3661 results about "Multiple image" patented technology

Disclosed herein are system, apparatus, device, method and / or computer program product embodiments, and / or combinations and sub-combinations thereof for blending multiple images of a financial instrument (e.g., check) into a single blended image to mitigate potential image errors. The method generates a confidence score for each of the plurality of images of the financial instrument, selects, based on the confidence score, a number of images of the financial instrument, ranks the number of images, arranging them from a highest to lowest confidence score, and assigns a weighting value, such as transparency, to each image of the selected number of images of the financial instrument, based on a respective ranking. The method builds a blended image by blending pixel content of common pixels, as modified by a respective weighting value, from the number of images and communicates the blended image to a remote deposit server.

The invention relates to an image processing technology, and discloses an efficient panoramic image splicing method and system based on multi-view fusion, and the method comprises the steps: collecting a plurality of images from different views; performing multi-scale feature extraction on each image, generating a feature descriptor for each extracted feature point, and matching a corresponding feature point pair; performing multi-view geometric constraint screening on the feature point pairs; according to the screened feature point pairs, estimating a homography matrix between adjacent images, and carrying out global optimization on the homography matrix; aligning all the images into the same coordinate system; determining an overlapping region between adjacent images; and according to the pixel information in the overlapping areas, fusing the overlapping areas by adopting a self-adaptive weighted fusion algorithm so as to splice the plurality of images into a panoramic image. The invention further discloses a control device and a computer readable storage medium. The invention aims to improve the efficiency and accuracy of generating the multi-view fused panoramic image.

A computer implemented method, system and non-transitory computer-readable device for a remote deposit environment. Upon receiving a user request, based on interactions with the UI, the method implements an electronic deposit of a financial instrument by activating a camera on the client device to generate a live stream of image data of a field of view of at least one camera, wherein the live stream includes imagery of at least a portion of the financial instrument. The method continues by extracting in real-time, based on the formation of byte array objects from the live stream of image data, data fields from a ranked sequence of imagery to be processed by an optical character recognition (OCR) program resident on the client device. The OCR process extracts one or more data fields from of the financial instrument that are communicated to a remote deposit server to complete the electronic deposit.

The invention provides a multi-image forgery detection method and system based on a cross-modal vision large language model, and relates to the technical field of image processing and computer vision, and the method comprises the steps: constructing a data set, and carrying out the preprocessing of the data set; according to the preprocessed data, respectively extracting visual features and language features through a pre-trained visual Transform and a language model so as to obtain cross-modal features; according to the cross-modal features, the visual features and the language features are clustered, cross-modal similarity is calculated, a matching relation is established, fusion is carried out, and fused multi-modal features are obtained; and according to the fused multi-modal features, performing adversarial training through a generator and a discriminator to generate an adversarial network. According to the method, high-precision detection and effective detection of multiple image counterfeiting types such as positioning splicing, copying and pasting, AIGC generation and the like are realized.

The invention relates to the technical field of road engineering detection, in particular to a highway pavement crack image intelligent detection system and method, and the system comprises an image acquisition module, a deep learning module, an image enhancement module, a crack measurement and calculation module, a crack development trend prediction module and an information visualization module. The core innovation of the invention lies in that a differential geometry theory is introduced to construct a crack development trend prediction module, and the module comprises a crack characterization model based on a differential manifold, a multi-scale crack evolution tensor field analysis model and a nonlinear space-time crack development prediction model. A pavement is regarded as a two-dimensional differential manifold, cracks are represented as singular curves on the manifold, a multi-scale tensor field analysis technology and a non-linear kinetic equation are combined, accurate prediction of the future development trend of the cracks is achieved, the system supports multiple image acquisition modes, transverse, longitudinal and net cracks can be accurately detected, and the detection precision is high. The method adapts to complex illumination and background conditions, and predicts the expansion rate and severity change of the crack.

Automated image analysis used in vascular state modeling. Coronary vasculature in particular is modeled in some embodiments. Methods of “virtual revascularization” of a presently stenotic vasculature are described; useful, for example, as a reference in disease state determinations. Structure and uses of a model which relates records comprising acquired images or other structured data to a vascular tree representation are described.

The invention relates to the technical field of artificial intelligence, and provides a video analysis method and device, equipment, a storage medium and a program product. The method comprises the steps of obtaining a target video sequence and a text prompt word of a user; the target video sequence comprises a plurality of images, and each image comprises a to-be-analyzed target selected by a user; performing feature extraction on the target video sequence to obtain visual features of the target video sequence; performing feature extraction on the text cue words to obtain text features of the text cue words; and inputting the visual features and the text features into a pre-trained large language model to obtain a description text of the to-be-analyzed target output by the large language model. Through the above mode, the analysis and description of the specific target in the video can be completed, and the interested content of the user can be focused.

The invention relates to the technical field of machine vision structure health monitoring, and discloses a steel structure weld fatigue cracking real-time monitoring system based on machine vision. The system comprises a space-time registration and fusion module, a multi-scale feature analysis module, a health monitoring module, a crack deduction calculation module and a regulation and control strategy generation module. Performing space-time registration and pixel-level fusion through the visual data of the plurality of image sensors to generate a synchronous multi-source image stream; a multi-level welding seam characteristic spectrum is constructed through multi-scale characteristic analysis, and a welding seam structure knowledge base is dynamically updated; the knowledge base and the real-time characteristic spectrum are used for monitoring the welding seam health state, and abnormity is recognized; deducing a crack initiation position and an evolution path in combination with historical damage data; and real-time load information is fused to pre-estimate the remaining service life, and a structural integrity regulation and control strategy is generated online. According to the invention, high-precision fusion of the multi-source visual data and active prediction of the crack trend are realized, and the monitoring accuracy and the early warning capability are improved.

The invention provides an industrial product defect automatic classification method and system, and the method comprises the steps: collecting original industrial product defect image data, and constructing a labeled image sample set and an unlabeled image sample set; constructing a training image sample set based on the labeled image sample set and the unlabeled image sample set in combination with a plurality of image synthesis strategies; based on the training image sample set, introducing a transfer learning strategy and fusing an attention mechanism, and constructing and optimizing an industrial product defect classification model; performing semi-supervised joint training and online learning based on the training image sample set and the real-time small-batch image sample set; and constructing an industrial product defect identification log based on the real-time image flow sample set, the classification model parameters and the corresponding classification prediction function. On the basis of multi-strategy image enhancement and semi-supervised training, transfer learning and a channel attention mechanism are fused, expansion of industrial product defect image samples and fine defect identification are achieved, and the method is suitable for an intelligent defect detection system in various industrial manufacturing fields.

The invention relates to a crack tracking and predicting method based on point cloud registration, belongs to the technical field of image processing, and solves the problem that an existing three-dimensional point cloud model is low in precision and lacks automatic crack tracking capability. The method comprises the following steps: after preprocessing a plurality of images regularly acquired by an unmanned aerial vehicle, identifying the plurality of images by using a deep learning model to obtain crack positions, and then extracting crack features; performing dynamic blocking and differential feature extraction and matching on the plurality of images, and constructing a point cloud model; mapping the crack position and the crack feature obtained in each period to a point cloud model constructed in a corresponding period, and storing the point cloud models in a point cloud model library according to a time sequence; the point cloud models of every two adjacent periods are registered, and a change area of crack characteristics is analyzed; and predicting the change trend of the crack in the future time according to the environmental data of the time sequence, the crack characteristics and the crack characteristic change rate. And improvement of the accuracy of the point cloud model and automatic tracking of the crack are realized.

The invention provides an electron microscope automatic focusing method and system based on a deep learning model, and relates to the technical field of electron microscope automatic focusing, and the method comprises the steps: collecting a plurality of images at different focusing distances through an electron microscope, and recording the focusing distance of each image; calculating the characteristic value of each collected image, combining the focusing distance and the characteristic value of the image into a characteristic vector, and generating a characteristic sequence according to the characteristic vectors obtained under different focusing distances; training a pre-constructed neural network model by using the feature sequence to obtain a trained neural network model; and inputting a to-be-tested image into the trained neural network model, calculating a difference value between the predicted optimal focusing distance and the focusing distance of the collected image, and judging whether the difference value is within a set range or not. According to the invention, the microscopic image acquisition efficiency and quality are obviously improved.

The invention relates to a multi-focus image fusion method based on multi-layer semantics and multi-scale self-attention, and the method is characterized in that the method comprises the steps: obtaining a source image, inputting the source image into an MSI-Dtrans model, carrying out the feature extraction of the source image through Haar wavelet transform, obtaining the feature information of different scales, and carrying out the fusion of the multi-focus image through the MSI-Dtrans model. Inputting the feature information of different scales into a dynamic Transform for processing, and obtaining an initial focus image; wherein the network architecture of the MSI-Dtrans model adopts a multi-stage up-down sampling structure of a U-shaped network and is obtained through training of a training set, and the training set comprises multiple image pairs generated based on blurred images of different degrees and training labels; and fusing the initial focus image with the source image to obtain a final fused image. According to the invention, image distortion is effectively avoided and a good visual effect is achieved.

The invention belongs to the technical field of image processing, and discloses a multi-image processing method based on multi-modal entity alignment, which comprises the following steps: acquiring a plurality of images; retrieving rich semantic information of the entity from an external knowledge base; selecting the most representative image for each entity in the multi-image scene by using semantic information; encoding the original input of each mode; performing first-layer fusion between a visual mode and a text mode by using cross-divergent attention, then performing second-layer interaction with a structured mode, and finally aligning an entity representation of an image by using contrast loss; and outputting multiple images fusing the text modality and the visual modality. According to the invention, hierarchical interaction fusion is utilized to enhance multi-modal interaction; enhancing entity text representation by integrating the external attribute value and the context information; and the most representative image is selected by using the semantic text, so that the influence of uncorrelated images is minimized.

A method includes obtaining multiple image frames captured using one or more imaging sensors of a video see-through (VST) extended reality (XR) device while a user's head is at a first head pose and depth data associated with the image frames. The method also includes predicting a second head pose of the user's head when rendered images will be displayed. The method further includes projecting at least one of the image frames onto one or more first planes to generate at least one projected image frame. The method also includes transforming the at least one projected image frame from the one or more first planes to one or more second planes corresponding to the second head pose to generate at least one transformed image frame. The method further includes rendering the at least one transformed image frame for presentation on one or more displays of the VST XR device.

The invention relates to the technical field of surface defect detection, and provides an injection molding surface defect detection method for an engineering plastic mold. The method comprises the following steps: transferring an engineering plastic mold to a defect detection area, and acquiring injection molding surface images of the mold by an image acquisition device to obtain a plurality of injection molding surface images; a splicing coordinate system is established, the multiple images are spliced on the splicing coordinate system, and an injection molding surface stereogram is obtained; constructing a defect library, and detecting the stereogram based on the defect library to obtain a defect detection result; mold injection molding constraints are extracted, and when the detection result does not meet the constraints, a maintenance instruction is generated according to the detection result and the injection molding constraints; and based on the maintenance instruction, the mold is transferred to the maintenance area for maintenance. The technical problems that the detection efficiency of the injection molding surface defects of the engineering plastic mold is low, the accuracy rate is insufficient, and subsequent maintenance is not timely are solved, efficient and accurate detection and automatic maintenance processes of the injection molding surface defects are achieved, and the technical effects of improving the mold quality and the production efficiency are achieved.

The invention discloses a surface defect detection method and system based on multi-light source fusion and a related product. The method comprises the following steps: collecting multiple groups of images of a sample to be detected under different light source conditions; marking image defects to obtain a marked data set, and combining the same group of multi-light-source image masks; establishing a multi-light-source fusion segmentation model with multi-image input, multi-feature fusion and single-image output; training the fusion segmentation model based on a multi-light-source data set, and optimizing a training process; the trained model is converted into an acceleration model for production line deployment, and nondestructive, real-time and automatic detection of product surface defects is achieved. According to the method, key information of various defects can be comprehensively captured through the changing light source, and the problems that a traditional industrial quality inspection method is low in efficiency and insufficient in precision are solved.

The embodiment of the invention provides a visual language model training method, an image tag prediction method and electronic equipment. According to the embodiment of the invention, a second visual language model is generated by training a first visual language model by using corresponding coding parameters in an image encoder and a text encoder in a fixed first visual language model and based on initial values and text samples of visual prompts respectively corresponding to various image classification tags; visual prompts respectively corresponding to various image classification labels are mined and learned, and the visual representation capability of a visual language model is enhanced. Further training a target visual language model by training a second visual language model based on learned visual prompts, text prompts and text samples, adjusting adapter parameters of model adapters configured for an image encoder and a text encoder respectively, and performing collaborative optimization on image feature extraction and text feature extraction; the process enables visual knowledge of the visual cue to be transferred to the text cue.

The invention discloses a cradle head tracking method, system and device, a storage medium and a program product, and relates to the technical field of cradle heads, and the method comprises the steps: obtaining the target position information of a tracking target in continuous multi-frame image frames collected by an image sensor, and the size of a detection frame, determining a pan-tilt rotation angle of a target pan-tilt carrying an image sensor when multiple image frames are acquired; determining a target position offset between the target position and the center of the image based on the target position information, and mapping the size of the detection frame into a target distance between the tracking target and the image sensor; inputting the target position offset and the holder rotation angle corresponding to the multiple image frames into a motion estimation model to obtain a predicted position; and determining a pan-tilt angle value of the target pan-tilt based on the predicted position and the target distance, and driving the target pan-tilt to rotate based on the pan-tilt angle value. According to the invention, the cradle head keeps stable tracking while quickly responding to target movement, so that the stability and reliability of cradle head tracking control are improved.

The invention provides a frequency domain Mama multi-scale hyperspectral image classification method and device, and relates to the technical field of hyperspectral image classification. The method comprises the following steps: collecting hyperspectral image data, preprocessing the hyperspectral image data, and segmenting the hyperspectral image data into a plurality of image blocks; inputting the image blocks into a space spectrum interaction feature extraction module, and extracting interaction features through a space branch and a spectrum space fusion branch; inputting the interaction features into a frequency domain disturbance embedding module to obtain features after frequency domain processing; inputting the features after frequency domain processing into an adaptive bidirectional Mama module, and extracting forward and backward spatial features and spectral features; and performing multi-level integration on the spectral features and the spatial features in different stages to obtain global features, and realizing final classification. According to the hyperspectral image classification method, the accuracy and robustness of hyperspectral image classification can be remarkably improved, and higher generalization ability and stability are shown in different data sets and complex scenes.

The invention relates to an intelligent electric meter reading method and system, and the method comprises the steps: enabling a high-definition camera to shoot an intelligent electric meter according to a preset meter reading time interval, obtaining an electric meter image, and uploading the electric meter image to an edge computing device through the Internet of Things; the high-definition camera is installed right in front of a dial plate of the intelligent electric meter. The edge computing device carries out image preprocessing on the electric meter image and transmits the electric meter image after image preprocessing to a server; the server recognizes the received electric meter images by adopting a plurality of image recognition models based on a deep learning algorithm, compares and verifies the electric meter readings obtained by recognition of the plurality of image recognition models, and if the comparison and verification are passed, sends the electric meter readings to the server; if yes, the current ammeter reading of the intelligent ammeter is obtained according to the ammeter reading obtained through identification processing of various image identification models; and the server performs associated storage according to the ammeter number of the intelligent ammeter and the current ammeter reading. According to the invention, the meter reading efficiency can be improved.

The invention provides a passive remote image read-write device and a device adjusting method, and relates to the technical field of remote image optical screens, the device comprises a frame assembly, a hinge, an optical module and a rigid skeleton assembly, the frame assembly comprises a first frame body, a second frame body and a third frame body; the hinge is connected to the frame assembly; the optical module comprises a first lens, a second lens and an imaging panel which are arranged on the frame assembly, a passive mode is adopted, geometric multiple image amplification is carried out on a target reading object through reflection and diffusion of projected light, and the rigid framework assembly is connected to the frame assembly and serves as a stress part for supporting and unfolding. The rigid framework assembly comprises two telescopic framework pieces which are symmetrically arranged on the two sides of the frame assembly. The device integrates multiple functions such as folding, passive technology and far image display, realizes compact folding and portability of the device, has the characteristics of compact structure, convenience in carrying and wide application scene, and meanwhile, ensures the accuracy and high efficiency of amplified image display.

The invention relates to the field of image processing, in particular to a fire-fighting equipment fault automatic detection method and system based on image processing, and the method comprises the steps: collecting a plurality of images in a plurality of regions at the same time interval, and carrying out the graying of the images; pixel points are classified according to gradient distribution of gray level images in the area, and corrosion probability parameters of the area are obtained; obtaining a water leakage probability parameter according to the time sequence change of pixel points in the suspected corrosion area; and comparing the change conditions of the pixel points of the suspected corrosion area and the non-suspected corrosion area to obtain a water leakage correction parameter, obtaining a fault early warning parameter by combining the parameters, setting a threshold value, comparing the threshold value with the fault early warning parameter, judging whether a water leakage condition exists or not, and completing automatic fault detection of the fire-fighting equipment. The method can effectively distinguish environment condensate water interference and real leakage, and has anti-noise capability.

The invention provides an AGV natural scene positioning method and system based on a 3D laser radar, and relates to the technical field of automatic guided vehicle control. The method comprises the following steps: constructing matching sub-graph information, and providing a key reference for subsequent positioning; a visual sensor is used for capturing multiple image data, IMU data and odometer data of the current pose of the AGV are collected in real time at the same time, and the motion state of the AGV is accurately analyzed according to the IMU data and the odometer data. A 3D laser radar obtains scene point cloud data to construct a local map, the local map is registered with a matched sub-graph, initial pose estimation is obtained, finally, the initial pose, a motion state and image data are integrated, final pose information of the AGV is determined through complex operation, multi-source data cooperatively exerts force, and the positioning accuracy and reliability of the AGV in a natural scene are comprehensively improved.

Technology is disclosed herein for part detection and augmented reality integration. A computing device displays in a user interface an image including a part. The computing device detects the part in the image and generates a parameter set based on the detection of the part in the image. In the user interface, the computing device displays an augmented reality depiction of the part overlaying the image based on the parameter set. In some implementations, to detect the part in the image, the computing device uses a neural network which is trained based on multiple images of the part in varying orientations. In some implementations, a second neural network is trained to generate a parameter set relating to the position and orientation based on the detection of the part based on parameter set data corresponding to the multiple training images.

The invention discloses a video data generation method and device and a nonvolatile storage medium. The method comprises the following steps: acquiring initial video data; analyzing an original image in the initial video data to obtain a plurality of image blocks output by the deep learning model and attention maps respectively corresponding to the plurality of image blocks; determining a target attention map of which the attention score meets a first preset condition in the attention map; converting a target image block corresponding to the target attention map into a mask image block; repairing the mask image block by using a second deep learning model to obtain a target image block; and performing fusion processing on the target image block and the original image to obtain a target image, and updating the target image to the initial video data to obtain target video data. According to the method and the device, the technical problem that sufficient training samples of a deep learning model cannot be provided due to the fact that video data cannot be efficiently amplified in related technologies is solved.

The invention belongs to the technical field of Internet of Things information security, and particularly relates to a radio frequency fingerprint identification method based on multi-image feature fusion. According to the method, multiple images are extracted from original IQ data, the limitation of single image features is made up, different basic networks are selected according to different types of image data, the basic networks are optimized, SA-D-ResNet18 and SA-ConvNeXt-T networks are provided, a cross attention mechanism module is introduced between the networks, and image feature information is exchanged. In the final stage of feature extraction, a Concat mode is used to splice and fuse the features of a plurality of images. Therefore, the method can still maintain high recognition accuracy in a more complex environment. According to the invention, a common cross attention mechanism in multiple modes is applied to radio frequency image feature fusion, an image-based classification technology is also applied to the field of radio frequency fingerprint identification, and the radio frequency fingerprint identification method based on multi-image feature fusion is researched.

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 discloses a detection method and device for intelligent visual detection of parts and a storage medium, belongs to the technical field of industrial quality detection, and aims to solve the problems that surface and internal defects of complex parts are difficult to identify synchronously and the identification precision is low. The method comprises the following steps: acquiring multi-modal image data obtained through structured light three-dimensional imaging and laser ultrasonic scanning; performing geometric registration and scale normalization on the image to generate a fused image; carrying out image preprocessing and edge analysis, and extracting a region of interest; dividing the candidate region of interest into a plurality of image blocks, and inputting the image blocks into an anomaly detection network; calculating a reconstruction error between the original image block and the reconstructed image block, and generating an abnormal scoring graph; and finally, extracting a defect area through image post-processing, and outputting information such as a defect type, a spatial position, a geometric dimension and a severity level. According to the method, the robustness and accuracy of multi-modal defect identification are improved, and the method is suitable for an online visual inspection task of an industrial production line.

The invention provides a photoacoustic endoscopic imaging system and method based on polarized light multi-angle rotary scanning, and belongs to the technical field of photoacoustic imaging, the photoacoustic endoscopic imaging system comprises a control system, a light source system, a light path system, an endoscope probe, a data acquisition system and a data reconstruction system, the control system is connected with the light source system and the data acquisition system, and the light path system is connected with the data reconstruction system. The light source system, the light path system and the endoscope probe are sequentially connected, and the data acquisition system is respectively connected with the endoscope probe and the data reconstruction system; the light path system at least comprises a hollow servo motor and a half-wave plate, and the hollow servo motor is used for responding to the time sequence pulse signal and controlling the half-wave plate to rotate by multiple preset angles so as to adjust the polarization direction of the linearly polarized light. The hollow servo motor and the half-wave plate are combined, the polarization direction of light can be rapidly and accurately adjusted, multi-angle scanning is achieved, the imaging speed is remarkably increased, multiple images can be obtained in a shorter time, and the device is suitable for clinical scenes needing real-time feedback.

The present application relates to the technical field of image processing, and discloses a method and apparatus for correcting a label of an image sample, an electronic device, and a storage medium. The method comprises: acquiring multiple image samples having annotation error rates lower than a set value; dividing the multiple image samples into N parts; executing N cycles: using N-1 parts of image samples to perform model training, and using a trained model to predict an unused part of image samples to obtain predicted labels, wherein an unused part of image samples in each cycle is different; and if it is determined on the basis of the number of image samples of which predicted labels are inconsistent with annotated labels that a correction stopping condition is not met, recording the inconsistent image samples to correct the annotated labels of the inconsistent image samples. Thus, image samples needing label correction are found by means of the inconsistency between predicted labels and annotated labels and are corrected, without the need to correct all image samples, so that human resources can be saved, and the correction efficiency can be improved.