Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
98 results about "Color face" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Psychological test method based on face images and eye movement fixation information
InactiveCN106407935AImplementing Synchronous Tracking RecordsAchieving identifiabilitySensorsPsychotechnic devicesReal time analysisPsychological status
The invention relates to a psychological test method based on face images and eye movement fixation information. The method uses color face images for expression recognition, head status recognition and hand status recognition. Meantime, the method uses an eye movement instrument to record eye movement fixation positions of a testee, and subjects the whole process to synchronous matching to obtain synchronous tracking records of behavior status and eye movement fixation status of the testee during the psychological test process. Then based on obtained status data, the method carries out modeling analysis to achieve psychological characteristic recognition of the testee. The method realizes online recognition and synchronous processing of expression, hand, head and eye movement status of the testee during the psychological test process, ultimately achieves real-time analysis and recording of psychological status, and has very high test precision and low misclassification rate.
Owner:俞大海
Method for detecting colour image human face under complex background
InactiveCN1932847APrecise positioningCharacter and pattern recognitionSkin complexionImage detection
One method using for picture detecting technology field, is especial a kind of color picture person face detecting method in complicated background. Detect the candidate area of person face using whole complexion and figure character, then detecting person face by eye and mouth local character. Take illumination compensate for pictures and partly eliminate the influence for detecting from illumination, then divide up and unite the two value picture traversed by complexion model to get the candidate area of person face. Detecting person face figure, eye and mouth to judge if the candidate area having the face and finish the face detecting. It can accurately locate face position and the face with large gauche angle. The examine rate is 89.7% for 1015 color face pictures taken in changing illumination and complex background containing gauche ones.
Owner:SHANGHAI JIAO TONG UNIV
Two tone storage bin
InactiveUS20120043289A1Easy constructionEasy to useShow cabinetsContainer decorationsEngineeringMechanical engineering
Owner:AKRO MILS DIV OF MYERS INDS
Microcrystalline foamed ceramic thermal insulation decoration composite plate and manufacturing method thereof
InactiveCN103938820AEnvironmentally friendlyLow thermal conductivityCovering/liningsCeramic layered productsPolymer modifiedThermal insulation
The invention discloses a microcrystalline foamed ceramic thermal insulation decoration composite plate which comprises a thermal insulation layer (1) and a decoration layer (2), wherein the decoration layer (2) is fixed onto the thermal insulation layer (1) by the adoption of an anti-flaming binder (8). The thermal insulation layer (1) is a microcrystalline foamed ceramic thermal insulation plate, the decoration layer (2) is a flexible facing clad material, and the decoration layer (2) sequentially comprises a flexible composite material sheet (3), color facing mortar (4) and a finishing coat (5) from bottom to top, wherein the anti-flaming binder (8) is a polymer modified cement mortar adhesive. Through the mode that the microcrystalline foamed ceramic thermal insulation plate with a fireproof function is combined with the flexible facing clad material through the anti-flaming binder, the microcrystalline foamed ceramic thermal insulation decoration composite plate has the advantages of factory component industrialization, construction assembly, fire hazard high-temperature anti-flaming fire prevention, thermal insulation, sound insulation and decoration composition.
Owner:山东鲁蒙低碳技术研究有限公司
A method for detecting and recognizing human face in vivo
InactiveCN109145817AJudging face spoofing behaviorAvoid defectsNeural learning methodsSpoof detectionColor imagePattern recognition
A method for detecting and recognizing human face in vivo comprises the steps of: a video human face image is acquired; the face part of the video frame image is segmented to get the optical flow modulus sequence and direction sequence; three kinds of feature information are extracted from the sequence, and the extracted feature is trained to get an SVM classifier to judge whether it is a living face or not; according to the living face image detected by infrared image, the face part in the color image is segmented, the color face image is extracted by using PCA algorithm, and the collected face image is represented by one-dimensional vector, and the covariance matrix C of the vector is obtained; the eigenface space W is obtained from the covariance matrix C, and the eigenface space W is used as the input of the neural network; the neural network is optimized and trained; after the training, the face images to be recognized are input into the network for face recognition. In order to solve the cheating behavior of photographs in face recognition method, the difference between living face and image video face can be judged effectively.
Owner:FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST +1
Multicore dictionary learning-based color face recognition method
ActiveCN105740790AEasy to identifyImprove robustnessCharacter and pattern recognitionLearning basedCore function
The invention discloses a multicore dictionary learning-based color face recognition method. According to the method, a multicore learning technology is applied to the dictionary learning and sparse coding processes of color face data; and through designing a core function selection criterion, optimal core mapping functions are respectively selected for three color components of a color face image training sample set, three characteristic extract coefficient matrixes, structural dictionaries and corresponding sparse codes are respectively learned for the three core mapped color components, the dictionaries obtained through learning are used for carrying out sparse coding on nonlinear characteristics of to-be-recognized samples, and classification and recognition are carried out according to reconstruction errors. The method disclosed in the invention is higher in recognition effect, and has relatively good robustness for the image quality problem.
Owner:NANJING UNIV OF INFORMATION SCI & TECH
Base material of inorganic coating and application of base material
ActiveCN103725051AAging resistantStrong weather resistanceArtist's paintsFire resistanceCompatibilization
Owner:FUKE TECH (SUZHOU) CO LTD
Semi-supervised multi-view dictionary learning based color face recognition method
ActiveCN107392190AEasy to identifyCharacter and pattern recognitionLearning basedDictionary learning
The invention discloses a semi-supervised multi-view dictionary learning based color face recognition method. According to the method, a multi-view leaning technology is applied to semi-supervised color facial image dictionary learning. In the training stage, by learning structured dictionaries of all chrominance components separately and making the dictionaries be orthogonal to one another, the correlation among all the chrominance components is removed, and complementary difference information among all the chrominance components is fully utilized; in the dictionary learning process, class-label-free color facial image samples are used for participating in training, and all training sample information is fully utilized. In the class test stage, all the chrominance components are added up, the dictionary corresponding to each class of training samples is used for reconstructing reconstruction errors of test samples, and finally the test samples are classified as the class with the smallest accumulative reconstruction error. Accordingly, the recognition effect is higher, and by means of semi-supervised multi-view dictionary learning, the color face recognition capacity is obviously enhanced.
Owner:NANJING UNIV OF INFORMATION SCI & TECH
Color correction method for color face image
InactiveCN106530361AImprove calibration accuracyEnsure coordinationImage enhancementImage analysisColor imageColor correction
The invention, which relates to the image processing technology, provides a color correction method for a color face image. With the provided method, the color correction precision is improved. Firstly, a face image is segmented into six target divided regions: an eye region, an ear region, a mouth region, a nose region, an eyebrow region, and a skin region by using a face five-sense-organ segmentation method; secondly, color blocks falling into all target divided region color ranges are selected from a color correction colour atla; thirdly, optimal color block sub sets of all target divided regions are selected by using a greedy searching algorithm, color correction models are established for all target divided regions at optimal color block sub sets of all target divided regions, and divided region color correction is carried out on a to-be-corrected color face image by using the established color correction models for all target divided regions. Therefore, the correction effect is closer to the practical face intrinsic color.
Owner:SHANGHAI EAST HOSPITAL +1
Granulation method for cementing material used for color pavement
InactiveCN101148512AEasy to transportImprove mixing efficiencyIn situ pavingsHigh pressureSURFACTANT BLEND
The present invention discloses color facing binding material palletizing process, which includes the following steps: 1. mixing materials; 2. reaction at 160-220 deg.c for 6-10 hr; 3. adding demolding agent and surfactant and stirring to obtain the binding material; and 4. vacuum debubbling the binding material, adding stuffing and colorizing agent at the temperature 20 deg.c higher than the softening point and mixing, extruding in an extruder, cooling, settling and cutting to obtain pelletized color facing binding material. The pelletized color facing binding material has easy use and high construction efficiency.
Owner:SHENZHEN OCEAN POWER INDUSTRIAL CO LTD +1
Distributed ink jetting digital printing method and system of supporting variable data
InactiveCN103182863AFast transmissionHigh speedVisual presentationOther printing apparatusData capacityComputer graphics (images)
Owner:PEKING UNIV FOUNDER GRP CO LTD +3
Face recognition method based on color images
ActiveCN102708359AThere is little correlation between classesExcellent Face Recognition MethodImage analysisCharacter and pattern recognitionColor imageHat matrix
The invention discloses a face recognition method based on color images. The method effectively uses color information of color images to convert the color images into single-color images on basis of CSDA (correlation similarity discriminant analysis) criterion, and is optimal as compared with the subsequent CSDA recognition method in terms of obtained color faces. The method includes: obtaining a feature space by the aid of a training image sample through similar features in a training stage; using projection factors of the training image sample in the feature space as features of the training image sample; projecting a test image sample to the feature space in a test stage; using factors obtained after the test image sample is projected to the feature space as features of the test image sample; matching the features of the training image sample with the features of the test image sample by a classification method to obtain classification results; using a similar feature extraction model for converting color images in concentrated training into single-color images according to an optimized combination coefficient vector X*; and obtaining features of training images according to an optimized projection matrix W*.
Owner:BEIJING UNIV OF TECH
Multi-color printing storage medium allocation method and system
InactiveCN101187853AIncrease profitTake advantage ofOther printing apparatusDigital output to print unitsColor printingDistributed computing
The invention discloses an allocating method and a system of multi-color printing storing medium for improving the utilization factor of the storing medium and improving the printing speed. The allocating method of the multi-color printing storing medium of the invention comprises storing medium allocating information which generates work to be printed according to data amount of each color face of work to be printed, and allocating storing space for each color face of work to be printed according to the storing medium allocating information.
Owner:PEKING UNIV FOUNDER GRP CO LTD +2
Face recognition method based on multi-kernel authentication color space
ActiveCN105740787AEasy to identifyImprove classification performanceCharacter and pattern recognitionFeature vectorModel method
The invention discloses a face recognition method based on a multi-kernel authentication color space. A multi-kernel learning technology is applied to a color face image, and three color components of the color face image are independently mapped by three different nonlinear kernels and are then subjected to color space transformation through a multi-kernel authentication color space method. In a new multi-kernel authentication color space, the characteristics of each color component are independently extracted by an enhanced Fisher linear authentication model method, the characteristic vectors of three color components of each color face image are connected into one column vector in series, and then, a nearest neighbor classifier is used to carry out classification and recognition. The face recognition method is high in recognition effect, and the classification capability of the authentication characteristics is obviously improved after the color face image is transformed to the multi-kernel authentication color space.
Owner:中通服网盈科技有限公司
Color face identification method based on RGB (red, green and blue) color feature double identification relevance analysis
ActiveCN103116742AImprove classification accuracyEasy to identifyCharacter and pattern recognitionPattern recognitionFeature set
The invention discloses a color face identification method based on RGB (red, green and blue) color feature double identification relevance analysis. Identification analysis is applied in R, G, B (red, green and blue) color components and among the same, feature double identification analysis based on relevance is realized in each color component and among different color components, a large amount of identification information can be acquired, classification accuracy is high, and identification capacity is high. The color face identification method based on RGB (red, green and blue) color feature double identification relevance analysis includes: defining intra-class feature relevance matrix and inter-class feature relevance matrix in each training sample set and intra-class feature relevance matrix and inter-class feature relevance matrix among color component training sample sets; defining target function and solving the same to obtain projected training sample feature sets; and obtaining projected test sample features according to the projected training sample feature sets, calculating relevance from the test sample features to the training sample features and classifying the same to a category in which the training sample with the largest relevance is.
Owner:NANJING UNIV OF INFORMATION SCI & TECH
Expression recognition method and system for privacy protection
ActiveCN110610144AStrong discriminationEasy to trainAcquiring/recognising facial featuresColor imagePrivacy protection
The invention discloses an expression recognition method and an expression recognition system for privacy protection. The method comprises the following steps: obtaining a plurality of color face images, and carrying out the preprocessing of the plurality of color face images, and obtaining the color components of the plurality of color face images; taking the color components as imaginary parts of a quaternion matrix, constructing a first quaternion matrix, and calculating a local variance of the first quaternion matrix; constructing a second quaternion matrix by taking the local variance asa real part of the quaternion matrix and the color component as an imaginary part of the quaternion matrix; performing encryption processing on the second quaternion matrix by adopting quaternion Gyrator transformation to generate a real number matrix; randomly scrambling the real number matrix so as to train the convolutional neural network, and using the trained convolutional neural network to identify and verify the color face image. The method has the advantages of stronger recognition performance, higher safety and revocation.
Owner:CAPITAL NORMAL UNIVERSITY
Face recognition method and device and computer readable storage medium
ActiveCN110969046AImprove visual qualityImprove accuracyCharacter and pattern recognitionPattern recognitionComputer graphics (images)
The invention discloses a face recognition method and device, and a computer readable storage medium. The method comprises the steps: obtaining to-be-recognized image data; extracting an original color face image from the image data; converting the original color face image into a first gray level image, and obtaining a first gray level average value of the first gray level image; according to thefirst gray average value, performing first image enhancement preprocessing on the original color face image to obtain a target face image so as to enable the target face image to accord with a presetrecognition condition; and face recognition is performed on the target face image, so that the accuracy of face recognition can be improved.
Owner:SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
Color face identification method based on RGB (red, green and blue) color feature double identification analysis
InactiveCN103116758AImprove classification accuracyEasy to identifyCharacter and pattern recognitionDistribution matrixFeature set
The invention discloses a color face identification method. Identification analysis is applied in R, G, B (red, green and blue) color components and among the same, feature double identification analysis based on Euclidean distance is realized in each color component and among different color components, a large amount of identification information can be acquired, classification accuracy is high, and identification capacity is high. The color face identification method based on RGB (red, green and blue) color feature double identification analysis includes: acquiring training sample sets first, and defining intra-class feature distribution matrix and inter-class feature distribution matrix in each training sample set and intra-class feature distribution matrix and inter-class feature distribution matrix among color component training sample sets; defining target function and solving the same to obtain projected training sample feature sets; and obtaining projected test sample features according to the projected training sample feature sets, calculating Euclidean distance from the test sample features to each training sample feature and classifying the same.
Owner:上海资汇信息科技有限公司
Method for producing color facing mortar
The invention provides to a method for producing color facing mortar. The method comprises the following steps of: producing white dry mixed facing mortar with controllable whiteness as the base material of color facing mortar; screening color paste compatible with the white dry mixed facing mortar with controllable whiteness to be as the color-mixing paste; building the color matching proportion relationship between the white dry mixed facing mortar and the color-mixing paste, wherein the proportion relationship can be expressed as the mode of a form, the mode of a point-line diagram or the mode of a curve diagram, preferably the mode of a curve diagram; and mixing and formulating the white dry mixed facing mortar and the color-mixing paste according to the proportion relationship obtained in Step 3 to obtain the color facing mortar. Based on the method for producing color facing mortar provided by the invention, the scale production of color facing mortar can be achieved, and the method also can be used for producing color facing mortar of special colors.
Owner:SHANGHAI GIANT ENERGY SAVING MATERIALS
Waterproof-antipollution outdoor plate and production method thereof
InactiveCN106760337AReasonable useImprove waterproof and moisture-proof performanceCovering/liningsFlooringSlurryTreated water
The invention discloses a waterproof-antipollution outdoor plate and a production method thereof. The waterproof-antipollution outdoor plate comprises a sanding water-residue color-chip magnesium-silicon plate composed of a water-residue magnesite cementing material (1), glass fiber grid fabrics (2), a natural color face layer (3), a sanding face (4), organic-silicon waterproof layers (5), a natural color face slurry (6), an antipollution coating (7) and a water-residue color-chip magnesite cementing material (8). According to the waterproof-antipollution outdoor plate and the production method thereof, specially-treated water residue powder is used as a filling material for making the magnesite cementing material, a waste high-filter-residue waste material which easily causes environment pollution is reasonably used accordingly, secondary utilization of waste recycling is achieved, and the good waterproof damp-proof performance is also achieved; the antipollution coating (7) is attached to the surface of the water-residue color-chip magnesite cementing material (8), the smooth surface is obtained, and the antipollution effect is achieved; the waterproof-antipollution outdoor plate also has the advantages that the heat conductivity coefficient is low, the heat resistance is good, the aging resistance is good, the waterproof-antipollution outdoor plate and other base materials are easily cemented and burned, and molten drops are not generated.
Owner:张维满
Face identification method on basis of duplex multi-kernel discriminant analysis of color features
InactiveCN104680150AEasy to identifyImprove classification performanceCharacter and pattern recognitionEuclidean Distance MeasurementNearest neighbor classifier
The invention discloses a face identification method on the basis of duplex multi-kernel discriminant analysis of color features. A multi-kernel subspace learning technology is applied to duplex discriminant analysis of the color face features; three different nonlinear kernel mappings are respectively used for three color components and then feature layer duplex discriminant analysis is carried out. For features acquired by duplex multi-kernel discriminant analysis, a nearest neighbor classifier on the basis of the Euclidean distance measurement is used for classification and identification. According to the face identification method, an identification effect is better and after the features of three color namely R (red), G (green) and B (blue) components are subjected to duplex multi-kernel discriminant analysis, classification capacity of the identifying features is obviously reinforced.
Owner:北京大为远达科技发展有限公司
Image processing method and device, electronic equipment and storage medium
PendingCN110956080AImprove recognition accuracyPrevent overfittingImage enhancementImage analysisImaging processingEngineering
The invention relates to an image processing method and device, electronic equipment and a storage medium. A face recognition model is obtained by pre-training a large number of color face image samples; based on the face recognition model, the face features in the image can be accurately recognized, a relatively small number of infrared face image samples are continuously trained by adopting theface recognition model, and the distinguishing features of the true and false faces in the positive and negative samples in the infrared face image samples are learned, so that the face anti-counterfeiting model for recognizing the true and false of the infrared face image is obtained through training. Therefore, the problem of overfitting of a small data set training model can be avoided, so thatthe finally trained face anti-counterfeiting model is relatively high in recognition accuracy.
Owner:JD DIGITS HAIYI INFORMATION TECHNOLOGY CO LTD
Method for producing personalized doll
The present invention relates to making process of personalized baby. The making process includes molding head sculpture with clay based on pictures or 3D video record input into computer, turning into hard head bone gypsum mold of head bone and hard head mask, computer aided matching of head bone mold and head mask, making GRP hard shell of head bone, making rubber or plastic face mask, jacketing the face mask onto the hard shell of head bone, adhering imitation hair, coloring face, fitting body model, fitting clothing and installing voice device. Making vivid personalized baby can maintain the image of children for long term.
Owner:陶德林
Single-image large-pose three-dimensional color face reconstruction method based on UV position map and CGAN
PendingCN113052976ASolve the self-occlusion problemImprove recognition accuracyDetails involving 3D image dataNeural architecturesPoint cloudRgb image
The invention discloses a single-image large-attitude three-dimensional color face reconstruction method based on a UV position map and a CGAN, and the method comprises the steps: generating a three-dimensional point cloud model through employing UV position recording, complementing an incomplete face through employing a network based on the CGAN design, and finally obtaining a complete color three-dimensional face model. designing coding-decoding network, generating and recording a two-dimensional UV position map of complete three-dimensional face information from an original RGB image, and then remolding a three-dimensional face from the two-dimensional UV position map by using a convolutional neural network; and then, considering the self-shielding condition of the large posture of the face, and complementing the deficiency of the UV texture image by designing a special conditional generative adversarial network. According to the method provided by the invention, higher reconstruction precision and more texture details can be realized, a more complete and real three-dimensional face model can be obtained especially in large-pose face image reconstruction application, and the method has stronger robustness in coping with complex environmental factors.
Owner:ZHEJIANG UNIV OF TECH
Face recognition method and device, computer equipment and storage medium
PendingCN113177449ALower requirementImprove accuracyBiological neural network modelsCharacter and pattern recognitionFeature vectorEngineering
The invention discloses a face recognition method and device, computer equipment and a storage medium, and particularly relates to the technical field of artificial intelligence such as deep learning and computer vision, and the specific scheme is that the method comprises the steps: carrying out the coding processing of a first three-primary-color face image through a first encoder, and determining a first feature vector corresponding to the first three-primary-color face image; utilizing a second encoder to encode the first three-primary-color face image to determine a second feature vector corresponding to the first three-primary-color face image, wherein training data corresponding to the second encoder is different from training data corresponding to the first encoder; fusing the first feature vector and the second feature vector to generate a fused feature vector; and identifying the fused feature vector to determine a user to which the first three-primary-color face image belongs. Therefore, the accuracy and reliability of face recognition are effectively improved.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD
Color face recognition method based on semi-supervised multi-view incremental dictionary learning
InactiveCN110046583AReduce training timeCharacter and pattern recognitionDictionary learningPattern recognition
The invention discloses a color face recognition method based on semi-supervised multi-view incremental dictionary learning, and belongs to the technical field of face recognition. The method fully utilizes an incremental learning technology, and comprises the steps of dividing a training stage into two sub-stages of a training sample set and dictionary initialization stage and a training sample set and dictionary updating stage; at the training sample set and dictionary initialization stage, using an initial color face image training sample set to carry out dictionary learning in a mode the same as that of a color face recognition method based on semi-supervised multi-view dictionary learning to obtain an initial dictionary; at the training sample set and dictionary updating stage, according to the change of the color face image training sample set, simply modifying the learned dictionary, and then carrying out dictionary updating. Compared with the color face recognition method basedon the semi-supervised multi-view dictionary learning, when the color face image training sample set changes, the training time consumed for updating the dictionary can be greatly shortened.
Owner:NANJING UNIV OF INFORMATION SCI & TECH
A biological feature recognition method and device
The invention provides a biological feature recognition method and device, and relates to the technical field of image processing and recognition. The method comprises the steps of obtaining a to-be-detected image; Projecting the first full quaternion matrix representing the to-be-detected image on a preset feature vector to obtain a projection matrix; Wherein the preset feature vector is a feature vector of a scrambling matrix of a second full quaternion matrix of the training image set; And using the obtained projection matrix to classify and identify the obtained to-be-detected image, and obtaining an identification result. According to the method, the image information amount borne by the quaternion matrix is increased, and the face color image can be expressed more accurately, so thatthe recognition precision is further improved; The realization process of the scrambling matrix is irreversible, and even if the registered or stored biological characteristic data is lost or stolen,only the biological characteristic data needs to be registered or stored again, so that the security and privacy of the biological characteristic data such as a color face image are effectively protected.
Owner:CAPITAL NORMAL UNIVERSITY
High-speed data transmission method and device
ActiveCN106155597AImprove printing efficiencyFew stepsDigital output to print unitsData segmentPrinting press
Embodiments of the present invention provide a high-speed data transmission method and device. The method includes: rasterizing the target file to obtain a plurality of data segments; respectively compressing the plurality of data segments to obtain a plurality of compressed segments; sending the plurality of compressed segments to a digital printing machine for printing . In the embodiment of the present invention, multiple data segments are obtained by rasterizing the target file. Compared with the prior art, the target file to be printed is rasterized to obtain multiple compressed color plane data, and the multiple compressed color planes The data is decompressed separately, and the decompressed multiple color surface data are organized into multiple data segments, which saves the steps of rasterizing the target file, improves the subsequent data transmission efficiency, and thus improves the printing efficiency of the digital printing machine .
Owner:NEW FOUNDER HLDG DEV LLC +1
A high-quality face generation method based on a multi-scale residual network
InactiveCN109903373AImprove resolutionReduce blurrinessCharacter and pattern recognitionNeural architecturesLow noiseData set
The invention discloses a high-quality face generation method based on a multi-scale residual network, and the method comprises the following steps: a data set design step: integrating a current mainstream face data set, and generating a data pair of a low-quality face and a high-quality face through software; A model design and training step: designing a multi-scale residual network, and performing model training by using data pairs to obtain a network model weight; And a model prediction step: carrying out model processing on the face image obtained in reality to obtain a prediction result.According to the invention, a deep learning network technology is applied to a generation task of a high-quality face to generate a color face image with high resolution, low fuzzy degree and low noise; And by using a deep learning network method, the time and cost of manual drawing can be reduced, and a solid foundation is laid for subsequent face feature extraction and recognition.
Owner:SOUTH CHINA UNIV OF TECH
Printing control method and device
ActiveCN106696482AImprove adjustment processing efficiencyGuaranteed printing qualityOther printing apparatusImaging dataComputer engineering
The invention provides a printing control method and device. The method comprises the following steps: monitoring whether a printed color-face image generates a left-right sleeving alignment error; if so, determining an error adjustment value corresponding to each piece of color-face image data to be adjusted, wherein the error adjustment values are left empty adjustment values of the color-face image data to be adjusted relative to reference color-face image data; and sending adjustment instructions to nozzles corresponding to the color-face image data to be adjusted to indicate each nozzle to adjust left empty values of the color-face image data to be adjusted according to the error adjustment values corresponding to the color-face image data to be adjusted so as to enable each nozzle to perform printing according to color-face image data after adjustment. According to the invention, when it is monitored that left-right sleeving alignment adjustment is needed, based on the left empty adjustment values determined relative to the reference color-face image data, left-right sleeving alignment adjustment of subsequently printed color-face image data is performed in real time in an online mode, the operation is convenient and rapid, and while the printing quality is guaranteed, the adjustment processing efficiency of left-right sleeving alignment is improved.
Owner:NEW FOUNDER HLDG DEV LLC +1
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com