287 results about "Edge extraction" patented technology

The invention discloses a weldment welding seam automatic detection method and device based on machine vision, and relates to the technical field of machine vision intelligent detection. The weldment welding seam automatic detection method and device based on machine vision comprises the steps that S1, surface images and forming feature data of a weldment are collected and preprocessed to construct a standardized image feature data set; s2, the boundary clearness of the weld joint is evaluated by combining the edge strength and the contour coherence, and the main contour extraction range is dynamically adjusted; s3, analyzing abnormal focusing characteristics of the candidate area, and adjusting a defect labeling range and a detection priority; and S4, integrating the boundary definition and the abnormal focusing features, analyzing the structure abnormality, and dynamically controlling and verifying a resource allocation strategy. The problems that in the weldment detection process, obvious light reflection and texture blurring phenomena exist in a heat affected area at a weld joint, a traditional image enhancement and edge extraction algorithm is difficult to stably recognize microdefects, and the credibility of a detection result is reduced are solved.

The invention discloses a geological map-oriented breakpoint repairing and closed curve reconstruction method and system and a medium. The method comprises the following steps of: preprocessing an original geological map to obtain a grayscale image; carrying out binarization and morphological closed operation processing to obtain a grayscale image of the edge of the smooth contour curve; performing pixel skeletonization to obtain a pixel-level skeleton diagram; performing secondary edge extraction, connected domain marking and endpoint statistics on the pixel-level skeleton diagram, and screening out a non-closed curve and an endpoint set; carrying out nearest neighbor retrieval by adopting KD-Tree to obtain a candidate pairing set of each end point; performing priority pairing in combination with the spatial distance and the direction smoothness; and generating a transition line segment according to a pairing result to supplement the fracture part of the non-closed curve. According to the method, non-closed breakpoints generated by scanning or drawing errors in the geological map can be automatically restored, and a closed curve with topological integrity and a smooth boundary is generated.

The invention discloses a fan blade clearance intelligent monitoring method based on multi-modal fusion. A laser radar and a visual sensor are adopted to collect point cloud data and image data of the fan blade; environment parameters are collected, validity judgment is conducted on the point cloud data and the image data of the fan blade according to the environment parameters, and radar monitoring data and visual monitoring data are obtained; modeling the fan blade according to the radar monitoring data to obtain a three-dimensional model of the fan blade, and further obtaining a radar measurement value of the blade clearance according to the three-dimensional model of the fan blade; performing image segmentation, edge extraction and depth estimation on the visual monitoring data in sequence to obtain a visual measurement value of the blade clearance; and the radar measurement value and the vision measurement value of the blade clearance are combined, and a multi-modal fusion algorithm is adopted for processing to obtain the fusion clearance distance of the fan blade. The accuracy and real-time performance of fan blade clearance monitoring are remarkably improved, blade collision accidents can be effectively prevented, and reliable guarantee is provided for safe operation of a wind turbine generator.

A video generation framework that is controllable, unsupervised and based on events (CUBE) includes an event camera, which captures changes in light intensity at each pixel of a scene asynchronously and generates event camera data. A text-to-image diffusion model that is conditioned on textual descriptions integrates the event camera data to control video synthesis. Further, an edge extraction module translates event data into a format usable by the text-to-image diffusion model, whereby the diffusion model synthesizes detailed and contextually accurate videos based on textual prompts. Further, an improved system (CUBE Plus) includes a content frame identification module which selectively identifies and uses only the most information-rich event segments of the event camera data to drive cross-frame attention, and an event driven attention mechanism that allows the framework to focus on event-dense moments.

The invention relates to a pavement disease detection method, system and device based on a hybrid architecture, and a storage medium. The method comprises the following steps: obtaining pavement image data; the method comprises the steps that data are input into a re-parameterized feature extraction network, the network is based on an HGNetV2 architecture, a RCHGBlock module is formed by embedding a RepConv structure into HGBlock, and a plurality of modules are cascaded and stacked to construct a four-stage progressive feature pyramid structure; based on a high-level semantic layer of a feature pyramid, integrating a space edge perception enhanced attention mechanism, enhancing disease edge features through a dual-path complementary processing framework of an edge extraction path and a standard convolution path, and performing multi-scale feature fusion by using an improved C3K2-SEAM module as a feature fusion unit; and performing end-to-end disease detection based on the fusion features, and outputting disease types, positions and confidence information. Compared with the prior art, the method has the advantage that the disease detection precision and robustness in a complex scene are remarkably improved.

The invention discloses a machine vision-based automatic identification and calculation method for pore change of a rock section under an SEM (scanning electron microscope), and the method comprises the steps: obtaining original image data of the rock section through a scanning electron microscope, transmitting the original image data to a machine vision SEM pore intelligent quantification cloud platform, and dividing the original image data into a plurality of image sub-regions which are not overlapped with each other; calling a special threshold inversion model to analyze the gray information of each sub-region, and determining a dual-phase pore segmentation threshold; carrying out edge extraction on the sub-regions after threshold processing by adopting a pore edge gradient enhancement algorithm; performing topological structure analysis on the intermediate image data by using a biphase pore topological inversion model, constructing and optimizing a pore space topological network, and eliminating false pore structure data; and according to the optimized pore space topology network, integrating calculation results of all the sub-regions to obtain a pore change identification calculation result of the whole rock section. The method improves the pore identification precision and processing efficiency, and adapts to different types of rock samples.

The invention discloses a semantic segmentation method based on phase contour constraint, and belongs to the technical field of computer vision. The method comprises the following steps of: acquiring a two-dimensional texture image and a deformed stripe image of a scene to be detected in the same view field by using a calibrated camera-projector system; resolving the deformed fringe image through a multi-step phase shift and Gray code technology to obtain absolute phase distribution, and calculating a gradient field; according to a preset sudden change condition, extracting a physical edge contour reflecting the depth change of the object from the gradient field; and mapping the physical edge contour into the two-dimensional texture image based on a pixel coordinate corresponding relation to accurately define a semantic object region, endowing a corresponding category label, and finally generating a semantic label mask image. According to the method, the uncertainty of the visual texture edge is corrected by utilizing the physical phase information, the problem of edge extraction in a complex illumination scene is effectively solved, automatic generation of semantic segmentation data is realized, and the training precision and robustness of a semantic segmentation model are improved.

The invention relates to a fine-grained target real-time image segmentation method and system based on a dynamic state modeling network, and belongs to the technical field of intelligent image processing. The method comprises the following steps: extracting multi-scale detail features by using a lightweight backbone network; through a dual-scale two-dimensional selective scanning module, the features are divided into a thin branch and a thick branch, and local scanning and global scanning are executed respectively; a dynamic cross-scale feature selection and aggregation module is adopted, redundancy is suppressed through reweighting and statistical filtering, and key target responses are highlighted; at a decoding end, local details and global semantics are fused through jump connection and an edge extractor; and finally, introducing a form-guided pseudo label hierarchical supervision strategy, and improving the structure learning ability of the model by using a coarse-to-fine morphological prior. According to the method, the segmentation precision, the boundary integrity and the tiny target recall rate of the fine-grained target under the scenes of ore separation, industrial defect detection, pavement crack recognition and the like are remarkably improved.

The invention belongs to the technical field of computer vision, and discloses a semantic edge guided three-dimensional scene reconstruction method based on an SDF diffusion model. The objective of the invention is to solve the problems of high bandwidth occupation of input data, poor structural consistency and insufficient reconstruction quality in traditional three-dimensional reconstruction. A point fine segmentation and gradient semantic edge extraction method is provided, edge information with consistent semantics and rich geometric details is extracted, and lightweight scene representation retaining key geometric information is realized. On the basis, a three-dimensional reconstruction framework of staged diffusion is proposed: firstly, a global occupancy field is generated to determine an object space range; then executing high-resolution SDF diffusion in the local area to recover a fine geometric surface; and finally, carrying out space alignment and fusion to ensure the consistency of a reconstruction result under a global coordinate system. According to the method, the geometric accuracy, semantic consistency and resource overhead of reconstruction are effectively balanced, and a novel solution is provided for high-quality three-dimensional scene reconstruction under a low-bandwidth condition.

The invention relates to a fire area inversion method based on airborne dual-spectrum detection and depth estimation, and belongs to the field of unmanned aerial vehicle detection. The method comprises the following steps: acquiring a multi-dimensional data set of a dual-spectrum image, a temperature image, an unmanned aerial vehicle attitude and the like; constructing a multi-modal space collaborative perception segmentation network, combining temperature change characteristics with temperature space distribution characteristics of flames to generate temperature region distribution characteristics, and coupling absolute temperature and pixel information to enhance flame weak edge extraction; designing a temperature-guided space structure loss function TSSLoss, and combining gradient change consistency constraint and temperature weight constraint on a segmentation loss function for network training; and according to the unmanned aerial vehicle pose, the target depth and the fire area segmentation pixel area, an early fire area is derived in combination with an airspace transmission inversion formula, and an actual fire area is calculated. According to the method, multi-source information is effectively combined for physical constraint, and more accurate fire detection segmentation and fire area calculation can be realized.

The invention relates to a reconstructed image anti-aliasing processing method based on an adaptive sampling rate, belongs to the technical field of CT (Computed Tomography) reconstructed image processing, and solves the problem that the existing anti-aliasing processing method for a CT reconstructed image is poor in effect. The anti-aliasing processing method for the reconstructed image comprises the following steps: preprocessing the reconstructed image to obtain a to-be-processed image; performing edge extraction on the to-be-processed image based on a preset gradient threshold and a preset Sobel operator, and segmenting the to-be-processed image into a to-be-replaced image region and a reserved image region; determining an adaptive sampling rate based on the horizontal direction edge pixel connection number and the vertical direction edge pixel connection number of all sawtooth vertex pixels in the to-be-processed image; determining a pixel value of each pixel in the to-be-replaced image region based on the adaptive sampling rate and the to-be-processed image, and obtaining a replaced image region; and combining the replaced image area and the reserved image area to obtain an image after anti-aliasing processing. And the anti-aliasing effect of the CT reconstructed image is improved.

A ferrite structure edge extraction method based on a microstructural phase diagram of steel, comprising: performing edge detection on a metallographic image of a low-carbon steel cold rolled sheet; closing grain boundaries; removing redundant boundaries; detecting grain parts of unconnected parts and grain unclosed parts in a labeled image on the basis of a network topology structural diagram, performing grain boundary edge determination, and when the vertex of each unclosed part grain remains unchanged, continuously traversing different grain boundary arcs connected to the unclosed part grain so as to determine whether the unclosed part grain satisfies the characteristics of a completely closed grain, thereby achieving grain reconstruction; and then performing reconstruction detection to finally complete extraction and reconstruction of ferrite structure edges. Thus, ferrite grains of a microstructural phase diagram of steel are accurately reconstructed, two grains connected by a narrow area are effectively segmented, accurate ferrite grains of a low-carbon steel cold rolled sheet can be extracted, and ferrite grain size grading of the low-carbon steel cold rolled sheet is assisted on the basis of the extracted accurate ferrite grains of the low-carbon steel cold rolled sheet.

The invention discloses a star sensor rapid tracking method based on dynamic window blind restoration, and belongs to the field of star sensor algorithms. The method comprises the following steps: estimating a coordinate estimation value of each star in an overlapped view field on a star map at the next moment through a historical star map, and extracting a local window image of a star point corresponding to each star in the overlapped view field; gaussian filtering, top-hat transformation and connected domain processing are carried out on the local window image, star point trailing information is extracted based on a Zernike moment sub-pixel edge extraction method, and a star point area is restored by using a Richardson-Lucy algorithm; then, star point centroids are extracted from the restored image, star points which are tracked successfully are screened out in combination with motion consistency, and initial attitude parameters are calculated through a QUEST method; and finally fusing the star point information newly entering the field of view to obtain attitude parameters of the star sensor under the reference coordinate system. According to the method, the image traversal range is greatly reduced, and the method has important engineering significance.

The invention relates to an abnormal region semantic segmentation method and system guided by a large model in an intelligent power scene, and the method comprises the following steps: obtaining a power scene image set shot at a long distance and a corresponding DSM image set, inputting the power scene image set into an SAM large model, employing a transform codec structure to extract and segment a small target object, and carrying out the segmentation of the small target object; obtaining a mask pattern of the small target abnormal region; inputting the power scene image set X into an edge module, performing multi-scale edge extraction to obtain boundary feature maps of different levels, and further fusing to obtain boundary information; and based on the power scene image set and the DSM image set, adopting a semantic segmentation backbone network to obtain an initial semantic segmentation result, and optimizing the initial semantic segmentation result by utilizing the mask pattern and the boundary information to obtain a final semantic segmentation result. Compared with the prior art, the method has the advantages of high small target attention and the like.

The invention relates to a priori information guided semi-supervised remote sensing image semantic segmentation method and system. The method comprises the following steps: acquiring multi-source remote sensing image data; the multi-source remote sensing image data comprises marked remote sensing image data and unmarked remote sensing image data; inputting the multi-source remote sensing image data into a preset semantic segmentation model to obtain a semantic segmentation result of the multi-source remote sensing data; the semantic segmentation model comprises a prior guidance module and a prior edge extraction module; by adopting the method, the capability of extracting information from unmarked data can be enhanced, a more reliable pseudo tag can be generated, the priori feature guide module adopts symmetric cross attention to combine extracted priori features with semantic features in a more balanced manner, the priori edge extraction module adopts reliable edge priori extracted from the unmarked data, and the accuracy of the pseudo tag is improved. In the training process, the feature map is guided to obtain a more accurate segmentation boundary, and the reliability of boundary information in unmarked data is enhanced.

The application relates to the field of machine vision and image recognition, and discloses a high-precision edge extraction method based on image automatic processing, which comprises the following steps: a standardized image system is constructed, and an initial standardized wood template image is acquired through the standardized image system; the initial standardized wood template image is subjected to multimodal fusion pretreatment; an Otsu algorithm is used to determine a high threshold value and a low threshold value, an initial edge image and an edge gradient image are generated after edge detection of a binary image; then, the initial edge image is input into a pre-trained lightweight adaptive U-Net model, and an edge probability image is output; the edge probability image is sequentially subjected to morphological opening operation denoising processing, B-spline curve smoothing fitting processing and coordinate system calibration processing, and wood template edge coordinates are obtained; the average error of the wood template edge coordinates and standard template edge coordinates is calculated. The application realizes accurate conversion of wood template edge from an image to actual physical coordinates.

The invention discloses a vector vortex super lens for directional selective edge detection and an imaging system with the vector vortex super lens, and the vector vortex super lens comprises a substrate and a nano-structure unit on the substrate. The nano-structure units are arranged on the substrate according to specific phase distribution to form a nano-structure unit array; x-line polarized light carrying sample information passes through the vector vortex super lens to generate left-handed and right-handed emergent light, the two paths of emergent light are superposed to obtain an edge image carrying polarization information, and a vector edge detection function is realized. The vector vortex super lens provided by the invention has the edge extraction capability of dynamic adjustment as required, and can realize real-time directional edge detection only by rotating the polarization analyzer without other hardware modification or digital post-processing.

The invention relates to the technical field of image processing, in particular to an insulator image enhancement method based on unmanned aerial vehicle infrared image denoising. The method comprises the following steps: preprocessing an original infrared image acquired by an unmanned aerial vehicle, and performing multi-scale decomposition on the preprocessed image by using wavelet transform to obtain a high-frequency detail coefficient and a low-frequency approximation coefficient; a high-frequency detail coefficient is processed by adopting an adaptive threshold value, Wiener filtering is carried out on a low-frequency approximation coefficient, and a de-noised image is obtained after wavelet reconstruction and guide filtering processing; based on the de-noised image, an edge detection operator is adopted to perform preliminary edge extraction, non-maximum suppression and dual-threshold processing are combined to obtain edge information, and a morphological edge reconstruction technology is adopted to connect edge gaps; and generating a final image after feature enhancement through adaptive contrast enhancement based on local temperature distribution and image fusion processing. According to the invention, efficient denoising and accurate feature enhancement of the insulator infrared image collected by the unmanned aerial vehicle can be realized.

The invention discloses an unmanned aerial vehicle visual autonomous docking and locking control system based on deep learning, and the system comprises the following modules: an image collection and light field enhancement module which is used for constructing a light field interference enhancement image and generating an interference significance mask image; the structure edge extraction module is used for outputting a structure dynamic edge response diagram based on the improved VMama model; the path correction module is used for extracting a cone contour tracking point set, calculating a time sequence displacement vector by adopting a Lucas-Kanade optical flow algorithm, and generating a landing path correction amount; the locking groove positioning module is used for determining the central position of the locking groove; the insertion path construction module is used for outputting an insertion path selection result; the locking state detection module is used for determining a locking state; and the docking judgment module is used for outputting a docking judgment result. According to the invention, the improved VMama model and multi-modal texture positioning are fused, and autonomous docking and locking control of the unmanned aerial vehicle is realized.

The invention relates to the technical field of on-line detection of the diameter of a green pellet, in particular to a method and device for determining the diameter of the green pellet, electronic equipment and a storage medium. Then extracting edges in the first image through an edge extraction operator, and refining according to a plurality of first edges obtained through extraction to obtain a plurality of second edges; a plurality of first green pellets are identified from the second edges in a circle center positioning mode, and the first diameter of each first green pellet is extracted; according to the method, the images of the green balls in the ball disc are obtained through snapshot, then the edges of the green balls are extracted through the edge extraction method, and finally, the statistical data are generated according to the diameters of the green balls, so that the statistical data are reliable, and the statistical data are more accurate. Online statistics of the diameter distribution condition of the green pellets is realized, and the production process quality of the green pellets is reflected from data.

The invention provides a building extraction method, system and device based on multi-source remote sensing data fusion. The method comprises the steps that original satellite hyperspectral image data of a to-be-detected target area is acquired and preprocessed; constructing a multi-scale collaborative observation system combining a satellite hyperspectral image and an unmanned aerial vehicle high-resolution image based on the preprocessed hyperspectral satellite image, and extracting a building candidate area; obtaining unmanned aerial vehicle image data based on the coordinate data of the building candidate area; performing data fusion and sub-pixel positioning optimization based on the unmanned aerial vehicle image data to generate a hyperspectral fusion image; and performing target positioning and edge extraction on the hyperspectral fusion image based on the boundary refinement model to obtain an extracted building area. According to the method, the problems of contradiction between the coverage range and the spatial resolution, fuzzy shielding scene edge, insufficient multi-dimensional data utilization rate and the like of hyperspectral building extraction are solved.

The invention discloses a star point motion parameter estimation method for a high-dynamic star sensor. The method specifically comprises the following steps: (1) acquiring a star map under a dynamic condition through a fixed star sensor; (2) carrying out filtering preprocessing on the fixed star sensor image obtained in the step (1); (3) carrying out threshold segmentation on the image processed in the step (2) and carrying out connected domain extraction to obtain rough star points; (4) selecting the brightest star point in the star points obtained in the step (3); (5) obtaining a sub-pixel star point track by using the brightest star point adjacent area obtained in the step (4) and adopting a Zernike moment sub-pixel edge extraction method; and (6) utilizing the sub-pixel star point trajectory obtained in the step (5), and adopting least square fitting to obtain star point motion parameters. The method has the beneficial effects that the precision of star point trailing length and angle estimation is improved, so that the extraction precision of star points in a dynamic environment is improved, and the precision of a fixed star sensor is improved.

The invention relates to the technical field of machine vision and image recognition, and discloses a high-precision edge extraction method based on automatic image processing, which comprises the following steps: constructing a standardized image system, and obtaining an initial standardized wood template image through the standardized image system; carrying out multi-modal fusion preprocessing on the initial standardized wood template image; determining a high threshold value and a low threshold value by adopting an Otsu algorithm, and generating an initial edge image and an edge gradient map after carrying out edge detection on the binarized image; inputting the initial edge image into a pre-trained lightweight adaptive U-Net model, and outputting an edge probability graph; performing morphological opening denoising processing, B-spline curve smooth fitting processing and coordinate system calibration processing on the edge probability graph in sequence to obtain wood template edge coordinates; and calculating an average error between the edge coordinates of the wood template and the edge coordinates of the standard template. According to the method, accurate conversion of the wood template edge from the image to the actual physical coordinate is realized.

The invention discloses a rapid visual measurement system and method for the boundary dimension of a supporting cylinder, and relates to the technical field of visual measurement, the measurement system comprises a tool positioning assembly, a visual measurement assembly and an image processing assembly, the tool positioning assembly comprises a positioning platform, a first support and a second support which are connected, the first bracket and the second bracket are respectively positioned above and on the side of the positioning platform; the vision measurement assembly comprises a first camera and a second camera, and the first camera and the second camera are arranged on the first support and the second support respectively; the image processing assembly comprises a main controller, and a sub-pixel edge extraction module, a size calculation module, a data management module and a human-computer interaction interface which are connected with the main controller; and the main controller is connected with the first camera and the second camera. According to the invention, the image processing assembly can automatically calculate and record the measurement result of the support cylinder through the sub-pixel edge extraction module and the size calculation module, and generates a report, thereby simplifying the operation process, and improving the measurement efficiency and precision.

The invention belongs to the technical field of automatic dense storage, and particularly relates to a goods allocation positioning method based on multi-sensor fusion, which comprises the following specific steps of: starting an equipment main power supply, and finishing initialized communication by a controller; line laser continuous scanning is carried out on a tray through a laser sensor, complete three-dimensional point cloud data are obtained, all contour features from a standard tray to a special-shaped and customized tray can be covered, the point cloud data are preprocessed, a contour fitting algorithm is called to extract edge features, the actual size of the tray is directly calculated, and the accuracy of the actual size of the tray is improved. Precise identification of trays of multiple sizes is realized, limitation of fixed threshold detection of a photoelectric sensor is broken through, an actually measured size is compared with a preset standard size, and even if the size of the tray exceeds a preset range, an actual contour of the tray can be determined through edge extraction of point cloud data. And misjudgment caused by exceeding the detection range of a single photoelectric sensor is avoided.

The present application relates to the technical field of image processing, in particular to an insulator image enhancement method based on infrared image denoising of a UAV. The original infrared image collected by the UAV is preprocessed, and the preprocessed image is decomposed in multiple scales by wavelet transform to obtain high-frequency detail coefficients and low-frequency approximation coefficients; the high-frequency detail coefficients are processed by adaptive thresholding, while the low-frequency approximation coefficients are subjected to Wiener filtering, and after wavelet reconstruction and guided filtering, a denoised image is obtained; based on the denoised image, an edge detection operator is used for preliminary edge extraction, edge information is obtained by combining non-maximum suppression and double thresholding, and the edge gap is connected by using morphological edge reconstruction technology; through adaptive contrast enhancement based on local temperature distribution and image fusion processing, the final image with enhanced features is generated. The present application can realize efficient denoising and accurate feature enhancement of the insulator infrared image collected by the UAV.

An uneven region is extracted with high precision from a captured image obtained by capturing an image of a dyed knitted fabric, and the dyeing quality of the knitted fabric is evaluated. An edge in a captured image of a captured knitted fabric is detected, a high-contrast region in which the gradient of the edge (11) is equal to or greater than a first predetermined value is extracted, and a non-uniform candidate region serving as a candidate for a non-uniform region is extracted from the high-contrast region (steps S105-S107). On the other hand, in the captured image, a plurality of highly similar regions having high similarities with the sample image of the trunk are extracted, information on the positions of representative points of the trunk corresponding to each of the highly similar regions is acquired, and information on the positions of the trunk is acquired on the basis of the information on the positions of the representative points (steps S108-S110). Afterwards, among the non-uniform candidate regions, regions that extend continuously in the course direction across a predetermined number or more of trunks are extracted as non-uniform regions (step S111), and the dyeing quality of the knitted fabric is evaluated on the basis of the extracted non-uniform regions (step S112).

This application provides a method and apparatus for three-dimensional surface reconstruction of medical images based on diffusion least squares, belonging to the field of medical image processing. The method includes: edge extraction based on a binary segmentation mask of a three-dimensional image to determine multiple edge voxels of the three-dimensional image; based on the edge voxels, selecting multiple sampling voxels from the voxels of the three-dimensional image; performing least squares fitting on multiple local coordinate data of the multiple sampling voxels to determine multiple fitting parameter values ​​and calculating the corresponding residual values; if the residual value is greater than the fitting error threshold, determining the global coordinate data of the edge voxels through data mapping based on the multiple fitting parameter values; and obtaining a three-dimensional surface mesh through Poisson surface reconstruction and mesh iterative deformation based on the multiple global coordinate data.

The invention provides a cloth main texture angle extraction method and system, a medium and a terminal. The method comprises the following steps: acquiring a to-be-detected cloth image; preprocessing the image of the cloth to be detected; performing edge extraction on the preprocessed cloth image to obtain an edge image; screening candidate straight line segments based on the edge image; scoring the candidate straight line segments based on a distance change scoring algorithm, and selecting the candidate straight line segment with the highest score as a target straight line segment; and calculating a main texture angle of the to-be-measured cloth based on the target straight line segment. According to the cloth main texture angle extraction method and system, the medium and the terminal, the cloth main texture angle can be stably and accurately extracted under a complex background.

A computer-implemented, in particular user-guided, method for selecting a photographic image (F) for use in production control, wherein the method comprises the following steps: a) Receiving from a multitude of input images (E1,...,En) specifying an object to be captured (30) in a multitude of lighting settings, wherein the lighting settings are specified by different configurations of an RGB-W lighting unit (20) and include a white image (E0); b) Selecting at least one candidate recording (K1,...,Km) from the initial recordings (E1,...,En) based on a first selection criterion; c) Defining a template image section (A0) within the white image (E0); d) Generating at least one target image section (A1,...,Am) in the at least one candidate image (K1,...,Km) that corresponds to the template image section (A0); e) Applying at least one image processing algorithm, in particular contour recognition, blob analysis, region analysis, code analysis or model matching, with a first set of parameters and / or parameter values ​​to the at least one target image section (A1,...,Am) to generate processed candidate images (K'1,...,K'm); f) Selecting at least one preselection recording (V1,...,Vk) from the set of processed candidate recordings (K'1,...,K'm) based on a second selection criterion; g) Check whether a pre-selection recording (V1,...,Vk) exists that meets a final screening criterion and, if so, select such a pre-selection recording (V1,...,Vk) as the final recording (F); otherwise h) Repeating steps e) to g), wherein the at least one preselection recording (V1,...,Vk) is used as the at least one candidate recording (K1,...,Km) and in step e) a second set of parameters and / or parameter values, in particular specified by a user, is used;wherein at least one of the selection criteria depends on an evaluation result of at least one image analysis algorithm, namely contour recognition, wherein a collection of reference images is used for the evaluation of the at least one selection criterion, wherein contours are extracted from object edges of the reference images during contour recognition and stored as reference contours, which are searched for in the multitude of input images, wherein the method further comprises calculating a value that indicates a match with a reference contour and wherein, if the value exceeds a threshold, the area under consideration is regarded as a match, wherein an image is rated as good if a predefined number of matches are found and wherein the image is selected as at least one candidate image if the image is rated as good.