33 results about "Image contour" patented technology

This application relates to a method, apparatus, processing equipment, and readable storage medium for optimizing processing parameters. The method includes: acquiring a workpiece processing planning position point cloud and a workpiece image contour point cloud under different combinations of processing parameters; determining the processing quality evaluation results under different combinations of processing parameters based on the workpiece processing planning position point cloud and the workpiece image contour point cloud; and determining the optimized processing parameter combination for the workpiece processing process based on the processing quality evaluation results under different combinations of processing parameters and the different processing parameter combinations. This method can effectively adjust processing parameters during workpiece processing, improving upon the problem that traditional processing parameter adjustment relies on engineers' experience and repeated trials, which is time-consuming, labor-intensive, and difficult to guarantee processing efficiency. It can ensure both workpiece processing efficiency and the accuracy and adjustability of the processing process, thereby meeting higher requirements for CNC machining effects.

A method for measuring volume of pomelo based on three view image contour fitting is provided, for measuring the volume of the pomelo based on images, includes: a number of image capturing devices capturing a number of surface images of a pomelo to be measured; calibrating a position of an image capturing device for capturing a top view image of the pomelo to be measured; performing enhanced extraction processing on the number of surface images, and obtaining a standard contour image; obtaining a size of each pomelo slice based on the standard contour image, and obtaining a B-spline curve by fitting a contour of the pomelo slice; and calculating volume of each pomelo slice according to the B-spline curve, and obtaining total volume of the pomelo to be measured by calculating a sum of the volume of all of the pomelo slices.

The application discloses a visual-based contact type measuring robot adaptive measuring point relative guiding method, which comprises a 2D visual-based product image contour matching method, realizes 4-degree-of-freedom measuring point guiding of plane translation, rotation and height scaling, and is suitable for contact type six-axis cooperative measuring robot measuring point guiding measurement of products with local features; the method comprises the following steps: teaching contact type six-axis cooperative measuring robot measuring points of a product to be measured; determining a teaching 2D measuring pose, obtaining a product multi-scale contour image template under the teaching 2D measuring pose and a multi-scale image of the current product, and performing contour matching of corresponding scale levels; based on the contour matching result, calculating a first pose deviation under the teaching 2D measuring pose, transforming the first pose deviation to all teaching point positions of the teaching 2D, performing pose transformation, performing iterative updating on all measuring point positions, and obtaining all updated first measuring point poses. The application better realizes adaptive contact type measuring point measurement of products.

The application discloses a binocular vision and laser radar-based bionic human eye target recognition system and method, which comprises the following steps: S1, collecting and registering synchronous monocular images and laser radar point clouds; S2, extracting image contours and point cloud attributes to generate feature maps and attribute sets; S3, jointly encoding to generate size-distance representations; S4, constructing an improved Ginzburg-Landau phase field energy model based on the representations and attribute sets, obtaining potential function parameters and anisotropy tensors; S5, introducing SE(2) sub-Riemann geodesic direction continuity constraints into a phase field gradient term to adjust the strength; S6, aligning and optimizing evolution of adjacent frame phase fields in time by using optical flow; S7, extracting zero isograms to generate contours and output parameters; S8, inputting the parameters and size-distance representations into a three-dimensional structure program generation module for matching and screening; S9, performing consistency checking and sorting to output a recognition result. The application fuses visual and point cloud features, and improves the recognition accuracy and stability in a complex scene.

The application discloses a method for fitting a circular arc based on feature points and restoring an image contour, which comprises the following steps: identifying each circular arc according to the feature point information of the contour of a target image, and determining the position information of each circular arc; determining the center and the radius of the circular arc according to the initial point, the intermediate point and the terminal point of the circular arc; determining the fitting direction of the circular arc according to the initial point, the intermediate point and the center of the circular arc by using the vector cross product; parameterizing the circular arc, and calculating the range of the corresponding angle of the circular arc according to the fitting direction of the circular arc; fitting the circular arc according to the center, the radius and the range of the corresponding angle of the circular arc; and connecting the remaining straight line feature points after fitting each circular arc, and restoring the contour of the target image. The application can improve the accuracy of the circular arc recognition, thereby improving the circular arc fitting capability, and completing the low data amount restoration of the image contour shape.

The application provides an automatic welding method, device and system for energy storage cabinet processing. The automatic welding method comprises the following steps: obtaining welding plan information of an energy storage cabinet body; generating a first welding instruction based on the welding plan information and sending the first welding instruction to a controller of a welding device to control the welding device to preliminarily weld the energy storage cabinet body, and obtaining two-dimensional image data of each welding area after the preliminary welding is completed, and extracting image contour features from the two-dimensional image data; judging an area that does not meet a target geometric feature threshold as a surface defect area; generating a second welding instruction according to the positions of the surface defect areas and corresponding function area identifiers, and performing repair welding on the surface defect areas of the energy storage cabinet body, and obtaining three-dimensional point cloud data of each welding area after the repair welding is completed and sending the three-dimensional point cloud data to a cloud server. Therefore, the application balances the overall product welding performance and cost by differentiating detection according to function areas, performing real-time repair welding closed loop and cloud three-dimensional analysis.

The application discloses an image recognition method and device, electronic equipment and readable storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring encoding data of a target image, wherein the encoding data of the target image comprises encoding data of a plurality of macroblocks in the target image, the consumed information amount of any macroblock in the plurality of macroblocks during encoding processing is proportional to the texture complexity of the any macroblock, and the texture complexity of the any macroblock is related to the pixel value of each pixel point in the any macroblock; acquiring a contour image corresponding to the target image based on the encoding data of each macroblock, wherein the contour image is used for reflecting the contour of an object in the target image; and performing image recognition processing on the contour image to obtain an image recognition result. Since the encoding data of the target image does not need to be decoded to obtain the target image, a large amount of computing resources can be saved, and the image recognition efficiency is improved.

An image processing method for extracting a target object from an image includes: obtaining, by using an image segmentation model, a first segmentation mask of the target object in a target region covering the image and a segmentation probability map representing a segmentation probability of each pixel in the target region belonging to the target object; detecting, by using a contour detection model, at least one image contour in the target region; determining, for the detected at least one image contour, whether a pixel inside each image contour belongs to the target object based on the segmentation probability map to obtain a second segmentation mask representing pixels belonging to the target object; and extracting the target object based on the first segmentation mask and the second segmentation mask.

This invention relates to the field of medical image processing technology and discloses an image enhancement method for breast imaging diagnosis assistance. The method acquires a raw dataset of breast images, comprehensively covering key information across multiple dimensions, including overall image brightness, image zone texture variability, and image floor interference intensity. Then, a dynamic feature representation system is constructed based on this raw dataset, outputting targeted image optimization and control parameters. These control parameters are used to calculate a real-time image quality factor, and a preset baseline image quality norm and the actual image contour evolution rate are fused to accurately generate an image quality deviation coefficient. A bidirectional correction operation is performed based on the quality deviation coefficient, generating brightness modulation and texture enhancement amounts, thereby effectively enhancing the image. The processed image dataset is fed back to the dynamic feature representation system to iteratively optimize the image optimization and control parameters.

An arrangement for optically capturing a railroad track includes a carrier device, a camera, and two light sources. The arrangement is mountable on a carrier vehicle that is movable on rails. The alignment of the two light sources and thus the central axes of the emitted light radiation or waves enclose an acute angle with a longitudinal axis of the rail. The light sources are coupled with the camera via control signal lines. The triggering or activation of the light sources is effected via the control signal lines by a predefined control signal. This achieves detailed, sharp image contours that allow high-precision image evaluation and object recognition at the highest possible working speed.

The application discloses a photovoltaic product detection method and device, a storage medium and computer equipment, relates to the photovoltaic detection technical field, and mainly aims at improving the detection efficiency and detection accuracy of photovoltaic products. The method comprises the following steps: acquiring a plurality of RGBD images of a to-be-detected photovoltaic product during movement along a production line in real time; performing image decomposition on each RGBD image respectively, and performing image contour extraction on the decomposed RGBD image; determining a line drawing of the to-be-detected photovoltaic product based on the extracted image contour; matching the line drawing with a standard line drawing in a preset photovoltaic product library, and determining a detection result of the to-be-detected photovoltaic product based on the matching result, wherein the preset photovoltaic product library stores standard line drawings corresponding to a plurality of qualified photovoltaic products. The application is suitable for the scene of quality detection of photovoltaic products.

This invention discloses a machine vision-based method and system for detecting laser solder joints on positive and negative electrode connectors of a battery cell. The method includes building a detection platform and acquiring three-dimensional point cloud data and two-dimensional image data of the laser solder joints on the positive and negative electrode connectors of the battery cell; preprocessing the acquired three-dimensional point cloud data and two-dimensional image data; extracting the annular contour and calculating the width parameter of the laser solder joint, and determining the passability of the solder joint annular width by comparing it with a preset standard width range; extracting the depth features of the laser solder joint area and fusing the grayscale features of the two-dimensional image data to comprehensively identify whether there is a weld penetration defect; integrating the annular width detection and weld penetration defect identification results to generate an inspection report. This invention, considering the structural characteristics of the positive and negative electrode connectors of the battery cell and combining the annular distribution characteristics of the laser solder joints, specifically designs a solder joint annular width detection process. Through two-dimensional image contour extraction, circle fitting, and center deviation verification, it achieves accurate measurement of the annular width.

The application relates to the technical field of auxiliary perception, in particular to an auxiliary system and method for perceiving a target, which comprises the following steps: delimiting a haptic perception field; establishing a target object model of a target to be perceived; when the target to be perceived is a two-dimensional structure, forming a target exploration section and acquiring virtual coordinate information; when the target to be perceived is a three-dimensional structure, forming a target exploration shell layer with a preset thickness and acquiring virtual coordinate information; acquiring position information of a haptic perception part of a user; if the position information is located in the range of the target exploration section or the target exploration shell layer, a signal for perceiving the target is fed back to the user; if the position information is located in the range of the target object model except the target exploration section or the target exploration shell layer, a haptic guiding signal is fed back to the user. Through the target exploration section, the target exploration shell layer and the guiding area, the application can ensure the explorability and reduce the phenomenon of haptic form distortion, so that the user can more accurately understand the two-dimensional image contour and the three-dimensional object structure.

This invention relates to the field of multispectral image fusion technology, specifically to an immunochromatographic quantitative algorithm and system based on multispectral image fusion. The algorithm acquires the detection area of ​​an immunochromatographic test strip and a visible light image Im(x,y) of the same detection area. Cross-modal registration is performed between the acquired multispectral signal Sp(λ) and the acquired visible light image Im(x,y). Through image contour recognition and spectral acquisition area calibration, the C and T regions of the test strip are accurately located and matched to obtain the registered target detection areas T and C. Baseline correction and feature extraction are performed on the multispectral signal Sp(λ) of the registered T and C regions to calculate the spectral feature vector Spf. The advantages of this invention are: by fusing multispectral signals and image signals, it compensates for the information limitations of a single modality, and combined with a robust temperature compensation and batch compensation mechanism, it achieves precise quantitative detection at the μg / mL or ng / mL level.

The application provides a scanning electron microscope image contour extraction method, system, medium, program product and terminal based on peak signal relocation. The method obtains corresponding brightness signal distribution on the boundary line of a layout, preliminarily locates the layout according to the brightness signal; obtains corresponding brightness signal distribution on the boundary line of the preliminarily located layout again to perform relocation search to obtain corresponding image edge points, generates a preliminary contour map of the SEM image based on a plurality of image edge points, and performs smoothing processing on the preliminary contour map to obtain a final contour map. The precision interference problem of the layout during scanning electron microscope image contour extraction is effectively solved.

The application discloses an abdominal organ image contour accurate segmentation method and system, and relates to the field of medical image processing.The method comprises the following steps: acquiring an abdominal medical image sequence to be segmented, which comprises CT image data of at least one phase and a corresponding Hounsfield unit matrix; obtaining a region of interest containing a target small organ and a preliminary spatial prior probability graph based on an abdominal organ positioning network; generating a local HU coincidence degree graph through an anatomical focus channel and a boundary response intensity graph through a boundary enhancement channel, and outputting a refined feature graph; inputting the refined feature graph into a main segmentation network; and fusing corresponding level features of a decoder network, performing upsampling and reconstruction, and generating an initial segmentation probability graph of the target small organ; and generating a final segmentation result graph and a comprehensive confidence graph.The application solves the technical problems of insufficient image segmentation accuracy and low confidence in the prior art due to the failure to fully exploit and utilize the inherent physical properties, resulting in ambiguous boundary positioning.

This invention discloses a method, system, and device for estimating the area of ​​the eye muscles and the backfat thickness of live pigs based on deep learning. The method includes: acquiring and constructing a dataset of live pig ultrasound images; selecting regions of interest (ROIs) in the ultrasound images, preprocessing them, and standardizing the input size; inputting the preprocessed ultrasound images into a ReAMS-UNet neural network for semantic segmentation of the eye muscle region; filtering the image contours to remove false positives and false negatives in the segmentation results; determining the upper and lower boundaries of the backfat thickness through image binarization; calculating the eye muscle area and backfat thickness, and outputting the calculation results. Based on a large-scale, highly diverse dataset of pig ultrasound images, this invention utilizes ReAMS-UNet to integrate residual learning for stable training, a hybrid attention mechanism for adaptive feature optimization, multi-scale fusion for contextual and spatial information fusion, and auxiliary supervision for enhanced gradient propagation. It achieves high segmentation accuracy, fast inference speed, accurate trait estimation, and results that reflect true carcass traits. The process is automated and suitable for high-throughput analysis applications.

A ship recognition device according to an embodiment of the present invention includes an image acquisition unit that acquires images captured from the sky, a contour extraction unit that extracts, on the basis of the image, the contour of the ship including a wake thereof, a convex hull creation unit that obtains, on the basis of the image, the convex hull of the ship including a wake thereof, and a movement recognition unit that recognizes the ship on the basis of the contour and the convex hull.

This application provides an evaluation method for curve mask process correction based on SEM image contour extraction. The method includes: acquiring an initial curve pattern and its corresponding standard SEM image contour; constructing a simulation prediction model using a machine learning model based on the initial curve pattern and the standard SEM image contour; obtaining a corrected curve pattern of the initial curve pattern using a curve mask method, and extracting the corrected SEM image contour corresponding to the corrected curve pattern; inputting the corrected curve pattern into the simulation prediction model to generate a corrected simulation image of the corrected curve pattern; calculating the correction difference value between the corrected SEM image contour, the initial curve pattern, and the corrected simulation image; and analyzing the correction difference value to obtain a correction evaluation result. This application can more comprehensively and objectively reflect the contour accuracy and stability after curve mask process correction.

This invention relates to the field of microbial counting technology, and more particularly to a digital clone accurate counting and identification system and method. The method includes the following steps: injecting the bacterial solution to be detected into a preset microchamber array and constructing several partitioned units; placing the microchamber array in a preset constant-temperature incubation environment for parallel cultivation and acquiring chamber image sets for each partitioned unit; segmenting the chamber image sets for each partitioned unit and extracting the corresponding image contours; identifying positive chambers based on the image contours to determine the predicted loading number of single-clone growth chambers; evaluating the relative growth capacity of each positive chamber based on the predicted loading number and the growth kinetic parameter set of each single-clone growth chamber, and identifying the target dominant clone type corresponding to each positive chamber. This application not only improves the screening efficiency and accuracy of probiotics and other microbial research and development, but also significantly enhances the stability, functionality, and safety of microbial products.

This application provides a method for evaluating the fidelity of jadeite carving based on the V-O-I protocol, relating to the field of image processing. The method includes: acquiring a material data package, which includes: a raw stone image, a contour mask, a color-carving mask, a crack mask, a backlit perspective view, and a light-transmitting mask; converting the material data package into knowledge layer constraints based on process rules; mapping the knowledge layer constraints to control handles; generating a design image using at least one generative AI model under the control handles; evaluating the design image based on four quantitative indicators: color utilization rate, contour deviation, consistency of texture, and consistency of intent, obtaining evaluation results; and combining failure mode analysis to perform attribution assessment of the evaluation results. The technical solution of this application provides the first quantifiable and comparable quality benchmark for the application of AIGC in traditional crafts, enabling designers to objectively evaluate and select AI solutions, significantly reducing trial-and-error costs and material risks.

This application proposes an image processing method, apparatus, electronic device, and storage medium. The method includes: acquiring a first color image and a second color image to be processed; wherein the first color image and the second color image are images of the same scene from different angles; extracting image contours from the first color image and the second color image respectively to obtain a first contour map and a second contour map; acquiring a color contour image based on the first color image and the first contour map; calculating the disparity of the region containing the contour based on the color contour image and the second color image, and comparing and verifying the disparity of the region containing the contour with the first contour map and the second contour map to generate a disparity map of the contour; and generating a depth map of the contour based on the disparity map of the contour. This application can solve the problems of existing depth calculations, such as requiring large amounts of computing resources, slow calculation speed, large calculation errors, and poor results.

A vehicle includes an authentication camera provided on an exterior of a body of the vehicle, a vehicle terminal provided on an interior of the body and receiving a user input, an auxiliary display provided on the interior of the body and displaying an review view image, and a processor controlling, upon receipt of a face registration start command for a user, the vehicle terminal to display guide information for a face registration procedure, controlling the auxiliary display to display a guideline and image information acquired by the authentication camera, acquiring outline information of a face image based on the acquired image information, recognizing face information based on the acquired outline information of the face image and location information of the guideline, and registering the recognized face information as the face information of the user.

The application provides a cigar automatic identification and cash register method, system, device and medium, and relates to the technical field of intelligent identification. The method comprises the following steps: acquiring the image, contour, weight information and mutual adjacency relationship and distance of each cigar; extracting brand information and determining the exposed area of the cigar wrapper, dividing the exposed area into adjacent influence sub-areas and independent sub-areas according to the adjacency relationship; acquiring the first color step feature of the independent sub-area and the second color step feature of the adjacent influence sub-area, performing scattering light compensation on the second color step feature according to the adjacency distance, and generating a final color step feature; combining the contour, weight and brand information to determine a candidate model, fusing the first color step feature and the final color step feature to form a color feature, and determining a target model from the candidate model through color matching; and searching for corresponding commodity information and a price according to the target model, and generating a cash register list. The application has the technical effect of meeting the requirements of recognition accuracy in actual cash register applications.

The application provides a scanning electron microscope image contour extraction method, system, medium, program product and terminal based on peak signal relocation. The method obtains corresponding brightness signal distribution on the boundary line of a layout, preliminarily locates the layout according to the brightness signal; obtains corresponding brightness signal distribution on the boundary line of the preliminarily located layout again to perform relocation search to obtain corresponding image edge points, generates a preliminary contour map of the SEM image based on a plurality of image edge points, and performs smoothing processing on the preliminary contour map to obtain a final contour map. The precision interference problem of the layout during scanning electron microscope image contour extraction is effectively solved.