Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

287results about How to "Simplify the training process" patented technology

Modular surgery retractor system

A reconfigurable modular retractor system including a set of interchangeable body modules, the body modules including mechanisms for forming retractors and slot mechanisms for connecting blades, and blades including locking mechanisms for locking inside the slot mechanisms. A method of using the retractor system by forming a retractor by using at least one body module, attaching blades to the body module, inserting the retractor into a surgical area, retracting tissue, removing retraction from the tissue, and removing the retractor.
Owner:GOMEDICA TECH

Deep neural network and reinforcement learning-based generative machine reading comprehension method

The invention discloses a deep neural network and reinforcement learning-based generative machine reading comprehension method. According to the method, texts and questions are encoded through an attention mechanism-combined deep neural network so as to form question information-fused text vector expressions, and decoding is carried out through a unidirectional LSTM decoder so as to gradually generate corresponding answer texts. According to the reading comprehension method, the advantages of extractive models and generative models are fused, training is carried out by adoption of a multi-taskcombined optimization manner, and a reinforcement learning method is used in the training process, so that benefit is brought to generate more correct and fluent answer texts.
Owner:SOUTH CHINA UNIV OF TECH

Remote sensing image segmentation method combining complete residual and multi-scale feature fusion

A remote sensing image segmentation method combining complete residual and multi-scale feature fusion includes S100 improving a convolution coding-decoding network as a segmentation backbone network,separately comprising S101 using the convolution coding-decoding network as the segmentation backbone network; S102 adding a feature pyramid module for aggregating multi-scale context information intothe backbone network; S103 adding a residual unit into the convolution layer corresponding to the encoder and the decoder of the backbone network, and meanwhile, fusing the features in the encoder into the corresponding layer of the decoder in a pixel-by-pixel manner; S200 using the improved image segmentation network combined with complete residual and multi-scale feature fusion for remote sensing image segmentation; S300 outputting the segmentation result of the remote sensing image. This method not only simplifies the training of the deep network and enhances the feature fusion, but also enables the network to extract rich context information, cope with changes in the scale of the target, and improve the segmentation performance.
Owner:SHAANXI NORMAL UNIV

Skin cancer image recognition method based on attention convolutional neural network

The invention discloses a skin cancer image recognition method based on an attention convolutional neural network, and the method comprises the steps: 1) carrying out the preprocessing of an image, which comprises the steps of image overturning, rotation, and affine transformation; 2) performing unbalanced sampling on the image, and performing undersampling on the image; 3) establishing a convolutional neural network framework which comprises a convolutional layer, a pooling layer and a full connection layer; 4) establishing an attention mechanism which comprises a channel attention module anda space attention module; and 5) designing an attention convolutional neural network to identify the skin cancer picture, wherein the network added with the attention module can be positioned in a local area more accurately, and images are mined with distinctive characteristics; and 6) performing transfer learning, and initializing parameters of the convolutional neural network by using the parameters of the pre-training network. Through the method of the invention, the accuracy of skin cancer image recognition can be effectively improved, and the development of artificial intelligence in themedical industry is promoted to a certain extent.
Owner:SOUTH CHINA UNIV OF TECH

Image super-resolution reconstruction method based on cascade residual convolutional neural network

The invention relates to the field of video and image processing. The objective of the invention is to effectively reduce the reconstruction difficulty of a high-resolution image, the good feature extraction capability of a convolutional neural network and the fitting capability of complex mapping. According to the image super-resolution reconstruction method based on the cascade residual convolutional neural network, the basic residual networks with the same structure are cascaded to form the cascade residual convolutional neural network, so that end-to-end mapping from inputting the low-resolution image to outputting the high-resolution image is realized; the basic residual network comprises a global residual channel and a feature extraction channel; down-sampling processing is carried out on the original high-resolution color image, so as to obtain a corresponding low-resolution image according to a basic residual network, performing bicubic interpolation upsampling on the low-resolution image to obtain an interpolation image, sending the interpolation image into a global residual channel of the basic residual network, and finally realizing information transmission between different levels of residual networks and forming final output. The image super-resolution reconstruction method is mainly applied to video and image processing occasions.
Owner:TIANJIN UNIV

Model training method, device and equipment and medium

The invention discloses a model training method which comprises the steps of obtaining a first sample data set, wherein each sample data in the first sample data set comprises a three-dimensional brain image, non-image information and a first labeling label of a tested person, and the first labeling labels are used for identifying whether the tested person suffers from a nervous system degeneration disease or is normal; using the first sample data set to train a neural network model, generating an end-to-end classification model, wherein the classification model takes a three-dimensional brainimage and non-image information of a first designated testee as input and takes a classification label of the first designated testee as output, and the classification label of the first designated testee is used for identifying that the first designated testee suffers from the nervous system degeneration disease or is normal. The method has higher accuracy and can provide reference suggestions for clinicians so as to improve the working efficiency of the clinicians. The invention further discloses a model training device and equipment and a computer storage medium.
Owner:NEUSOFT CORP

Speech key of mobile

A mobile phone voice key is composed of voice receiving unit, voice preprocessing module, voice key training module and unlocking module. It features that neural network voice identification technique is applied on voice key to utilize human voice to unlock key of mobile phone and to finalize status certification course of owner.
Owner:上海优浪信息科技有限公司

HTTP tunnel detection method based on decision tree classification algorithm

The invention discloses a HTTP (Hyper Text Transport Protocol) tunnel detection method based on decision tree classification algorithm, used for solving the technical problem of poor stability of a conventional tunnel detection method based on the transport layer packet statistic characteristic analysis. In the technical scheme of the invention, an HTTP data stream and a tunnel data stream are used to train a decision tree classification model, with lower requirement on quantity of training sets than a statistic fingerprint method; secondly, compared with the statistic fingerprint method in which only two flow characteristics can be utilized, the decision tree classification method can use more characteristics to train the model, therefore, obtained classification rules are more precise and stable; the process to train the model is relatively simple, does not involve image fingerprint consumes less internal storage; finally, the judgment of the decision tree classification method is made according to attributes on a plurality of branch nodes without depending on one specific critical value, which achieving better stability.
Owner:JIANGSU ZHONGWEI HEAVY IND MACHINERY +1

Structural system for optimizing performance of a millimeter wave concealed object detection system

A structural system for optimizing the performance of a millimeter wave concealed object detection system is disclosed. In a particular embodiment, a shell is provided to house and protect the millimeter wave concealed object detection system so that the detection system can operate optimally in a controlled and managed environment by eliminating or mitigating spurious millimeter wave emissions or reflections from outside or inside the shell. The shell can be free-standing or attached to a parent structure. The entry and exit to the system is controlled by entry and exit barriers. In addition, an inspection lane is configured according to each particular application to guide a subject through the detection system.
Owner:MICROSEMI

Air conditioning energy saving method based on genetic algorithm and long and short term memory circulatory neural network

The invention provides an air conditioning energy saving method based on a genetic algorithm and a long and short term memory circulatory neural network. The air conditioning energy saving method comprises the following steps that step1, an air conditioning energy consumption prediction and evaluation model is established; step2, optimization parameters are confirmed; step3, coding is performed onthe cooling water supply temperature and the cooling supply and return water temperature difference utilizing the genetic algorithm, and according to the coding, within a certain range, the cooling water supply temperature and the cooling supply and return water temperature difference are generated stochasticly to obtain an initial population composed of a plurality of chromosomes; step4, other parameters of the current working condition and chromosome parameters are decoded and input into an LSTM-RNN air conditioning prediction and evaluation model, chromosome evaluation is performed, a fitness function is calculated and crossover and mutation are performed on the better chromosomes, and the obtained optimal chromosomes are decoded as the optimal parameters; and step5, the optimal parameters are input into the prediction and evaluation model in combination with the other parameters under the current working condition to obtain optimized air conditioning power consumption. By means ofthe air conditioning energy saving method based on the genetic algorithm and the long and short term memory circulatory neural network, the prediction and evaluation accuracy rate is increased, and the good energy consumption optimizing effect is achieved.
Owner:ZHEJIANG UNIV OF TECH

K-means and deep learning-based image classification algorithm

The invention discloses a K-means and deep learning-based image classification algorithm. The algorithm comprises the steps of 1) taking untagged images as input images, and randomly extracting image blocks to form an untagged image set of the untagged images same in size; 2) extracting a primary optimal clustering center by adopting a K-means algorithm; 3) constructing a feature mapping function, and extracting image features of the untagged image set; 4) performing pooling operation and normalization processing; 5) extracting a secondary optimal clustering center by adopting the K-means algorithm, extracting final image features by adopting convolution operation, and performing standardization processing on the final image features; and 6) classifying the final image features subjected to the standardization processing through a sorter. The algorithm has the advantages of simplicity, high efficiency, few training parameters and the like, and has a very good effect for classification of massive high-dimensional images; and the input images are preprocessed, so that the effects of improving the image classification effect and enhancing the classification precision are achieved.
Owner:HUBEI UNIV OF TECH

Method for detecting behaviors and mentalities of students based on homomorphic encryption federated learning

The invention provides a method for detecting behaviors and mentalities of students based on homomorphic encryption federated learning. The method comprises the following steps: acquiring mutually independent data sets A and B; selecting intersection data through the consistency of data corresponding to the same feature items between the data sets A and B by adopting an encryption-based user sample alignment technology, and distinguishing a to-be-tested data set with the difference between the data sets B and A; encrypting the selected intersection data of the data set A and the data set B through the homomorphic encryption technology; constructing a convolutional recurrent neural network, and training intersection data of the homomorphic encrypted data sets A and B through federated learning to obtain a model for predicting the psychological state of the student; and predicting the psychological state in the model for predicting the psychological state of the student by taking each piece of data in the to-be-tested data set as the to-be-tested data. By implementing the method, the requirements of student behavior and psychological detection are met on the premise of protecting data privacy, and the problems in the prior art are solved by adopting a convergent homomorphic encryption federated learning algorithm.
Owner:WENZHOU MEDICAL UNIV

Large-scale repeated video retrieval method based on random multi-view hash

The invention discloses a large-scale repeated video retrieval method based on random multi-view hash. Video key frames are extracted through a time interval sampling method, and color histogram HSV and local binary pattern LBP characteristics of the key frames are extracted; the HSV and LBP characteristics are mapped to quasi-hash space through linear mapping and the sigmoid function, and hash codes representing videos finally are obtained through quasi-hash codes generated through thresholding processing; the Hamming distance between a test video hash code sequence and other video hash code sequences is calculated, and approximate repeated videos of the test video are retrieved according to the Hamming distance. Multi-view characteristic information of the videos is used, retrieval efficiency and accuracy are improved through hash mapping, and large-scale quick retrieval of the approximate repeated videos is achieved.
Owner:HEFEI UNIV OF TECH

Training method of reinforced learning model, node, system and storage medium

The invention discloses a training method of a reinforced learning model, a node, a system and a storage medium. The training method comprises the steps of acquiring local data by a training node, andinputting the local data as a sample into a first neural network for training, thereby obtaining a first optimal sub-objective function; receiving a parameter from a second optimal sub-objective function of a neighboring node; introducing the parameter of the second optimal sub-objective function into the first optimal sub-objective function for obtaining a second optimal sub-objective function;and performing weighted averaging operation on the first optimal sub-objective function and the second sub-objective function, thereby obtaining an optimal objective function. Through the method, a data leakage problem in the training process of the reinforced leaning model can be settled.
Owner:BCM SOCIAL CORP +1

Back-propagation network calculating method of apparent resistivity

The invention relates to a back-propagation network calculating method of apparent resistivity, which is especially suitable for calculating the apparent resistivity under the condition of a transientelectromagnetic detecting center return-wire device and belongs to the field of geophysical exploration and engineering geological exploration. The back-propagation network calculating method of theapparent resistivity comprises the following steps: defining a kernel function of an expression of a secondary magnetic field of the transient electromagnetic detecting center return-wire device, which is changed following time, and establishing a solving function of the apparent resistivity; selecting a sample training function and a reverse training method taking a kernel function value as inputand a transient parameter as output; carrying out initial calculation through measuring values; and guiding calculating results into different network structures according to different measuring characteristics. The back-propagation network calculating method replaces a numerical value method with a trained back-propagation network for calculation, thereby simplifying the calculating process andbeing easy to realize the programming; and in addition, with the parallel structure processing characteristics of a neural network, the calculating time is greatly shortened.
Owner:CHONGQING UNIV

Classification optimization method and device

InactiveCN109447146AAdd mutually orthogonal constraintsDiscriminativeCharacter and pattern recognitionNeural architecturesFeature vectorNetwork model
An embodiment of the present application provides a classification optimization method and device. The method includes initializing a pre-constructed neural network, constructing a parameter matrix, and orthogonally initializing parameters of a classification layer in the neural network by using the parameter matrix; importing a training image into the neural network to obtain a feature vector outputted after the training image passes through the network layer; according to the parameter matrix and eigenvector, obtaining the loss function; according to the loss function, performing gradient calculation on the network layer weights corresponding to each network layer and the classification layer weights corresponding to the classification layer to update the network layer weights and the classification layer weights; and training the input image according to the neural network which updates the weights of the network layer and the classification layer. The classification optimization scheme adds the constraint of orthogonality between the class parameters, which makes the different classes relatively independent, and makes the neural network model more discriminant.
Owner:XIAMEN MEITUZHIJIA TECH

Infrared and visible light image fusion method

The invention belongs to the technical field of image processing, and particularly relates to an infrared and visible light image fusion method. According to the infrared and visible light image fusion method based on the hybrid l1-l0 decomposition model and the auto-encoder, the hybrid l1-l0 decomposition model is used to take the image decomposition result as the output of the double-layer auto-encoding network, so that the double-layer auto-encoding network has self-contained layer decomposition capability. Image features are decomposed into base layer features and detail layer features, and different fusion strategies are customized for different layers, so that more texture information and heat radiation information can be maintained. And the l1 norm strategy is utilized to compensatethe neglected thermal radiation information of saliency detection, so that the robustness of base layer fusion is improved. The network adopts an end-to-end mode to simplify the training process, andthe model complexity is reduced. Through matrix operation, the time consumption of feature fusion processing is reduced, and the response speed of a fusion framework is further improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Computational lithography method for model-driven convolution neural network

The invention discloses a computational lithography method for a model-driven convolution neural network (MCNN), and the method can improve the computation speed and convergence performance of OPC (optical proximity correction) method. The technical scheme includes: expanding and truncating the gradient iterative algorithm, and constructing a model-driven convolution neural network (MCNN); based on an imaging model of a lithography system, constructing a decoder corresponding to the MCNN; bringing the MCNN and the decoder to end-to-end connection, and subjecting the MCNN to the following training: optimizing the parameters of the MCNN by back propagation algorithm to minimize the error between the input data of MCNN and the decoder; separating the decoder from the MCNN at the end of the training; inputting a to-be-optimized circuit layout into the trained MCNN so as to obtain an estimated result of an OPC mask; taking the estimated result of OPC mask as the initial value, and carryingout iterative updating on the set number of times of the mask by gradient iterative algorithm, thus obtaining the final OPC mask optimization result.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY

Semantic matching method and device and storage medium

The embodiment of the invention discloses a semantic matching method and device and a storage medium, and is applied to the technical field of information processing. The method includes: enabling Thesemantic matching device to determine word pair characteristics of the to-be-matched text and the target text according to the first word characteristic of the to-be-matched text and the second wordcharacteristic of the target text; And converting the word pair characteristics, the first word characteristics and the second word characteristics into semantic matching vectors, enabling the formatsof the semantic matching vectors to be the same as the format of input data in a preset semantic classification model, and determining the similarity between the to-be-matched text and the target text according to the semantic matching vectors and the semantic classification model. In this process, when a semantic matching vector is determined, the text to be matched and the target text are directly obtained, the time of multiplication calculation between vectors is saved, the matching process of the text to be matched and the target text is simplified, then the structure for achieving semantic matching is simplified, and the training process of the structure for achieving semantic matching is correspondingly simplified.
Owner:TENCENT TECH (SHENZHEN) CO LTD

An image sample upsampling method based on convolutional self-coding

The invention discloses an image sample upsampling method based on convolution self-coding, and the method comprises the steps of carrying out the cutting of each three-dimensional magnetic resonanceimaging sample, obtaining two-dimensional images of a region where a tumor is located through cutting, and carrying out the scale normalization of all the two-dimensional images; building a network structure in a form of cascade connection of an encoder and a decoder, and serving as a model; training the model by setting a learning rate and a loss function; carrying out optimization processing onthe trained model by adopting an adaptive moment estimation optimizer; inputting any random positive sample into the trained network to obtain low-dimensional features extracted by the encoder, calculating Euclidean distance center points of eight groups of features, and randomly selecting one group of features from the eight groups of features to obtain new features; and inputting the new features into a decoder for image reconstruction, and outputting a positive sample image. According to the method, the feature extraction is carried out through the encoder, sample enhancement is carried outon samples at the feature level, image reconstruction is carried out through the decoder, upsampling of a few types of samples is obtained, and the method can be used for balance preprocessing of classification problems.
Owner:TIANJIN UNIV

Emotion recognition method, device and apparatus, and storage medium

The embodiment of the invention discloses an emotion recognition method, device and apparatus and a storage medium. The method comprises the following steps: determining the fusion session characteristics of the multimodal session information; inputting the fusion session characteristics of the multimodal session information into a multimodal emotion recognition model constructed in advance, and obtaining the emotion characteristics of the multimodal session information. The technical scheme provided by the embodiment of the invention fuses the session features of each mode in the multimodal session information to obtain the fused session features, and inputs the features of the fusion session into a unified multi-modal emotion recognition model for model training, the final emotion results can be predicted directly without training of each modal recognition model separately, and the results of different models can be fused. The sample training process is simplified and the accuracy ofemotion recognition results is improved.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Road surface crack image detection method

The invention discloses a pavement crack image detection method. The method comprises the following steps: acquiring a pavement image to be detected; obtaining training data, wherein the training datacomprises a plurality of road surface images and crack mark images corresponding to the road surface images; obtaining a pre-trained depth model, and constructing an initial pavement crack detectionmodel based on the depth model; based on the training data, training the initial pavement crack detection model; and acquiring a crack mark image of the to-be-detected pavement image based on the trained pavement crack detection model to obtain a pavement crack image detection result. According to the method, the pavement crack detection model can be constructed according to the pre-trained depthmodel, the model training efficiency is improved, and the precision of the obtained crack mark image is improved.
Owner:ZHENGZHOU UNIV

Method for fast identifying speeking person based on comparing ordinal number of archor model space projection

The invention relates to a fast speaker confirming method based on the ordinal number comparison of anchor model spatial projection, firstly making anchor model mapping on the test voice, and then making ordinal number comparison between the mapped test voice and the speaker declared by the test voice. The anchor model mapping: firstly extracting the characteristics of the test voice to obtain an eigenvector sequence, then estimating the probability density of each Gauss mixed model in the anchor model and the background model to obtain a mapped score vector. And the ordinal number comparison arranges the scores in the vector components and compares the score ordinal numbers of the test voice and the declared speaker and calculates Euclidian distance between the ordinal numbers, and finally compares the distance with a threshold value to obtain the final result. The invention has wider safety and adaptivity.
Owner:ZHEJIANG UNIV

Multi-attribute depth characteristic-based vehicle re-recognition method

The invention discloses a multi-attribute depth characteristic-based vehicle re-recognition method. The method comprises the steps of extracting, by using a characteristic extraction model, a depth characteristic of a tested image set of an Ath pooling layer, obtaining, by using the depth characteristic of the tested image set and a W matrix, a Mahalanobis distance between a depth characteristic of a tested image in a searched set and a depth characteristic of a target image in a candidate set, ranking in an ascending order according to the Mahalanobis distance so as to obtain a similarity ranking result of the tested image and the target image, wherein tested image sets comprise a seeking set and a searching set, the tested image sets refer to images comprising vehicles, and the characteristic extraction model is trained through steps of accessing a vehicle multi-attribute classifier behind the Ath pooling layer of GoogLeNet, so as to obtain improved GoogLeNet, training by using training images to improve GoogLeNet so as to obtain the characteristic extraction model. The method simplifies the model training process and greatly improves re-recognition accuracy, and the model has strong generalization performance.
Owner:HUAZHONG UNIV OF SCI & TECH

Network security threat analysis method and system based on LDA machine learning

The invention discloses a network security threat analysis method and system based on document topic generation model (LDA) machine learning, and the method comprises the following steps: step 1, carrying out the data collection of different types of network flows in a data collection module according to a specific application scene; and step 2, in a machine learning calculation module, calculating the abnormal probability of network connection by using an LDA topic model machine learning algorithm; and step 3, in the operation analysis module, in combination with a threat intelligence database, detecting the attack type of the suspicious network connection by using a credibility detection-based method. Suspicious connection, abnormal flow and unknown attacks can be effectively detected.
Owner:杉树岭网络科技有限公司

Hash learning method based on an evolutionary tree and an unsupervised online Hash learning method thereof

InactiveCN109829549AEquilibrium and Stable ConvergenceAchieving local similarityCharacter and pattern recognitionMachine learningHamming codeData set
The invention relates to a Hash learning method based on an evolutionary tree. the evolution tree is trained through data points in the data set; obtaining a trained evolution tree; carrying out initialization Hamming code coding on all nodes except a root node in the trained evolution tree, optimizing a similarity protection loss function of the whole evolution tree by using a greedy path codingstrategy, and taking Hamming code coding corresponding to a minimum value of the similarity protection loss function as Hash coding of each leaf node of the evolution tree; and calculating an optimalmatching point of a certain data point in the evolution tree, finding a splitting path of a leaf node corresponding to the optimal matching point of the data point split from the root node, orderly combining Hash codes of the corresponding leaf node in the splitting path of the optimal matching point of the data point, and taking the Hash codes as Hash codes of the data point. The invention also discloses an unsupervised online Hash learning method. According to the Hash method, the coding complexity can be reduced, and the good query performance is achieved.
Owner:NINGBO UNIV

Power line inspection image automatic identification method based on neural network and power line inspection image automatic identification device thereof

The invention discloses a power line inspection image automatic identification method based on a neural network and a power line inspection image automatic identification system thereof. The method comprises the steps that input images acquired in power line inspection are acquired, and the input images are inputted to a convolutional neural network; 2) a feature vector group is obtained, and the input images apply the feature vectors in the feature vector group in turn so that digital description of the select box of the target type and the target position is obtained; and 3) convolutional operation is performed on the target input image so that the select box of the target object and the target position is obtained, and the object and the position expected to be selected of the highest confidence are also obtained. An end-to-end training model is established so that the target object in the images can be automatically identified, power line inspection image automatic identification can be realized based on the neural network and the efficiency can be enhanced.
Owner:北京泛化智能科技有限公司 +4

Residual single image rain removal method based on attention mechanism

The invention discloses a residual single image rain removal method based on an attention mechanism, and mainly solves the problems that the existing single image rain removal technology has limitation and is not ideal in processing effect. According to the scheme, the method comprises the following steps: 1) preprocessing an input image to obtain a preprocessed image; 2) constructing an attention residual neural network model comprising a residual network module and a codec network module; 3) inputting the preprocessed image into an attention residual neural network model for training, constraining the attention residual neural network model by using a loss function, and then performing back propagation for parameter updating to obtain a trained rain removal neural network model; and 4) inputting a to-be-processed rain image into the rain removal neural network model for image processing to obtain a rain-free clear image. According to the invention, rain stripes in a single rain-containing image can be effectively removed, and a clear image is obtained; and meanwhile, background information in the original image is fully reserved.
Owner:XIDIAN UNIV

Vehicle classifier training method

The invention provides a vehicle classifier training method, which comprises the following steps: utilizing a few samples to train an initial classifier; converting videos collected by a camera sensor into pictures; carrying out detection on the pictures through the initial classifier; then, keeping the pictures passing detection of the initial classifier and pictures comprising a vehicle target but failing the detection of the classifier, wherein the pictures passing detection of the initial classifier may comprise correct detected vehicle pictures and wrong detected vehicle pictures; defining the wrong detected vehicle pictures as a negative sample hard example, and defining the pictures comprising the vehicle target but failing the detection of the classifier as a positive sample hard example; and adding the positive sample hard example and the negative sample hard example to a positive and negative sample library and continuing training a vehicle classifier until detection rate and false detection rate of the trained classifier reach requirements of clients. The method can increase diversity of classifier training samples, improve the detection rate of vehicle detection and reduce the false detection rate, and finally, optimizes the classifier training flow.
Owner:GUANGDONG UNIV OF TECH

Acer palmatum Sangokaku tissue culture propagation process

The invention discloses an acer palmatum Sangokaku tissue culture propagation process which comprises the following steps: S1, explant sterilization; S2, inoculation and propagation, namely inoculating a sterilized stem section with a bud to a culture medium for growth, culturing for 2-3 weeks, and inducing the germination of an axillary bud; S3, enrichment subculture, namely shearing the germinated axillary bud, inoculating on a subculture medium, culturing for 3-5 weeks, and inducing the generation of caespitose buds; S4 rooting culture, namely cutting adventitious buds positioned on the caespitose buds, inoculating on a rooting culture medium, culturing for 2-3 weeks, and inducing the generation of a root. The acer palmatum Sangokaku tissue culture propagation process disclosed by the invention can be used for building a Sangokaku tissue culture propagation system, and realizing the breakthrough of the Sangokaku tissue culture propagation system, is low in production cost, high in propagation coefficient, short in propagation period, an effective way for the fast propagation of acer palmatum Sangokaku, and capable of preventing the virus accumulation, and achieving the easiness for domesticated seedling survival, and by using the process, the issue culture seedlings with consistent inheritable characters and the sterile acer palmatum Sangokaku seedlings can be relatively easily obtained.
Owner:SICHUAN COLORLINK CO LTD
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
PatSnap group products