741results about How to "Clear boundaries" patented technology

The invention relates to a mobile phone casing defect detecting method based on depth learning. The method comprises the steps that (1) the image of a mobile phone casing to be detected is acquired and pre-processed; and (2) the pre-processed image is input into a pre-trained defect detection model for defect detecting to acquire the position of a defect on the mobile phone casing, and the confidence of the position as the defect is provided. The defect detection model is a depth network based on depth learning, and comprises a feature extraction network and a classifier and regression device network, wherein the feature extraction network and the classifier and regression device network are in successive cascade. The feature extraction network carries out feature extraction on the pre-processed image to acquire a feature image. The classifier and regression device network classifies and regresses the feature image to acquire the defect position and the confidence of the mobile phone casing. Compared with the prior art, the method provided by the invention has the advantages of high detection precision and accurate and reliable detection result.

A photowriting display device which is capable of performing bright full color display and a photowriting display apparatus which incorporates the photowriting display device and on which the pen moving operation is directly reflected as information to be displayed. A photowriting display device is disclosed which incorporates: an electrochromic display member incorporating a photoconductor in which only regions irradiated with writing light generate carriers to realize conductivity; an electrochromic layer in which light absorption of the regions are reversibly changed owing to electrochemical oxidation and reduction reactions caused to occur due to the conductivity; an electrolyte in which the electrochromic layers are laminated or an electrochromic material is dissolved; and a pair of electrodes laminated through the photoconductor, the electrochromic layer and the electrolyte. A plurality of the electrochromic display members are laminated.

A domain object stores a business rule, and an object management is provided with an interface for data access. A service object executes a service requested by other objects. A control object controls the collaboration relationship among these objects according to the process request from a client, and notifies the client of the process result.

A water body information automatic extraction method for a multi-spectral image of a remote sensing satellite comprises the steps of (1) implementing normalized difference water index (NDWI) extraction on apparent reflectivity data of the multi-spectral image of the domestic remote sensing satellite, and forming an NDWI image; (2) implementing maximum between-cluster variance algorithm based global threshold segmentation initial water body information extraction on the NDWI image; (3) implementing local buffer area expansion and threshold segmentation on the initial water body information, and obtaining a stable water body unit result set; and (4) according to elevation data, obtaining slope and shadow information, removing a shadow from the water body unit result set, and finally finishing the water body information extraction. According to the method, by adopting a computer automatic interpretation method and utilizing a thought of from global segmentation to local iterative segmentation, the NDWI is subjected to water body information extraction in a process manner; and the method is high in extraction precision and easy in engineering.

The invention discloses a production method of hot stamping foil, which adopts six production process flows: release coating, protective layer coating, color layer coating, accurate aluminizing and curing glue layer coating. In the whole production process, water soluble glue, water soluble ink and water soluble gloss oil are used to realize the integrated production of the hot stamping foil, methacrylates and monomers which are emulsified and polymerized are mixed in a certain ratio, a dye leveler, thickener and the like are added in the mixture, the resulting product is coated and dried, polyvinyl butyral-based glue is coated, and the whole production of the hot stamping foil is finished. The hot stamping foil produced by the process has the characteristics of energy conservation, environmental protection and sanitation.

The invention relates to an image semantic segmentation method based on global features and local features of deep learning. The method comprises the following steps: at an encoding end, the basic deep features of an image are extracted by using a convolution neural network model based on deep learning; meanwhile, the features are divided into low-level features and high-level features according to the deep of the convolution layer; the feature fusion module fuses the low-level feature and the high-level feature into the enhanced deep feature; the feature fusion module fuses the low-level feature and the high-level feature into the enhanced deep feature; after the deep feature is acquired, the deep feature is inputted to the decoding end; the cross-entropy loss function is used to train the network and mIoU is used to evaluate the performance of the network. The invention is reasonable in design, and uses the deep convolution neural network model to extract the global and local features of an image, fully utilizes the complementarity of the global features and the local features, further improves the performance by utilizing the stack pooling layer, and effectively improves the accuracy of image semantic segmentation.

The invention discloses an edge finding cutting method of a laser cutting device which is characterized in that images of an object needing to be cut are collected through a camera. A correcting document is used for the correction to generate a contour graph. Then, based on the contour graph, a matching model is constructed. Then, the patterns cut in real time are collected through the camera according to set parameters. The vectorization treatment is implemented on the collected images to generate graphs. The graphs are compared with the matching model according to the set similarity. An image satisfying the set similarity is the successful matching image. To the successful matching image, cutting data are generated according to the contour graph of the actually paragraphed image. Finally, the cutting data are sent to the laser cutting device to be cut. The cutting method is characterized by automatically adapting to the cut image differences within certain similarity scope and realizing the precise cutting of images.

The invention provides a method and a device for realizing the photoelectrochemical micro-etch processing of a masked electrode, and relates to the micro processing field in the manufacturing technology. A masked electrode used by the invention comprises a glass substrate, an indium tin oxide (ITO) layer and a photoresist mask layer, wherein the conductive light-permeable ITO layer is used as a tool electrode for electrochemical processing and can be permeated by a laser beam, and the photoresist mask layer can limit the action zones of the laser beam and the electrochemical electrode to achieve the double effects of a beam mask and an electric field mask. When the laser beam permeates the masked electrode, a mask pattern is imaged on the surface of a workpiece, the force effect of a shock wave generated by the irradiation of the laser between the workpiece and the electrolyte enables the passivation layer to be removed by the generation of stress corrosion. Meanwhile, the workpiece material at the laser-irradiated part is removed by etching under the action of the photoelectrochemical reaction. The invention can effectively enhance the processing efficiency, the micro processing degree and the processing precision of the complex pattern, and is applicable to the micro processing of the conductive metal material.

The invention relates to a method for manufacturing a conductive film, in particular to a method for manufacturing a conductive graphene film through ink-jet printing. Graphite or graphite derivatives are used as raw materials and ultrasonically separated in dispersant / ethyl alcohol / dimethylformamide solvent to prepare graphene dispersion solution, and supernatant liquid is taken through centrifugation, and graphene powder is obtained after the supernatant liquid undergoes flocculation; the graphene powder is prepared into printing ink, the printing ink is injected into an ink box, and the printing ink is deposited on a preprocessed substrate according to a preset pattern through the ink-jet printing technology; the conductive graphene film is formed through thermal treatment at 200 DEG C to 350 DEG C. According to the method, the graphene is prepared through the liquid phase separation method, and the conductive graphene film is manufactured through the ink-jet printing technology. The manufactured film can be patterned and is high in electric conductivity and good in mechanical property. Equipment used for ink-jet printing is simple, operation does need to be performed according to an original template, complex patterns are easy to make, cost is low, and the method is expected to be used for replacing existing complex film coating and photoetching technologies under certain conditions.

The invention provides a non-contact biometric feature identification method and system. The method comprises the following steps of: extracting biometric features of a visible light image and a near-infrared image collected in a non-contact way; calculating the similarity x1 between the biometric feature of the visible light image and a prestored visible light biometric feature template and the similarity x2 between the biometric feature of the near-infrared image and a prestored near-infrared light biometric feature template; and comparing a detected sample x=(x1 x2) consisting of x1 and x2 with a training sample to judge whether the detected sample belongs to a within-class sample, and if so, judging that the identification is successful. By using the method provided by the embodiment of the invention, the identification precision of the method is greatly higher than that of a single biometric feature identification way, and the problems of less feature information and low distinguishing precision caused by the adoption of the current single palm pulse identification way and poorer anti-fake capability caused by the adoption of a single palm print identification way can be solved.

Based on an area detection signal, a layer separation section outputs a text component of a document, to a feature point calculating section, and generates four layers from a pictorial component of the document to output the generated layers to the feature point calculating section. The feature point calculating section sums feature points extracted for each component. A features calculating section calculates a hash value based on the feature points. A vote processing section searches a hash table based on the hash value, and votes for a reference image associated with the hash value. Based on the voting result, a similarity determination processing section determines whether the document image is similar to any reference image, and then outputs the determination result. Thus, even if the document contains a photograph, accurate matching can be performed.

The invention discloses a method for improving plasma sprayed ceramic coatings and base binding strength, which is sprayed ceramic coating fusion processing method. The method is that sceramic coatings which are prepared by plasma spraying are put in special environment which is 300-550 DEG C for 4-8 hours and then is cooled along with a stove. The coatings and a workpiece base are mutually diffused or are formed into a new phase, thereby playing a role of a transition layer between the coatings and the base. The bonding strength of the coatings and the base are improved by about 20 percent and is capable of meeting the application requirements for industries.

The invention discloses a high-resolution SAR image individual building extraction method, and the method comprises the steps: firstly carrying out domain ontology modeling through combining the imaging features of a high-resolution SAR image individual building and the characteristics of a complex morphological structure, and constructing an individual building body semantic model in a high-resolution SAR image; secondly obtaining image regions with the good homogeneity and clear boundary through employing SAR image segmentation based on an object, wherein the image regions are the basic processing units extracted by building base units; combining with the related rule of the building base units in the body model, wherein the extracted image object characteristics comprise regional features, shape features, geometric features, texture features, and topological features; forming the object expression of body semantic description according to the body semantic rule and the object features, guiding the image objects to be automatically recognized as the building base units, and achieving the large-scale individual building recognition which takes the semantic knowledge as the center. The method can extract a large-scale individual building in the high-resolution SAR image accurately and quickly.

The present invention relates to methods and apparatuses for transferring pattern, a flexible display panel, a flexible solar cell, an electronic book, a thin film transistor, an electromagnetic-shielding sheet, and a flexible printed circuit board applying thereof. A pattern transfer method related to the present invention comprises: a first step of forming a pattern material on a substrate; a second step of hardening the pattern material in the solid state; a third step of patterning the pattern material by irradiating a laser beam to the hardened pattern material in the solid state; and a fourth step of pressing the patterned pattern material in the solid state and a flexible substrate facing each other and transferring the pattern material to the flexible substrate by a viscous force of the flexible substrate occurring in a facing part between the pattern material and the flexible substrate by irradiating the laser beam from the pattern material to the flexible substrate or from the flexible substrate to the pattern material.

The invention relates to a preservation solution for exfoliated cells, which is characterized by comprising a pH buffering agent, an osmotic pressure maintaining agent, an anti-corrosion antistaling agent, a fixative for maintaining cellular morphologies, an anticoagulant, a mucus softener, proteinase K and a component for destroying red blood cells. Compared with the prior art, the preservation solution has the advantages that the cell storage rate is high, the storage time at normal temperature is long, the mucus is sufficiently dissolved and the red blood cells are partially destroyed, the sheet-making effect comprises quite even cell distribution, the cellular morphologies are good, the cytolymph and the cell nucleus are divided clearly and are well arranged, the brightness of the cytolymph and the cell nucleus is quite good, and the karyoplasms, the morphological structures and the amount of the cells are quite clear.

The invention discloses an interpolating method of self-adapting medical sequence image among fault space based on interesting area, which utilizes tissue relativity and body relativity to judge whether the interpolated point belongs to the interesting area to select fitful interpolating method. The invention considers the change of grey and structural outline, which solves the insufficiency of traditional interpolating method to make new interpolated image approach actual condition. The interpolating method modifies the visual effect and image quality greatly, which reduces the noise and shortens the calculating time to be applied in three-dimensional reconstruction and display system.

The invention provides an angiography image blood vessel segmentation method and an angiography image blood vessel segmentation system. The angiography image blood vessel segmentation method includesthe steps of taking each pixel coordinate of a live image as a reference coordinate, selecting one pixel coordinate matched with the reference coordinate from a mask image and taking the pixel coordinate as a contrast coordinate; extracting sub images in the same size from the live image and the mask image respectively to form an image pair; inputting all the images to a dual-passage convolutionalneural network to output a first blood vessel segmentation image; extracting multiple images in different size from each reference image according to preset rules, inputting all the images in different size to a multi-scale convolutional neural network to output a second blood vessel segmentation image, and finally displaying the second blood vessel segmentation image. As the dual-passage convolutional neural network and the multi-scale convolutional neural network are utilized for achieving twice classification, blood vessels of the images displayed finally have defined boundaries and cleardetails, and during the whole process, full-automatic interaction is achieved with high efficiency.

A gas-shielded flux-cored wire with recyclable welding slag belongs to the welding field. In the invention, the skin of the gas-shielded flux-cored wire is made from a mild steel strip, and welding slag powder is partially or completely instead of natural rutile, thus the purposes of saving the resource and reducing the cost are achieved. The powder of the flux-cored wire comprises the following chemical components in percentage by weight: 15-35% of the welding slag powder of the flux-cored wire (including 20-65% of TiO2, 5-15% of MnO, 5-15% of MgO, 5-15% of SiO2, 1-10% of Fe2O3 and 1-10% of Al2O3), 15-35% of TiO2, 2-7% of Si, 3-8% of Mn, 0.5-5% of Al-Mg, 0-5% of Na, 0-5% of K, 1-5% of Mg and the balance of ferrous powder. When the flux-cored wire manufactured by adopting the welding slag powder is applied to welding, the gas-shielded flux-cored wire has the advantages of excellent technical performance of welding and omnibearing welding adaptability, attractive appearance good humidity resistance, low content of diffusible hydrogen in a welding seam, excellent crack resistance, high connection strength and good low-temperature impact toughness.

The invention, which belongs to the technical field of data processing, discloses a radar radiation source signal feature selection method based on a membrane particle swarm multi-target algorithm. According to the method disclosed by the invention, a membrane calculation optimization theory is combined with a particle swarm optimization algorithm and the uniformity and diversity of a crowding degree maintenance set are utilized; and a data object is optimized by using two objective functions of correlation and redundancy and application to in-pulse feature selection of a radar radiation source signal is carried out. According to the invention, with non-dominated sorting and a crowding distance mechanism in a skin membrane, rapid convergence of the multi-target particle swarm optimizationalgorithm is kept by the algorithm and the solution set has high diversity. And then with KUT and ZDT series test functions, comparison testing is carried out on the algorithm and MOPSO, SPEA2 and PESA2 algorithms. Therefore, rapid convergence to the real Pareto leading edge is realized and the provided algorithm is feasible and effective.

A safeguard system for a power secondary system comprises an application security equipment and system, a safety operation and maintenance system, a forward and reverse isolating device and a personal communication gateway, wherein the application security equipment and system is arranged in a production control area, the safety operation and maintenance system is arranged in the production control area, a production management area and a management information area, the forward and reverse isolating device is arranged between the production control area and the production management area, and the personal communication gateway is arranged between the production management area and the management information area. The production control area comprises a service module of a power secondary system real-time or quasi real-time service. The production management area comprises a service module for collecting and managing data in the production control area. The management information area comprises a service module for managing information. The power secondary system is divided again based on the technical feature and the deployment architecture of the power secondary system, the arrangement of safety protection is carried out based on the division of a safety area, the deep protection for the power secondary system is achieved from different aspects, and the safety of the power secondary system is improved.

The method for preparing metal oxide function film by using ink-jet printing process includes the following steps: 1). using soluble metal compound as raw material, dissolving it in water or organic solvent, the weight ratio of raw material and water or organic solvent is 1-30:100-200; or dispersing nano granules of metal oxide in water or organic solvent according to same weight ratio; 2) addingadditive, added quantity is 0.01-5% of weight of water or organic solvent, the controlled ink viscosity is 20-60 mPa.s and its surface tension is 20-40 mNm(-1), and preparing metal oxide ink with stable property; 3). injecting said ink into ink box and adopting conventional ink-jet printing process to make the ink deposit on the substrate; and 4). heating film layer deposited on the substrate at 200-700 deg.C to form the metal oxide functional film.

The invention belongs to the technical field of marine engineering concrete material durability test equipment, and particularly relates to a test device for simulating marine environment dynamic andstatic combined concrete loading; compared with the prior art, the device has the advantages that 1, the structure is simple, the installation is convenient, the automation degree is relatively high,manpower and material and time cost are saved, and meanwhile, the overall control function of a control box and the real-time detection and recording function are realized, and the accuracy is improved; 2, an upper water level sensor, a lower water level sensor, a communication water pipe, a test box and a liquid storage box are matched to carry out a dry-wet circulation test, so that clear boundaries of an underwater area, a tidal area and a wave-splashing area can be ensured, the underwater area is always in the soaking environment, the tidal area is located in the soaking and drying environment, and the wave-splashing area is in a spraying environment; and 3, the characteristics of chemical and mechanical coupling and dynamic and static combined loading are considered, so that the testdevice is more suitable for the environment where the concrete is in service, and can be widely applied to the concrete durability test occasions.

The invention provides a method for automatically segmenting consistent damage areas for buddha figure Thangkas. The method includes the steps of conducting vertical projection for a head light area of a Thangka image, obtaining an image symmetric axis by using a one-dimensional function symmetry detection method, obtaining an initial segmentation result by employing a partitioning segmentation method based on the symmetric axis, obtaining the image covered by the damage areas, extracting texture characteristics by using Gabor transformation, constructing a multi-scale and multi-characteristic set in combination with Lab space color characteristics, employing KNN classification to obtain a secondary segmentation result, further refining the damage areas by using morphological operation, and removing small damage areas to finally obtain a template of consistent damage areas. Through the method, various large-scale linear and block falling areas in the buddha figure Thangkas can be automatically segmented, the segmentation speed is fast, the efficiency and accuracy are high, and rapid automatic segmentation of the damage areas of buddha figure Thangkas can be realized.

The invention provides a color ceramic, a casing, preparation methods thereof and an electronic device. The preparation method of the color ceramic comprises the steps of placing a plurality of ceramic modules in a coordinated manner, and sintering an obtained product, wherein the two ceramic modules placed adjacent to each other are different in color. Therefore, the preparation method is simpleand easy to operate, the process is mature, and the industrial production is easy. According to the above preparation method, the ceramic modules of different colors are directly spliced together, the color of the obtained color ceramic is more full, the boundaries between the different colors are clear and distinct, a strong color contrast effect between different colors can be realized, and therefore, the individualization of the color ceramic is improved. By sintering, the two adjacent ceramic modules can be tightly combined to allow a plurality of ceramic modules to form a whole body, and the color ceramic with a color contrast pattern is achieved.

The present invention discloses a method for manufacturing an image sensor which makes the boundaries between microlenses clear by forming a guide layer in advance and can increase the focal distance of light and the quantity of light by forming the spheres of the microlenses to have a constant height.

The present invention discloses a method for manufacturing an image sensor which makes the boundaries between microlenses clear by forming a guide layer in advance and can increase the focal distance of light and the quantity of light by forming the spheres of the microlenses to have a constant height.

The invention relates to a method for producing touch sensor, wherein said sensor comprises touch contact layer 1, space layer 2, and substrate layer 3 while they are made from flexible material; the touch contact layer 1 has micro cam array above; the space layer 2 is between the layers 2 and 3, while it has chamber array relative to the micro cam array; the contact faces between layers 1, 3 and 2 have several parallel row electrodes 4 and longitudinal electrodes 5 while they are vertical to each other; each crossed part has one switch sensitive unit; when the force of units are different, it will generate different switch signals to represent the surface state of matter. The invention has simple structure, high spatial resolution, and low cost.

An X-ray imaging method and apparatus are provided for forming an X-ray image having reduced noise and showing a clear boundary of a lesion region. The X-ray imaging method includes performing a first main shot which irradiates an object in a compressed state by using X-rays at least once to obtain a single two-dimensional image, performing a second main shot which irradiates the object by using X-rays at different positions to obtain a plurality of two-dimensional images, and forming a two-dimensional final image by removing a lesion region having a unclear boundary from each of the plurality of two-dimensional images and substituting a lesion region of the single two-dimensional image into an area which corresponds to the removed lesion region.