29results about How to "Clear texture" patented technology

The invention relates to a ginkgo leaf canopy near-earth remote sensing image super-resolution reconstruction method, which comprises the following steps: (1) collecting ginkgo multispectral remote sensing images at different heights, and establishing a data set by aligning real LR images and HR images; (2) recovering a high-resolution image from the low-resolution remote sensing image by adopting a super-resolution reconstruction model; the super-resolution reconstruction model RTGAN takes an SRGAN model as a baseline model; the RTGAN is composed of a generator network and a discriminator network, an MDRB composed of a plurality of continuous residual blocks is integrated in the generator network, and a U-Trans discriminator is used as a discrimination network; the generator network maps the LR image into an SR image through multilayer nonlinear transformation and feature extraction; the discriminator network evaluates the quality and authenticity of the generated image, and distinguishes a real HR image and a generated SR image; finally, the discriminator network cannot distinguish the two images, and a high-quality SR image is obtained.

The invention discloses a UV (ultraviolet) excimer skin-touch paint for a relief melamine base material and application of the UV excimer skin-touch paint, and relates to the technical field of paints.The UV excimer skin-touch paint comprises the following components in percentage by weight: 15-50% of UV adhesion promoting resin; 5-10% of modified epoxy acrylate resin; 20 to 50% of special modified polyurethane acrylate resin; 5-20% of amino acrylate resin; 1-5% of phosphoric acid modified acrylate resin; 0.1-1% of a surface tension control agent A; 0.1-1% of a surface tension control agent B; 0.1-1% of a defoaming agent; 0.2-2% of an organosilicon hand feeling auxiliary agent; 0.1 to 0.5 percent of organic silicon leveling agent; 2-8% of a photoinitiator C; 0.3-1% of a wetting dispersant; 1-5% of polyethylene wax powder; and 10-30% of a UV active monomer. According to the invention, the relief melamine base material can realize open coating of the excimer skin-touch paint, and the coated paint film has good surface effect, uniform plate surface gloss without floating, no dust and no white exposure of the guide pipe, and good open effect.

The invention provides a wood lacquer coating composition, and relates to the technical field of wood lacquer. The wood lacquer coating composition consists of a component A and a component B according to a molar equivalence ratio of 1: (1-1.1), the component A comprises the following raw material components: composite aspartic ester resin consisting of first aspartic ester resin and second aspartic ester resin; the weight of the second aspartic ester resin accounts for 10-40% of the weight of the composite aspartic ester resin; the first aspartic acid ester resin is bifunctional aspartic acid ester, the second aspartic acid ester resin is monofunctional aspartic acid ester, and the first aspartic acid ester resin and the second aspartic acid ester resin are both low in viscosity; and the component B is an isocyanate curing agent. A coating formed by curing the wood lacquer coating composition has good water resistance, heat resistance, aging resistance, smudginess resistance, hand feeling and the like.

The invention belongs to the field of artificial intelligence, is applied to the field of financial virtual customer service, and relates to a digital human generation method which comprises the following steps: receiving an audio signal and initial digital human image data, and converting the audio signal and the initial digital human image data into audio features and initial image implicit features; inputting the audio features and the initial image implicit features into an autoregressive Transform model, generating image implicit features corresponding to each time step of the audio features through the autoregressive Transform model, and taking the image implicit features as target image implicit features; decoding the implicit features of the target image to obtain a target digital human image; a digital human video sequence is generated based on the audio features and the target digital human image. The invention further provides a digital human generation device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the digital human video sequence can be stored in a block chain. According to the invention, the trueness and fluency of the generated digital human are effectively improved.

The invention discloses a deamination and grinding process for the surface of CMF integrated colored crystal glass, which belongs to the technical field of colored crystal glass preparation, and comprises the following steps: performing bottom sealing protection on the tin surface of the tempered glass; performing plasma treatment on the air surface of the tempered glass; degassing polyurethane ink, coating the deamination polyurethane ink on the air surface of the tempered glass and performing pre-crosslinking; deamination of the pre-crosslinked polyurethane ink layer by a pressing method or a vacuum method; performing embossing, secondary crosslinking and grinding on the air surface of the tempered glass in sequence to obtain a finished product, wherein the polyurethane ink comprises a first polyol and a second polyol, wherein the first polyol is a polyol having a diimidazole structure, and the second polyol is poly-ε-caprolactone diol; and the invention can directly form a pattern with a strong concave-convex feeling on the glass surface coating through a simple coating treatment and embossing process, thereby improving production efficiency.

The utility model belongs to the technical field of automation equipment, and particularly relates to a small magnetic shoe surface texture processing device. The magnetic shoe mounting seat comprises a magnetic shoe mounting seat body, the magnetic shoe mounting seat body comprises a magnetic shoe bottom fixing part and a side connecting body part, and the top wall surface of the magnetic shoe bottom fixing part is arc-shaped. In the machining process, the magnetic shoe is placed at the magnetic shoe bottom fixing part, the top wall face of the magnetic shoe bottom fixing part is arc-shaped, matched with the bottom of the magnetic shoe and high in fitting degree, the front end and the rear end of the magnetic shoe are abutted and fixed through the end fixing piece, the magnetic shoe is prevented from shaking, then the two sides of the magnetic shoe are clamped and fixed through the side clamping piece, and the magnetic shoe bottom fixing part is fixed to the magnetic shoe bottom fixing part. According to the magnetic tile surface polishing device, multi-directional fixing is formed, stability is high, after fixing is completed, the magnetic tile surface polishing assembly is used for polishing the surfaces of the magnetic tiles, protruding particles on the surfaces of the magnetic tiles are removed, polishing is comprehensive, the surfaces of the magnetic tiles are kept smooth, lines are clear, meanwhile, the magnetic tile surface polishing assembly can avoid too deep polishing in the polishing process, and the surface quality of the magnetic tiles is guaranteed.

The invention discloses a special grinding brush for quartz stone and a manufacturing process thereof, comprising a base, wherein a bristle group is arranged on the bottom surface of the base, and the bristles in the bristle group have at least two different diameters; the bristle group comprises a plurality of first bristle groups and a plurality of second bristle groups, and there is a height difference between the bristles of the first bristle group and the bristles of the adjacent second bristle groups. The invention provides a special grinding brush for quartz stone which has a concave-convex effect after polishing, high clarity and an antique effect, and a manufacturing process thereof.

The utility model discloses a decorative plate capable of improving the effect of a digital printing pattern. The decorative plate comprises a bottom plate, a putty layer fixed on the bottom plate, a printing white bottom layer fixed on the putty layer, a 3D transparent developing layer fixed on the printing white bottom layer and an ink layer fixed on the 3D transparent developing layer. The stone and wood patterns of the decorative plate are real, and the texture is clear; the 3D transparent developing layer in the decorative plate improves the color developing property of ink, and the presented pattern is bright in color; the 3D transparent developing layer is connected with the printing white bottom layer and the ink layer, so that ink can be perfectly spread on the transparent layer and can be well attached and matched with the printing white bottom layer, and the transition effect of connecting the top and the bottom is achieved; and by adding the 3D transparent developing layer, the appearance quality of the digitally printed decorative plate and the qualified rate of a finished plate are improved.

The utility model belongs to the technical field of leather processing equipment, and particularly relates to stamping equipment for motorcycle cushion leather, which is arranged on a working table and comprises a support frame fixedly connected to the working table, a stamping bottom plate arranged at the lower part of the support frame and used for supporting the leather, and a stamping component arranged at the top of the support frame and used for stamping the leather, the device further comprises a pressure control system electrically connected with the imprinting assembly. The precise pressure control system and the precise positioning system ensure that the leather is uniform in pressure and accurate in position in the embossing process, so that embossed patterns and textures are clear and firm, and the percent of pass and the quality of products are improved.

The invention belongs to the technical field of food processing, and discloses low-salt sauced beef and a preparation method thereof. The preparation method comprises the following steps: steaming the sweet potatoes, adding the steamed sweet potatoes into the corn juice, inoculating pichia pastoris and mucor minuta, and fermenting to obtain fermentation liquor; adding a salt substitute, spices and seasonings into water to prepare brine, putting the fresh beef into the brine, boiling with big fire, then turning to soft fire for first marinating, and then adding the fermentation liquor for second marinating. The color, flavor and texture of the sauced beef can be improved, meanwhile, the problem that the sauced beef has peculiar smell due to the fact that salt substitutes potassium chloride is solved, and the quality of the prepared low-salt sauced beef is close to that of traditional sauced beef under the condition that salt is not added. The sauced beef is red, compact in tissue, clear in texture, appropriate in meat hardness, easy to chew, appropriate in saltiness, rich in sauce flavor and good in overall taste.

The utility model discloses a device for collecting mosquito egg images of a mosquito and egg trapping device in multiple scenes, the main body structure of the device is composed of an industrial camera, a light supplementing lamp panel and a macro lens, and the device is characterized in that the industrial camera is embedded into a slot position of the light supplementing lamp panel and is fixed through a buckle; the light supplementing lamp panel is in a circular ring shape, and light supplementing lamps evenly distributed along the circular ring are arranged on the light supplementing lamp panel. The device body can directly cover the upper portion of the mosquito and egg trapping device with the cover opened to shoot filter paper in the mosquito and egg trapping device, and can also be fixed to the telescopic supporting vertical plate to shoot filter paper in the mosquito and egg trapping device or taken out independently. The device has the flexibility of adapting to multi-scene application, allows operators to efficiently obtain clear and countable filter paper pictures of mosquito eggs under the condition of not using a stereoscope or a microscope for observation, is convenient for subsequent work such as manual or machine identification and counting of egg granules and picture storage, and is high in practicability. And the efficiency of identifying and counting the eggs after the mosquito and egg trapping device is recovered is effectively improved.

The utility model discloses a kind of multi-effect synergic anti-wrinkle non-deformation pearl plush forming device, belong to pearl plush processing technical field, its technical scheme main points include support frame, the inner side of the support frame is provided with conveying mechanism, hot setting mechanism is welded in the both sides of support frame top, the hot setting mechanism includes mounting bracket, screw rod, threaded sleeve, servo motor, connecting rod, rotating roller, several heating rods, setting roller and temperature sensor, heating rod in hot setting mechanism is evenly distributed in rotating roller surface, cooperate temperature sensor real-time monitoring temperature, and adjust through PLC feedback, ensure that setting roller surface temperature is stably in optimum range, both guarantee that fabric fiber is fully set, avoid damage or deformation caused by overheating, setting roller is driven screw rod to adjust height by servo motor, can be flexibly adjusted with the interval of conveying belt according to fabric thickness, ensure that pressure is uniform, make the texture of pearl plush surface set clear, form consistent, improve product appearance texture.

The invention discloses an image enhancement processing method for remote sensing and mapping of unmanned aerial vehicles, and relates to the technical field of image enhancement processing. During the operation of the system, the flight attitude and position information are recorded by GNSS and IMU equipment, the flight path of the unmanned aerial vehicle is controlled, and the collected original image is preliminarily processed to calculate and obtain: flight stability coefficient Fs, image acquisition quality coefficient Iq and terrain feature retention coefficient Tf, and the non-local mean NLM algorithm is used to remove random noise in the remote sensing image, optimize the edge area, and use the Laplace pyramid algorithm to improve the edge clarity and texture details of the terrain image, strengthen the mountain and hilly landform features, correct the color distortion caused by the complex lighting conditions in the mountains, make the image color truly restore the terrain features, avoid the loss of important landform information due to excessive brightness or darkness, optimize the terrain feature extraction, and generate the final index Z final ,Quality assessment of enhanced and rectified images.

The application discloses a preparation method of concave-convex texture ceramic tiles with uniform color and luster, and comprises the following steps: A, blank is pressed into a blank body by roller forming, and the blank body layer is obtained after first drying; B, printing ink of a mold is printed according to a preset pattern, digital face glaze is sprayed, and the concave-convex texture layer is formed after second drying; C, color ink is printed according to the preset pattern, and the inkjet printing layer is formed; D, digital protection glaze is sprayed, and the protection glaze layer is formed after third drying and fourth drying; E, kiln firing is performed, and the concave-convex texture ceramic tiles with uniform color and luster are obtained after polishing. The preparation method of the concave-convex texture ceramic tiles with uniform color and luster is simple in steps and high in operability, and under the premise of solving the black edge problem and ensuring the uniform color and luster of the ceramic tiles, the concave-convex texture effect with clear texture, high consistency and high fidelity is obtained on the surface of the ceramic tiles.

The invention discloses a three-dimensional model texture mapping method, device and system and a storage medium. The method comprises the following steps: acquiring oblique photography data of a plurality of measuring areas; performing aerial triangular encryption and three-dimensional reconstruction on the oblique photography data of the plurality of measuring areas, and constructing a texture-free geometric model; performing back rejection and shielding detection on the texture-free geometric model; performing global uniform light and color by using a Laplacian algorithm, and filling the average color of the texture blocks into the texture image; local dodging and color dodging are carried out on the texture blocks by adopting a resolution reduction Poisson dodging method; and performing texture layout on the texture blocks, and outputting a live-action three-dimensional model with consistent texture colors.

The application relates to the field of image processing and discloses a ground penetrating radar image sharpening method based on super-resolution reconstruction, which firstly carries out pretreatment on acquired original radar image data. In view of the problems of low-frequency ground penetrating radar image blurring and low resolution, the application proposes using an improved Real-ESRGAN super-resolution network to carry out image reconstruction. Core improvements include: a degradation model conforming to a GPR physical imaging mechanism is designed, which is used to more truly simulate low-quality image generation in the training stage; a hybrid loss function containing a depth-weighted pixel loss, a structure mask-weighted Charbonnier loss and an A-scan direction consistency loss is constructed, so that the recovery capability for deep weak signals, key structural features and echo waveform consistency is enhanced. The application can effectively improve the resolution and visual clarity of the ground penetrating radar image, enhance structural details and depth information, and provide a more reliable image basis for subsequent intelligent analysis tasks such as target recognition and disease detection.

The present invention belongs to the field of digital image processing technology, and specifically is an unsupervised image denoising method based on uncertainty perception. The method of the present invention comprises: constructing a smooth noise extraction module and a rough denoising network to simulate noise blocks and perform rough denoising on images; constructing a network for modeling accidental uncertainty, estimating pixels with high uncertainty in the noise image, generating an uncertainty map, and guiding the next stage of the network to perform denoising; constructing a fine denoising network, and guiding the network to reduce the influence of uncertainty on the denoising process through the weighted objective function of the uncertainty map, so that the network can achieve better denoising effect. Experimental results show that the present invention can effectively remove noise from images, and the denoised images have good texture structure and visual quality.

The application discloses a model training method, a crack detection method, a computing device and a readable storage medium, and relates to the field of weld detection. The model training method comprises the following steps: training a model based on a StyleGAN3 architecture through an original sample set to obtain a virtual image sample set corresponding to a weld crack image, wherein the number of weld crack images of the virtual image sample set is greater than that of the original sample set; and training an initial model based on the virtual image sample set to obtain a weld crack detection model, wherein the initial model comprises a Faster RCNN model with a Swin Transformer network as a backbone network, and the initial model comprises an FPN module and an ACmix attention mechanism module. The FPN architecture and the ACmix attention mechanism are introduced according to the characteristics of the weld crack to improve the model, thereby improving the detection accuracy of the weld crack.

This invention relates to a Gaussian super-resolution reconstruction method based on physically consistent sparsity and frequency awareness, comprising: performing feature extraction and saliency prediction on the spacecraft image to be processed to obtain a multi-scale deep feature tensor and a foreground saliency mask; using the foreground saliency mask to perform spatial feature modulation on the multi-scale deep feature tensor to obtain a modulated multi-scale deep feature tensor; decoding the feature vector corresponding to each spatial position of the modulated multi-scale deep feature tensor to predict the corresponding Gaussian kernel parameters; based on the foreground saliency mask, performing a physically consistent hard gating operation on the opacity of all Gaussian kernel parameters to generate a sparsified set of Gaussian kernel parameters; and based on the sparsified set of Gaussian kernel parameters, obtaining the final super-resolution result image through differentiable Gaussian sputtering. This method can obtain high-quality arbitrary-scale super-resolution reconstruction results while meeting the high-performance requirements of spaceborne edge devices.

This invention provides a washable woven four-way stretch denim fabric and its preparation method. The warp and weft yarns of the washable woven four-way stretch denim fabric both comprise double-core spun yarns. Each double-core spun yarn comprises a first core filament, a second core filament, and a carrier yarn wrapped around the first and second core filaments. The first core filament comprises spandex, and the second core filament comprises T400 elastic fiber. The preparation method of this invention is simple to operate, and the resulting washable woven four-way stretch denim fabric simultaneously meets the requirements of "high count and high density, lightweight, high elasticity, and high recovery," and also has the advantages of washability and "zero weft shrinkage."

The present invention discloses an anti-skid sole, comprising a sole body, wherein the sole body is provided with a plurality of anti-skid protrusions protruding downward, wherein the anti-skid protrusion is a truncated cone, and a countersunk hole is provided at the center of the anti-skid protrusion, and a plurality of V-shaped grooves extending toward the bottom surface are provided on the upper surface of the anti-skid protrusion, wherein the V-shaped grooves are evenly distributed around the center of the anti-skid protrusion, and the anti-skid protrusion is divided into a plurality of arc-shaped protrusion monomers, wherein the anti-skid protrusions are arranged in a matrix to form an anti-skid combination, and the bottoms of adjacent anti-skid protrusions are in contact with each other to form an exhaust port. The present invention also discloses a forming mold for forming the above-mentioned anti-skid sole, an upper mold plate and a lower mold plate, wherein the upper mold plate is provided with an upper mold groove, and the lower mold plate is provided with a lower mold groove, and the upper and lower mold grooves are processed by precision carving of aviation aluminum, so that the formed anti-skid sole has higher precision and better anti-chemical effect.

The application relates to the field of dyeing and finishing processes of textiles, and particularly discloses a short-process polyester-cotton school uniform fabric dyeing and finishing process which comprises the following steps: S1, knitted double-sided cloth is first subjected to enzyme treatment by adding enzymes and glacial acetic acid, without washing and liquid discharge, so as to obtain pretreated fabric; S2, dyeing auxiliaries and water are added to the pretreated fabric, acid is added to adjust the pH, then dyes are added to perform dyeing treatment, and after refining, dyed fabric is obtained; S3, the dyed fabric is subjected to reduction cleaning and cloth washing, and after drying, finished fabric is obtained; the process has the advantages of efficient treatment, high dyeing rate and good mechanical performance of the fabric.

The invention discloses an image generation method and system based on multi-exposure and multi-focal-length fusion, and the method comprises the steps: obtaining multi-exposure image data, carrying out the Laplacian pyramid decomposition of each image, and fusing the Laplacian pyramids of a plurality of images into a new Laplacian pyramid; carrying out nonlinear stretching on the fused top layer image of the new Laplacian pyramid; carrying out pyramid inverse decomposition to obtain a recovered and fused multi-exposure fusion image; obtaining a plurality of images after multi-exposure fusion of the cameras with different focal lengths, and zooming the images of the cameras with different focal lengths into the same size as the image blocks of the corresponding areas in the image of the camera with the shortest focal length; matching the zoomed images with different focal lengths with the image blocks of the shortest focal length image to obtain a final image estimation block; and combining and generating a new clear image according to all the image estimation blocks. According to the invention, high-definition, wide-view and high-dynamic-range images can be generated.

The invention discloses a double-layer four-way stretch fabric and a preparation method thereof, and belongs to the technical field of textile fabric production. The double-layer warp is composed of surface layer warp and inner layer warp, and the surface layer warp is formed by blending cotton and lyocell fibers. The warp yarns of the inner layer are blended by polyester filament yarns and spandex yarns; the weft yarns consist of spandex yarns, cotton and polyester staple fibers; the number of the warps on the surface layer is 60-70 tex, the number of the warps on the inner layer is 8-10 tex, and the warp density of the double-layer warps is 381-391 pieces per 10 cm; the number of the weft yarns is 58.3-64.8 tex, and the weft-wise density is 161-172 pieces per 10 cm; comprising the following steps of spinning, warping, dyeing, leasing, slashing, drawing-in, weaving and finishing. The fabric has the advantages of no elasticity loss, no curling, softness and comfort.

The utility model belongs to the technical field of knitting, and particularly relates to a high-performance dense-stitch-length warp knitting outdoor fabric. The fabric is formed by weaving nylon and Lycra elastic yarn, the fabric is formed by warp knitting and weaving of double-comb weave by adopting a dense-needle-pitch E36 needle machine number, the double-comb weave specifically comprises a front comb GB1 and a rear comb GB2, the front comb GB1 and the rear comb GB2 both adopt 01 / 21 / 32 / 12 / / four-row warp satin weave, 01 and 32 are open loops, and 21 and 12 are closed loops. The fabric has the advantages of traditional knitting and tatting at the same time, is suitable for being used as an outdoor leisure sports fabric, achieves the effects of being anti-perspective, breathable, moisture-absorbing, soft, skin-friendly, clear in texture and free of wrinkling and bulging during stretching, has a long-term high-performance anti-UV ecological function, and protects skin health of people.

This invention belongs to the field of thin-layer chromatography (TLC) identification technology for traditional Chinese medicine, and specifically relates to a rapid TLC identification method and application for American ginseng and ginseng. The TLC identification method includes the following steps: taking a test sample, adding a solvent, sonicating, and taking the supernatant as the test solution; taking American ginseng and ginseng reference materials, adding solvents respectively, sonicating, and taking the supernatant as American ginseng reference material solutions and ginseng reference material solutions; taking ginsenoside Rg1, ginsenoside Rf, ginsenoside Re, ginsenoside Rd, and pseudoginsenoside F11 reference standards, adding solvents, mixing, and obtaining reference solution; finally, performing TLC analysis and result determination on the test solution, reference material solution, and reference solution. This invention is simple to operate, highly efficient and rapid, has good repeatability and high accuracy, and is low in toxicity and durable, and can simultaneously detect adulteration, substitution, and confusion in American ginseng and ginseng.

The application discloses a kind of based on triangulated mesh differentiable rendering animated face three-dimensional reconstruction method, this method takes single-view or multi-view portrait head portrait video as input, single-frame reconstruction and sequence frame reconstruction are successively carried out, finally output the portrait head portrait basic model of triangular mesh format, face main joint position information and control weight, face expression mixed shape and multiple face color map.The geometric structure of the face three-dimensional model reconstructed by the method is accurate, the color map is high in definition, and the animation can be edited by joint parameters and expression mixing, which can meet the needs of film and television, game industry for face animation model.

The invention discloses an airport runway foreign matter self-adaptive focusing method based on scene perception. The method comprises the following steps that 1, multiplying power calculation and focal length calibration are conducted on an optical camera used for airport runway foreign matter detection; 2, according to the distance between the foreign matter in the runway and the optical camera, an evidence obtaining multiplying power and a corresponding initial focal length are set, and a runway area in the image is extracted; 3, collecting video image data of the optical camera, and calculating an image quality coefficient of the runway area; and step 4, driving a lens of the optical camera to adjust the focal length in a progressive increase mode and a progressive decrease mode according to a preset step length, calculating the quality coefficient of the runway area under each focal length in real time, determining the optimal focusing distance corresponding to the maximum quality coefficient, and driving the camera to be switched to the focusing distance to complete the scene perception-based airport runway foreign matter self-adaptive focusing.