65 results about "Local color" patented technology

The invention discloses an image registration and multi-resolution fusion-based panoramic image splicing method. An adaptive threshold of sequence images is subjected to binary processing and image contour information is extracted by utilizing a pixel neighborhood relationship; a similar region of an image contour structure is quickly estimated through a similarity measurement method for Hu momentinvariant features; and SIFT feature point extraction is performed in a similar region part of two original images. Moreover, feature point initial matching is performed by using a bidirectional K-nearest classification algorithm; mismatched points are screened by an RANSAC algorithm; and an affine transformation matrix among the images is estimated. In addition, in an image fusion aspect, brightness equalization and local color mapping processing is adopted. Then, through an improved Laplacian pyramid multi-resolution fusion algorithm, spliced images are fused to realize seamless splicing. According to the method, the image splicing time is shortened, the image splicing efficiency is improved, the similar region can be quickly located, the mismatch in splicing is effectively improved, and the image registration precision is improved.

The invention discloses a method for automatically tagging animation scenes for matching through comprehensively utilizing an overall color feature and local invariant features, which aims to improve the tagging accuracy and tagging speed of animation scenes through comprehensively utilizing overall color features and color-invariant-based local invariant features. The technical scheme is as follows: preprocessing a target image (namely, an image to be tagged), calculating an overall color similarity between the target image and images in an animation scene image library, and carrying out color feature filtering on the obtained result; after color feature filtering, extracting a matching image result and the colored scale invariant feature transform (CSIFT) feature of the target image, and calculating an overall color similarity and local color similarities between the matching image result and the CSIFT feature; fusing the overall color similarity and the local color similarities so as to obtain a final total similarity; and carrying out text processing and combination on the tagging information of the images in the matching result so as to obtain the final tagging information of the target image. By using the method provided by the invention, the matching accuracy and matching speed of an animation scene can be improved.

The invention discloses an image sorting method based on local colors and distribution characteristics of characteristic points, which mainly solves the problem of the poor effectiveness of image characteristic description and the ambiguity in image understanding in the prior art. The method comprises the following steps of: firstly, performing scale normalization and rotation normalization on the image, and detecting characteristic points; then, dividing the normalized image into a series of fan-shaped sub-regions with unequal acreage according to the distribution of the characteristic points, and extracting the local colors and the space distribution characteristics of the characteristic points in each sub-region, generating a characteristic vector, measuring the similarity and orderingthe sub-regions; taking the image as a multi-instance package to obtaining characteristics of a target image through a multi-instance learning method; and finally, recalculating the similarity, and outputting the sorting result. The method not only improves the effectiveness of the image characteristic description, but also reduces the ambiguity in the process of sorting out the images, so that the method can sort out internet images more accurately, and can be used for searching image information in the internet.

The invention discloses a method and a system for controlling a local color gamut, a backlight source and a display device. The method comprises the steps of receiving an image signal of a frame to be displayed; resolving the image signal to obtain a high-color-gamut region in the frame to be displayed, wherein a color-gamut value of the high-color-gamut region exceeds a preset range; controlling different regions of the backlight source according to the high-color-gamut region. In the method, the image signal to be displayed is analyzed and divided into a high-color-gamut region and a low-color-gamut region according to the color-gamut value, the high-color-gamut region is obtained according to an analysis result, control of different regions of the backlight source is achieved, and only a low-color-rendering LED lamp is required to be lightened on in several regions in which high-color-gamut images are not required to be displayed. Therefore, the power consumption of the backlight source can be reduced while the frame quality is ensured, and the energy-saving purpose is achieved. The invention further provides the system for controlling the local color gamut based on the method, the backlight source and the display device including the backlight source. Energy saving is achieved.

A method for designing a mask for fabricating an integrated circuit is provided wherein a mask layout that requires coloring, such as for alternating phase shift, double-exposure and double-exposure-etch masks, is organized into uncolored hierarchical design units. Prior to modification by OPC, each hierarchical design unit is locally colored. OPC is then performed on the locally colored hierarchical design unit. The local coloring information for the hierarchically arranged OPC-modified design unit may be discarded. After OPC modification, the uncolored OPC-modified design units may be placed within the mask layout, and the flattened data may be colored. Thus, turnaround time for mask design is significantly improved since the numerically intensive OPC is performed on the hierarchical data, avoiding the need to perform OPC on flattened data, whereas the less intensive global coloring is performed on flattened data.

The invention relates to a specified adaptive illumination migration method and system in a cross-camera scene, and the method comprises the steps: carrying out the close image clustering of a targetimage and a source image according to a fuzzy clustering algorithm, carrying out the local color brightness migration between clustered images, and introducing a membership factor to improve the colorbrightness migration effect. According to the invention, the illumination difference of images under different cameras is weakened, and the adverse effect caused by the illumination difference is reduced.

The invention discloses a point cloud registration method and device based on multi-feature fusion and a storage medium. The method comprises the following steps: respectively extracting a plurality of source point cloud feature points and a plurality of target point cloud feature points from a source point cloud and a target point cloud; extracting a local depth feature, a normal angle feature, apoint cloud density feature and a local color feature of each feature point, and then generating a feature descriptor corresponding to each feature point according to the local depth feature, the normal angle feature, the point cloud density feature and the local color feature of each feature point, wherein the feature points comprise source point cloud feature points and target point cloud feature points; pairing the source point cloud feature points with the target point cloud feature points according to the feature descriptors to generate feature point pairs; and generating a transformation matrix according to the feature point pairs, transforming the source point cloud according to the transformation matrix to generate a second source point cloud, and performing fine registration on the second source point cloud and the target point cloud. By implementing the embodiment of the invention, the expression capability of the feature descriptor can be improved, so that the overall registration precision is improved.

A method for printing an object using a color image printer is provided. The printer applies colorant dots having a flat shape. The object has an apparent surface with a locally varying color for representing a color image on the surface. The printer comprises a white colorant, that is applied as a background underneath a surface colorant for begetting a local color of the apparent surface. The invented method comprises the steps of: generating two-dimensional image data for composing the object in slices; determining a local surface orientation of the apparent surface of the object; and applying colorant material in accordance with the two-dimensional image data, wherein, in dependence on the local surface orientation, white colorant dots are deposited between other colorant dots to compensate a color effect of an orientation of a surface colorant dot relative to the local surface orientation.

The invention discloses a non-repetition multispectral / hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering, and relates to a multispectral / hyperspectral remote sensing image color uniformizing method. The objective of the invention is to solve the problem of poor effect of an obtained image due to the fact that color uniformization between images without overlapping regions is not involved in an existing method. The method comprises the following steps: 1, carrying out band-dividing processing on a multi-spectral / hyperspectral remote sensing image; 2, selecting a reference image as a reference; 3, obtaining a result after clustering; 4, performing category matching; 5, obtaining various types of data after local color uniformization processing; 6, synthesizing a new to-be-homogenized image; 7, carrying out the histogram matching, and carrying out the color uniformization; 8, repeatedly executing the steps 3-7 by taking theimage subjected to the color uniformization processing as a reference image until all grayscale images in the same waveband are subjected to color uniformization processing, and splicing the images; 9, repeating the steps 2 to 8 to obtain all spliced images, and synthesizing a new multispectral / hyperspectral remote sensing image. The method is applied to the field of image color uniformization.

The invention discloses a multi-high-resolution remote sensing image mosaic method considering surface feature category difference. The method comprises the steps of performing geometric registrationand overlapping region coordinate determination on high-resolution images; performing color uniformization on the whole input image by using a histogram matching method by adopting an integral and local color matching strategy, and further performing local color uniformization on different ground objects by using a moment matching method; generating an initial seam line network by utilizing the Voronoi diagram; endowing different ground objects in the overlapping area with different weights, searching for a path with the minimum total weight in the buffer area based on a dynamic planning method, and taking the path as an optimized seam line network; and eliminating splicing seams by using an inverse distance weighted image fusion algorithm to obtain a final mosaic image. According to the method, the tone consistency of the mosaic image on the whole can be ensured, the local chromatic aberration can be remarkably weakened, the joint line network bypassing the building can be automatically generated, the error accumulation of searching the joint lines one by one is effectively avoided, and the mosaic image with visual nature is quickly obtained.

A system and method enable similarity measures to be computed between pairs of images and between a color name and an image in a common feature space. Reference image representations are generated by embedding color name descriptors for each reference image in the common feature space. Color name representations for different color names are generated by embedding synthesized color name descriptors in the common feature space. For a query including a color name, a similarity is computed between its color name representation and one or more of the reference image representations. For a query which includes a query image, a similarity is computed between a representation of the query image and one or more of reference image representations. The method also enables combined queries which include both a query image and a color name to be performed. One or more retrieved reference images, or information based thereon, is then output.

The invention provides a color correction method for jointly optimizing global and local color consistency. The color correction method mainly comprises the following steps of: step 1, carrying out super-pixel segmentation on an image; step 2, constructing a color correction model, namely for different superpixel parts in one image, modeling a mapping function by applying different linear models;step 3, optimizing model parameters, specifically, designing an energy function considering color consistency and gradient maintenance at the same time based on the model, and additionally fusing global color constraints to ensure that the corrected image has similar global hue; and finally, performing color correction on each part in the image according to a super-pixel segmentation result so asto realize generation of the large-scale synthetic image with color consistency. According to the color correction method, on the basis of global optimization, a local optimization model is provided based on superpixel segmentation, so that a color correction algorithm can effectively eliminate global and local color differences among a plurality of images, and the image gradient is reserved as much as possible.

The embodiment of the disclosure relates to local color range selection. Techniques of editing images using a digital image editing tool involve defining a local adjustment that includes, as separatemasks, a spatial mask and a range mask. The spatial mask specifies a region of the image to be adjusted and the range mask specifies ranges of colors and tones to be adjusted independent of the regionspecified by the spatial mask. In applying these masks, when a user changes a setting in the digital image editing tool, the digital image editing tool weights the effect of the setting according tothe values of the spatial mask and the range mask for each pixel of the image.

An embodiment of the invention provides an image fusion method, an image fusion device, a storage medium and computer equipment. The image fusion method comprises the following steps of: acquiring a visible light image and a near-infrared light image from image acquisition equipment; performing color correction processing on the visible light image according to brightness information of the near-infrared light image to obtain a corrected visible light image; and fusing the corrected visible light image and the near-infrared light image to generate a fused image. In the image fusion method of the embodiment of the invention, color correction processing is carried out on the visible light image through the brightness information of the near-infrared light image to obtain the corrected visible light image; the corrected visible light image and the near-infrared light image are fused to generate the fused image, and color cast in the generated fused image is removed due to color correctionon the visible light image, so that the problem of local color cast of the image is solved.

Provided are a color moire reducing method, a color moire reducing apparatus, and an image processing apparatus. The color moire reducing method includes calculating a plurality of local color mean values around a pixel in a selected region of a current image, calculating difference values between the local color mean values and a maximum difference value from among the difference values, and setting a moire correction weight to the pixel on the basis of the maximum difference value.

The invention relates to the technical field of image processing, in particular to a self-adaptive adjustment method for the angle of a cleaning brush of a sweeper, which comprises the following steps of: acquiring a plurality of frames of pavement images, dividing the images into a plurality of image areas, acquiring Lab color differences of pixel points of the image areas, acquiring local color abnormity degree and overall color abnormity degree according to the Lab color differences, and adjusting the angle of the cleaning brush of the sweeper. Obtaining attention according to the local color anomaly degree and the overall color anomaly degree, determining an initial seed point according to the attention, performing superpixel segmentation on the pavement image according to the initial seed point, and selecting small-size superpixels; and obtaining an abnormal rate of the small-size superpixels according to the small-size superpixels and target superpixels at corresponding positions in a next frame of image, redistributing the superpixels according to the abnormal rate to obtain a final superpixel image, and obtaining a pavement feature category and confidence according to the final superpixel image. According to the method, the pavement feature categories can be accurately recognized, and then control over the cleaning brush is achieved.

The invention discloses an image foreground segmentation method combining main body determination and edge precision, which combines a main body determination process for positioning a salient region and an edge precision process for precisely segmenting a target. Firstly, a main body part is determined, and a context sensing pyramid feature extraction module is designed to obtain rich context features; a channel attention mechanism CA module after feature mapping of a context sensing pyramid feature extraction module and a space attention mechanism SA module after low-level feature mapping are combined, and cross entropy loss is used for supervising generation of significant boundary positioning information so as to obtain positioning information; secondly, an edge process is precise, non-local color features in the image are obtained on the basis of a spectrum extinction technology, advanced semantic features are obtained through a ResNet-101 deep residual network, pixel points in the image are classified by combining the non-local color features with the advanced semantic features through a Laplacian matrix, and the effect of precise target segmentation is achieved; and finally, the results of the two processes are fused.

The invention provides a local color pencil drawing generation method and device, and belongs to the technical field of image processing. The local color pencil drawing generation method comprises thefollowing steps: inputting an original color image; carrying out image segmentation on the original color image to obtain a color segmentation image, carrying out grayscale processing on the color segmentation image to obtain a grayscale segmentation image, carrying out binarization processing on the grayscale segmentation image to obtain a binary image, and determining a foreground region and abackground region of the original color image according to the binary image; performing image processing on the original color image to obtain a contour map and a texture map, and combining the contour map and the texture map to obtain a gray scale pencil drawing; and adding the color information of the foreground area of the original color image to the corresponding area in the grayscale pencil drawing to obtain and output a local color pencil drawing. According to the local color pencil drawing generation method, the color information of the foreground area of the original color image is added to the corresponding area in the gray scale pencil drawing to obtain the local color pencil drawing, so that the local color can be better highlighted, and the artistic expression form of the colorpencil drawing is enriched.

The invention provides an image character editing method of an improved FANnet generative network. The method comprises the following steps: firstly, accurately extracting image characters defined by a user by using an improved adaptive character segmentation model based on an HC saliency detection algorithm; secondly, generating a network according to the FANnet, and generating a target character binary image consistent with the font of the source character; and finally, migrating the color of the source character to the target character through the proposed local color migration model for color complexity discrimination. Therefore, the target editing and modifying character highly consistent with the font structure and color change of the source character is generated, and the purpose of character editing is achieved. Experimental results show that the method is superior to an existing algorithm. For actual scene image characters with relatively complex font structures and color gradient distribution, the invention is also very effective, and has certain theoretical significance and application prospects for image reutilization, automatic error correction of an image character computer, text information restorage and the like.

The invention relates to a high-rise building fireproof plugging module defect detection device and method based on line structured light, the device comprises a detection device framework, a line laser measuring instrument and a driving motor, a detection device main body adopts an aluminum alloy framework, and the line laser measuring instrument is fixed on a line rail slide block through a mounting rack to realize free sliding on a line rail; the driving motor is a stepping motor. The method comprises the following steps: carrying out three-dimensional modeling on the surface of a fireproof plugging module, converting 3D point cloud data into a two-dimensional color image, extracting the outer contour of an object from the two-dimensional image, registering the outer contour with a standard template, carrying out local color comparison according to a matching result, and judging whether the fireproof plugging module has defects or not according to a color comparison result.

The invention discloses a local color change type numerical control bending machine product crack detection device, and belongs to the technical field of numerical control bending machine product detection equipment. The local color change type numerical control bending machine product crack detection device comprises a detection workpiece, a draught fan and a sealing piece, and the draught fan and the sealing piece are installed on the detection workpiece; the detection workpiece is sleeved with a detection sleeve, the upper end and the lower end of the detection sleeve are fixedly connected with elastic connecting films, the side walls, away from the detection sleeve, of the two elastic connecting films are fixedly connected with the same breathable film, a plurality of evenly-distributed elastic telescopic lines are fixedly connected between the breathable film and the detection sleeve, and the upper end and the lower end of the breathable film are fixedly connected with sealing rings. The device can detect workpieces processed by a numerical control bending machine, small cracks can be easily found by people while cracks can be detected, meanwhile, the device can detect two workpieces with different shapes, namely plates and round pipes, is very simple to use, and effectively improves the detection efficiency.

The invention relates to the technical field of architectural ceramics, and particularly discloses a preparation method of a cloth-pattern-imitated rock plate, which comprises the following steps: S1, applying cover glaze to a green body and drying; S2, printing a pattern by adopting oily matte ink and ceramic ink-jet ink; S3, applying a velvet-like glaze material; S4, applying a particle-like glaze material, and then drying; and S5, firing. According to the invention, the texture pattern with a three-dimensional effect is preliminarily formed on the surface of the green body through the oily matte ink, the unique velvet texture of the cloth grains is reduced by combining the velvet-like glaze, and then the soft fine particle texture of the cloth grains with slight fluctuating particles is reduced by superposing the granular-like glaze, so that the unique texture of the cloth grains is highly reduced; in addition, the velvet-like glaze and the particle-like glaze can make the color development of the ceramic ink-jet ink more uniform, local color difference is avoided, and the manufactured cloth-pattern-like rock plate is high in reduction degree, fine and smooth in hand feeling and good in decoration effect; the velvet-like glaze and the granular-like glaze can also endow the rock plate with high hardness and high wear resistance, and the prepared rock plate is excellent in antifouling property and scratch resistance.

The present invention relates to a system and method for matching the color and appearance of a target coating. The system and method includes receiving the target image data associated with a target coating; using a color model and a local color model to predict the color differences between the target coating and a sample coating, wherein the color model and the local color model include a feature extraction analysis processing that determines the image features by analyzing the target pixel feature differences within the target coating; performing an optimization routine upon the color differences for determining the automotive paint components for spraying a substrate.

The invention discloses a method and a system for controlling a local color gamut, a backlight source and a display device. The method comprises the steps of receiving an image signal of a frame to be displayed; resolving the image signal to obtain a high-color-gamut region in the frame to be displayed, wherein a color-gamut value of the high-color-gamut region exceeds a preset range; controlling different regions of the backlight source according to the high-color-gamut region. In the method, the image signal to be displayed is analyzed and divided into a high-color-gamut region and a low-color-gamut region according to the color-gamut value, the high-color-gamut region is obtained according to an analysis result, control of different regions of the backlight source is achieved, and only a low-color-rendering LED lamp is required to be lightened on in several regions in which high-color-gamut images are not required to be displayed. Therefore, the power consumption of the backlight source can be reduced while the frame quality is ensured, and the energy-saving purpose is achieved. The invention further provides the system for controlling the local color gamut based on the method, the backlight source and the display device including the backlight source. Energy saving is achieved.

Disclosed is a method for generating an image from a source image for encoding a projection of a part of a three-dimensional scene. Pixels of the source image comprise a depth and a color attribute. Pixels of the source image are de-projected as colored point cloud. A de-projected point in a 3D space has the color attribute of the pixel that it has been de-projected from. Also, a score is attributed to the generated point according to a local depth gradient and / or a local color gradient of the pixel that the generated point comes from, and the lower the gradient is, the higher the score is. In a second step, the generated point cloud is captured by a virtual camera for rendering on a display device. The point cloud is projected onto a viewport image by blending color of points projected on a same pixel, the blending being weighted by the scores of these points.

The present invention provides a method for repairing images in cultural collections based on self-color transfer, which includes the following steps: S1 to obtain the original image of the skeleton texture image, S2 to repair the damaged part, S3 to remove the background color and inlay the skeleton texture image, and S4 to obtain the local color migration source image , S5 obtains the local color migration reference image, S6 performs local color migration, S7 accurately fills the damaged parts, and S8 repairs other damaged parts in the image. The self-color restoration of the present invention saves the search step of the reference image and replaces it with the intact part of the image to be repaired, which saves repair time and improves the repair effect; reduces the manual pressure of the restorer and other workers, and obtains better virtual effects for the restorer to refer to , to increase the repair rate.

The invention provides an image classification method based on RGB three-component grouping attention weighted fusion, and the method comprises the steps: collecting a target image in a complex environment, and carrying out the noise reduction processing, and obtaining a denoised target image; and respectively extracting RGB three-channel component images of the denoised target image. According to the image classification method based on RGB three-component grouping attention weighted fusion, RGB three components are introduced, an attention mechanism is introduced into the residual network model, global and local color three-component features are fully utilized for feature extraction, and the classification effect on targets with noise interference and bright colors, especially small targets, is good.

The invention relates to a method for color correction of a consistent stereoscopic image based on gradient maintenance. Firstly, feature extraction and matching are performed on a reference image and a target image by using SIFT feature extraction and matching to obtain a structural image and a matching image; then, the structural similarity is used The algorithm generates a confidence map of the matching image and the target image, performs local mapping on areas with low confidence in the image, and generates an initial color correction result image; finally uses the gradient-holding algorithm to reference the color and structure of the initial color correction result image Optimize to get the final result image. The invention solves the structural consistency problem of the local color correction algorithm and the regional color confusion problem of the global color correction calculation, and also retains the gradient information of the image, thereby improving the fidelity of the image.

An LED 3D display device includes: multiple groups of light emitting diodes, each group of light emitting diodes is provided with sub-pixels composed of four single primary color luminous bodies; multiple groups of prisms are symmetrically arranged on both sides of any sub-pixel; Each sub-pixel forms two groups of images through its adjacent prisms, which are respectively projected into the left and right eyes of the viewer. Multiple groups of prisms are symmetrically arranged on the left and right sides or the top and bottom sides of any sub-pixel, and the sub-pixels are distributed in strips or squares. The sub-pixels of different columns are arranged in a staggered manner, so that after different pixels pass through the prism, the color is more uniform and soft, and the light penetration effect is good, which solves the phenomenon of high contrast of each color and too deep local color. In addition, when the pixels are arranged in a square shape, the width of the prism increases. This arrangement reduces the display resolution, but the color is uniform. It is more suitable for the application of large-scale 3D display devices, and the manufacturing requirements are low. It is suitable for large-scale LEDs. TV Wall.