116results about How to "Good identification effect" patented technology

The invention provides a spectrum library generating method, comprising the following steps: selecting analyzed spectrograms of an experimental tandem mass spectrometry, in which information of female ionic peptide sequences, electronic charges, modified types and sites are included; removing redundant spectrograms from the analyzed spectrograms of the experimental tandem mass spectrometry to obtain representing spectrograms; dividing the female ionic peptide sequences corresponding to the representing spectrograms according to a theoretical fragmentation mode to obtain theoretical spectrograms corresponding to the representing spectrograms; combining the theoretical spectrograms and the representing spectrograms to obtain optimized spectrograms; and labeling spectral peaks for the optimized spectrograms, and utilizing the optimized spectrograms with labeled spectral peaks to generate a spectrogram database. The invention further provides a spectrogram identifying method of the tandemmass spectrometry. In the invention, in the process of matching candidate spectrograms and the spectrograms of the tandem mass spectrometry to be analyzed, mass-to-charge ratio offset of the spectralpeak possibly introduced by a potential modification is concerned so that ionic spectral peak containing modified fragments is matched, thereby achieving better modified spectrogram identifying effect.

The invention provides a sparse self-adaptive semi-supervised manifold learning hyperspectral image classification method and provides a semi-supervised sparse manifold learning dimension reduction algorithm and a nearest manifold classification algorithm. Internal attributes and a manifold structure contained in high-dimensional data are well discovered by marking small amount of data points in a data sample and combining part of unmarked data points for learning, low-dimension embedded features with better identification performance can be extracted, classification result is improved, classification precision of land feature classification in hyperspectral remote sending images is improved, and problems about 'out-of-sample learning' of a sparse manifold clustering and embedding algorithm and difficulty in labeling the remote sensing image classification can be effectively solved; meanwhile, as is shown in experimental results in a PaviaU data set and compared with a common identification method in the prior art, the sparse self-adaptive semi-supervised manifold learning hyperspectral image classification method is better in classification result.

The invention provides an Alzheimer's disease and mild cognitive impairment identification method based on two-dimension features and three-dimension features. The method particularly comprises a step of performing pretreatment of a medical image, wherein the pretreatment comprises pre-segmentation, registration and other processes; a step of performing two-dimension textural feature extraction of the medical image, wherein features comprise the quadratic statistic of a gray-level co-occurrence matrix and a multiscale and multidirectional feature value of Gabor wavelet transformation; a step of performing three-dimension morphological feature extraction of the medical image, i.e., extracting volume features of an area of interest; a step of performing feature fusion of three-dimension morphological features and two-dimension textural features; and a step of constructing a support vector machine to achieve identification of Alzheimer's disease and mild cognitive impairment. According to the method provided by the invention, the three-dimension morphological features and the two-dimension textural features are combined, so that the content of the medical image can be expressed in a comprehensive and accurate manner. The method can improve identification of Alzheimer's disease and mild cognitive impairment, thereby providing a more effective clinic assistant diagnosis.

The invention provides a gene pool containing IST2 gene sequence fragments of labiate Isodon serra(Maxim.)Kudo and Rabdosia lophanthoides. The invention also provides a method for identifying plant species of the labiate Isodon serra(Maxim.)Kudo and Rabdosia lophanthoides. The method comprises a step of comparing IST2 gene or its sequence fragment of a plant sample, plant species of which is to be identified, to the gene pool provided by the invention. The invention also provides an application of the IST2 gene or its sequence fragment in identification of the labiate Rabdosia lophanthoides and the labiate Isodon serra(Maxim.)Kudo. It proves that the IST2 sequence is general, is easy to amplify and compare, and has good amplification and identification effects on the labiate Rabdosia lophanthoides and the labiate Isodon serra(Maxim.)Kudo.

The invention relates to a technical method for high-efficient breeding of wheat, which comprises low-temperature vernalization, south breeding and generation adding, shuttle breeding, multi-point combined identification and the like. In particular, the technical method comprises the following steps of: treating the seeds obtained after the strong-winterness wheat blossoms for 15 to 20 days by hydrogen peroxide, washing the seeds by pure water, sprouting the seeds at the room temperature, putting the seedlings growing to 1 to 2 centimeters in an artificial weather room, performing the green-body vernalization of the seedlings for 45 and 50 days at a temperature of between 3 and 5 DEG C and a relative humidity of 70 percent and under a light intensity of 15001x; hardening the seedlings of the winter wheat undergoing the vernalization treatment at the normal temperature for 1 to 2 days, and transporting the seedlings to Yuanmou in Yunnan province; and preparing a rice seedling bed, watering and soaking the rice seedling bed, discharging visible water before transplanting, and transplanting the seedlings in mud at dusk. The disease resistance, stress resistance, adaptability and yieldstability selections of breeding materials are carried out by shuttle breeding and multi-point combined identification and the like. The technical method for breeding provides rich reserve of raw materials for the rapid improvement of the wheat variety, and also lays a sold foundation for demonstration and popularization of a new variety in large areas.

The invention relates to a liquor vintage recognition method based on a fusion technology of ion mobility spectrometry / mass spectrometry / Raman spectroscopy. According to the present invention, by employing a pattern recognition technology, liquors of different specifications are determined through Raman spectroscopy, ion mobility spectrometry and mass spectrometry; a method of combining principal component analysis and linear discriminant analysis is used for feature extraction from Raman spectroscopy, ion mobility spectrometry and mass spectrometry data; a support vector machine method is adopted for establishing corresponding classification models; and experiment results show that a multi-spectral feature fusion algorithm has a very high classification accuracy and recognition rate for liquor vintage.

The embodiment of the invention discloses a malicious URL (unified resource locator) authenticating method and a malicious URL authenticating device. The authenticating method comprises the steps that a URL contained in the content of a communication message is matched with a preset URL blacklist; if the URL is successfully matched, a risk prompt is generated, if not, the IP address of a sending end of the communication message is matched with a preset IP (internet protocol) blacklist; and if the IP is successfully matched, a risk prompt is generated. The malicious URL (unified resource locator) authenticating method and the authenticating device can remind a user after the user receives the communication message containing the malicious URL. In the technical scheme of the embodiment, the malicious URL can be authenticated without authenticating the website content of the malicious URL, so that the authentication effect of the malicious URL is effectively improved.

The invention discloses a mobile terminal, which comprises an image acquisition device and an anti-counterfeiting detection device, wherein the anti-counterfeiting detection device is used for analyzing images, acquired by the image acquisition device, of anti-counterfeiting characteristic points to identify the authenticity of the anti-counterfeiting characteristic points. When used for performing anti-counterfeiting detection, the mobile terminal can identify one or more anti-counterfeiting characteristics in an image processing mode so as to greatly improve anti-counterfeiting detection accuracy; if the number of the identified anti-counterfeiting characteristic points is larger, the identification effect of the anti-counterfeiting detection is better; moreover, the mobile terminal of the embodiment can enable users to perform the anti-counterfeiting detection anytime anywhere so as to bring great convenience to the users.

The invention discloses a detection method of main active ingredients in a folium ginkgo-radix salviae miltiorrhizae vasodistal soft capsule. 1000 folium ginkgo-radix salviae miltiorrhizae vasodistalsoft capsules are prepared from 500 g of folium ginkgo, 500 g of radix salviae miltiorrhizae, 300 g of herba erigerontis, 300 g of fiveleaf gynostemma herb, 400 g of fructus crataegi, 400 g of garlic,200 g of radix notoginseng and 10 g of blumea camphor. The detection method comprises the steps of quantitatively analyzing flavonoid constituents, phenolic acids and the like, wherein the quantitative analysis method is a high-performance liquid-phase chromatography-mass spectrometry. The detection method has the advantages of higher main ingredient quantitative analysis sensitivity to the folium ginkgo-radix salviae miltiorrhizae vasodistal soft capsule, good precision, high identification capacity, capability of detecting more ingredients, and good detection data accuracy; and the batch similarity of the qualitative analysis of the folium ginkgo-radix salviae miltiorrhizae vasodistal soft capsule is good, and the overall chemical contour of the folium ginkgo-radix salviae miltiorrhizaevasodistal soft capsule can be better reflected.

The invention provides an SAR (synthetic aperture radar) image naval ship target identification method based on a change detection technology. According to the technical scheme, the SAR image naval ship target identification method based on the change detection technology comprises the following steps of firstly, establishing change detection amount by using ROI (region of interest) section gray scale data and generating a standard gray scale difference image; secondly, performing threshold segmentation on the difference image and acquiring the number of potential target pixels and the number of real target pixels; and finally, identifying an ROI section by using pixel aggregation degree of targets according to the ratio of the number of the real target pixels to the number of the potential target pixels. By the SAR image naval ship target identification method based on the change detection technology, the separation capacity on naval ship targets in an SAR image and sea clutter false alarm can be effectively improved, and the adaptive capacity on the identification method can also be improved effectively.

The present invention relates to a multiple microsatellite identification system for rapidly and efficiently carrying out litopenaeus vannamei family identification, and belongs to the field of molecule assisted breeding in genetic breeding. Specifically 15 microsatellite sites with high polymorphism are screened to carry out primer design, primers are divided into two primer systems according to primer annealing temperatures and amplification product lengths, the primers in every group are subjected to different fluorescence labeling according to the fragment length, system optimization is performed to obtain the optimal amplification system so as to carry out microsatellite typing on the candidate parents and the filial generation through the multiple microsatellite identification system, and family identification is performed by using the typing data of the 15 sites, such that efficiency is rapid, the result is accurate and reliable, and good identification effects are further provided for families with close kinship.

A face detection training method, a detection method and an apparatus thereof are disclosed. A face detector comprises a first classifier and a second classifier. The training method comprises the following steps of collecting face and non-face images as training sample sets; extracting a brightness comparison characteristic of each training sample in the training sample sets; according to the brightness comparison characteristic, acquiring a corresponding fern characteristic; using the fern characteristic and a Bayes theorem to carry out training and acquiring the first classifier; using the brightness comparison characteristic and a minimized weight mean square error criterion to carry out P-round training, and acquiring P decision tree classifiers, wherein the P is greater than or equal to 1 and the P is an integer; and cascading the P decision tree classifiers so as to form the second classifier. The face detector acquired through applying the training method is used to carry out face detection so that complexity and a calculated amount of face detection can be reduced and detection efficiency can be increased.

The invention discloses a bifidobacteria detecting method in the milk product, which is characterized by the following: adding antibiotics in the culture base to inhibit growing other bacteria; detecting bifidobacteria selectively; studying lithium chloride, sodium propionate and maclicine to obtain fittest antibiotics proportion and quantity of bifidobacteria selectivity count.

The invention provides an image classification method based on unsupervised domain adversarial domain adaptation. According to the method, a generative adversarial network technology is applied to image classification based on unsupervised domain adaptation; in order to eliminate the misclassification rate of edge samples, a source domain sample and a target domain sample are jointly processed based on a deep dual-channel network. The method comprises the following steps: firstly, parameters of a dual-channel network are trained by utilizing a labeled source domain sample; then, domain differences are eliminated by learning and invariant features through adversarial games and a correlation alignment method; in addition, the method enables domain invariant features to have better discrimination by combining a center discrimination method and a feature similarity enhancement method, is better in classification effect, adapts to an image classification method through an unsupervised and adversarial field, and effectively alleviates the misclassification rate of edge samples.

The invention provides a finger vein image anti-counterfeiting identification method and device. The method comprises the steps of: S1, collecting finger vein images and performing true and false marking on the collected images; S2; dividing the marked true and false images into a training set, a verification set and a testing set, wherein the images in the training set are obtained by performingpartitioning operation on the marked images; S3, performing DBN model building and training; S4, performing BP model building and training; S5, extracting the characteristics of all hidden layers in the BP model; S6, inputting the extracted characteristics of all the hidden layers, as multi-layer feature vectors of the input images, into an SVM model for training and determining SVM parameters; S7, fusing true and false scores of all the blocks of each image to calculate an overall score and judging whether a finger vein image is true for false via the overall score. The method and the devicecan effectively improve the accuracy of finger vein image anti-counterfeiting identification and improve the security performance of certification systems.

The invention is applicable to the field of data mining and sample cleaning and provides a facial sample cleaning method and system based on deep learning features. The facial sample cleaning method comprises the steps that A, the deep learning technology is utilized to extract facial image features; B, a sample needing to be processed is partitioned according to a given process number, and the partitioned samples are allocated to all processes; C, corresponding facial features in each process are clustered; D, a class with most images is selected in each clustering result to serve as a main class; E, the image corresponding to the features of the main class is copied to a target directory, and an original file structure is reserved. The facial features extracted through deep learning are low in dimension and have very good identification capability; on the one hand, sample cleaning precision can be improved, and on the other hand, cleaning time can be saved; multiple processes are designed concurrently, the operational capability of hardware an be fully utilized, therefore, the efficiency of entire operation can be improved, and consumed time is shortened.

The invention relates to an image invariant feature extraction method based on the circular trace transform, and belongs to the field of image processing and computer vision. In this method, a circular trace line of the new circular trace transform is used to track an image, functional results on the circular trace line are mapped to a space generated by the three parameters of radius, length and angle, the result of the circular trace transform is obtained, the result is further subjected to functional integration, and image quadruple circular trace spatial features can be obtained. Different circular trace transform results can be obtained by using different functions on the circular trace line, that is, different texture properties of the image can be represented and multi-dimensional circular trace transform texture feature information is generated. According to the invention, the texture features extracted by the circular trace transform have an RST invariant property, deeper image information can be obtained, a better resolution capability is gained for images containing circular and arc-shaped textures, and the recognition capability is improved significantly in the case of fewer training samples.

The invention discloses a method for extracting an estuary intertidal zone classification area by using an object-oriented classification technology, characterized by comprising the following steps of: (1) extracting water edges of estuary intertidal zones, wherein places involving water and the intertidal zones in a high resolution No.1 satellite remote sensing image are made into a mask by using Global Mapper software; supervised classification is performed on the water and the intertidal zones in ENVI; classification results are classified and clustered; vector graphs are guided out and then guided into the Global Mapper software for correction; and the water edges of the estuary intertidal zones are extracted and obtained; (2) making the vector graphs with an shp format; and (3) extracting the estuary intertidal zone classification area, wherein intertidal zone classification is performed by using a sample-based object-oriented flow of the ENVI software, and the data of the intertidal zone classification area is extracted. The method of the invention can perform high precision extraction on the intertidal zone classification utilization information. The operation is convenient, and the feasibility is strong.

The invention discloses a curved surface similar label identification method based on improved structure similarity. The method comprises the steps of image acquisition, template image processing, image segmentation and stretching, image registration, similarity identification and the like; the image acquisition comprises acquisition of a to-be-detected image and a template image; the template image processing realizes stretching of the template image and tailoring of a label region; the image segmentation and stretching realize segmentation of the label region from the to-be-detected image, so that a to-be-detected label image is obtained; the image registration step is used for registering a template label image and the to-be-detected label image; and the similarity identification step is used for calculating the similarity between the template label image and the to-be-detected label image through the improved structure similarity GDSIM, so that whether labels are the same labels ornot is identified. The label identification method disclosed by the invention is simple in step and is suitable for not only plane labels but also curved surface labels; and for the problem that thelabel is difficult to identify under the condition of non-uniform illumination and slight deformation in the label image, a good identification effect can be achieved.

The invention discloses a method for identifying a cherry variety, and belongs to the field of molecule identification of cherry varieties. The invention firstly discloses 11 pairs of SSR (Simple Sequence Repeats) primers for identifying the varieties of cherry, wherein the nucleotide sequences of the primers are as shown in SEQ ID No.1 to SEQ ID No.22. By adopting the method, core primer combinations are further screened from the 11 pairs of the SSR primers, 87 cherry germplasms can be distinguished by using 5 core primer combinations, and the obtained primer combinations have the advantages of being high in polymorphism, high in amplification stability, good in repeatability, clear in electrophoretic band and the like. The invention further discloses a cherry variety identification method and a kit based on S genotype information and SSR primer combinations. By adopting the primers, identification upon different cherry varieties can be rapidly and accurately completed. The SSR primer pairs, the cherry variety identification method and the kit disclosed by the invention can be applied to cherry germplasm evaluation, cherry germplasm innovation, parent choice for breeding, and the like.

The invention relates to a multifunctional chemical crosslinking agent. The multifunctional chemical crosslinking agent is a three-arm type structure consisting of two reaction functional group arms and an arm containing an affine functional group and a cleavage site. The invention further provides a preparation method of the multifunctional chemical crosslinking agent. The multifunctional crosslinking agent is very excellent in both of water solubility and stability, and high in crosslinking efficiency; when the multifunctional crosslinking agent is applied to protein analysis; its good crosslinking peptide fragment identification ability is presented in samples of simple systems such as BSA, and ten standard protein mixtures; the crosslinking agent also can identify considerate crosslinking site in complex biological samples such as escherichia coli 70S ribosome, escherichia coli full cell lysis buffer and caenorhabditis elegans full cell lysis buffer, and present very good application value; thereby providing a powerful tool for the future study of interaction of complex biological system proteins.

The invention discloses an SAR target identification method based on feature dimension reduction, and relates to research on a target identification method in SAR image automatic target identification. The method includes the steps that firstly, an SAR training image set is preprocessed, and a training sample set is established; secondly, a linear model is established for the training sample set, an optimal dimension reduction matrix is acquired, dimension reduction is conducted on the training sample set, a dimension-reduced training sample set is obtained, and a probability density function of the dimension-reduced training sample set is acquired; thirdly, SAR test images are preprocessed, and test samples are established; fourthly, dimension reduction is conducted on the test samples through the optimal dimension reduction matrix, dimension-reduced test samples are obtained, the likelihood probability of the dimension-reduced test samples is acquired, and the dimension-reduced test samples are identified through a Bayes classifier. The method mainly achieves the purpose of SAR target identification under the small sample condition, compared with the prior art, the identification performance of the method is obviously improved, and the method can be used for SAR target identification.

The invention relates to Chinese cabbage EST-SSR labeled primers and an application thereof to identification of varieties, belonging to the technical field of molecular biology. The invention provides sequences of a Chinese cabbage EST-SSR labeled primer BRE28, a Chinese cabbage EST-SSR labeled primer BRE121 and a Chinese cabbage EST-SSR labeled primer BRE131, and an application of the labeled primers to identification of varieties of Chinese cabbages. The amplified products of the EST-SSR primers of the invention are in parental complementary banding patterns which have obvious size difference, thus hybrids and parental inbred lines can be well distinguished, and different varieties of the Chinese cabbages can be identified. The amplified products among individuals in the same variety have consistent banding patterns.

The invention relates a PML gene and RARA gene detection probe and a preparation method thereof. The method comprises the following steps that at least one of RP11-832J18, CTD-2529B11, RP11-756N20 and RP11-1031J4 and a selected BAC cline for an RARA gene is at least one of CTD-2360L10, RP11-737D6, CTD-3087O22, RP11-48O10 and CTD-2134K5 are included; a plasmid DNA is obtained; labeling is performed. The invention further discloses a reagent kit containing the PML gene and RARA gene detection probe for detecting acute promyelocytic leukemia PML and RARA fusion genes. The optimal PML gene and RARA gene detection probe is obtained through screening, the signal counting row is accurate and rapid, and the result repeatability is good.

The invention provides a method of identifying protein phosphorylation modification sites on the basis of tandem mass spectrometry. According to the method, application result data is searched by tandem mass spectrometry MGF-formatted (mascot generic file-formatted) data and mascot and pFind databases; programming is performed by a Perl language program; identified protein phosphorylation modification sites are re-located fast; and the re-located protein phosphorylation modification sites are calculated by a new scoring algorithm. The method is more creditable and also allows for fast automatic batch exporting of mass spectrograms related to the protein phosphorylation modification sites. The method has the advantages that operation is simple, locating information of the modification sites is highly creditable and the extracted mass spectrograms are high in resolution. The method is well applicable to the field of proteomics study.

The present invention discloses an anti-rotation HDO local feature description method for target robust identification. The method comprises the following steps: setting a circular detection region of an image; calculating a similar RGT gradient of the image; calculating a structure tensor, and obtaining a main direction and consistency of each pixel point; dividing a circular image into a plurality of ring-shaped sectors to be used as cells, combining every four adjacent cells into a block, and calculating a feature vector of each Block; and combining the feature vector of each Block together to form an HDO feature description. According to the method disclosed by the present invention, an RGT conversion technology is introduced, and the structure tensor is constructed during construction of a pixel point circular neighbourhood, so as to ensure that the main direction and consistency of each pixel point do not change when a picture rotates, and then a main direction histogram of each Block is calculated, and by adopting a spatial pool division manner of the ring-shaped sectors, the obtained local feature has an excellent differentiation ability and anti-rotation conversion ability.

The invention discloses an SAR target discrimination method based on non-similarity transformation A-type SVM model. The method includes the steps of 1. preprocessing a training image and a testing image to obtain a training and testing sample set; 2. constructing a non-similarity transformation A-type SVM model based on the training sample set to deduce the combined posteriori distribution of model parameters; 3. deducing the condition posteriori distribution of a single model parameter based on the combined posteriori distribution of the model parameters; 4. sampling the model parameters for I times by means of Gibbs sampling, starting from I+1 and storing the sampling result for one time for every I<sp> interval, and saving for T<s> times; 5. obtaining the testing samples after the characteristic transformation and the corresponding clustering labels based on the stored sampling result; and 6. bringing the transformed testing samples into the A-type SVM corresponding to the clustering labels to output testing object class labels. The method has the advantages of convenient model parameter selection and high identification performance, and is applicable to SAR target discrimination.

The invention provides a quality control method for Yuyeqinghuo capsule. The thin layer chromatography identification can be simultaneously performed for Mussaenda pubescen and gardenia, the thin layer chromatography identification can be performed for yerbadetajo, and the content of the characteristic components of green chiretta such as andrographolide and the dehydrated andrographolide can be detected. The quality control method for the Yuyeqinghuo capsule has the advantages of environmental protection, good separation degree of content detection method, simplified identification method and strong operability.

The invention relates to a method for identifying forsythia suspensa derivatives. The method comprises the following steps: (1) directly obtaining the forsythia suspensa derivatives as a forsythia suspensa lignans and phenylethanoid glycoside characteristic extract containing an active component group; (2) carrying out IGD (Integrated Graphics Driver) nuclear magnetic resonance spectroscopy fingerprint spectrum detection on the forsythia suspensa lignans and phenylethanoid glycoside characteristic extract so as to obtain peak intensities of characteristic peaks of a plurality of active components in the characteristic extract according to a fingerprint spectrum; and detecting the peak intensity of the characteristic peak of a standard reference corresponding to each active component in the same manner; (3) obtaining the absolute content of the standard reference by a quantitative analysis means; (4) calculating the content of each active component and the content of the active component group in the forsythia suspensa derivatives in a ratio of the peak intensities of the characteristic peaks and the absolute content. The method provided by the invention can be used for reflecting the lignans and phenylethanoid glycoside compounds contained in the forsythia suspensa derivatives and a ratio of the lignans compounds to the phenylethanoid glycoside compounds, so that the purpose of identifying the quality of the forsythia suspensa derivatives can be realized.

The invention provides a gene pool containing rbcL gene sequence fragments of labiate Isodon serra(Maxim.)Kudo and Rabdosia lophanthoides (Buch.-Ham. ex D. Don) Hara var. graciliflora (Benth.) Hara. The invention also provides a method for identifying plant species of the labiate Isodon serra(Maxim.)Kudo and Rabdosia lophanthoides (Buch.-Ham. ex D. Don) Hara var. graciliflora (Benth.) Hara. The method comprises the step of comparing a rbcL gene or its sequence fragment of a plant sample, plant species of which is to be identified, to the gene pool provided by the invention. The invention also provides an application of the rbcL gene or its sequence fragment in identifying the labiate Rabdosia lophanthoides (Buch.-Ham. ex D. Don) Hara var. graciliflora (Benth.) Hara and the labiate Isodon serra(Maxim.)Kudo. It proves that the rbcL sequence is general, is easy to amplify and compare, and has good amplification and identification effects on the labiate Rabdosia lophanthoides (Buch.-Ham. ex D. Don) Hara var. graciliflora (Benth.) Hara and the labiate Isodon serra(Maxim.)Kudo.