity than the article using a second threshold value different from the first threshold value.

The invention provides a sterile filling process control method and system for midazolam oral liquid nitrogen charging protection, and relates to the technical field of medicine filling process control. After midazolam oral liquid is subjected to nitrogen charging, a headspace gas multispectral image sequence in a bottle before sealing is collected through a transmission imaging system integrated with a filling line; extracting oxygen characteristic absorption wave band light intensity attenuation data through spectrum separation, and generating a bottleneck plane oxygen two-dimensional concentration diagram; calculating the local oxygen partial pressure of the pixel, and constructing a three-dimensional oxygen concentration field and marking an oxygen-enriched area by combining pre-stored geometric parameters of the bottle body; and then the model reference adaptive controller is used for comparing the model with an ideal nitrogen model to generate supplementary parameters containing purging angle, intensity and time, an execution mechanism is driven to perform fixed-point pulse purging, and after verification reaches the standard, a screw cap is used for sealing, so that accurate detection, directional processing and standard verification of the headspace oxygen-enriched area in the midazolam oral liquid bottle can be realized, and the safety of the midazolam oral liquid bottle is ensured. And the oxygen concentration before sealing meets the standard.

The beam limiting device structure comprises a shell assembly, a chopping disc and a driving structure. The shell assembly comprises a front shell and a rear shell, the front shell and the rear shell are oppositely combined to form a cavity, the rear shell is provided with a fan-shaped collimation structure, the fan-shaped collimation structure comprises a transversely formed fan-shaped collimation slit, the front shell is provided with a groove, and the groove is aligned with the fan-shaped collimation slit. The chopping disc is arranged in the cavity, and a plurality of back scattering imaging slits formed in the radial direction and at least one transmission imaging slit formed in the tangential direction are formed in the chopping disc. And the driving structure is in communication connection with the chopping disc to drive the chopping disc to rotate, so that the transmission imaging slits and the fan-shaped collimation slits are matched to form a transmission imaging channel, and the plurality of back scattering imaging slits and the fan-shaped collimation slits are alternately intersected to form a back scattering imaging channel which reciprocates periodically. The double detection requirements for transmission imaging and back scattering imaging can be met at the same time.

An X-ray inspection apparatus includes an X-ray radiator configured to generate X-rays by applying a first voltage between a negative pole and a positive pole in an X-ray bulb and radiate X-rays to a transported article, an X-ray detector configured to detect the X-rays radiated from the X-ray radiator, an inspection unit configured to generate an X-ray transmission image based on a detection result of the X-ray detector and inspect the article, and a control unit configured to change a voltage applied between the negative pole and the positive pole. The control unit applies a second voltage higher than the first voltage between the negative pole and the positive pole before starting radiation of X-rays generated by applying the first voltage or after completing radiation of X-rays generated by applying the first voltage.

An imaging device includes two cameras capturing transmission images of an article from opposite directions, a first light source emitting light that is transmitted through the article in a first direction, and a second light source emitting light that is transmitted through the article in a second direction. The first camera captures a first image that is a transmission image of the article. The second camera captures a second image that is a transmission image of the article. The first half mirror reflects first transmitted light toward the first camera while the second light source is turned off, and permits transmission of light traveling from the second light source toward the article. The second half mirror reflects second transmitted light toward the second camera while the first light source is turned off, and also permits transmission of light traveling from the first light source toward the article.

The invention discloses a method for testing the thickness of a surface oxide layer of micron-sized boron particles, which comprises the following steps of: (1) preparing the micron-sized boron particles, and selecting boron powder particles with the particle size of 100nm-50mu m; (2) preparing a transmission sample of micron-sized boron particles, depositing a Pt protective layer on the surfaces of the particles by using a focused ion beam system before preparing a boron powder transmission sample, protecting an oxidation shell layer on the surfaces of the boron particles, and thinning in a selected area when thinning a slice to ensure the mechanical strength of the slice; and (3) transmission characterization of the micron-sized boron particles: the thickness and measurement error of the oxide layer of the boron particles are calculated by combining transmission images and energy spectrum comprehensive analysis, and the method has the advantages of high sample preparation success rate, high characterization accuracy, high characterization precision and the like.