360results about How to "Low background noise" patented technology

The invention discloses a robust license plate and logo recognition method. The method based on Adaboost detection, SVM screening and texture analysis edge removal is adopted to perform license plate precise detection to effectively respond to different scenes, illuminations, viewing angles, resolutions and the like, and a detected license plate region only contains less background. License plate recognition is performed mainly by using maximum stable extremal region detection assisted by sliding window detection in cooperation with energy optimization, thus, characters which are difficult to process under the conditions of license plate contamination, insufficient definitions and the like based on a character segmentation method traditionally can be effectively detected, character detection and recognition are performed synchronously, and the traditional mode of ''recognition after segmentation'' is broken. A feature code weighted based on confidence is adopted to express a logo sample, a group-based sparse discriminative dictionary pair model is utilized to recognize logo features of the code, and the method has high robustness on the logo sample containing a complex background.

The invention relates to an EGFR gene mutation detection primer probe and a kit thereof. The kit comprises a digital PCR master mix used for preparing digital PCR reaction liquor, a liquid droplet stabilizer and primer probe mixed liquor. The primer probe mixed liquor comprises an upstream primer a, a downstream primer a, a deficiency probe a and a detection probe a, wherein the upstream primer a, the downstream primer a, the deficiency probe a and the detection probe a are used for detecting 19 exon E19-Dels locus; the primer probe mixed liquor further comprises a mutation upstream primer b, a mutation probe b, a wild upstream primer b, a wild probe b, and an universal downstream primer b, wherein the mutation upstream primer b, the mutation probe b, the wild upstream primer b, the wild probe b and the universal downstream primer b are used for detecting a 20 exon T790M locus; the primer probe mixed liquor further comprises a mutation upstream primer c, a mutation probe c, a wild upstream primer c, a wild probe c and an universal downstream primer c, wherein the mutation upstream primer c, the mutation probe c, the wild upstream primer c, the wild probe c and the universal downstream primer c are used for detecting 21 exon L858R locus. The EGFR gene mutation detection kit is capable of quickly, conveniently and accurately detecting situations of EGFR gene mutation in a patient with non-small cell lung cancer.

The invention discloses an inter-frame difference and convolutional neural network fusion-based ship video detection method. The method comprises the four parts of preprocessing a video; obtaining anROI of each frame and extracting low layer features; obtaining high layer features of each frame of image by using a modified VGG16 network; and predicting a ship saliency map of the ROI of each frameand extracting a ship target. A relationship between continuous video frames is fully utilized; the interference of a background is reduced; a moving ship is accurately located; a ship moving regionis obtained; and compared with ship image saliency detection only using the low layer features, the method not only can be directly applied to the ship video detection but also reduces the situation of incomplete ship detection, has higher adaptability to a complex inland river moving ship scene, has higher detection precision, solves the problem of inaccurate inland river ship target saliency detection, and has extremely high practical application values.

The invention discloses a hyper-blocking fluorescence quantitative PCR method with high sensitivity for detecting rare mutation. The invention adopts specific primers and a probe technology and can rapidly detect gene point mutation in a blood sample. The method has the advantage that (1) the conventional ARMS primers are modified by LNA or mismatched bases are introduced into 3' tail 2th site totail 3th site so that the sensitivity of the mutation detection is not influenced and the specificity of the single base mutation based on the mutation specific primers is guaranteed, (2) the modifiedblocker probe completely complementary to the wild type gene is introduced so that the wild type background interference is further reduced with keeping the efficiency of the mutant amplification, (3) based on the high specificity modified blocker probe, the ARMS primers can detect different base mutation forms at the same site at the same time so that multiple sites in the same gene can be detected by only a few systems, (4) sensitivity is high and (5) a detection rate is fast.

The invention relates to a machine vision automatic deviation rectifying system of a tire crane and a deviation rectifying method. An acquisition module acquires an image of a regulated line in the advancing process of the tire crane; a calibration module acquires coordinates of the feature portion of a calibration reference object in a pixel coordinate system and an actual coordinate system; a coordinate conversion module achieves conversion between the pixel coordinate system and the actual coordinate system; a pre-processing module processes the image of the acquisition module to acquire data with clear and stable features; a line recognition module detects and recognizes the regulated line in the image, determines the direction deviation delta alpha and the distance deviation delta d between the actual line and the regulated line in the actual driving process, and sends the deviations to a PLC communication module; and the PLC communication module stores the data and sends the datato a tire crane control system for deviation rectifying. By means of the machine vision technology, automatic deviation rectifying in the tire crane cart advancing process is achieved, the working efficiency is improved, and accidents are reduced.

A sensitivity raising detection method of colloid gold immunity chromatography method comprises: when using general colloid gold immunity chromatography to check object sample, adding an object sample, adding signal amplifying agents of 10 to 80ul between the gold label antibody layer and the detection line; processing the detection line obtained by general colloid gold immunity chromatography method; reacting under room temperature for 1 to 10min; if the object sample contains antigen, the detection carrier is formed with a detection line and a control line as clear black or grey black color, to represent positive property, or if the object sample not contains antigens, the control line is black or grey black color, and the detection line has not color, to represent negative property. The method can significantly improve the sensitivity of colloid gold immunity chromatography reagent kit on the detection of biological macromolecules, having fast color development, lower background interference compared with general silver stain method, wide application prospect and high development value.

Provided is a personnel recognition method based on multi-visual-feature fusion. Firstly, a monitoring video is analyzed, information of related personnel is extracted, features are described, and finally searching is carried out to obtain a recognition result of the related personnel according to an input video image. The method comprises the three operation stages or steps of video tracking processing, human body block mass processing and personnel recognition. The method can well extract proper personnel images from the video automatically and carry out preprocessing; the existing problems of feature description are solved correspondingly, relatively general features are selected, the features are regrouped, and new features are fused. The method achieves innovation on the aspects of removing a background part, blocking the human body images and extracting semantic color features. The testing result of the monitoring video by multiple times of simulation examples shows that the method is easy to implement, convenient to use, effective and good in recognition effect, and therefore the method has good application and popularization prospects.

The invention relates to two novel difluoro boron dipyrromethene compounds which can be used as near-infrared fluorescent dyes and a preparation method thereof and belongs to the techcnial field of fluorescent probes. 8-(4-(chloromethyl) phenyl)-4,4-difluoro-1,3,5,7-tetramethyl-4-boron-3a,4a-dipyrrole (labeled as BODIPY-C), 1,2,3,4-tetrahydro naphthalene, 5-hydroxyl isophthalate and p-anisaldehyde are used as raw materials to synthesize the two novel difluoro boron dipyrromethene (BODIPY) derivatives. The two compounds are compounds for near-infrared absorption and near-infrared fluorescence emission and can be expected to be used as fluorescent probes for imaging in cells or organisms, and background interference is reduced.

The invention discloses an electromechanical system equipment health assessment method, and the method comprises the following steps: carrying out the structure and function decomposition of an electromechanical system; obtaining historical operation parameters of all sub-parts; carrying out an extension failure mode and impact analysis based on a decomposition result, and determining representation parameters for representing a fault; determining a key feature factor set affecting the health of the system, and constructing multi-dimensional space parameters representing early state mode recognition indexes; obtaining a sensor signal, and carrying out fault abnormality detection according to the multi-dimensional space parameters. The method is low in testing cost, is weaker in background noises, is complete in state information, and can meet the information demands for equipment health management.

The invention discloses a method for detection and quality control of a medicine composition. The medicine composition is a composition containing hypericum perforatum, the content of hyperoside, the content of rutin and the content of lilac glycosides are detected through liquid chromatography, and the adopted liquid chromatography determination conditions are characterized in that octadecylsilane chemically bonded silica serves as filler of a chromatographic column, a mobile phase A is a NaH2PO4 buffer solution, a mobile phase B is a mixed solution of acetonitrile and methyl alcohol, and gradient elution is adopted. The method has the advantages of being quick, efficient, stable, accurate and the like, and quality control over the medicine composition can be quickly and effectively conducted.

The invention relates to the technical field of molecular biology, in particular to adjustable luciferase segmentation fusion protein and a preparing method and application thereof. The fusion protein comprises luciferase N-terminal protein, a flexible peptide fragment 1, MBP protein, an active valve, a flexible peptide fragment 2 and luciferase C-terminal protein, wherein luciferase N-terminal protein and luciferase C-terminal protein form luciferase together, and the active valve is a fragment of 4-8 hydrophobic short-peptide amino acids. By means of the activity adjustment mode that a short-peptide chain amino acid sequence is used as the active valve and specific cleavage enzyme is used as a valve key, a novel fluorescence complementation protein switching mode is realized, and the novel fluorescence complementation protein switching mode can be used for evaluating interaction of other protein dynamics such as combination of a ligand and a substrate, interaction capable of generating a new binding site, protein-protein interaction capable of deactivating protein, and protein-protein interaction capable of changing the specificity of a protein active substrate.

The invention discloses an improved antibody chip kit capable of quantitatively detecting multiple cell factors synchronously. The kit includes a standard tissue slide which is coated with activated amino groups and is used as a surface carrier. Various antigen-specificity antibodies are spotted on a surface of the slide to form a microarray through a non-contacting sample spotting instrument. The slide is divided into sixteen small zones, which are not interfered with each other, through a detachable 2*8-hole plastic frame, wherein each small zone contains an antibody microarray. Each captured antibody is repeated by four times in each antibody microarray. The slide and the frame are tightly clamped with each other through plastic clamping plates which are arranged at the two sides to form an antibody chip. Experimental reagents of a multiple sandwich ELISA reaction are completed on the surface of the slide. By means of the antibody chip kit, multiple cell factors can be quantitatively detected synchronously. A sensitivity of the kit is similar to that of single ELISA but a dynamic detection range of the cell factors is wider. Repeated data, which is as four times as that of ELISA, can be obtained from a single-sample experiment. The kit is high in sensitivity, is high in flux, is little in sample usage amount, is low in cost and is easy to popularize.

The invention discloses a luciferase complementary quantum dot biosensor as well as a construction method and application thereof, belonging to the technical field of biosensing. The luciferase complementary quantum dot biosensor comprises a quantum dot, a luciferase amino terminal fragment, a luciferase carboxyl terminal fragment, a probe of specifically recognizable determinand and a substrate which have bioluminescence reaction with luciferase. With the combination of optical advantages of the quantum dot sensor, a catalysis function can be reconstructed through induction complementation of the luciferase amino terminal fragment and the luciferase carboxyl terminal fragment on the surface of the quantum dot, a novel high-sensitivity biosensor can be constructed, and the biosensor is low in background noise, high in sensitivity, stable in structure and easy to use, can be used in high-target detection on multiple biological markers, and is applicable to accurate quantification on target testing articles in homogeneous systems.

The invention discloses a cognition-based star networking method for broadband wireless access equipment, and the cognition-based star networking method is used for realizing the spectrum sensing and strategy selection of an initial access phase and the access and adaptive strategy adjustment of late accessing equipment at a communication phase. The initial access phase is a phase from equipment startup to communication establishment and mainly used for realizing an accurate spectrum sensing function; the terminal polling access function is realized through signaling waveforms of 4 kbps; the channel estimation function is realized through waveforms of 80 kbps; and the frequency and rate selection function is used for determining the same working frequency of a whole network through channel selection and matching and channel estimation and determining the communication rate of each link through pairwise channel estimation between nodes and terminal equipment. The communication phase is a phase from the communication establishment to equipment shutdown, spectrum sensing timeslots, access timeslots and channel cognition timeslots are respectively reserved in all communication frames, and both the function of adaptive transmission and adjustment and the function of late networking of new startup equipment are realized at the phase.

A liver cancer marker phosphatidylinositol proteoglycan 3 (Glypican-3, GPC3) is used as a research object, a GPC3 aptamer is used as a recognition probe, on the basis of good electron transfer effectand excellent loading capacity of a reductive graphene oxide-chitosan-ferrocene/nano platinum and palladium (Pt-Pd NPs/RGO-CS-Fc) composite material, the GPC3 aptamer can specifically recognize and becombined with GPC3 protein, and a novel aptamer sensor capable of performing specific recognition and quantitative analysis on the GPC3 protein is constructed and used for detecting the content of GPC3 in serum. The method is simple to operate, time-saving, low in cost and relatively low in detection limit.

The invention discloses a coomassie brilliant blue staining solution and a staining method. The coomassie brilliant blue staining solution comprises 0.1-10 percent by volume of acid, 1-15 percent by volume of ethyl alcohol, 10-50g/L of soluble starch and 20-1000mg/L of coomassie brilliant blue aqueous solution. The staining solution does not contain reagents harmful to human bodies and is environmental friendly. The staining method using the staining solution has the beneficial effects that due to addition of the soluble starch, the staining background of gel can be reduced, a protein band can be specifically stained, the sensitivity of staining is effectively improved, and therefore, the whole staining process of the protein band can be completed within 20 minutes by using the staining method, the steps such as gel fixation, sensitization and destaining in a conventional dyeing process are omitted, operating steps are greatly simplified, and the dyeing time is saved; the staining method has the advantages of short cycle, high sensitivity and small background interference.

The invention belongs to the technical field of medical image processing, and particularly relates to a granulocyte picture fine-grained classification and recognition system based on deep learning. The system comprises a positioning module and a classification module; the positioning module performs feature extraction on an input granulocyte picture by using a Hourglass network model, positions all cells in the granulocyte picture, cuts out the positioned cells, leaves a single complete cell, and performs size normalization processing on all cut-out cells; the classification module is used for classifying the granulocytes positioned by the positioning module by adopting the constructed deep learning classification model; clinical doctors are assisted in accurately and efficiently completing granulocyte classification, identification and counting tasks, errors caused by subjectivity are reduced, the workload of the doctors is reduced, and the doctors are assisted in making disease judgment. According to the system, cell classification under unbalanced data and fine-grained classification among granulocytes can be effectively solved, and the network classification and recognition effect is improved.

The invention discloses a lysosomal targeting fluorescent probe and a preparation method thereof. A D-Pi-A-Pi-D (donor-Pi-receptor-Pi-donor)-type large Pi conjugated system is constructed by alpha, beta-unsaturated ketone as a receptor. Through intramolecular charge transfer, compared with the existing many fluorescent probes for lysosome, lysosomal targeting fluorescent probe can realize large red shift of the excitation wavelength and emission wavelength of the molecule produce so that background signal interference is effectively reduced. The compound provided by the invention is used for fluorescence imaging of lysosome. In the cell environment, red fluorescence can be emitted under acidic conditions, and the maximum emission wavelength is about 625nm so that the lysosome targeting marker is obtained and background interference is small. The preparation method is sensitive, simple and quick.

The invention discloses polymer fluorescent microspheres in the near-infrared II region and a preparation method thereof, wherein the preparation method includes: (1) dissolving the fluorescent dye with a water-immiscible organic solvent so as to obtain a fluorescent dye solution, the fluorescent dye It has the structure shown in formula I; (2) disperse the polymer microspheres in the sodium dodecylsulfonate aqueous solution, so as to obtain the microsphere carrier solution; (3) mix the fluorescent dye solution and the microsphere carrier solution and perform ultrasonic processing, so as to obtain the emulsified mixed solution; (4) swelling the emulsified mixed solution, so that the fluorescent dye solution is immersed in the nanopores produced in the swelling process of the polymer microspheres; and (5) the mixture obtained in step (4) is processed After heating, with the volatilization of dichloromethane, the fluorescent dye crystallizes out and is wrapped in the nanopores, so as to obtain polymer fluorescent microspheres in the near-infrared II region. The fluorescent microspheres have high fluorescence quantum efficiency, strong penetration ability and low background interference during fluorescence detection.