69results about How to "Fast detection rate" patented technology

The embodiment of the invention discloses a method for detecting a human face. The method comprises the following steps of: carrying out LBP (Length Between Perpendiculars) characteristic calculation on an acquired image to obtain an LBP characteristic pattern; distinguishing the LBP characteristic pattern by using an AdaBoost classifier trained based on LBP characteristics to obtain first human face region data; carrying out Haar characteristic solving on the first human face region data to obtain an Haar characteristic pattern and distinguishing the Haar characteristic pattern by using the AdaBoost classifier trained based on the Haar characteristics to obtain second human face region data; clustering the second human face region data and combining the overlapped human face regions to obtain fourth human face region data; and outputting a human face region in the image. The embodiment of the invention also discloses a device for detecting the human face. According to the method and the device disclosed by the invention, the detection rate of human face detection is greatly increased; the false detecting rate is reduced, high detection speed is obtained, an interframe human face tracking step can also be added and further the detection speed is increased and the requirements of users on high detection rate and high detection speed are met.

The invention discloses a detection method for isothermal amplification of single or multiple target gene fragments. According to the method, FIB and / or BIP primer 5' end is added with a restriction enzyme cutting site sequence during LAMP amplification and is marked with fluorophore, and other parts of the primer are marked with quenching groups; after amplification, amplification results of the corresponding target genes are displayed according to a fluorescence detection, thereby accomplishing detection of single or multiple target gene fragments by one-time amplification. Compared with traditional LAMP, the method provided by the invention has the advantages of single or multiple detection, high efficiency amplification, rapid reaction, specific detection and simple operation.

An attack detection system based on a decision-making tree comprises a detection data acquisition unit, a detection excavation processor and a classifier, namely, a decision-making tree. The detection data acquisition unit serves as a detection signal inputting end of the attack detection system to acquire to-be-detected data. An output end of the detection data acquisition unit is connected with a signal input end of the detection excavation processor. A signal output end of the detection excavation processor is connected with a signal input of the classifier. A signal output end of the classifier is used for outputting of the attack detection system based on the decision-making tree to display a detection state. According to the system, an association rule method is adopted to establish a normal behavior rule set for detecting abnormal attack; further classification forecasting is performed by the decision-making tree so that false alarm rate is reduced; and according to attack detects based on the decision-making tree, the false alarm rate of an ad hoc network is reduced and capacity of detecting a new intrusion behavior of the system is improved.

The invention provides an end-to-end neural network based fabric defect detection method. The end-to-end neural network based fabric defect detection method comprises the following steps that initialparameters of a SSD neural network model are set, a fabric defect image in a fabric defect database is input the set SSD neural network model to train, and a fabric detection model of deep learning isobtained; the fabric image to be detected is input into the fabric detection model trained in the step one, feature extraction is carried out on the fabric image, and a plurality of candidate frameswhich may be defect targets are selected and taken out; and based on a set judgement threshold value, the candidate frames in the step two are identified to obtain final defect targets, defect targetframes are selected by using intersection and comparison thresholds of the candidate frames where the defect targets are located, and location coordinate information of defects is stored and the defect target frames are output. The end-to-end neural network based fabric defect detection method has good adaptability and detection performance to both plain fabric and mode fabric, and expands the application range; the detection rate is fast, and the problem of slow manual detection speed is effectively solved; and the model is easy to train, and the operation is simple.

The invention relates to a method for item identification and classification and defect detection based on machine vision. The method includes an item category identification and classification process based on a support vector machine and a defect detection process based on a machine vision defect detection algorithm, wherein the item category identification and classification process includes amodel training process and a process of loading models to achieve classification; and the defect detection process based on the machine vision defect detection algorithm includes the following steps:performing a graph correction process, and calculating Hu invariant moments of graphs for similarity comparison; and judging whether pictures have defects according to a detection result. According tothe scheme of the invention, a support vector machine training template and a loading template are used for multi-classification, so that the categories of different objects can be identified, the detection of different objects can be realized, the universality of the algorithm can be improved, and the accuracy and detection speed of the defect detection can be improved.

The invention provides a method for rapidly and nondestructively detecting astaxanthin in C.zofingiensis cells. The method comprises the following steps of (1) re-suspending algal cells collected from a known C.zofingiensis suspension sample to regulate the known C.zofingiensis suspension sample into heavy suspension with cell density of 6*10(5) to 2*10<6>CFU / mL by virtue of de-ionized water or a phosphate buffer solution, detecting the average fluorescence intensity of the heavy suspension in an FL1 channel or an FL2 channel by virtue of a flow cytometer, and performing linear regression on a log value of the content of astaxanthin in the known C.zofingiensis suspension sample and a log value of the corresponding measured average fluorescence intensity in the FL1 or FL2 channel to obtain a standard curve; (2) preparing a sample to be detected: re-suspending algal cells collected from C.zofingiensis suspension to be detected to regulate the C.zofingiensis suspension to be detected into algal cell heavy suspension to be detected with cell density of 6*10(5) to 2*10<6>CFU / mL by virtue of de-ionized water or a phosphate buffer solution; (3) detecting the average fluorescence intensity of the sample to be detected in the FL1 channel or the FL2 channel by virtue of the flow cytometer, and calculating the content of astaxanthin in the sample to be detected according to the standard curve obtained in step (1). The method has the characteristic of high detection efficiency.

The invention discloses an LED light source short-circuit detection method and device, an LED backlight and a liquid crystal display device. The LED light source short-circuit detection method and device aims to simplify the short-circuit detection of an existing LED light source. The LED light source short-circuit detection method is applied to the backlight of the liquid crystal display device, wherein the backlight comprises a plurality of LED lamp strips. The LED light source short-circuit detection method comprises the following steps of inputting M unequal detection voltages to each LED lamp strip; receiving and recording breakover feedback of each LED lamp strip at under each detection voltage; judging whether LED lamps are short-circuited in each LED lamp strip according to the breakover feedback, wherein M is an integer which is not smaller than 1, and the maximum detection voltage is not larger than the normal working voltage of each LED lamp strip. The LED light source short-circuit detection method and device is used for the short-circuit detection of the LED light source, and has the advantages of being easy and convenient to achieve, fast in achievement, sensitive in detection and the like.

The invention relates to a face detection method based on clustering analysis and model compression. The method comprises the steps: firstly obtaining a face detection data set, carrying out K-means clustering analysis of the face data set, carrying out analysis of the number and a size of anchor frames and an application degree of the data set, and finally generating a detection anchor frame mostsuitable for the data set; applying the generated detection anchor frame to a deep learning network, and training a face detection network; finally, after layer pruning or channel pruning is performed on the trained face detection network, carrying out fine adjustment on the network, and acquiring a lighter-weight network; and detecting the image and the video by using the network to obtain a final result. The method has advantages of high detection accuracy and a high detection rate, and can be applied to human face attendance, access control systems, traffic identity approval and other scenes.

The invention relates to an augmented reality image data processing method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a reality scene image collected by a camera carried on a refrigerator; identifying food materials in the real scene image through a food material identification model, wherein the food material identification model is a cascadenetwork of a feature pyramid network and a YOLOV3 network; obtaining virtual resources corresponding to the food materials in the real scene image, wherein the virtual resources are virtual animationresources designed according to nutritional ingredients of the food materials; and displaying the virtual animation resources and the real scene images in a combined manner, wherein the feature pyramid network and the YOLOV3 network can extract food materials of different scales; according to the invention, the requirements of various food materials are met, the detection speed is high, the food materials can be quickly and accurately recognized, the virtual animation image is displayed in an AR (augmented reality) mode to display the nutritional ingredients of the food materials, a user selects the food materials according to the nutritional ingredients, and the diet quality is guaranteed.

Provided is a method for detecting the saturation of a current transformer (CT) on the basis of a third-order central moment. The method comprises: sampling current at the secondary side of the CT; acquiring a current waveform from a position near the peak value of a waveform by using a data window in order to obtain a waveform symmetric about the peak value and with less sampling points; computing a dispersion coefficient by using the third-order central moment after the acquired waveform is subjected to waveform mirror image transformation; and outputting a detected result. In the method, a dispersion coefficient after a standard sinusoidal current waveform is subjected to mirror image transformation. By means of analysis and computation, the dispersion coefficient can be considered as a fixed value so as to be used as a comparison basis. The method mainly solves problems of low detection rate and low detection precision when the CT saturation occurs, may fast and accurately detect the generation of the CT saturation just by using sampled data in half cycle so as to improve relay protection reliability to a certain extent and have certain practical significance in the aspect of guaranteeing the accurate and reliable operation of the CT.

The present invention discloses a non-contact wafer annealing device and method. The device comprises a wafer, an air floating platform deck, a light source, an infrared temperature measurement probe and a controller. A plurality of air holes are uniformly distributed on the air floating platform deck, air is pumped in from the air holes to form an air cushion for supporting the wafer; the light source is arranged right above the wafer, and the wafer is heated through radiation; the infrared temperature measurement probe is arranged at the right below the air floating platform deck, and the temperature of the wafer is measured through the temperature measurement hole arranged at the diameter of the air floating platform deck; and the controller is connected with the infrared temperature measurement probe. The non-contact wafer annealing device and method are simple to perform, the annealing temperature is uniform, the measurement precision is high, and the non-contact wafer annealing device and method can avoid damaging the wafer and perform annealing of the back surface of the wafer while the fashioned front surface and the edges of the wafer do not damaged and can realize the automation operation.

The invention provides a preparation method of a palladium-copper bimetallic nanoflower peroxide. The preparation method comprises the following steps: adding sodium tetrachloropalladate, tungsten hexacarbonyl, copper chloride dihydrate, dimethylformamide and glacial acetic acid to a round-bottom flask; ultrasonically and uniformly mixing the above solutions, and then heating and stirring the uniformly mixed solutions through an oil bath; and finally, centrifugally washing the obtained product by using water and ethanol for serval times, so as to obtain a bimetallic alloy nanomaterial, namelyPdCu nanoflower. The preparation process of the palladium-copper bimetallic nanoflower peroxide is simple and the yield is high; and through the prepared unique two-dimensional structure, the reactionrate is promoted and the detection time is saved. The invention further discloses the application of the palladium-copper bimetallic nanoflower peroxide to glucose detection. Through such a detectionmethod, the sensitivity and the selective detection of glucose can be achieved.

A blind detection method of implicit image on frequency domain includes transforming space domain to be DCT domain, deriving out differential histogram in DCT domain and its amplitude spectrum as well as analyzing it, carrying out implicit writing detection according to the lowest and the highest number and position of spectrum energy, presenting trend to go down for non-implicit writing DCT domain image and DCT spectrum from low frequency to intermediate frequency but presenting trend to go up for implicit writing image spectrum at the same position .

The invention provides a colorimetric analysis method for quickly detecting carbon deposition on a solid catalyst. The method includes the steps of simulating color situations of carbon-deposited catalysts in a manner of mixing carbon powder and the catalysts, collecting the colors of the catalysts containing carbon powder in different mass through a color imaging device, and comparing the color situations with the color of a to-be-tested solid catalyst to determine the carbon deposition content in the to-be-tested solid catalyst. The method is simple and reliable, can quickly obtain the content information of carbon deposition on the solid catalyst, and has important significance of guiding production.

The invention relates to a method for detecting a wireless radio frequency identification tag and a device thereof; the method uses a shading mode to rapidly judge whether the wireless radio frequency identification tag is good or bad. The method for detecting the wireless radio frequency identification tag is mainly divided into two steps: firstly, all of plurality of wireless radio frequency identification tags in a readable region are read, then whether bad tags exist in plurality of wireless radio frequency identification tags is judged; if all the tags have no problem, the tags are rapidly passed; otherwise, if certain wireless radio frequency identification tags can not be read, a mode of shading a single tag or a plurality of tags is used to find out the positions of the bad wireless radio frequency identification tags. Through the method and the device provided by the invention, the disadvantages that the readable region of the prior art is not easy to design and detecting speed is slow can be overcome.

The embodiment of the invention provides a method for detecting proxy network access. The method comprises the following steps: establishing a proxy device identifier table in advance; receiving a Web webpage request message sent by a first user terminal after establishing a TCP connection with a Web server; feeding back a message used for detecting identification information of the user terminal to the first user terminal according to terminal type information in the Web webpage request message; receiving a message containing the identification information of the first user terminal sent by the first user terminal; when the source IP address of the message containing the identification information of the first user terminal is in the proxy device identifier table, determining whether the user terminal is a user terminal that surf the Internet through a proxy device according to the identification information of the first user terminal and the proxy device identifier table. Meanwhile, the invention further provides an apparatus for detecting proxy network access. According to the method and apparatus provided by the embodiment of the invention, the false alarm rate is low, and the network access experience of users is good.

The invention discloses a leakage current detection method, device and equipment for alternating current and a storage medium. The method includes the following steps: collecting a leakage current analog signal at each sampling time, and converting the leakage current analog signal at the current sampling time into a sampled value of leakage current by analog-to-digital conversion; when a sampledvalue of leakage current is acquired, judging whether the total number of sampled values of leakage current in a storage queue reaches a preset number of samples per period; and when the total numberof sampled values of leakage current in the storage queue reaches the preset number of samples per period, acquiring the effective value of leakage current at the previous sampling time, and obtainingthe effective value of leakage current at the current sampling time according to the effective value of leakage current at the previous sampling time, the sampled value of leakage current corresponding to the earliest data in the storage queue and the sampled value of leakage current at the current sampling time. The technical problem that the existing leakage current detection method is slow indetection and cannot realize real-time detection is solved.

The invention discloses an infrared image small target detection method based on a generative adversarial network. According to the method, a false background image block is reconstructed for a targetimage block containing a small target; pairing the false background image block with the target image block to obtain first pairing data, training the generative adversarial network by using the data; pairing the two original background image blocks which do not contain the small target in the image sequence block to obtain second pairing data; continuously training by using the data to obtain atarget generative adversarial network model; and inputting a to-be-detected image block sequence into the target generative adversarial network model to obtain a detection sequence result, splicing the detection sequence result according to the size of the to-be-detected original infrared image, making a residual error between the spliced image and the to-be-detected original infrared image, and filtering the image after the residual error is made to obtain a detection result. Through the method provided by the invention, background interference can be greatly suppressed while a relatively high detection rate is ensured.

The invention discloses a magnetic nano composite material and a preparation method and application thereof. The magnetic nano composite material is of a core-shell structure, an inner core is Fe3O4, a shell layer is SiO2, and a middle layer is further arranged between the inner core and the shell layer; wherein the intermediate layer is from a polymer; and the polymer is selected from at least one of polyvinylpyrrolidone and polydopamine. According to the magnetic nano composite material provided by the invention, sample DNA can be rapidly extracted, and the extracted DNA is applied to a qPCR (real-time fluorescence quantification) detection technology.

The invention discloses a self-adaptive hierarchical image segmentation identification method, device and system. The method comprises the following steps: acquiring an original image of a certain frame in a high-definition video; performing image segmentation on the original image to obtain a plurality of image slices with overlapped pixels; carrying out iterative segmentation and identificationon the sub-image slices; and finally, selecting all identification results to obtain an identification result of the final image. According to the method, the problems of low speed and low small object detection rate of existing high-definition image object recognition are solved, and the effects of high object recognition speed and high detection rate in the high-definition image are achieved.

The invention relates to a method for measuring an interface surface shape of a multi-interface target body by adopting ultrashort pulse laser, which comprises the following steps of: selecting an ultrashort pulse laser light source; dividing the ultrashort laser pulse into two beams of light by a spectroscope after the ultrashort laser pulse is subjected to spectral filtering and enters a Michelson interferometer, and one beam of light is reflected by a reference mirror and enters an interference light receiving system as reference light; the other beam is reflected by the interface to be measured of the target body and enters the interference light receiving system as signal light; adjusting the length of the reference arm or the length of the measuring arm of the Michelson interferometer so that the reference light only interferes with the signal light reflected by the interface to be measured of the target body and does not interfere with the signal light reflected by other interfaces of the target body, and the computer system obtains the surface shape of the interface to be detected according to the acquired double-interface interference fringes. The method achieves the interface surface type measurement of the multi-interface target body by utilizing the coherence characteristic between the ultrashort pulses, which is a novel measurement method and has the advantages ofsimplicity, stability, high efficiency and the like.

The invention discloses the one-step hydrothermal synthesis based on ionic liquid novel fluorescent carbon dots and the detection application of one-step hydrothermal synthesis for sulfathiazole. Theone-step hydrothermal synthesis is characterized by taking 1-allyl-3-vinyl imidazole tetrafluoroborate as a carbon source, the malonic acid as a passivating agent, and synthesizing the novel fluorescent carbon dots capable of specifically recognizing sulfathiazole through a high-temperature hydrothermal reaction. A novel sulfathiazole fluorescent probe synthesized by the invention is simple in preparation process, low in cost and high in selectivity, has high sensitivity and accuracy in the detection of the trace sulfathiazole remained in an environmental sample, and has a wide application prospect in the field of analysis and detection of sulfathiazole.

The invention relates to a non-contact milk freshness detection system and a detection method thereof, belongs to the technical field of milk freshness detection, and aims at providing a hardware structure of the non-contact milk freshness detection system and improving a detection method thereof. The system comprises a microprocessor for data collecting and processing, the microprocessor is connected with an external information interaction device including a keyboard and a display screen concretely, a peripheral circuit of the microprocessor is connected with a clock control chip and a temperature sensor, the signal output end of the microprocessor is connected with a data storage module and a data communication module, the data communication module includes a GPRS wireless communicationmodule concretely, the GPRS wireless communication module establishes connection with a host computer via the wireless network, and the display screen for displaying freshness data of milk is arranged outside the host computer; and software for training collection data is arranged in the host computer. Thus, the milk freshness is detected.

The invention discloses an automatic device for measuring sulfur dioxide capacity of active coke with a continuous method. The automatic device comprises a flue gas mixing device, a water vapor generating device, a gas mixing device and a reaction tube, wherein the flue gas mixing device comprises a premixer; the water vapor generating device comprises a pump, a vaporizer and a gas flow meter, and water enters the vaporizer for vaporization via the pump; mixed gas is obtained after gas at an outlet of the premixer and water vapor after vaporization by the vaporizer enter the gas mixing device and enters the reaction tube via a pipeline; a resistance wire and a distribution plate are arranged in the reaction tube, the mixed gas is fully contacted with activated coke in the reaction tube, and the mixed gas after adsorption by the activated coke is discharged out of the reaction tube. Compared with existing devices, the automatic device has the characteristics that the sulfur dioxide adsorption capacity of the activated coke can be measured automatically, the gas component composition is accurate and stable, the integration level is high, the operation is convenient and quick and the like, and the method has positive significance in solving the problem of high difficulty in measurement of adsorption capacity of the activated coke at present.

The invention discloses a full-automatic workpiece surface quality detection device. A workpiece fixing assembly is arranged on a base, a workpiece upper surface detection assembly is arranged on the upper surface of a to-be-detected workpiece, and a workpiece lower surface detection assembly is arranged on the lower surface of the to-be-detected workpiece. The workpiece upper surface detection assembly and the workpiece lower surface detection assembly are both driven by a detection assembly driving assembly to achieve reciprocating motion of the workpiece upper surface detection assembly and the workpiece lower surface detection assembly, and therefore the whole surfaces of the to-be-detected workpiece can be detected in a full coverage mode. The upper surface and the lower surface of the workpiece are detected in an omni-bearing mode through an upper computer, the detection rate is high, back-and-forth motion of a rack can be achieved only by driving a gear to rotate by a positive and reverse rotating motor, and an upper surface quality detection head and a lower surface quality detection head can detect the upper surface and the lower surface of the workpiece in an omni-bearing mode; detection efficiency is greatly improved, and the accuracy of surface quality detection is improved.

The invention relates to a high temperature-resistant interdigital electrode for protecting outer surfaces of glass glazes and a preparation method thereof. The electrode comprises a substrate (2), aninterdigital electrode layer (3) and an outer surface protection layer (4), wherein the interdigital electrode layer contains precious metal. The preparation method comprises the steps of firstly forming the interdigital electrode layer (3) on the ceramic substrate (2); photoetching an interdigital electrode pattern comprising an interdigital (1) on the surface; coating a micro-level glass glazelayer on the whole substrate and carrying out sintering at high temperature to form the protection layer; and finally carrying out scribing and cutting on the product obtained through the sintering toform the glass glaze-coated interdigital electrode. The interdigital electrode has favorable air permeability through the external glass glaze protection layer without influence the signal transfer,and can be repeatedly used, so that the service life and stability of the electrode under the high temperature conditions are improved.

The invention relates to an immunoglobulin heavy-chain light-chain detection kit and a use method thereof, the kit comprises a stationary liquid, a heavy-chain polyclonal antibody and a light-chain polyclonal antibody, and relates to all types of immunoglobulins, combined light chains and free light chains in a human body. The kit not only can detect IgG-[kappa], IgG-[lambda], IgA-[kappa], IgA-[lambda], IgM-[kappa], IgM-[lambda], IgD-[kappa], IgD-[lambda], IgE-[kappa] and IgE-[lambda], but also can detect a Kappa type and a Lambda type. By selecting the multi-site polyclonal antibody capable of being specifically bound, the kit has the advantages of strong specificity, multiple specific binding sites, good affinity, high titer and good rabbit antiserum stability, can greatly improve the detection of different mutation binding sites of immunoglobulin immune dysplasia, can also reduce the influence of other lesion interferents, has high sensitivity, is simple and convenient to operate, and has wide application prospects. The kit is high in detection rate, low in cost, convenient to automate and suitable for clinical detection application.

The invention discloses a detection device used in the production process of a pop can. The detection device comprises a conveyor belt, wherein batches of to-be-detected pop cans are arranged on the conveyor belt; two sides of the conveyor belt are symmetrically provided with a first support and a second support which are respectively provided with an adjusting rod; one end of each adjusting rod is connected with a protective sheet; the first support is further provided with a photoelectric switch; the second support is further provided with a lens; a screening mechanism is arranged above thepop cans and comprises an electromagnet, an air cylinder, an induction probe and a conveyor; one side of the electromagnet is connected with the induction probe; and the air cylinder is connected withand arranged between the conveyor belt and the electromagnet. Thus, the detection device used in the production process of the pop can is capable of effectively detecting unqualified pop cans and hashigh detection rate.

The invention relates to the technical field of pork quality detection and particularly relates to a fresh pork quality detection device. The device comprises a single-chip microcomputer, a display module, a comparison module, a memory module, an alarm module, an AD conversion circuit module, a PH value detection module, a meat tenderness detection module, a moisture detection module, a volatile basic nitrogen detection module, a meat color detection module, a weighing sensor, a key input module and a power supply module. The single-chip microcomputer is in signal connection with a display module, a memory module and an alarm module. The comparison module is in bidirectional signal connection with the single-chip microcomputer, the key input module is in signal connection with the single-chip microcomputer, the power module is electrically connected with the single-chip microcomputer, the PH value detection module, the meat tenderness detection module, the moisture detection module, the volatile basic nitrogen detection module and the meat color detection module, and the weighing sensor is in signal connection with the AD conversion circuit module. According to the invention, all-around quality detection can be carried out along with pork quality while weighing is carried out, the detection rate is high, and the detection effect is accurate.

The invention belongs to the technical field of deep learning anomaly detection, and discloses an industrial part surface defect detection method and system based on an anomaly detection algorithm. The method comprises the following steps: obtaining an image of a to-be-detected product, and collecting the surface image data of a to-be-detected good product shot by an industrial camera; the image is input into a teach-student anomaly detection network model to be trained; detecting defect data and non-defective product data by using a model produced after training is completed; returning a detection result to the client, and displaying the detection result by the client; and transmitting the detected abnormal region and the size of the region to a client of software, and judging whether the defect needs to be eliminated or not through an area threshold value on the software. The detection of surface abnormal areas of most parts with simple surface structures can be met. Compared with target detection, a large amount of model training and data collection time is saved, and the method has a great promotion effect on project promotion and acceptance as soon as possible.